From 3ff340e24c9dd5cff9fc07d67914c5adf67f80d6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 11 Jun 2021 08:42:50 +0300 Subject: [PATCH 0001/1469] bus: ti-sysc: Fix gpt12 system timer issue with reserved status Jarkko Nikula reported that Beagleboard revision c2 stopped booting. Jarkko bisected the issue down to commit 6cfcd5563b4f ("clocksource/drivers/timer-ti-dm: Fix suspend and resume for am3 and am4"). Let's fix the issue by tagging system timers as reserved rather than ignoring them. And let's not probe any interconnect target module child devices for reserved modules. This allows PM runtime to keep track of clocks and clockdomains for the interconnect target module, and prevent the system timer from idling as we already have SYSC_QUIRK_NO_IDLE and SYSC_QUIRK_NO_IDLE_ON_INIT flags set for system timers. Fixes: 6cfcd5563b4f ("clocksource/drivers/timer-ti-dm: Fix suspend and resume for am3 and am4") Reported-by: Jarkko Nikula Tested-by: Jarkko Nikula Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 38cb116ed433..188cdb0a394e 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -100,6 +100,7 @@ static const char * const clock_names[SYSC_MAX_CLOCKS] = { * @cookie: data used by legacy platform callbacks * @name: name if available * @revision: interconnect target module revision + * @reserved: target module is reserved and already in use * @enabled: sysc runtime enabled status * @needs_resume: runtime resume needed on resume from suspend * @child_needs_resume: runtime resume needed for child on resume from suspend @@ -130,6 +131,7 @@ struct sysc { struct ti_sysc_cookie cookie; const char *name; u32 revision; + unsigned int reserved:1; unsigned int enabled:1; unsigned int needs_resume:1; unsigned int child_needs_resume:1; @@ -3093,8 +3095,8 @@ static int sysc_probe(struct platform_device *pdev) return error; error = sysc_check_active_timer(ddata); - if (error) - return error; + if (error == -EBUSY) + ddata->reserved = true; error = sysc_get_clocks(ddata); if (error) @@ -3130,11 +3132,15 @@ static int sysc_probe(struct platform_device *pdev) sysc_show_registers(ddata); ddata->dev->type = &sysc_device_type; - error = of_platform_populate(ddata->dev->of_node, sysc_match_table, - pdata ? pdata->auxdata : NULL, - ddata->dev); - if (error) - goto err; + + if (!ddata->reserved) { + error = of_platform_populate(ddata->dev->of_node, + sysc_match_table, + pdata ? pdata->auxdata : NULL, + ddata->dev); + if (error) + goto err; + } INIT_DELAYED_WORK(&ddata->idle_work, ti_sysc_idle); From 47661ee1821fc3a6b5ae07aac37410d6ccada976 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 18 Jun 2021 13:18:46 +0200 Subject: [PATCH 0002/1469] memory: tegra: Add compile-test stub for tegra_mc_probe_device() The tegra_mc_probe_device() symbol is only available when the TEGRA_MC Kconfig option is enabled. Provide a stub if that's not the case so that the driver can be compile-tested. Reported-by: kernel test robot Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20210618111846.1286166-1-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index e19c2504a14b..1066b1194a5a 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -237,14 +237,19 @@ unsigned int tegra_mc_get_emem_device_count(struct tegra_mc *mc); #ifdef CONFIG_TEGRA_MC struct tegra_mc *devm_tegra_memory_controller_get(struct device *dev); +int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev); #else static inline struct tegra_mc * devm_tegra_memory_controller_get(struct device *dev) { return ERR_PTR(-ENODEV); } + +static inline int +tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev) +{ + return -ENODEV; +} #endif -int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev); - #endif /* __SOC_TEGRA_MC_H__ */ From bf3ec9deaa33889630722c47f7bb86ba58872ea7 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 21 Jun 2021 16:00:36 +0200 Subject: [PATCH 0003/1469] dt-bindings: arm-smmu: Fix json-schema syntax Commit 4287861dca9d ("dt-bindings: arm-smmu: Add Tegra186 compatible string") introduced a jsonschema syntax error as a result of a rebase gone wrong. Fix it. Fixes: 4287861dca9d ("dt-bindings: arm-smmu: Add Tegra186 compatible string") Reported-by: Rob Herring Signed-off-by: Thierry Reding Acked-by: Rob Herring Link: https://lore.kernel.org/r/20210621140036.2879563-1-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 1181b590db71..03f2b2d4db30 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -52,16 +52,14 @@ properties: items: - const: marvell,ap806-smmu-500 - const: arm,mmu-500 - - description: NVIDIA SoCs that program two ARM MMU-500s identically - items: - description: NVIDIA SoCs that require memory controller interaction and may program multiple ARM MMU-500s identically with the memory controller interleaving translations between multiple instances for improved performance. items: - enum: - - const: nvidia,tegra194-smmu - - const: nvidia,tegra186-smmu + - nvidia,tegra194-smmu + - nvidia,tegra186-smmu - const: nvidia,smmu-500 - items: - const: arm,mmu-500 From cc3ddee97cff034cea4d095de4a484c92a219bf5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:08:59 +0100 Subject: [PATCH 0004/1469] vboxsf: Honor excl flag to the dir-inode create op Honor the excl flag to the dir-inode create op, instead of behaving as if it is always set. Note the old behavior still worked most of the time since a non-exclusive open only calls the create op, if there is a race and the file is created between the dentry lookup and the calling of the create call. While at it change the type of the is_dir parameter to the vboxsf_dir_create() helper from an int to a bool, to be consistent with the use of bool for the excl parameter. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index eac6788fc6cf..6ff84343edca 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -253,7 +253,7 @@ static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, } static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, - umode_t mode, int is_dir) + umode_t mode, bool is_dir, bool excl) { struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -261,10 +261,12 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, int err; params.handle = SHFL_HANDLE_NIL; - params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | - SHFL_CF_ACT_FAIL_IF_EXISTS | - SHFL_CF_ACCESS_READWRITE | - (is_dir ? SHFL_CF_DIRECTORY : 0); + params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | SHFL_CF_ACCESS_READWRITE; + if (is_dir) + params.create_flags |= SHFL_CF_DIRECTORY; + if (excl) + params.create_flags |= SHFL_CF_ACT_FAIL_IF_EXISTS; + params.info.attr.mode = (mode & 0777) | (is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE); params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING; @@ -292,14 +294,14 @@ static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { - return vboxsf_dir_create(parent, dentry, mode, 0); + return vboxsf_dir_create(parent, dentry, mode, false, excl); } static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode) { - return vboxsf_dir_create(parent, dentry, mode, 1); + return vboxsf_dir_create(parent, dentry, mode, true, true); } static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) From ab0c29687bc7a890d1a86ac376b0b0fd78b2d9b6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:22:27 +0100 Subject: [PATCH 0005/1469] vboxsf: Make vboxsf_dir_create() return the handle for the created file Make vboxsf_dir_create() optionally return the vboxsf-handle for the created file. This is a preparation patch for adding atomic_open support. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 6ff84343edca..87d5b2fef592 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -253,7 +253,7 @@ static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, } static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, - umode_t mode, bool is_dir, bool excl) + umode_t mode, bool is_dir, bool excl, u64 *handle_ret) { struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -278,30 +278,34 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, if (params.result != SHFL_FILE_CREATED) return -EPERM; - vboxsf_close(sbi->root, params.handle); - err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info); if (err) - return err; + goto out; /* parent directory access/change time changed */ sf_parent_i->force_restat = 1; - return 0; +out: + if (err == 0 && handle_ret) + *handle_ret = params.handle; + else + vboxsf_close(sbi->root, params.handle); + + return err; } static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { - return vboxsf_dir_create(parent, dentry, mode, false, excl); + return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL); } static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode) { - return vboxsf_dir_create(parent, dentry, mode, true, true); + return vboxsf_dir_create(parent, dentry, mode, true, true, NULL); } static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) From 02f840f90764f22f5c898901849bdbf0cee752ba Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:55:03 +0100 Subject: [PATCH 0006/1469] vboxsf: Add vboxsf_[create|release]_sf_handle() helpers Factor out the code to create / release a struct vboxsf_handle into 2 new helper functions. This is a preparation patch for adding atomic_open support. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/file.c | 73 ++++++++++++++++++++++++++++------------------ fs/vboxsf/vfsmod.h | 7 +++++ 2 files changed, 52 insertions(+), 28 deletions(-) diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index c4ab5996d97a..864c2fad23be 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -20,18 +20,40 @@ struct vboxsf_handle { struct list_head head; }; -static int vboxsf_file_open(struct inode *inode, struct file *file) +struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode, + u64 handle, u32 access_flags) { struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle; + + sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); + if (!sf_handle) + return ERR_PTR(-ENOMEM); + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + + /* init our handle struct and add it to the inode's handles list */ + sf_handle->handle = handle; + sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; + sf_handle->access_flags = access_flags; + kref_init(&sf_handle->refcount); + + mutex_lock(&sf_i->handle_list_mutex); + list_add(&sf_handle->head, &sf_i->handle_list); + mutex_unlock(&sf_i->handle_list_mutex); + + return sf_handle; +} + +static int vboxsf_file_open(struct inode *inode, struct file *file) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); struct shfl_createparms params = {}; struct vboxsf_handle *sf_handle; u32 access_flags = 0; int err; - sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); - if (!sf_handle) - return -ENOMEM; - /* * We check the value of params.handle afterwards to find out if * the call succeeded or failed, as the API does not seem to cleanly @@ -83,24 +105,15 @@ static int vboxsf_file_open(struct inode *inode, struct file *file) err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); if (err == 0 && params.handle == SHFL_HANDLE_NIL) err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT; - if (err) { - kfree(sf_handle); + if (err) return err; + + sf_handle = vboxsf_create_sf_handle(inode, params.handle, access_flags); + if (IS_ERR(sf_handle)) { + vboxsf_close(sbi->root, params.handle); + return PTR_ERR(sf_handle); } - /* the host may have given us different attr then requested */ - sf_i->force_restat = 1; - - /* init our handle struct and add it to the inode's handles list */ - sf_handle->handle = params.handle; - sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; - sf_handle->access_flags = access_flags; - kref_init(&sf_handle->refcount); - - mutex_lock(&sf_i->handle_list_mutex); - list_add(&sf_handle->head, &sf_i->handle_list); - mutex_unlock(&sf_i->handle_list_mutex); - file->private_data = sf_handle; return 0; } @@ -114,22 +127,26 @@ static void vboxsf_handle_release(struct kref *refcount) kfree(sf_handle); } -static int vboxsf_file_release(struct inode *inode, struct file *file) +void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle) { struct vboxsf_inode *sf_i = VBOXSF_I(inode); - struct vboxsf_handle *sf_handle = file->private_data; - - /* - * When a file is closed on our (the guest) side, we want any subsequent - * accesses done on the host side to see all changes done from our side. - */ - filemap_write_and_wait(inode->i_mapping); mutex_lock(&sf_i->handle_list_mutex); list_del(&sf_handle->head); mutex_unlock(&sf_i->handle_list_mutex); kref_put(&sf_handle->refcount, vboxsf_handle_release); +} + +static int vboxsf_file_release(struct inode *inode, struct file *file) +{ + /* + * When a file is closed on our (the guest) side, we want any subsequent + * accesses done on the host side to see all changes done from our side. + */ + filemap_write_and_wait(inode->i_mapping); + + vboxsf_release_sf_handle(inode, file->private_data); return 0; } diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h index 6a7a9cedebc6..9047befa66c5 100644 --- a/fs/vboxsf/vfsmod.h +++ b/fs/vboxsf/vfsmod.h @@ -18,6 +18,8 @@ #define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info) #define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode) +struct vboxsf_handle; + struct vboxsf_options { unsigned long ttl; kuid_t uid; @@ -80,6 +82,11 @@ extern const struct file_operations vboxsf_reg_fops; extern const struct address_space_operations vboxsf_reg_aops; extern const struct dentry_operations vboxsf_dentry_ops; +/* from file.c */ +struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode, + u64 handle, u32 access_flags); +void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle); + /* from utils.c */ struct inode *vboxsf_new_inode(struct super_block *sb); int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, From 52dfd86aa568e433b24357bb5fc725560f1e22d8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 12:54:18 +0100 Subject: [PATCH 0007/1469] vboxsf: Add support for the atomic_open directory-inode op Opening a new file is done in 2 steps on regular filesystems: 1. Call the create inode-op on the parent-dir to create an inode to hold the meta-data related to the file. 2. Call the open file-op to get a handle for the file. vboxsf however does not really use disk-backed inodes because it is based on passing through file-related system-calls through to the hypervisor. So both steps translate to an open(2) call being passed through to the hypervisor. With the handle returned by the first call immediately being closed again. Making 2 open calls for a single open(..., O_CREATE, ...) calls has 2 problems: a) It is not really efficient. b) It actually breaks some apps. An example of b) is doing a git clone inside a vboxsf mount. When git clone tries to create a tempfile to store the pak files which is downloading the following happens: 1. vboxsf_dir_mkfile() gets called with a mode of 0444 and succeeds. 2. vboxsf_file_open() gets called with file->f_flags containing O_RDWR. When the host is a Linux machine this fails because doing a open(..., O_RDWR) on a file which exists and has mode 0444 results in an -EPERM error. Other network-filesystems and fuse avoid the problem of needing to pass 2 open() calls to the other side by using the atomic_open directory-inode op. This commit fixes git clone not working inside a vboxsf mount, by adding support for the atomic_open directory-inode op. As an added bonus this should also make opening new files faster. The atomic_open implementation is modelled after the atomic_open implementations from the 9p and fuse code. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Reported-by: Ludovic Pouzenc Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 87d5b2fef592..c4769a9396c5 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -308,6 +308,53 @@ static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, return vboxsf_dir_create(parent, dentry, mode, true, true, NULL); } +static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry, + struct file *file, unsigned int flags, umode_t mode) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_handle *sf_handle; + struct dentry *res = NULL; + u64 handle; + int err; + + if (d_in_lookup(dentry)) { + res = vboxsf_dir_lookup(parent, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* Only creates */ + if (!(flags & O_CREAT) || d_really_is_positive(dentry)) + return finish_no_open(file, res); + + err = vboxsf_dir_create(parent, dentry, mode, false, flags & O_EXCL, &handle); + if (err) + goto out; + + sf_handle = vboxsf_create_sf_handle(d_inode(dentry), handle, SHFL_CF_ACCESS_READWRITE); + if (IS_ERR(sf_handle)) { + vboxsf_close(sbi->root, handle); + err = PTR_ERR(sf_handle); + goto out; + } + + err = finish_open(file, dentry, generic_file_open); + if (err) { + /* This also closes the handle passed to vboxsf_create_sf_handle() */ + vboxsf_release_sf_handle(d_inode(dentry), sf_handle); + goto out; + } + + file->private_data = sf_handle; + file->f_mode |= FMODE_CREATED; +out: + dput(res); + return err; +} + static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) { struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -428,6 +475,7 @@ const struct inode_operations vboxsf_dir_iops = { .lookup = vboxsf_dir_lookup, .create = vboxsf_dir_mkfile, .mkdir = vboxsf_dir_mkdir, + .atomic_open = vboxsf_dir_atomic_open, .rmdir = vboxsf_dir_unlink, .unlink = vboxsf_dir_unlink, .rename = vboxsf_dir_rename, From ca46ad2214473df1a6a9496be17156d65ba89b9f Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Jun 2021 18:37:42 +0930 Subject: [PATCH 0008/1469] ARM: dts: aspeed: Fix AST2600 machines line names Tacoma and Rainier both have a line-names array that is too long: gpio gpiochip0: gpio-line-names is length 232 but should be at most length 208 This was probably copied from an AST2500 device tree that did have more GPIOs on the controller. Fixes: e9b24b55ca4f ("ARM: dts: aspeed: rainier: Add gpio line names") Fixes: 2f68e4e7df67 ("ARM: dts: aspeed: tacoma: Add gpio line names") Link: https://lore.kernel.org/r/20210624090742.56640-1-joel@jms.id.au Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts | 5 +---- arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts index 941c0489479a..481d0ee1f85f 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts @@ -280,10 +280,7 @@ /*W0-W7*/ "","","","","","","","", /*X0-X7*/ "","","","","","","","", /*Y0-Y7*/ "","","","","","","","", - /*Z0-Z7*/ "","","","","","","","", - /*AA0-AA7*/ "","","","","","","","", - /*AB0-AB7*/ "","","","","","","","", - /*AC0-AC7*/ "","","","","","","",""; + /*Z0-Z7*/ "","","","","","","",""; pin_mclr_vpp { gpio-hog; diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts index e863ec088970..48038b2ef3df 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts @@ -136,10 +136,7 @@ /*W0-W7*/ "","","","","","","","", /*X0-X7*/ "","","","","","","","", /*Y0-Y7*/ "","","","","","","","", - /*Z0-Z7*/ "","","","","","","","", - /*AA0-AA7*/ "","","","","","","","", - /*AB0-AB7*/ "","","","","","","","", - /*AC0-AC7*/ "","","","","","","",""; + /*Z0-Z7*/ "","","","","","","",""; }; &fmc { From 33c8516841ea4fa12fdb8961711bf95095c607ee Mon Sep 17 00:00:00 2001 From: Rander Wang Date: Fri, 25 Jun 2021 15:50:39 -0500 Subject: [PATCH 0009/1469] ASoC: Intel: boards: fix xrun issue on platform with max98373 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On TGL platform with max98373 codec the trigger start sequence is fe first, then codec component and sdw link is the last. Recently a delay was introduced in max98373 codec driver and this resulted to the start of sdw stream transmission was delayed and the data transmitted by fw can't be consumed by sdw controller, so xrun happened. Adding delay in trigger function is a bad idea. This patch enable spk pin in prepare function and disable it in hw_free to avoid xrun issue caused by delay in trigger. Fixes: 3a27875e91fb ("ASoC: max98373: Added 30ms turn on/off time delay") BugLink: https://github.com/thesofproject/sof/issues/4066 Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Signed-off-by: Rander Wang Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210625205042.65181-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw_max98373.c | 77 +++++++++++++++-------- 1 file changed, 51 insertions(+), 26 deletions(-) diff --git a/sound/soc/intel/boards/sof_sdw_max98373.c b/sound/soc/intel/boards/sof_sdw_max98373.c index 0e7ed906b341..25daef910aee 100644 --- a/sound/soc/intel/boards/sof_sdw_max98373.c +++ b/sound/soc/intel/boards/sof_sdw_max98373.c @@ -55,43 +55,68 @@ static int spk_init(struct snd_soc_pcm_runtime *rtd) return ret; } -static int max98373_sdw_trigger(struct snd_pcm_substream *substream, int cmd) +static int mx8373_enable_spk_pin(struct snd_pcm_substream *substream, bool enable) { + struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); + struct snd_soc_dai *codec_dai; + struct snd_soc_dai *cpu_dai; int ret; + int j; - switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - case SNDRV_PCM_TRIGGER_RESUME: - case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - /* enable max98373 first */ - ret = max_98373_trigger(substream, cmd); - if (ret < 0) - break; + /* set spk pin by playback only */ + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) + return 0; - ret = sdw_trigger(substream, cmd); - break; - case SNDRV_PCM_TRIGGER_STOP: - case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - ret = sdw_trigger(substream, cmd); - if (ret < 0) - break; + cpu_dai = asoc_rtd_to_cpu(rtd, 0); + for_each_rtd_codec_dais(rtd, j, codec_dai) { + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(cpu_dai->component); + char pin_name[16]; - ret = max_98373_trigger(substream, cmd); - break; - default: - ret = -EINVAL; - break; + snprintf(pin_name, ARRAY_SIZE(pin_name), "%s Spk", + codec_dai->component->name_prefix); + + if (enable) + ret = snd_soc_dapm_enable_pin(dapm, pin_name); + else + ret = snd_soc_dapm_disable_pin(dapm, pin_name); + + if (!ret) + snd_soc_dapm_sync(dapm); } - return ret; + return 0; +} + +static int mx8373_sdw_prepare(struct snd_pcm_substream *substream) +{ + int ret = 0; + + /* according to soc_pcm_prepare dai link prepare is called first */ + ret = sdw_prepare(substream); + if (ret < 0) + return ret; + + return mx8373_enable_spk_pin(substream, true); +} + +static int mx8373_sdw_hw_free(struct snd_pcm_substream *substream) +{ + int ret = 0; + + /* according to soc_pcm_hw_free dai link free is called first */ + ret = sdw_hw_free(substream); + if (ret < 0) + return ret; + + return mx8373_enable_spk_pin(substream, false); } static const struct snd_soc_ops max_98373_sdw_ops = { .startup = sdw_startup, - .prepare = sdw_prepare, - .trigger = max98373_sdw_trigger, - .hw_free = sdw_hw_free, + .prepare = mx8373_sdw_prepare, + .trigger = sdw_trigger, + .hw_free = mx8373_sdw_hw_free, .shutdown = sdw_shutdown, }; From 0c4f8fd3ed9cb27228497f0ae495ea6cef7017b1 Mon Sep 17 00:00:00 2001 From: Peter Robinson Date: Sun, 27 Jun 2021 11:59:55 +0100 Subject: [PATCH 0010/1469] ASoC: remove zte zx dangling kconfig In commit dc98f1d we removed the zte zx sound drivers but there was a dangling Kconfig left around for the codec so fix this. Fixes: dc98f1d655ca ("ASoC: remove zte zx drivers") Signed-off-by: Peter Robinson Cc: Arnd Bergmann Cc: Mark Brown Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210627105955.3410015-1-pbrobinson@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 5 ----- 1 file changed, 5 deletions(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 3abdda48dc8e..bea7b47eddbe 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1813,11 +1813,6 @@ config SND_SOC_ZL38060 which consists of a Digital Signal Processor (DSP), several Digital Audio Interfaces (DAIs), analog outputs, and a block of 14 GPIOs. -config SND_SOC_ZX_AUD96P22 - tristate "ZTE ZX AUD96P22 CODEC" - depends on I2C - select REGMAP_I2C - # Amp config SND_SOC_LM4857 tristate From dd6fb8ff2210f74b056bf9234d0605e8c26a8ac0 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Sat, 26 Jun 2021 16:59:39 +0100 Subject: [PATCH 0011/1469] ASoC: wm_adsp: Correct wm_coeff_tlv_get handling When wm_coeff_tlv_get was updated it was accidentally switch to the _raw version of the helper causing it to ignore the current DSP state it should be checking. Switch the code back to the correct helper so that users can't read the controls when they arn't available. Fixes: 73ecf1a673d3 ("ASoC: wm_adsp: Correct cache handling of new kernel control API") Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20210626155941.12251-1-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 37aa020f23f6..59d876d36cfd 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1213,7 +1213,7 @@ static int wm_coeff_tlv_get(struct snd_kcontrol *kctl, mutex_lock(&ctl->dsp->pwr_lock); - ret = wm_coeff_read_ctrl_raw(ctl, ctl->cache, size); + ret = wm_coeff_read_ctrl(ctl, ctl->cache, size); if (!ret && copy_to_user(bytes, ctl->cache, size)) ret = -EFAULT; From e588332271b9cde6252dac8973b77e580cd639bd Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Sat, 26 Jun 2021 16:59:40 +0100 Subject: [PATCH 0012/1469] ASoC: wm_adsp: Add CCM_CORE_RESET to Halo start core When starting the Halo core it is advised to also write the core reset bit, this ensures the part starts up in the appropriate state. Omitting this doesn't cause issues on most parts but cs40l25 requires it and it is advised on all Halo parts. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20210626155941.12251-2-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 59d876d36cfd..549d98241dae 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -282,6 +282,7 @@ /* * HALO_CCM_CORE_CONTROL */ +#define HALO_CORE_RESET 0x00000200 #define HALO_CORE_EN 0x00000001 /* @@ -3333,7 +3334,8 @@ static int wm_halo_start_core(struct wm_adsp *dsp) { return regmap_update_bits(dsp->regmap, dsp->base + HALO_CCM_CORE_CONTROL, - HALO_CORE_EN, HALO_CORE_EN); + HALO_CORE_RESET | HALO_CORE_EN, + HALO_CORE_RESET | HALO_CORE_EN); } static void wm_halo_stop_core(struct wm_adsp *dsp) From 2b6a761be079f9fa8abf3157b5679a6f38885db4 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Sat, 26 Jun 2021 23:58:32 +0800 Subject: [PATCH 0013/1469] regulator: rtmv20: Fix wrong mask for strobe-polarity-high Fix wrong mask for strobe-polarity-high. Signed-off-by: ChiYuan Huang In-reply-to: Reviewed-by: Axel Lin Link: https://lore.kernel.org/r/1624723112-26653-1-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- drivers/regulator/rtmv20-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/rtmv20-regulator.c b/drivers/regulator/rtmv20-regulator.c index 852fb2596ffd..d7372599385e 100644 --- a/drivers/regulator/rtmv20-regulator.c +++ b/drivers/regulator/rtmv20-regulator.c @@ -36,7 +36,7 @@ #define RTMV20_WIDTH2_MASK GENMASK(7, 0) #define RTMV20_LBPLVL_MASK GENMASK(3, 0) #define RTMV20_LBPEN_MASK BIT(7) -#define RTMV20_STROBEPOL_MASK BIT(1) +#define RTMV20_STROBEPOL_MASK BIT(0) #define RTMV20_VSYNPOL_MASK BIT(1) #define RTMV20_FSINEN_MASK BIT(7) #define RTMV20_ESEN_MASK BIT(6) From 6549c46af8551b346bcc0b9043f93848319acd5c Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 27 Jun 2021 16:04:18 +0800 Subject: [PATCH 0014/1469] regulator: rt5033: Fix n_voltages settings for BUCK and LDO For linear regulators, the n_voltages should be (max - min) / step + 1. Buck voltage from 1v to 3V, per step 100mV, and vout mask is 0x1f. If value is from 20 to 31, the voltage will all be fixed to 3V. And LDO also, just vout range is different from 1.2v to 3v, step is the same. If value is from 18 to 31, the voltage will also be fixed to 3v. Signed-off-by: Axel Lin Reviewed-by: ChiYuan Huang Link: https://lore.kernel.org/r/20210627080418.1718127-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- include/linux/mfd/rt5033-private.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 2d1895c3efbf..40a0c2dfb80f 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -200,13 +200,13 @@ enum rt5033_reg { #define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32 +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21 /* RT5033 regulator LDO output voltage uV */ #define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U #define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32 +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19 /* RT5033 regulator SAFE LDO output voltage uV */ #define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U From 1988e0d84161dabd99d1c27033fbd6ee439bf432 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 4 Jun 2021 01:18:30 +0200 Subject: [PATCH 0015/1469] drm/panel: nt35510: Do not fail if DSI read fails Failing to read the MTP over DSI should not bring down the system and make us bail out from using the display, it turns out that this happens when toggling the display off and on, and that write is often still working so the display output is just fine. Printing an error is enough. Tested by killing the Gnome session repeatedly on the Samsung Skomer. Fixes: 899f24ed8d3a ("drm/panel: Add driver for Novatek NT35510-based panels") Cc: Stephan Gerhold Reported-by: newbyte@disroot.org Acked-by: Stefan Hansson Signed-off-by: Linus Walleij Link: https://patchwork.freedesktop.org/patch/msgid/20210603231830.3200040-1-linus.walleij@linaro.org --- drivers/gpu/drm/panel/panel-novatek-nt35510.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35510.c b/drivers/gpu/drm/panel/panel-novatek-nt35510.c index ef70140c5b09..873cbd38e6d3 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35510.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35510.c @@ -706,9 +706,7 @@ static int nt35510_power_on(struct nt35510 *nt) if (ret) return ret; - ret = nt35510_read_id(nt); - if (ret) - return ret; + nt35510_read_id(nt); /* Set up stuff in manufacturer control, page 1 */ ret = nt35510_send_long(nt, dsi, MCS_CMD_MAUCCTR, From 7c1a80e80cde008f271bae630d28cf684351e807 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 25 Jun 2021 13:23:54 +0300 Subject: [PATCH 0016/1469] net: xfrm: fix memory leak in xfrm_user_rcv_msg Syzbot reported memory leak in xfrm_user_rcv_msg(). The problem was is non-freed skb's frag_list. In skb_release_all() skb_release_data() will be called only in case of skb->head != NULL, but netlink_skb_destructor() sets head to NULL. So, allocated frag_list skb should be freed manualy, since consume_skb() won't take care of it Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Reported-and-tested-by: syzbot+fb347cf82c73a90efcca@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b47d613409b7..7aff641c717d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2811,6 +2811,16 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = link->doit(skb, nlh, attrs); + /* We need to free skb allocated in xfrm_alloc_compat() before + * returning from this function, because consume_skb() won't take + * care of frag_list since netlink destructor sets + * sbk->head to NULL. (see netlink_skb_destructor()) + */ + if (skb_has_frag_list(skb)) { + kfree_skb(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } + err: kvfree(nlh64); return err; From 2c70ff56e49ae219640689a0c86041c0f656046f Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 28 Jun 2021 23:04:58 +0200 Subject: [PATCH 0017/1469] ASoC: codecs: allow SSM2518 to be selected by the user Allow the Analog SSM2518 driver to be enabled without a large bunch of other drivers. Signed-off-by: Lucas Stach Link: https://lore.kernel.org/r/20210628210458.2508973-1-l.stach@pengutronix.de Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index bea7b47eddbe..3a42c4611414 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1325,7 +1325,7 @@ config SND_SOC_SSM2305 high-efficiency mono Class-D audio power amplifiers. config SND_SOC_SSM2518 - tristate + tristate "Analog Devices SSM2518 Class-D Amplifier" depends on I2C config SND_SOC_SSM2602 From 5db5dd5be70eaf808d9fd90174b957fc5c2912cb Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 30 Jun 2021 15:42:46 +0800 Subject: [PATCH 0018/1469] regulator: hi6421v600: Fix getting wrong drvdata that causes boot failure Since config.dev = pdev->dev.parent in current code, so dev_get_drvdata(rdev->dev.parent) actually returns the drvdata of the mfd device rather than the regulator. Fix it. Fixes: 9bc146acc331 ("regulator: hi6421v600: Fix setting wrong driver_data") Reported-by: Mauro Carvalho Chehab Signed-off-by: Axel Lin Tested-by: Mauro Carvalho Chehab Reviewed-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/20210630074246.2305166-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- drivers/regulator/hi6421v600-regulator.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/regulator/hi6421v600-regulator.c b/drivers/regulator/hi6421v600-regulator.c index 48922704f0e1..a8501e8720d0 100644 --- a/drivers/regulator/hi6421v600-regulator.c +++ b/drivers/regulator/hi6421v600-regulator.c @@ -98,10 +98,9 @@ static const unsigned int ldo34_voltages[] = { static int hi6421_spmi_regulator_enable(struct regulator_dev *rdev) { - struct hi6421_spmi_reg_priv *priv; + struct hi6421_spmi_reg_priv *priv = rdev_get_drvdata(rdev); int ret; - priv = dev_get_drvdata(rdev->dev.parent); /* cannot enable more than one regulator at one time */ mutex_lock(&priv->enable_mutex); @@ -119,9 +118,10 @@ static int hi6421_spmi_regulator_enable(struct regulator_dev *rdev) static unsigned int hi6421_spmi_regulator_get_mode(struct regulator_dev *rdev) { - struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev); + struct hi6421_spmi_reg_info *sreg; unsigned int reg_val; + sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc); regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val); if (reg_val & sreg->eco_mode_mask) @@ -133,9 +133,10 @@ static unsigned int hi6421_spmi_regulator_get_mode(struct regulator_dev *rdev) static int hi6421_spmi_regulator_set_mode(struct regulator_dev *rdev, unsigned int mode) { - struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev); + struct hi6421_spmi_reg_info *sreg; unsigned int val; + sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc); switch (mode) { case REGULATOR_MODE_NORMAL: val = 0; @@ -159,7 +160,9 @@ hi6421_spmi_regulator_get_optimum_mode(struct regulator_dev *rdev, int input_uV, int output_uV, int load_uA) { - struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev); + struct hi6421_spmi_reg_info *sreg; + + sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc); if (!sreg->eco_uA || ((unsigned int)load_uA > sreg->eco_uA)) return REGULATOR_MODE_NORMAL; @@ -252,13 +255,12 @@ static int hi6421_spmi_regulator_probe(struct platform_device *pdev) return -ENOMEM; mutex_init(&priv->enable_mutex); - platform_set_drvdata(pdev, priv); for (i = 0; i < ARRAY_SIZE(regulator_info); i++) { info = ®ulator_info[i]; config.dev = pdev->dev.parent; - config.driver_data = info; + config.driver_data = priv; config.regmap = pmic->regmap; rdev = devm_regulator_register(dev, &info->desc, &config); From e4a5c19888a5f8a9390860ca493e643be58c8791 Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Wed, 30 Jun 2021 10:45:19 +0200 Subject: [PATCH 0019/1469] spi: stm32h7: fix full duplex irq handler handling In case of Full-Duplex mode, DXP flag is set when RXP and TXP flags are set. But to avoid 2 different handlings, just add TXP and RXP flag in the mask instead of DXP, and then keep the initial handling of TXP and RXP events. Also rephrase comment about EOTIE which is one of the interrupt enable bits. It is not triggered by any event. Signed-off-by: Amelie Delaunay Signed-off-by: Alain Volmat Reviewed-by: Amelie Delaunay Link: https://lore.kernel.org/r/1625042723-661-3-git-send-email-alain.volmat@foss.st.com Signed-off-by: Mark Brown --- drivers/spi/spi-stm32.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 8ffcffbb8157..65b37c8dc49f 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -884,15 +884,18 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) ier = readl_relaxed(spi->base + STM32H7_SPI_IER); mask = ier; - /* EOTIE is triggered on EOT, SUSP and TXC events. */ + /* + * EOTIE enables irq from EOT, SUSP and TXC events. We need to set + * SUSP to acknowledge it later. TXC is automatically cleared + */ + mask |= STM32H7_SPI_SR_SUSP; /* - * When TXTF is set, DXPIE and TXPIE are cleared. So in case of - * Full-Duplex, need to poll RXP event to know if there are remaining - * data, before disabling SPI. + * DXPIE is set in Full-Duplex, one IT will be raised if TXP and RXP + * are set. So in case of Full-Duplex, need to poll TXP and RXP event. */ - if (spi->rx_buf && !spi->cur_usedma) - mask |= STM32H7_SPI_SR_RXP; + if ((spi->cur_comm == SPI_FULL_DUPLEX) && !spi->cur_usedma) + mask |= STM32H7_SPI_SR_TXP | STM32H7_SPI_SR_RXP; if (!(sr & mask)) { dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n", From 812bae32e5d50914f75a6e036d3bde39ca86b0c3 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Fri, 16 Apr 2021 02:51:13 -0500 Subject: [PATCH 0020/1469] ARM: dts: aspeed: Update e3c246d4i vuart properties This device-tree was merged with a provisional vuart IRQ-polarity property that was still under review and ended up taking a somewhat different form. This patch updates it to match the final form of the new vuart properties, which additionally allow specifying the SIRQ number and LPC address. Signed-off-by: Zev Weiss Reviewed-by: Andrew Jeffery Fixes: ca03042f0f12 ("serial: 8250_aspeed_vuart: add aspeed, lpc-io-reg and aspeed, lpc-interrupts DT properties") Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20210416075113.18047-1-zev@bewilderbeest.net Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts index 33e413ca07e4..9b4cf5ebe6d5 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts @@ -4,6 +4,7 @@ #include "aspeed-g5.dtsi" #include #include +#include /{ model = "ASRock E3C246D4I BMC"; @@ -73,7 +74,8 @@ &vuart { status = "okay"; - aspeed,sirq-active-high; + aspeed,lpc-io-reg = <0x2f8>; + aspeed,lpc-interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; }; &mac0 { From 2d6608b57c50c54c3e46649110e8ea5a40959c30 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Fri, 25 Jun 2021 15:40:17 +0930 Subject: [PATCH 0021/1469] ARM: dts: tacoma: Add phase corrections for eMMC The degree values were reversed out from the magic tap values of 7 (in) and 15 + inversion (out) initially suggested by Aspeed. With the patch tacoma survives several gigabytes of reads and writes using dd while without it locks up randomly during the boot process. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210625061017.1149942-1-andrew@aj.id.au Fixes: 2fc88f92359d ("mmc: sdhci-of-aspeed: Expose clock phase controls") Fixes: 961216c135a8 ("ARM: dts: aspeed: Add Rainier system") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts index 48038b2ef3df..e33153dcaea8 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts @@ -186,6 +186,7 @@ &emmc { status = "okay"; + clk-phase-mmc-hs200 = <36>, <270>; }; &fsim0 { From faffd1b2bde3ee428d6891961f6a60f8e08749d6 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Mon, 28 Jun 2021 11:06:05 +0930 Subject: [PATCH 0022/1469] ARM: dts: everest: Add phase corrections for eMMC The values were determined experimentally via boot tests, not by measuring the bus behaviour with a scope. We plan to do scope measurements to confirm or refine the values and will update the devicetree if necessary once these have been obtained. However, with the patch we can write and read data without issue, where as booting the system without the patch failed at the point of mounting the rootfs. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210628013605.1257346-1-andrew@aj.id.au Fixes: 2fc88f92359d ("mmc: sdhci-of-aspeed: Expose clock phase controls") Fixes: a5c5168478d7 ("ARM: dts: aspeed: Add Everest BMC machine") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts index d26a9e16ff7c..53c049daf853 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts @@ -2832,6 +2832,7 @@ &emmc { status = "okay"; + clk-phase-mmc-hs200 = <180>, <180>; }; &fsim0 { From ab4a49d36010564c70fe5586a4c2b1985866616f Mon Sep 17 00:00:00 2001 From: "B. J. Wyman" Date: Thu, 10 Jun 2021 20:29:41 +0000 Subject: [PATCH 0023/1469] ARM: dts: aspeed: everest: PSU #3 address change The third power supply had an I2C address conflict with another device in the system. The device will have the address changed from 6Ah to 6Dh. Signed-off-by: B. J. Wyman Reviewed-by: Eddie James Link: https://lore.kernel.org/r/20210610202940.3650554-1-bjwyman@gmail.com Fixes: d66d720b64e5 ("ARM: dts: aspeed: everest: Add power supply i2c devices") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts index 53c049daf853..aa24cac8e5be 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts @@ -406,15 +406,15 @@ reg = <0x69>; }; - power-supply@6a { - compatible = "ibm,cffps"; - reg = <0x6a>; - }; - power-supply@6b { compatible = "ibm,cffps"; reg = <0x6b>; }; + + power-supply@6d { + compatible = "ibm,cffps"; + reg = <0x6d>; + }; }; &i2c4 { From 0fc4dcc13f090c941abfab453a24945a4005b350 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 29 Jun 2021 11:39:07 +0200 Subject: [PATCH 0024/1469] bpf, devmap: Convert remaining READ_ONCE() to rcu_dereference_check() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There were a couple of READ_ONCE()-invocations left-over by the devmap RCU conversion. Convert these to rcu_dereference_check() as well to avoid complaints from sparse. Fixes: 782347b6bcad ("xdp: Add proper __rcu annotations to redirect map entries") Reported-by: kernel test robot Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Reviewed-by: Paul E. McKenney Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210629093907.573598-1-toke@redhat.com --- kernel/bpf/devmap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2546dafd6672..fdc20892837c 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -558,7 +558,8 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { - dst = READ_ONCE(dtab->netdev_map[i]); + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdp, exclude_ifindex)) continue; @@ -654,7 +655,8 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { - dst = READ_ONCE(dtab->netdev_map[i]); + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); if (!dst || dst->dev->ifindex == exclude_ifindex) continue; From 9cf76a72af6ab81030dea6481b1d7bdd814fbdaf Mon Sep 17 00:00:00 2001 From: Kyle Russell Date: Mon, 21 Jun 2021 21:09:41 -0400 Subject: [PATCH 0025/1469] ASoC: tlv320aic31xx: fix reversed bclk/wclk master bits These are backwards from Table 7-71 of the TLV320AIC3100 spec [1]. This was broken in 12eb4d66ba2e when BCLK_MASTER and WCLK_MASTER were converted from 0x08 and 0x04 to BIT(2) and BIT(3), respectively. -#define AIC31XX_BCLK_MASTER 0x08 -#define AIC31XX_WCLK_MASTER 0x04 +#define AIC31XX_BCLK_MASTER BIT(2) +#define AIC31XX_WCLK_MASTER BIT(3) Probably just a typo since the defines were not listed in bit order. [1] https://www.ti.com/lit/gpn/tlv320aic3100 Signed-off-by: Kyle Russell Link: https://lore.kernel.org/r/20210622010941.241386-1-bkylerussell@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic31xx.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h index 81952984613d..2513922a0292 100644 --- a/sound/soc/codecs/tlv320aic31xx.h +++ b/sound/soc/codecs/tlv320aic31xx.h @@ -151,8 +151,8 @@ struct aic31xx_pdata { #define AIC31XX_WORD_LEN_24BITS 0x02 #define AIC31XX_WORD_LEN_32BITS 0x03 #define AIC31XX_IFACE1_MASTER_MASK GENMASK(3, 2) -#define AIC31XX_BCLK_MASTER BIT(2) -#define AIC31XX_WCLK_MASTER BIT(3) +#define AIC31XX_BCLK_MASTER BIT(3) +#define AIC31XX_WCLK_MASTER BIT(2) /* AIC31XX_DATA_OFFSET */ #define AIC31XX_DATA_OFFSET_MASK GENMASK(7, 0) From 8888ef2304d0ae78f3d5ec19653fa7cc4ffdbd7a Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 23 Jun 2021 23:34:43 +0800 Subject: [PATCH 0026/1469] regulator: bd9576: Fix testing wrong flag in check_temp_flag_mismatch Fix trivial copy-paste typo. Signed-off-by: Axel Lin Reviewed-by: Matti Vaittinen Link: https://lore.kernel.org/r/20210623153443.623856-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- drivers/regulator/bd9576-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/bd9576-regulator.c b/drivers/regulator/bd9576-regulator.c index e16c3727db7a..aa42da4d141e 100644 --- a/drivers/regulator/bd9576-regulator.c +++ b/drivers/regulator/bd9576-regulator.c @@ -294,9 +294,9 @@ static bool check_temp_flag_mismatch(struct regulator_dev *rdev, int severity, struct bd957x_regulator_data *r) { if ((severity == REGULATOR_SEVERITY_ERR && - r->ovd_notif != REGULATOR_EVENT_OVER_TEMP) || + r->temp_notif != REGULATOR_EVENT_OVER_TEMP) || (severity == REGULATOR_SEVERITY_WARN && - r->ovd_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) { + r->temp_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) { dev_warn(rdev_get_dev(rdev), "Can't support both thermal WARN and ERR\n"); if (severity == REGULATOR_SEVERITY_WARN) From c36748ac545421d94a5091c754414c0f3664bf10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Thu, 1 Jul 2021 08:28:25 -0700 Subject: [PATCH 0027/1469] misc: eeprom: at24: Always append device id even if label property is set. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to append device id even if eeprom have a label property set as some platform can have multiple eeproms with same label and we can not register each of those with same label. Failing to register those eeproms trigger cascade failures on such platform (system is no longer working). This fix regression on such platform introduced with 4e302c3b568e Reported-by: Alexander Fomichev Fixes: 4e302c3b568e ("misc: eeprom: at24: fix NVMEM name with custom AT24 device name") Cc: stable@vger.kernel.org Signed-off-by: Jérôme Glisse Signed-off-by: Bartosz Golaszewski --- drivers/misc/eeprom/at24.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 7a6f01ace78a..305ffad131a2 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -714,23 +714,20 @@ static int at24_probe(struct i2c_client *client) } /* - * If the 'label' property is not present for the AT24 EEPROM, - * then nvmem_config.id is initialised to NVMEM_DEVID_AUTO, - * and this will append the 'devid' to the name of the NVMEM - * device. This is purely legacy and the AT24 driver has always - * defaulted to this. However, if the 'label' property is - * present then this means that the name is specified by the - * firmware and this name should be used verbatim and so it is - * not necessary to append the 'devid'. + * We initialize nvmem_config.id to NVMEM_DEVID_AUTO even if the + * label property is set as some platform can have multiple eeproms + * with same label and we can not register each of those with same + * label. Failing to register those eeproms trigger cascade failure + * on such platform. */ + nvmem_config.id = NVMEM_DEVID_AUTO; + if (device_property_present(dev, "label")) { - nvmem_config.id = NVMEM_DEVID_NONE; err = device_property_read_string(dev, "label", &nvmem_config.name); if (err) return err; } else { - nvmem_config.id = NVMEM_DEVID_AUTO; nvmem_config.name = dev_name(dev); } From 56ea7ed103b46970e171eb1c95916f393d64eeff Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Thu, 13 May 2021 17:31:03 -0700 Subject: [PATCH 0028/1469] igc: Fix use-after-free error during reset Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring. Failure to do so can cause invalid memory accesses. If igc_poll() runs while the controller is being reset this can lead to the driver try to free a skb that was already freed. Log message: [ 101.525242] refcount_t: underflow; use-after-free. [ 101.525251] WARNING: CPU: 1 PID: 646 at lib/refcount.c:28 refcount_warn_saturate+0xab/0xf0 [ 101.525259] Modules linked in: sch_etf(E) sch_mqprio(E) rfkill(E) intel_rapl_msr(E) intel_rapl_common(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) binfmt_misc(E) kvm_intel(E) kvm(E) irqbypass(E) crc32_pclmul(E) ghash_clmulni_intel(E) aesni_intel(E) mei_wdt(E) libaes(E) crypto_simd(E) cryptd(E) glue_helper(E) snd_hda_codec_hdmi(E) rapl(E) intel_cstate(E) snd_hda_intel(E) snd_intel_dspcfg(E) sg(E) soundwire_intel(E) intel_uncore(E) at24(E) soundwire_generic_allocation(E) iTCO_wdt(E) soundwire_cadence(E) intel_pmc_bxt(E) serio_raw(E) snd_hda_codec(E) iTCO_vendor_support(E) watchdog(E) snd_hda_core(E) snd_hwdep(E) snd_soc_core(E) snd_compress(E) snd_pcsp(E) soundwire_bus(E) snd_pcm(E) evdev(E) snd_timer(E) mei_me(E) snd(E) soundcore(E) mei(E) configfs(E) ip_tables(E) x_tables(E) autofs4(E) ext4(E) crc32c_generic(E) crc16(E) mbcache(E) jbd2(E) sd_mod(E) t10_pi(E) crc_t10dif(E) crct10dif_generic(E) i915(E) ahci(E) libahci(E) ehci_pci(E) igb(E) xhci_pci(E) ehci_hcd(E) [ 101.525303] drm_kms_helper(E) dca(E) xhci_hcd(E) libata(E) crct10dif_pclmul(E) cec(E) crct10dif_common(E) tsn(E) igc(E) e1000e(E) ptp(E) i2c_i801(E) crc32c_intel(E) psmouse(E) i2c_algo_bit(E) i2c_smbus(E) scsi_mod(E) lpc_ich(E) pps_core(E) usbcore(E) drm(E) button(E) video(E) [ 101.525318] CPU: 1 PID: 646 Comm: irq/37-enp7s0-T Tainted: G E 5.10.30-rt37-tsn1-rt-ipipe #ipipe [ 101.525320] Hardware name: SIEMENS AG SIMATIC IPC427D/A5E31233588, BIOS V17.02.09 03/31/2017 [ 101.525322] RIP: 0010:refcount_warn_saturate+0xab/0xf0 [ 101.525325] Code: 05 31 48 44 01 01 e8 f0 c6 42 00 0f 0b c3 80 3d 1f 48 44 01 00 75 90 48 c7 c7 78 a8 f3 a6 c6 05 0f 48 44 01 01 e8 d1 c6 42 00 <0f> 0b c3 80 3d fe 47 44 01 00 0f 85 6d ff ff ff 48 c7 c7 d0 a8 f3 [ 101.525327] RSP: 0018:ffffbdedc0917cb8 EFLAGS: 00010286 [ 101.525329] RAX: 0000000000000000 RBX: ffff98fd6becbf40 RCX: 0000000000000001 [ 101.525330] RDX: 0000000000000001 RSI: ffffffffa6f2700c RDI: 00000000ffffffff [ 101.525332] RBP: ffff98fd6becc14c R08: ffffffffa7463d00 R09: ffffbdedc0917c50 [ 101.525333] R10: ffffffffa74c3578 R11: 0000000000000034 R12: 00000000ffffff00 [ 101.525335] R13: ffff98fd6b0b1000 R14: 0000000000000039 R15: ffff98fd6be35c40 [ 101.525337] FS: 0000000000000000(0000) GS:ffff98fd6e240000(0000) knlGS:0000000000000000 [ 101.525339] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 101.525341] CR2: 00007f34135a3a70 CR3: 0000000150210003 CR4: 00000000001706e0 [ 101.525343] Call Trace: [ 101.525346] sock_wfree+0x9c/0xa0 [ 101.525353] unix_destruct_scm+0x7b/0xa0 [ 101.525358] skb_release_head_state+0x40/0x90 [ 101.525362] skb_release_all+0xe/0x30 [ 101.525364] napi_consume_skb+0x57/0x160 [ 101.525367] igc_poll+0xb7/0xc80 [igc] [ 101.525376] ? sched_clock+0x5/0x10 [ 101.525381] ? sched_clock_cpu+0xe/0x100 [ 101.525385] net_rx_action+0x14c/0x410 [ 101.525388] __do_softirq+0xe9/0x2f4 [ 101.525391] __local_bh_enable_ip+0xe3/0x110 [ 101.525395] ? irq_finalize_oneshot.part.47+0xe0/0xe0 [ 101.525398] irq_forced_thread_fn+0x6a/0x80 [ 101.525401] irq_thread+0xe8/0x180 [ 101.525403] ? wake_threads_waitq+0x30/0x30 [ 101.525406] ? irq_thread_check_affinity+0xd0/0xd0 [ 101.525408] kthread+0x183/0x1a0 [ 101.525412] ? kthread_park+0x80/0x80 [ 101.525415] ret_from_fork+0x22/0x30 Fixes: 13b5b7fd6a4a ("igc: Add support for Tx/Rx rings") Reported-by: Erez Geva Signed-off-by: Vinicius Costa Gomes Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 95323095094d..1d00a63eb935 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -232,6 +232,8 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } + tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++; From 7b292608db23ccbbfbfa50cdb155d01725d7a52e Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Thu, 13 May 2021 17:31:04 -0700 Subject: [PATCH 0029/1469] igb: Fix use-after-free error during reset Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring. Failure to do so can cause invalid memory accesses. If igb_poll() runs while the controller is reset this can lead to the driver try to free a skb that was already freed. (The crash is harder to reproduce with the igb driver, but the same potential problem exists as the code is identical to igc) Fixes: 7cc6fd4c60f2 ("igb: Don't bother clearing Tx buffer_info in igb_clean_tx_ring") Signed-off-by: Vinicius Costa Gomes Reported-by: Erez Geva Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 7e6435dc7e80..a61e2e5e95c0 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4835,6 +4835,8 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } + tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++; From 05682a0a61b6cbecd97a0f37f743b2cbfd516977 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 21 May 2021 12:50:19 -0700 Subject: [PATCH 0030/1469] igc: change default return of igc_read_phy_reg() Static analysis reports this problem igc_main.c:4944:20: warning: The left operand of '&' is a garbage value if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) && ~~~~~~~~ ^ phy_data is set by the call to igc_read_phy_reg() only if there is a read_reg() op, else it is unset and a 0 is returned. Change the return to -EOPNOTSUPP. Fixes: 208983f099d9 ("igc: Add watchdog") Signed-off-by: Tom Rix Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9e0bbb2e55e3..5901ed9fb545 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -578,7 +578,7 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data) if (hw->phy.ops.read_reg) return hw->phy.ops.read_reg(hw, offset, data); - return 0; + return -EOPNOTSUPP; } void igc_reinit_locked(struct igc_adapter *); From dd2aefcd5e37989ae5f90afdae44bbbf3a2990da Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 15:46:09 +0200 Subject: [PATCH 0031/1469] ixgbe: Fix an error handling path in 'ixgbe_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 6fabd715e6d8 ("ixgbe: Implement PCIe AER support") Signed-off-by: Christophe JAILLET Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ffff69efd78a..913253f8ecb4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11067,6 +11067,7 @@ err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From c6bc9e5ce5d37cb3e6b552f41b92a193db1806ab Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 22:00:05 +0200 Subject: [PATCH 0032/1469] igc: Fix an error handling path in 'igc_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: c9a11c23ceb6 ("igc: Add netdev") Signed-off-by: Christophe JAILLET Tested-by: Dvora Fuxbrumer Acked-by: Sasha Neftin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 1d00a63eb935..e29aadbc6744 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6056,6 +6056,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From fea03b1cebd653cd095f2e9a58cfe1c85661c363 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 22:08:33 +0200 Subject: [PATCH 0033/1469] igb: Fix an error handling path in 'igb_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 40a914fa72ab ("igb: Add support for pci-e Advanced Error Reporting") Signed-off-by: Christophe JAILLET Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a61e2e5e95c0..abc239b736fb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3615,6 +3615,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From e85e14d68f517ef12a5fb8123fff65526b35b6cd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:00:36 +0200 Subject: [PATCH 0034/1469] fm10k: Fix an error handling path in 'fm10k_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 19ae1b3fb99c ("fm10k: Add support for PCI power management and error handling") Signed-off-by: Christophe JAILLET Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index dbcae92bb18d..adfa2768f024 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2227,6 +2227,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_netdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From 4589075608420bc49fcef6e98279324bf2bb91ae Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:05:53 +0200 Subject: [PATCH 0035/1469] e1000e: Fix an error handling path in 'e1000_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 111b9dc5c981 ("e1000e: add aer support") Signed-off-by: Christophe JAILLET Acked-by: Sasha Neftin Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index d150dade06cf..757a54c39eef 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7664,6 +7664,7 @@ err_flashmap: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From af30cbd2f4d6d66a9b6094e0aa32420bc8b20e08 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:53:02 +0200 Subject: [PATCH 0036/1469] iavf: Fix an error handling path in 'iavf_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Christophe JAILLET Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index e612c24fa384..44bafedd09f2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3798,6 +3798,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_pci_reg: err_dma: From 6c19d772618fea40d9681f259368f284a330fd90 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Thu, 22 Apr 2021 10:19:23 +0000 Subject: [PATCH 0037/1469] igb: Check if num of q_vectors is smaller than max before array access Ensure that the adapter->q_vector[MAX_Q_VECTORS] array isn't accessed beyond its size. It was fixed by using a local variable num_q_vectors as a limit for loop index, and ensure that num_q_vectors is not bigger than MAX_Q_VECTORS. Fixes: 047e0030f1e6 ("igb: add new data structure for handling interrupts and NAPI") Signed-off-by: Aleksandr Loktionov Reviewed-by: Grzegorz Siwik Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Slawomir Laba Reviewed-by: Sylwester Dziedziuch Reviewed-by: Mateusz Palczewski Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index abc239b736fb..9470ba891483 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -931,6 +931,7 @@ static void igb_configure_msix(struct igb_adapter *adapter) **/ static int igb_request_msix(struct igb_adapter *adapter) { + unsigned int num_q_vectors = adapter->num_q_vectors; struct net_device *netdev = adapter->netdev; int i, err = 0, vector = 0, free_vector = 0; @@ -939,7 +940,13 @@ static int igb_request_msix(struct igb_adapter *adapter) if (err) goto err_out; - for (i = 0; i < adapter->num_q_vectors; i++) { + if (num_q_vectors > MAX_Q_VECTORS) { + num_q_vectors = MAX_Q_VECTORS; + dev_warn(&adapter->pdev->dev, + "The number of queue vectors (%d) is higher than max allowed (%d)\n", + adapter->num_q_vectors, MAX_Q_VECTORS); + } + for (i = 0; i < num_q_vectors; i++) { struct igb_q_vector *q_vector = adapter->q_vector[i]; vector++; From 382a7c20d9253bcd5715789b8179528d0f3de72c Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Fri, 11 Jun 2021 22:42:17 +0000 Subject: [PATCH 0038/1469] igb: Fix position of assignment to *ring Assignment to *ring should be done after correctness check of the argument queue. Fixes: 91db364236c8 ("igb: Refactor igb_configure_cbs()") Signed-off-by: Jedrzej Jagielski Acked-by: Vinicius Costa Gomes Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9470ba891483..171a7a629b20 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1685,14 +1685,15 @@ static bool is_any_txtime_enabled(struct igb_adapter *adapter) **/ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) { - struct igb_ring *ring = adapter->tx_ring[queue]; struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; u32 tqavcc, tqavctrl; u16 value; WARN_ON(hw->mac.type != e1000_i210); WARN_ON(queue < 0 || queue > 1); + ring = adapter->tx_ring[queue]; /* If any of the Qav features is enabled, configure queues as SR and * with HIGH PRIO. If none is, then configure them with LOW PRIO and From a3609ac24c18947737f5bc1746b8735814c521d1 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 29 Jun 2021 06:43:05 +0200 Subject: [PATCH 0039/1469] net: usb: asix: ax88772: suspend PHY on driver probe After probe/bind sequence is the PHY in active state, even if interface is stopped. As result, on some systems like Samsung Exynos5250 SoC based Arndale board, the ASIX PHY will be able to negotiate the link but fail to transmit the data. To handle it, suspend the PHY on probe. Fixes: e532a096be0e ("net: usb: asix: ax88772: add phylib support") Signed-off-by: Oleksij Rempel Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: David S. Miller --- drivers/net/usb/asix_devices.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index aec97b021a73..2c115216420a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -701,6 +701,7 @@ static int ax88772_init_phy(struct usbnet *dev) return ret; } + phy_suspend(priv->phydev); priv->phydev->mac_managed_pm = 1; phy_attached_info(priv->phydev); From b18114476a1432ad1db5d5605bc8cd131814d264 Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Tue, 29 Jun 2021 09:22:11 +0200 Subject: [PATCH 0040/1469] openvswitch: Optimize operation for key comparison In the current implement when comparing two flow keys, we will return result after comparing the whole key from start to end. In our optimization, we will return result in the first none-zero comparison, then we will improve the flow table looking up efficiency. Signed-off-by: Baowen Zheng Signed-off-by: Louis Peens Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/openvswitch/flow_table.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index c89c8da99f1a..d4a2db0b2299 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -670,13 +670,13 @@ static bool cmp_key(const struct sw_flow_key *key1, { const long *cp1 = (const long *)((const u8 *)key1 + key_start); const long *cp2 = (const long *)((const u8 *)key2 + key_start); - long diffs = 0; int i; for (i = key_start; i < key_end; i += sizeof(long)) - diffs |= *cp1++ ^ *cp2++; + if (*cp1++ ^ *cp2++) + return false; - return diffs == 0; + return true; } static bool flow_cmp_masked_key(const struct sw_flow *flow, From 996af62167d0e0ec69b938a3561e96f84ffff1aa Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Jun 2021 15:22:37 +0800 Subject: [PATCH 0041/1469] net/802/mrp: fix memleak in mrp_request_join() I got kmemleak report when doing fuzz test: BUG: memory leak unreferenced object 0xffff88810c239500 (size 64): comm "syz-executor940", pid 882, jiffies 4294712870 (age 14.631s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 01 00 00 00 01 02 00 04 ................ backtrace: [<00000000a323afa4>] slab_alloc_node mm/slub.c:2972 [inline] [<00000000a323afa4>] slab_alloc mm/slub.c:2980 [inline] [<00000000a323afa4>] __kmalloc+0x167/0x340 mm/slub.c:4130 [<000000005034ca11>] kmalloc include/linux/slab.h:595 [inline] [<000000005034ca11>] mrp_attr_create net/802/mrp.c:276 [inline] [<000000005034ca11>] mrp_request_join+0x265/0x550 net/802/mrp.c:530 [<00000000fcfd81f3>] vlan_mvrp_request_join+0x145/0x170 net/8021q/vlan_mvrp.c:40 [<000000009258546e>] vlan_dev_open+0x477/0x890 net/8021q/vlan_dev.c:292 [<0000000059acd82b>] __dev_open+0x281/0x410 net/core/dev.c:1609 [<000000004e6dc695>] __dev_change_flags+0x424/0x560 net/core/dev.c:8767 [<00000000471a09af>] rtnl_configure_link+0xd9/0x210 net/core/rtnetlink.c:3122 [<0000000037a4672b>] __rtnl_newlink+0xe08/0x13e0 net/core/rtnetlink.c:3448 [<000000008d5d0fda>] rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3488 [<000000004882fe39>] rtnetlink_rcv_msg+0x369/0xa10 net/core/rtnetlink.c:5552 [<00000000907e6c54>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504 [<00000000e7d7a8c4>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<00000000e7d7a8c4>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340 [<00000000e0645d50>] netlink_sendmsg+0x78e/0xc90 net/netlink/af_netlink.c:1929 [<00000000c24559b7>] sock_sendmsg_nosec net/socket.c:654 [inline] [<00000000c24559b7>] sock_sendmsg+0x139/0x170 net/socket.c:674 [<00000000fc210bc2>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350 [<00000000be4577b5>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404 Calling mrp_request_leave() after mrp_request_join(), the attr->state is set to MRP_APPLICANT_VO, mrp_attr_destroy() won't be called in last TX event in mrp_uninit_applicant(), the attr of applicant will be leaked. To fix this leak, iterate and free each attr of applicant before rerturning from mrp_uninit_applicant(). Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- net/802/mrp.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/802/mrp.c b/net/802/mrp.c index bea6e43d45a0..35e04cc5390c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); From a34dcbfa1475f18a8f1b1dc3dedb76d746874e61 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 29 Jun 2021 11:19:44 +0300 Subject: [PATCH 0042/1469] sctp: prevent info leak in sctp_make_heartbeat() The "hbinfo" struct has a 4 byte hole at the end so we have to zero it out to prevent stack information from being disclosed. Fixes: fe59379b9ab7 ("sctp: do the basic send and recv for PLPMTUD probe") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/sctp/sm_make_chunk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 6c08e5048d38..b8fa8f1a7277 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1163,7 +1163,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size) { - struct sctp_sender_hb_info hbinfo; + struct sctp_sender_hb_info hbinfo = {}; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, From 42ca63f980842918560b25f0244307fd83b4777c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Jun 2021 19:53:28 +0800 Subject: [PATCH 0043/1469] net/802/garp: fix memleak in garp_request_join() I got kmemleak report when doing fuzz test: BUG: memory leak unreferenced object 0xffff88810c909b80 (size 64): comm "syz", pid 957, jiffies 4295220394 (age 399.090s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 08 00 00 00 01 02 00 04 ................ backtrace: [<00000000ca1f2e2e>] garp_request_join+0x285/0x3d0 [<00000000bf153351>] vlan_gvrp_request_join+0x15b/0x190 [<0000000024005e72>] vlan_dev_open+0x706/0x980 [<00000000dc20c4d4>] __dev_open+0x2bb/0x460 [<0000000066573004>] __dev_change_flags+0x501/0x650 [<0000000035b42f83>] rtnl_configure_link+0xee/0x280 [<00000000a5e69de0>] __rtnl_newlink+0xed5/0x1550 [<00000000a5258f4a>] rtnl_newlink+0x66/0x90 [<00000000506568ee>] rtnetlink_rcv_msg+0x439/0xbd0 [<00000000b7eaeae1>] netlink_rcv_skb+0x14d/0x420 [<00000000c373ce66>] netlink_unicast+0x550/0x750 [<00000000ec74ce74>] netlink_sendmsg+0x88b/0xda0 [<00000000381ff246>] sock_sendmsg+0xc9/0x120 [<000000008f6a2db3>] ____sys_sendmsg+0x6e8/0x820 [<000000008d9c1735>] ___sys_sendmsg+0x145/0x1c0 [<00000000aa39dd8b>] __sys_sendmsg+0xfe/0x1d0 Calling garp_request_leave() after garp_request_join(), the attr->state is set to GARP_APPLICANT_VO, garp_attr_destroy() won't be called in last transmit event in garp_uninit_applicant(), the attr of applicant will be leaked. To fix this leak, iterate and free each attr of applicant before rerturning from garp_uninit_applicant(). Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- net/802/garp.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/802/garp.c b/net/802/garp.c index 400bd857e5f5..f6012f8e59f0 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); From 0dbffbb5335a1e3aa6855e4ee317e25e669dd302 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Jun 2021 07:12:45 -0700 Subject: [PATCH 0044/1469] net: annotate data race around sk_ll_usec sk_ll_usec is read locklessly from sk_can_busy_loop() while another thread can change its value in sock_setsockopt() This is correct but needs annotations. BUG: KCSAN: data-race in __skb_try_recv_datagram / sock_setsockopt write to 0xffff88814eb5f904 of 4 bytes by task 14011 on cpu 0: sock_setsockopt+0x1287/0x2090 net/core/sock.c:1175 __sys_setsockopt+0x14f/0x200 net/socket.c:2100 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88814eb5f904 of 4 bytes by task 14001 on cpu 1: sk_can_busy_loop include/net/busy_poll.h:41 [inline] __skb_try_recv_datagram+0x14f/0x320 net/core/datagram.c:273 unix_dgram_recvmsg+0x14c/0x870 net/unix/af_unix.c:2101 unix_seqpacket_recvmsg+0x5a/0x70 net/unix/af_unix.c:2067 ____sys_recvmsg+0x15d/0x310 include/linux/uio.h:244 ___sys_recvmsg net/socket.c:2598 [inline] do_recvmmsg+0x35c/0x9f0 net/socket.c:2692 __sys_recvmmsg net/socket.c:2771 [inline] __do_sys_recvmmsg net/socket.c:2794 [inline] __se_sys_recvmmsg net/socket.c:2787 [inline] __x64_sys_recvmmsg+0xcf/0x150 net/socket.c:2787 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0x00000101 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 14001 Comm: syz-executor.3 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/busy_poll.h | 2 +- net/core/sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 73af4a64a599..40296ed976a9 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -38,7 +38,7 @@ static inline bool net_busy_loop_on(void) static inline bool sk_can_busy_loop(const struct sock *sk) { - return sk->sk_ll_usec && !signal_pending(current); + return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); diff --git a/net/core/sock.c b/net/core/sock.c index ba1c0f75cd45..dd9599656c40 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1201,7 +1201,7 @@ set_sndbuf: if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); } break; case SO_PREFER_BUSY_POLL: From 873a1e3d207ae587a7a1cc1d84545146b449ea5d Mon Sep 17 00:00:00 2001 From: Harman Kalra Date: Tue, 29 Jun 2021 22:30:04 +0530 Subject: [PATCH 0045/1469] octeontx2-af: cn10k: Setting up lmtst map table Introducing a new mailbox to support updating lmt entries and common lmt base address scheme i.e. multiple pcifuncs can share lmt region to reduce L1 cache pressure for application. Parameters passed to mailbox includes the primary pcifunc value whose lmt regions will be shared by other secondary pcifuncs. Here secondary pcifunc will be the one who is calling the mailbox. For example: By default each pcifunc has its own LMT base address: PCIFUNC1 LMT_BASE_ADDR A PCIFUNC2 LMT_BASE_ADDR B PCIFUNC3 LMT_BASE_ADDR C PCIFUNC4 LMT_BASE_ADDR D Application will choose PCIFUNC1 as base/primary pcifunc and as and when other pcifunc(secondary pcifuncs) gets probed, this mailbox will be called and LMTST table will be updated as: PCIFUNC1 LMT_BASE_ADDR A PCIFUNC2 LMT_BASE_ADDR A PCIFUNC3 LMT_BASE_ADDR A PCIFUNC4 LMT_BASE_ADDR A On FLR lmtst map table gets resetted to the default lmt base addresses for all secondary pcifuncs. Signed-off-by: Harman Kalra Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.h | 7 + .../net/ethernet/marvell/octeontx2/af/rvu.c | 1 + .../net/ethernet/marvell/octeontx2/af/rvu.h | 4 + .../ethernet/marvell/octeontx2/af/rvu_cn10k.c | 140 ++++++++++++++++++ .../ethernet/marvell/octeontx2/af/rvu_reg.h | 5 + .../marvell/octeontx2/af/rvu_struct.h | 3 +- 6 files changed, 159 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 770d86262838..638db868125a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -134,6 +134,8 @@ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ +M(LMTST_TBL_SETUP, 0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req, \ + msg_rsp) \ M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ @@ -1278,6 +1280,11 @@ struct set_vf_perm { u64 flags; }; +struct lmtst_tbl_setup_req { + struct mbox_msghdr hdr; + u16 base_pcifunc; +}; + /* CPT mailbox error codes * Range 901 - 1000. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 0b092949d7ac..10cddf1ac7b9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2333,6 +2333,7 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc) rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA); + rvu_reset_lmt_map_tbl(rvu, pcifunc); rvu_detach_rsrcs(rvu, NULL, pcifunc); mutex_unlock(&rvu->flr_lock); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 9e5d9ba6f01e..3c0a7e981f72 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -243,6 +243,7 @@ struct rvu_pfvf { u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ + u64 lmt_base_addr; /* Preseving the pcifunc's lmtst base addr*/ unsigned long flags; }; @@ -754,6 +755,9 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); int rvu_set_channels_base(struct rvu *rvu); void rvu_program_channels(struct rvu *rvu); +/* CN10K RVU - LMT*/ +void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc); + #ifdef CONFIG_DEBUG_FS void rvu_dbg_init(struct rvu *rvu); void rvu_dbg_exit(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 7d9e71c6965f..87f56e1f32e3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -10,6 +10,146 @@ #include "cgx.h" #include "rvu_reg.h" +/* RVU LMTST */ +#define LMT_TBL_OP_READ 0 +#define LMT_TBL_OP_WRITE 1 +#define LMT_MAP_TABLE_SIZE (128 * 1024) +#define LMT_MAPTBL_ENTRY_SIZE 16 + +/* Function to perform operations (read/write) on lmtst map table */ +static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, + int lmt_tbl_op) +{ + void __iomem *lmt_map_base; + u64 tbl_base; + + tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + + lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE); + if (!lmt_map_base) { + dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); + return -ENOMEM; + } + + if (lmt_tbl_op == LMT_TBL_OP_READ) { + *val = readq(lmt_map_base + index); + } else { + writeq((*val), (lmt_map_base + index)); + /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S + * changes effective. Write 1 for flush and read is being used as a + * barrier and sets up a data dependency. Write to 0 after a write + * to 1 to complete the flush. + */ + rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, BIT_ULL(0)); + rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CTL); + rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, 0x00); + } + + iounmap(lmt_map_base); + return 0; +} + +static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) +{ + return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) + + (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; +} + +int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, + struct lmtst_tbl_setup_req *req, + struct msg_rsp *rsp) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); + u32 pri_tbl_idx, sec_tbl_idx; + int err = 0; + u64 val; + + /* Reconfiguring lmtst map table in lmt region shared mode i.e. make + * multiple PF_FUNCs to share an LMTLINE region, so primary/base + * pcifunc (which is passed as an argument to mailbox) is the one + * whose lmt base address will be shared among other secondary + * pcifunc (will be the one who is calling this mailbox). + */ + if (req->base_pcifunc) { + /* Calculating the LMT table index equivalent to primary + * pcifunc. + */ + pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc); + + /* Truncating secondary pcifunc to calculate the LMT table index + * equivalent to secondary pcifunc. + */ + sec_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->hdr.pcifunc); + /* Read the base lmt addr of the secondary pcifunc */ + err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, + LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + sec_tbl_idx, err); + goto error; + } + + /* Storing the seondary's lmt base address as this needs to be + * reverted in FLR. Also making sure this default value doesn't + * get overwritten on multiple calls to this mailbox. + */ + if (!pfvf->lmt_base_addr) + pfvf->lmt_base_addr = val; + + /* Read the base lmt addr of the primary pcifunc */ + err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val, + LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + pri_tbl_idx, err); + goto error; + } + + /* Update the base lmt addr of secondary with primary's base + * lmt addr. + */ + err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, + LMT_TBL_OP_WRITE); + if (err) { + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + sec_tbl_idx, err); + goto error; + } + } + +error: + return err; +} + +/* Resetting the lmtst map table to original base addresses */ +void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + u32 tbl_idx; + int err; + + if (is_rvu_otx2(rvu)) + return; + + if (pfvf->lmt_base_addr) { + /* This corresponds to lmt map table index */ + tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc); + /* Reverting back original lmt base addr for respective + * pcifunc. + */ + err = lmtst_map_table_ops(rvu, tbl_idx, &pfvf->lmt_base_addr, + LMT_TBL_OP_WRITE); + if (err) + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + tbl_idx, err); + pfvf->lmt_base_addr = 0; + } +} + int rvu_set_channels_base(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 76837d5e19c6..61bafe956aae 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -692,4 +692,9 @@ #define LBK_LINK_CFG_ID_MASK GENMASK_ULL(11, 6) #define LBK_LINK_CFG_BASE_MASK GENMASK_ULL(5, 0) +/* APR */ +#define APR_AF_LMT_CFG (0x000ull) +#define APR_AF_LMT_MAP_BASE (0x008ull) +#define APR_AF_LMT_CTL (0x010ull) + #endif /* RVU_REG_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 14aa8e37ea41..5bbe6727d11d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -35,7 +35,8 @@ enum rvu_block_addr_e { BLKADDR_NDC_NPA0 = 0xeULL, BLKADDR_NDC_NIX1_RX = 0x10ULL, BLKADDR_NDC_NIX1_TX = 0x11ULL, - BLK_COUNT = 0x12ULL, + BLKADDR_APR = 0x16ULL, + BLK_COUNT = 0x17ULL, }; /* RVU Block Type Enumeration */ From 893ae97214c385be02f8ec097298cc48c7f0d905 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 29 Jun 2021 22:30:05 +0530 Subject: [PATCH 0046/1469] octeontx2-af: cn10k: Support configurable LMTST regions This patch extends the lmtst_tbl_setup_req mbox to support run time LMTST configuration. RVU PF/VF and DPDK/ODP allocates a LMT region, creates a translation entry for a device via VFIO IOCTLs. This IOVA is shared with AF through above mbox. AF then uses RVU_SMMU transulation Widget and gets PA for the IOVA and updates the LMTtable entry for that device. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.h | 3 + .../ethernet/marvell/octeontx2/af/rvu_cn10k.c | 130 +++++++++++++----- .../ethernet/marvell/octeontx2/af/rvu_reg.h | 5 + 3 files changed, 103 insertions(+), 35 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 638db868125a..9672cbf8a90a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1283,6 +1283,9 @@ struct set_vf_perm { struct lmtst_tbl_setup_req { struct mbox_msghdr hdr; u16 base_pcifunc; + u8 use_local_lmt_region; + u64 lmt_iova; + u64 rsvd[4]; }; /* CPT mailbox error codes diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 87f56e1f32e3..8d48b64485c6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -55,14 +55,101 @@ static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; } +static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, + u64 iova, u64 *lmt_addr) +{ + u64 pa, val, pf; + int err; + + if (!iova) { + dev_err(rvu->dev, "%s Requested Null address for transulation\n", __func__); + return -EINVAL; + } + + rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); + pf = rvu_get_pf(pcifunc) & 0x1F; + val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | + ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF); + rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val); + + err = rvu_poll_reg(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS, BIT_ULL(0), false); + if (err) { + dev_err(rvu->dev, "%s LMTLINE iova transulation failed\n", __func__); + return err; + } + val = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS); + if (val & ~0x1ULL) { + dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val); + return -EIO; + } + /* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21] + * PA[11:0] = IOVA[11:0] + */ + pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21; + pa &= GENMASK_ULL(39, 0); + *lmt_addr = (pa << 12) | (iova & 0xFFF); + + return 0; +} + +static int rvu_update_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 lmt_addr) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + u32 tbl_idx; + int err = 0; + u64 val; + + /* Read the current lmt addr of pcifunc */ + tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc); + err = lmtst_map_table_ops(rvu, tbl_idx, &val, LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + tbl_idx, err); + return err; + } + + /* Storing the seondary's lmt base address as this needs to be + * reverted in FLR. Also making sure this default value doesn't + * get overwritten on multiple calls to this mailbox. + */ + if (!pfvf->lmt_base_addr) + pfvf->lmt_base_addr = val; + + /* Update the LMT table with new addr */ + err = lmtst_map_table_ops(rvu, tbl_idx, &lmt_addr, LMT_TBL_OP_WRITE); + if (err) { + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + tbl_idx, err); + return err; + } + return 0; +} + int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, struct lmtst_tbl_setup_req *req, struct msg_rsp *rsp) { - struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); - u32 pri_tbl_idx, sec_tbl_idx; + u64 lmt_addr, val; + u32 pri_tbl_idx; int err = 0; - u64 val; + + /* Check if PF_FUNC wants to use it's own local memory as LMTLINE + * region, if so, convert that IOVA to physical address and + * populate LMT table with that address + */ + if (req->use_local_lmt_region) { + err = rvu_get_lmtaddr(rvu, req->hdr.pcifunc, + req->lmt_iova, &lmt_addr); + if (err < 0) + return err; + + /* Update the lmt addr for this PFFUNC in the LMT table */ + err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, lmt_addr); + if (err) + return err; + } /* Reconfiguring lmtst map table in lmt region shared mode i.e. make * multiple PF_FUNCs to share an LMTLINE region, so primary/base @@ -76,27 +163,6 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, */ pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc); - /* Truncating secondary pcifunc to calculate the LMT table index - * equivalent to secondary pcifunc. - */ - sec_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->hdr.pcifunc); - /* Read the base lmt addr of the secondary pcifunc */ - err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, - LMT_TBL_OP_READ); - if (err) { - dev_err(rvu->dev, - "Failed to read LMT map table: index 0x%x err %d\n", - sec_tbl_idx, err); - goto error; - } - - /* Storing the seondary's lmt base address as this needs to be - * reverted in FLR. Also making sure this default value doesn't - * get overwritten on multiple calls to this mailbox. - */ - if (!pfvf->lmt_base_addr) - pfvf->lmt_base_addr = val; - /* Read the base lmt addr of the primary pcifunc */ err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val, LMT_TBL_OP_READ); @@ -104,24 +170,18 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, dev_err(rvu->dev, "Failed to read LMT map table: index 0x%x err %d\n", pri_tbl_idx, err); - goto error; + return err; } /* Update the base lmt addr of secondary with primary's base * lmt addr. */ - err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, - LMT_TBL_OP_WRITE); - if (err) { - dev_err(rvu->dev, - "Failed to update LMT map table: index 0x%x err %d\n", - sec_tbl_idx, err); - goto error; - } + err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, val); + if (err) + return err; } -error: - return err; + return 0; } /* Resetting the lmtst map table to original base addresses */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 61bafe956aae..8b01ef6e2c99 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -49,6 +49,11 @@ #define RVU_AF_PFX_VF_BAR4_ADDR (0x5400 | (a) << 4) #define RVU_AF_PFX_VF_BAR4_CFG (0x5600 | (a) << 4) #define RVU_AF_PFX_LMTLINE_ADDR (0x5800 | (a) << 4) +#define RVU_AF_SMMU_ADDR_REQ (0x6000) +#define RVU_AF_SMMU_TXN_REQ (0x6008) +#define RVU_AF_SMMU_ADDR_RSP_STS (0x6010) +#define RVU_AF_SMMU_ADDR_TLN (0x6018) +#define RVU_AF_SMMU_TLN_FLIT1 (0x6030) /* Admin function's privileged PF/VF registers */ #define RVU_PRIV_CONST (0x8000000) From 5c0512072f6517326d9fba083c4467f173ddd984 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 29 Jun 2021 22:30:06 +0530 Subject: [PATCH 0047/1469] octeontx2-pf: cn10k: Use runtime allocated LMTLINE region The current driver uses static LMTST region allocated by firmware. This memory gets populated as PF/VF BAR2. RVU PF/VF driver ioremap the memory as device memory for NIX/NPA operation. Since the memory is mapped as device memory we see performance degration. To address this issue this patch implements runtime memory allocation. RVU PF/VF allocates memory during device probe and share the base address with RVU AF. RVU AF then configure the LMT MAP table accordingly. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/nic/cn10k.c | 93 ++++++++----------- .../ethernet/marvell/octeontx2/nic/cn10k.h | 3 +- .../marvell/octeontx2/nic/otx2_common.h | 7 +- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 17 ++-- .../marvell/octeontx2/nic/otx2_txrx.h | 1 + .../ethernet/marvell/octeontx2/nic/otx2_vf.c | 12 +-- 6 files changed, 57 insertions(+), 76 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 1b08896b46d2..184de9466286 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -22,69 +22,52 @@ static struct dev_hw_ops cn10k_hw_ops = { .refill_pool_ptrs = cn10k_refill_pool_ptrs, }; -int cn10k_pf_lmtst_init(struct otx2_nic *pf) +int cn10k_lmtst_init(struct otx2_nic *pfvf) { - int size, num_lines; - u64 base; - if (!test_bit(CN10K_LMTST, &pf->hw.cap_flag)) { - pf->hw_ops = &otx2_hw_ops; + struct lmtst_tbl_setup_req *req; + int qcount, err; + + if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { + pfvf->hw_ops = &otx2_hw_ops; return 0; } - pf->hw_ops = &cn10k_hw_ops; - base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) + - (MBOX_SIZE * (pf->total_vfs + 1)); + pfvf->hw_ops = &cn10k_hw_ops; + qcount = pfvf->hw.max_queues; + /* LMTST lines allocation + * qcount = num_online_cpus(); + * NPA = TX + RX + XDP. + * NIX = TX * 32 (For Burst SQE flush). + */ + pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32); + pfvf->npa_lmt_lines = qcount * 3; + pfvf->nix_lmt_size = LMT_BURST_SIZE * LMT_LINE_SIZE; - size = pci_resource_len(pf->pdev, PCI_MBOX_BAR_NUM) - - (MBOX_SIZE * (pf->total_vfs + 1)); - - pf->hw.lmt_base = ioremap(base, size); - - if (!pf->hw.lmt_base) { - dev_err(pf->dev, "Unable to map PF LMTST region\n"); + mutex_lock(&pfvf->mbox.lock); + req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); return -ENOMEM; } - /* FIXME: Get the num of LMTST lines from LMT table */ - pf->tot_lmt_lines = size / LMT_LINE_SIZE; - num_lines = (pf->tot_lmt_lines - NIX_LMTID_BASE) / - pf->hw.tx_queues; - /* Number of LMT lines per SQ queues */ - pf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines; + req->use_local_lmt_region = true; + + err = qmem_alloc(pfvf->dev, &pfvf->dync_lmt, pfvf->tot_lmt_lines, + LMT_LINE_SIZE); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + pfvf->hw.lmt_base = (u64 *)pfvf->dync_lmt->base; + req->lmt_iova = (u64)pfvf->dync_lmt->iova; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + mutex_unlock(&pfvf->mbox.lock); - pf->nix_lmt_size = pf->nix_lmt_lines * LMT_LINE_SIZE; return 0; } - -int cn10k_vf_lmtst_init(struct otx2_nic *vf) -{ - int size, num_lines; - - if (!test_bit(CN10K_LMTST, &vf->hw.cap_flag)) { - vf->hw_ops = &otx2_hw_ops; - return 0; - } - - vf->hw_ops = &cn10k_hw_ops; - size = pci_resource_len(vf->pdev, PCI_MBOX_BAR_NUM); - vf->hw.lmt_base = ioremap_wc(pci_resource_start(vf->pdev, - PCI_MBOX_BAR_NUM), - size); - if (!vf->hw.lmt_base) { - dev_err(vf->dev, "Unable to map VF LMTST region\n"); - return -ENOMEM; - } - - vf->tot_lmt_lines = size / LMT_LINE_SIZE; - /* LMTST lines per SQ */ - num_lines = (vf->tot_lmt_lines - NIX_LMTID_BASE) / - vf->hw.tx_queues; - vf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines; - vf->nix_lmt_size = vf->nix_lmt_lines * LMT_LINE_SIZE; - return 0; -} -EXPORT_SYMBOL(cn10k_vf_lmtst_init); +EXPORT_SYMBOL(cn10k_lmtst_init); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) { @@ -93,9 +76,11 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) struct otx2_snd_queue *sq; sq = &pfvf->qset.sq[qidx]; - sq->lmt_addr = (__force u64 *)((u64)pfvf->hw.nix_lmt_base + + sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base + (qidx * pfvf->nix_lmt_size)); + sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE); + /* Get memory to put this msg */ aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); if (!aq) @@ -158,15 +143,13 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) { - struct otx2_nic *pfvf = dev; - int lmt_id = NIX_LMTID_BASE + (qidx * pfvf->nix_lmt_lines); u64 val = 0, tar_addr = 0; /* FIXME: val[0:10] LMT_ID. * [12:15] no of LMTST - 1 in the burst. * [19:63] data size of each LMTST in the burst except first. */ - val = (lmt_id & 0x7FF); + val = (sq->lmt_id & 0x7FF); /* Target address for LMTST flush tells HW how many 128bit * words are present. * tar_addr[6:4] size of first LMTST - 1 in units of 128b. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index 71292a4cf1f3..1a1ae334477d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -12,8 +12,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); -int cn10k_pf_lmtst_init(struct otx2_nic *pf); -int cn10k_vf_lmtst_init(struct otx2_nic *vf); +int cn10k_lmtst_init(struct otx2_nic *pfvf); int cn10k_free_all_ipolicers(struct otx2_nic *pfvf); int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf); int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 234b330f3183..20a9c69f020f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -218,8 +218,8 @@ struct otx2_hw { unsigned long cap_flag; #define LMT_LINE_SIZE 128 -#define NIX_LMTID_BASE 72 /* RX + TX + XDP */ - void __iomem *lmt_base; +#define LMT_BURST_SIZE 32 /* 32 LMTST lines for burst SQE flush */ + u64 *lmt_base; u64 *npa_lmt_base; u64 *nix_lmt_base; }; @@ -363,8 +363,9 @@ struct otx2_nic { /* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */ int nix_blkaddr; /* LMTST Lines info */ + struct qmem *dync_lmt; u16 tot_lmt_lines; - u16 nix_lmt_lines; + u16 npa_lmt_lines; u32 nix_lmt_size; struct otx2_ptp *ptp; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 59912f73417b..088c28df849d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1533,10 +1533,10 @@ int otx2_open(struct net_device *netdev) if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) { /* Reserve LMT lines for NPA AURA batch free */ - pf->hw.npa_lmt_base = (__force u64 *)pf->hw.lmt_base; + pf->hw.npa_lmt_base = pf->hw.lmt_base; /* Reserve LMT lines for NIX TX */ - pf->hw.nix_lmt_base = (__force u64 *)((u64)pf->hw.npa_lmt_base + - (NIX_LMTID_BASE * LMT_LINE_SIZE)); + pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base + + (pf->npa_lmt_lines * LMT_LINE_SIZE)); } err = otx2_init_hw_resources(pf); @@ -2526,7 +2526,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_detach_rsrc; - err = cn10k_pf_lmtst_init(pf); + err = cn10k_lmtst_init(pf); if (err) goto err_detach_rsrc; @@ -2630,8 +2630,8 @@ err_del_mcam_entries: err_ptp_destroy: otx2_ptp_destroy(pf); err_detach_rsrc: - if (hw->lmt_base) - iounmap(hw->lmt_base); + if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) + qmem_free(pf->dev, pf->dync_lmt); otx2_detach_resources(&pf->mbox); err_disable_mbox_intr: otx2_disable_mbox_intr(pf); @@ -2772,9 +2772,8 @@ static void otx2_remove(struct pci_dev *pdev) otx2_mcam_flow_del(pf); otx2_shutdown_tc(pf); otx2_detach_resources(&pf->mbox); - if (pf->hw.lmt_base) - iounmap(pf->hw.lmt_base); - + if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) + qmem_free(pf->dev, pf->dync_lmt); otx2_disable_mbox_intr(pf); otx2_pfaf_mbox_destroy(pf); pci_free_irq_vectors(pf->pdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 52486c1f0973..2f144e2cf436 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -83,6 +83,7 @@ struct otx2_snd_queue { u16 num_sqbs; u16 sqe_thresh; u8 sqe_per_sqb; + u32 lmt_id; u64 io_addr; u64 *aura_fc_addr; u64 *lmt_addr; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 13a908f75ba0..a8bee5aefec1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -609,7 +609,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_detach_rsrc; - err = cn10k_vf_lmtst_init(vf); + err = cn10k_lmtst_init(vf); if (err) goto err_detach_rsrc; @@ -667,8 +667,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_unreg_netdev: unregister_netdev(netdev); err_detach_rsrc: - if (hw->lmt_base) - iounmap(hw->lmt_base); + if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) + qmem_free(vf->dev, vf->dync_lmt); otx2_detach_resources(&vf->mbox); err_disable_mbox_intr: otx2vf_disable_mbox_intr(vf); @@ -700,10 +700,8 @@ static void otx2vf_remove(struct pci_dev *pdev) destroy_workqueue(vf->otx2_wq); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); - - if (vf->hw.lmt_base) - iounmap(vf->hw.lmt_base); - + if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) + qmem_free(vf->dev, vf->dync_lmt); otx2vf_vfaf_mbox_destroy(vf); pci_free_irq_vectors(vf->pdev); pci_set_drvdata(pdev, NULL); From b71d09871566a20ae8a1064e50f1e94813b18482 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 29 Jun 2021 23:32:15 +0300 Subject: [PATCH 0048/1469] net: dsa: return -EOPNOTSUPP when driver does not implement .port_lag_join The DSA core has a layered structure, and even though we end up returning 0 (success) to user space when setting a bonding/team upper that can't be offloaded, some parts of the framework actually need to know that we couldn't offload that. For example, if dsa_switch_lag_join returns 0 as it currently does, dsa_port_lag_join has no way to tell a successful offload from a software fallback, and it will call dsa_port_bridge_join afterwards. Then we'll think we're offloading the bridge master of the LAG, when in fact we're not even offloading the LAG. In turn, this will make us set skb->offload_fwd_mark = true, which is incorrect and the bridge doesn't like it. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/switch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/switch.c b/net/dsa/switch.c index af71b8638098..248455145982 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -427,7 +427,7 @@ static int dsa_switch_lag_join(struct dsa_switch *ds, info->port, info->lag, info->info); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_lag_leave(struct dsa_switch *ds, @@ -440,7 +440,7 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return ds->ops->crosschip_lag_leave(ds, info->sw_index, info->port, info->lag); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_mdb_add(struct dsa_switch *ds, From 5a3c680aa2c12c90c44af383fe6882a39875ab81 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Tue, 29 Jun 2021 17:14:19 -0700 Subject: [PATCH 0049/1469] net: bcmgenet: ensure EXT_ENERGY_DET_MASK is clear Setting the EXT_ENERGY_DET_MASK bit allows the port energy detection logic of the internal PHY to prevent the system from sleeping. Some internal PHYs will report that energy is detected when the network interface is closed which can prevent the system from going to sleep if WoL is enabled when the interface is brought down. Since the driver does not support waking the system on this logic, this commit clears the bit whenever the internal PHY is powered up and the other logic for manipulating the bit is removed since it serves no useful function. Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Doug Berger Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 17 ++--------------- .../net/ethernet/broadcom/genet/bcmgenet_wol.c | 6 ------ 2 files changed, 2 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 41f7f078cd27..35e9956e930c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1640,7 +1640,8 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, switch (mode) { case GENET_POWER_PASSIVE: - reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS | + EXT_ENERGY_DET_MASK); if (GENET_IS_V5(priv)) { reg &= ~(EXT_PWR_DOWN_PHY_EN | EXT_PWR_DOWN_PHY_RD | @@ -3292,7 +3293,6 @@ static int bcmgenet_open(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); unsigned long dma_ctrl; - u32 reg; int ret; netif_dbg(priv, ifup, dev, "bcmgenet_open\n"); @@ -3318,12 +3318,6 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - if (priv->internal_phy) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - /* Disable RX/TX DMA and flush TX queues */ dma_ctrl = bcmgenet_dma_disable(priv); @@ -4139,7 +4133,6 @@ static int bcmgenet_resume(struct device *d) struct bcmgenet_priv *priv = netdev_priv(dev); struct bcmgenet_rxnfc_rule *rule; unsigned long dma_ctrl; - u32 reg; int ret; if (!netif_running(dev)) @@ -4176,12 +4169,6 @@ static int bcmgenet_resume(struct device *d) if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) bcmgenet_hfb_create_rxnfc_filter(priv, rule); - if (priv->internal_phy) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - /* Disable RX/TX DMA and flush TX queues */ dma_ctrl = bcmgenet_dma_disable(priv); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index facde824bcaa..e31a5a397f11 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -186,12 +186,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, reg |= CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); - if (priv->hw_params->flags & GENET_HAS_EXT) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg &= ~EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - reg = UMAC_IRQ_MPD_R; if (hfb_enable) reg |= UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM; From 650b2a846dddf33321489597287e6d825ec1d0ba Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 29 Jun 2021 23:30:36 -0400 Subject: [PATCH 0050/1469] sctp: check pl.raise_count separately from its increment As Marcelo's suggestion this will make code more clear to read. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/transport.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 5f23804f21c7..397a6244dd97 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -335,10 +335,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + } else if (t->pl.state == SCTP_PL_COMPLETE) { + t->pl.raise_count++; + if (t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } } } From 1d11fa231cabeae09a95cb3e4cf1d9dd34e00f08 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 29 Jun 2021 23:34:08 -0400 Subject: [PATCH 0051/1469] sctp: move 198 addresses from unusable to private scope MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The doc draft-stewart-tsvwg-sctp-ipv4-00 that restricts 198 addresses was never published. These addresses as private addresses should be allowed to use in SCTP. As Michael Tuexen suggested, this patch is to move 198 addresses from unusable to private scope. Reported-by: Sérgio Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/constants.h | 4 +--- net/sctp/protocol.c | 3 ++- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 265fffa33dad..5859e0a16a58 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -360,8 +360,7 @@ enum { #define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK /* Based on IPv4 scoping , - * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, - * 192.88.99.0/24. + * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24. * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP * addresses. */ @@ -369,7 +368,6 @@ enum { ((htonl(INADDR_BROADCAST) == a) || \ ipv4_is_multicast(a) || \ ipv4_is_zeronet(a) || \ - ipv4_is_test_198(a) || \ ipv4_is_anycast_6to4(a)) /* Flags used for the bind address copy functions. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3c1fbf38f4f7..ec0f52567c16 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -398,7 +398,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; From 7da467d82d1ed4fb317aff836f99709169e73f10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:26 +0200 Subject: [PATCH 0052/1469] net: dsa: mv88e6xxx: enable .port_set_policy() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy") introduced .port_set_policy() method with implementation for several models, but forgot to add Topaz, which can use the 6352 implementation. Use the 6352 implementation of .port_set_policy() on Topaz. Signed-off-by: Marek Behún Fixes: f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 961fa6b75cad..6bcee3e012d4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3583,6 +3583,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_speed_duplex = mv88e6341_port_set_speed_duplex, .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, @@ -4383,6 +4384,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_speed_duplex = mv88e6341_port_set_speed_duplex, .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, From 11527f3c4725640e6c40a2b7654e303f45e82a6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:27 +0200 Subject: [PATCH 0053/1469] net: dsa: mv88e6xxx: use correct .stats_set_histogram() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") introduced wrong .stats_set_histogram() method for Topaz family. The Peridot method should be used instead. Signed-off-by: Marek Behún Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 6bcee3e012d4..b125d3227dbd 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3597,7 +3597,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_cmode = mv88e6341_port_set_cmode, .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, - .stats_set_histogram = mv88e6095_g1_stats_set_histogram, + .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, .stats_get_stats = mv88e6390_stats_get_stats, @@ -4398,7 +4398,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_cmode = mv88e6341_port_set_cmode, .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, - .stats_set_histogram = mv88e6095_g1_stats_set_histogram, + .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, .stats_get_stats = mv88e6390_stats_get_stats, From 3709488790022c85720f991bff50d48ed5a36e6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:28 +0200 Subject: [PATCH 0054/1469] net: dsa: mv88e6xxx: enable .rmu_disable() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 9e5baf9b36367 ("net: dsa: mv88e6xxx: add RMU disable op") introduced .rmu_disable() method with implementation for several models, but forgot to add Topaz, which can use the Peridot implementation. Use the Peridot implementation of .rmu_disable() on Topaz. Signed-off-by: Marek Behún Fixes: 9e5baf9b36367 ("net: dsa: mv88e6xxx: add RMU disable op") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b125d3227dbd..d4b05c10e5f2 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3607,6 +3607,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -4408,6 +4409,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, From c07fff3492acae41cedbabea395b644dd5872b8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:29 +0200 Subject: [PATCH 0055/1469] net: dsa: mv88e6xxx: enable devlink ATU hash param for Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 23e8b470c7788 ("net: dsa: mv88e6xxx: Add devlink param for ATU hash algorithm.") introduced ATU hash algorithm access via devlink, but did not enable it for Topaz. Enable this feature also for Topaz. Signed-off-by: Marek Behún Fixes: 23e8b470c7788 ("net: dsa: mv88e6xxx: Add devlink param for ATU hash algorithm.") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d4b05c10e5f2..354ff0b84b7f 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3608,6 +3608,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, + .atu_get_hash = mv88e6165_g1_atu_get_hash, + .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -4410,6 +4412,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, + .atu_get_hash = mv88e6165_g1_atu_get_hash, + .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, From a03b98d68367b18e5db6d6850e2cc18754fba94a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:30 +0200 Subject: [PATCH 0056/1469] net: dsa: mv88e6xxx: enable SerDes RX stats for Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 0df952873636a ("mv88e6xxx: Add serdes Rx statistics") added support for RX statistics on SerDes ports for Peridot. This same implementation is also valid for Topaz, but was not enabled at the time. We need to use the generic .serdes_get_lane() method instead of the Peridot specific one in the stats methods so that on Topaz the proper one is used. Signed-off-by: Marek Behún Fixes: 0df952873636a ("mv88e6xxx: Add serdes Rx statistics") Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++++ drivers/net/dsa/mv88e6xxx/serdes.c | 6 +++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 354ff0b84b7f..1e95a0facbd4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3623,6 +3623,9 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_irq_enable = mv88e6390_serdes_irq_enable, .serdes_irq_status = mv88e6390_serdes_irq_status, .gpio_ops = &mv88e6352_gpio_ops, + .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, + .serdes_get_strings = mv88e6390_serdes_get_strings, + .serdes_get_stats = mv88e6390_serdes_get_stats, .phylink_validate = mv88e6341_phylink_validate, }; @@ -4429,6 +4432,9 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, + .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, + .serdes_get_strings = mv88e6390_serdes_get_strings, + .serdes_get_stats = mv88e6390_serdes_get_stats, .phylink_validate = mv88e6341_phylink_validate, }; diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index e4fbef81bc52..b1d46dd8eaab 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -722,7 +722,7 @@ static struct mv88e6390_serdes_hw_stat mv88e6390_serdes_hw_stats[] = { int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) { - if (mv88e6390_serdes_get_lane(chip, port) < 0) + if (mv88e6xxx_serdes_get_lane(chip, port) < 0) return 0; return ARRAY_SIZE(mv88e6390_serdes_hw_stats); @@ -734,7 +734,7 @@ int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, struct mv88e6390_serdes_hw_stat *stat; int i; - if (mv88e6390_serdes_get_lane(chip, port) < 0) + if (mv88e6xxx_serdes_get_lane(chip, port) < 0) return 0; for (i = 0; i < ARRAY_SIZE(mv88e6390_serdes_hw_stats); i++) { @@ -770,7 +770,7 @@ int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, int lane; int i; - lane = mv88e6390_serdes_get_lane(chip, port); + lane = mv88e6xxx_serdes_get_lane(chip, port); if (lane < 0) return 0; From 953b0dcbe2e3f7bee98cc3bca2ec82c8298e9c16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:31 +0200 Subject: [PATCH 0057/1469] net: dsa: mv88e6xxx: enable SerDes PCS register dump via ethtool -d on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bf3504cea7d7e ("net: dsa: mv88e6xxx: Add 6390 family PCS registers to ethtool -d") added support for dumping SerDes PCS registers via ethtool -d for Peridot. The same implementation is also valid for Topaz, but was not enabled at the time. Signed-off-by: Marek Behún Fixes: bf3504cea7d7e ("net: dsa: mv88e6xxx: Add 6390 family PCS registers to ethtool -d") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 1e95a0facbd4..beb41572d04e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3626,6 +3626,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6341_phylink_validate, }; @@ -4435,6 +4437,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6341_phylink_validate, }; From 6f14078e3ee59ccc5806f7bff0f25f94a6d3ff80 Mon Sep 17 00:00:00 2001 From: Sunil Kumar Kori Date: Wed, 30 Jun 2021 15:40:57 +0530 Subject: [PATCH 0058/1469] octeontx2-af: DMAC filter support in MAC block MAC block supports 32 dmac filters which are logically divided among all attached LMACS. For example MAC block0 having one LMAC then maximum supported filters are 32 where as MAC block1 having 4 enabled LMACS them maximum supported filteres are 8 for each LMAC. This patch adds mbox handlers to add/delete/update mac entry in DMAC filter table. Signed-off-by: Sunil Kumar Kori Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/cgx.c | 264 +++++++++++++++++- .../net/ethernet/marvell/octeontx2/af/cgx.h | 7 + .../marvell/octeontx2/af/lmac_common.h | 12 +- .../net/ethernet/marvell/octeontx2/af/mbox.h | 48 +++- .../net/ethernet/marvell/octeontx2/af/rvu.h | 2 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 109 ++++++++ .../ethernet/marvell/octeontx2/af/rvu_nix.c | 3 + 7 files changed, 425 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index fac6474ad694..bc413f96b430 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -86,6 +86,22 @@ bool is_lmac_valid(struct cgx *cgx, int lmac_id) return test_bit(lmac_id, &cgx->lmac_bmap); } +/* Helper function to get sequential index + * given the enabled LMAC of a CGX + */ +static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id) +{ + int tmp, id = 0; + + for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + if (tmp == lmac_id) + break; + id++; + } + + return id; +} + struct mac_ops *get_mac_ops(void *cgxd) { if (!cgxd) @@ -211,37 +227,229 @@ static u64 mac2u64 (u8 *mac_addr) return mac; } +static void cfg2mac(u64 cfg, u8 *mac_addr) +{ + int i, index = 0; + + for (i = ETH_ALEN - 1; i >= 0; i--, index++) + mac_addr[i] = (cfg >> (8 * index)) & 0xFF; +} + int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); struct mac_ops *mac_ops; + int index, id; u64 cfg; + /* access mac_ops to know csr_offset */ mac_ops = cgx_dev->mac_ops; + /* copy 6bytes from macaddr */ /* memcpy(&cfg, mac_addr, 6); */ cfg = mac2u64 (mac_addr); - cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (lmac_id * 0x8)), + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max; + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg | CGX_DMAC_CAM_ADDR_ENABLE | ((u64)lmac_id << 49)); cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); - cfg |= CGX_DMAC_CTL0_CAM_ENABLE; + cfg |= (CGX_DMAC_CTL0_CAM_ENABLE | CGX_DMAC_BCAST_MODE | + CGX_DMAC_MCAST_MODE); cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); return 0; } +int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + int index, idx; + u64 cfg = 0; + int id; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Get available index where entry is to be installed */ + idx = rvu_alloc_rsrc(&lmac->mac_to_index_bmap); + if (idx < 0) + return idx; + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + idx; + + cfg = mac2u64 (mac_addr); + cfg |= CGX_DMAC_CAM_ADDR_ENABLE; + cfg |= ((u64)lmac_id << 49); + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg); + + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_CAM_ACCEPT); + + if (is_multicast_ether_addr(mac_addr)) { + cfg &= ~GENMASK_ULL(2, 1); + cfg |= CGX_DMAC_MCAST_MODE_CAM; + lmac->mcast_filters_count++; + } else if (!lmac->mcast_filters_count) { + cfg |= CGX_DMAC_MCAST_MODE; + } + + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + + return idx; +} + +int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + u8 index = 0, id; + u64 cfg; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Restore index 0 to its default init value as done during + * cgx_lmac_init + */ + set_bit(0, lmac->mac_to_index_bmap.bmap); + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0); + + /* Reset CGXX_CMRX_RX_DMAC_CTL0 register to default state */ + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg &= ~CGX_DMAC_CAM_ACCEPT; + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE); + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + + return 0; +} + +/* Allows caller to change macaddress associated with index + * in dmac filter table including index 0 reserved for + * interface mac address + */ +int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct mac_ops *mac_ops; + struct lmac *lmac; + u64 cfg; + int id; + + lmac = lmac_pdata(lmac_id, cgx_dev); + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Validate the index */ + if (index >= lmac->mac_to_index_bmap.max) + return -EINVAL; + + /* ensure index is already set */ + if (!test_bit(index, lmac->mac_to_index_bmap.bmap)) + return -EINVAL; + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + + cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8))); + cfg &= ~CGX_RX_DMAC_ADR_MASK; + cfg |= mac2u64 (mac_addr); + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg); + return 0; +} + +int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + u8 mac[ETH_ALEN]; + u64 cfg; + int id; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Validate the index */ + if (index >= lmac->mac_to_index_bmap.max) + return -EINVAL; + + /* Skip deletion for reserved index i.e. index 0 */ + if (index == 0) + return 0; + + rvu_free_rsrc(&lmac->mac_to_index_bmap, index); + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + + /* Read MAC address to check whether it is ucast or mcast */ + cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8))); + + cfg2mac(cfg, mac); + if (is_multicast_ether_addr(mac)) + lmac->mcast_filters_count--; + + if (!lmac->mcast_filters_count) { + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg &= ~GENMASK_ULL(2, 1); + cfg |= CGX_DMAC_MCAST_MODE; + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + } + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0); + + return 0; +} + +int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + + if (lmac) + return lmac->mac_to_index_bmap.max; + + return 0; +} + u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); struct mac_ops *mac_ops; + int index; u64 cfg; + int id; mac_ops = cgx_dev->mac_ops; - cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8); + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max; + + cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8); return cfg & CGX_RX_DMAC_ADR_MASK; } @@ -297,35 +505,51 @@ int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable) void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable) { struct cgx *cgx = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx); + u16 max_dmac = lmac->mac_to_index_bmap.max; struct mac_ops *mac_ops; + int index, i; u64 cfg = 0; + int id; if (!cgx) return; + id = get_sequence_id_of_lmac(cgx, lmac_id); + mac_ops = cgx->mac_ops; if (enable) { /* Enable promiscuous mode on LMAC */ cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); - cfg &= ~(CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE); - cfg |= CGX_DMAC_BCAST_MODE; + cfg &= ~CGX_DMAC_CAM_ACCEPT; + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE); cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); - cfg = cgx_read(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8)); - cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE; - cgx_write(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg); + for (i = 0; i < max_dmac; i++) { + index = id * max_dmac + i; + cfg = cgx_read(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8)); + cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE; + cgx_write(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8), cfg); + } } else { /* Disable promiscuous mode */ cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); cfg |= CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE; cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); - cfg = cgx_read(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8)); - cfg |= CGX_DMAC_CAM_ADDR_ENABLE; - cgx_write(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg); + for (i = 0; i < max_dmac; i++) { + index = id * max_dmac + i; + cfg = cgx_read(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8)); + if ((cfg & CGX_RX_DMAC_ADR_MASK) != 0) { + cfg |= CGX_DMAC_CAM_ADDR_ENABLE; + cgx_write(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + + index * 0x8), + cfg); + } + } } } @@ -1234,6 +1458,15 @@ static int cgx_lmac_init(struct cgx *cgx) } lmac->cgx = cgx; + lmac->mac_to_index_bmap.max = + MAX_DMAC_ENTRIES_PER_CGX / cgx->lmac_count; + err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap); + if (err) + return err; + + /* Reserve first entry for default MAC address */ + set_bit(0, lmac->mac_to_index_bmap.bmap); + init_waitqueue_head(&lmac->wq_cmd_cmplt); mutex_init(&lmac->cmd_lock); spin_lock_init(&lmac->event_cb_lock); @@ -1274,6 +1507,7 @@ static int cgx_lmac_exit(struct cgx *cgx) continue; cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, false); cgx_configure_interrupt(cgx, lmac, lmac->lmac_id, true); + kfree(lmac->mac_to_index_bmap.bmap); kfree(lmac->name); kfree(lmac); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 12521262164a..0c613f83a41c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -23,6 +23,7 @@ #define CGX_ID_MASK 0x7 #define MAX_LMAC_PER_CGX 4 +#define MAX_DMAC_ENTRIES_PER_CGX 32 #define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */ #define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX) @@ -46,6 +47,7 @@ #define CGXX_CMRX_RX_DMAC_CTL0 (0x1F8 + mac_ops->csr_offset) #define CGX_DMAC_CTL0_CAM_ENABLE BIT_ULL(3) #define CGX_DMAC_CAM_ACCEPT BIT_ULL(3) +#define CGX_DMAC_MCAST_MODE_CAM BIT_ULL(2) #define CGX_DMAC_MCAST_MODE BIT_ULL(1) #define CGX_DMAC_BCAST_MODE BIT_ULL(0) #define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset) @@ -139,7 +141,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat); int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable); int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable); int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr); +int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id); u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id); +int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr); +int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index); +int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id); void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable); void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable); int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable); @@ -165,4 +171,5 @@ u8 cgx_get_lmacid(void *cgxd, u8 lmac_index); unsigned long cgx_get_lmac_bmap(void *cgxd); void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val); u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset); +int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index 45706fd87120..a8b7b1c7a1d5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -10,17 +10,19 @@ #include "rvu.h" #include "cgx.h" /** - * struct lmac + * struct lmac - per lmac locks and properties * @wq_cmd_cmplt: waitq to keep the process blocked until cmd completion * @cmd_lock: Lock to serialize the command interface * @resp: command response * @link_info: link related information + * @mac_to_index_bmap: Mac address to CGX table index mapping * @event_cb: callback for linkchange events * @event_cb_lock: lock for serializing callback with unregister + * @cgx: parent cgx port + * @mcast_filters_count: Number of multicast filters installed + * @lmac_id: lmac port id * @cmd_pend: flag set before new command is started * flag cleared after command response is received - * @cgx: parent cgx port - * @lmac_id: lmac port id * @name: lmac port name */ struct lmac { @@ -29,12 +31,14 @@ struct lmac { struct mutex cmd_lock; u64 resp; struct cgx_link_user_info link_info; + struct rsrc_bmap mac_to_index_bmap; struct cgx_event_cb event_cb; /* lock for serializing callback with unregister */ spinlock_t event_cb_lock; - bool cmd_pend; struct cgx *cgx; + u8 mcast_filters_count; u8 lmac_id; + bool cmd_pend; char *name; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 9672cbf8a90a..f5ec39de026a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -165,7 +165,15 @@ M(CGX_SET_LINK_MODE, 0x214, cgx_set_link_mode, cgx_set_link_mode_req,\ M(CGX_FEATURES_GET, 0x215, cgx_features_get, msg_req, \ cgx_features_info_msg) \ M(RPM_STATS, 0x216, rpm_stats, msg_req, rpm_stats_rsp) \ - /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ +M(CGX_MAC_ADDR_ADD, 0x217, cgx_mac_addr_add, cgx_mac_addr_add_req, \ + cgx_mac_addr_add_rsp) \ +M(CGX_MAC_ADDR_DEL, 0x218, cgx_mac_addr_del, cgx_mac_addr_del_req, \ + msg_rsp) \ +M(CGX_MAC_MAX_ENTRIES_GET, 0x219, cgx_mac_max_entries_get, msg_req, \ + cgx_max_dmac_entries_get_rsp) \ +M(CGX_MAC_ADDR_RESET, 0x21A, cgx_mac_addr_reset, msg_req, msg_rsp) \ +M(CGX_MAC_ADDR_UPDATE, 0x21B, cgx_mac_addr_update, cgx_mac_addr_update_req, \ + msg_rsp) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \ npa_lf_alloc_req, npa_lf_alloc_rsp) \ @@ -403,6 +411,38 @@ struct cgx_mac_addr_set_or_get { u8 mac_addr[ETH_ALEN]; }; +/* Structure for requesting the operation to + * add DMAC filter entry into CGX interface + */ +struct cgx_mac_addr_add_req { + struct mbox_msghdr hdr; + u8 mac_addr[ETH_ALEN]; +}; + +/* Structure for response against the operation to + * add DMAC filter entry into CGX interface + */ +struct cgx_mac_addr_add_rsp { + struct mbox_msghdr hdr; + u8 index; +}; + +/* Structure for requesting the operation to + * delete DMAC filter entry from CGX interface + */ +struct cgx_mac_addr_del_req { + struct mbox_msghdr hdr; + u8 index; +}; + +/* Structure for response against the operation to + * get maximum supported DMAC filter entries + */ +struct cgx_max_dmac_entries_get_rsp { + struct mbox_msghdr hdr; + u8 max_dmac_filters; +}; + struct cgx_link_user_info { uint64_t link_up:1; uint64_t full_duplex:1; @@ -501,6 +541,12 @@ struct cgx_set_link_mode_rsp { int status; }; +struct cgx_mac_addr_update_req { + struct mbox_msghdr hdr; + u8 mac_addr[ETH_ALEN]; + u8 index; +}; + #define RVU_LMAC_FEAT_FC BIT_ULL(0) /* pause frames */ #define RVU_LMAC_FEAT_PTP BIT_ULL(1) /* precision time protocol */ #define RVU_MAC_VERSION BIT_ULL(2) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 3c0a7e981f72..bc0d24507033 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -657,6 +657,8 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable); int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start); int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id, int index, int rxtxflag, u64 *stat); +void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc); + /* NPA APIs */ int rvu_npa_init(struct rvu *rvu); void rvu_npa_freemem(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 6e2bf4fcd29c..9c6f4ba2d726 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -454,6 +454,31 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return 0; } +void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) +{ + int pf = rvu_get_pf(pcifunc); + int i = 0, lmac_count = 0; + u8 max_dmac_filters; + u8 cgx_id, lmac_id; + void *cgx_dev; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgx_dev = cgx_get_pdata(cgx_id); + lmac_count = cgx_get_lmac_cnt(cgx_dev); + max_dmac_filters = MAX_DMAC_ENTRIES_PER_CGX / lmac_count; + + for (i = 0; i < max_dmac_filters; i++) + cgx_lmac_addr_del(cgx_id, lmac_id, i); + + /* As cgx_lmac_addr_del does not clear entry for index 0 + * so it needs to be done explicitly + */ + cgx_lmac_addr_reset(cgx_id, lmac_id); +} + int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { @@ -557,6 +582,63 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu, return 0; } +int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu, + struct cgx_mac_addr_add_req *req, + struct cgx_mac_addr_add_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + int rc = 0; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + rc = cgx_lmac_addr_add(cgx_id, lmac_id, req->mac_addr); + if (rc >= 0) { + rsp->index = rc; + return 0; + } + + return rc; +} + +int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu, + struct cgx_mac_addr_del_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_del(cgx_id, lmac_id, req->index); +} + +int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu, + struct msg_req *req, + struct cgx_max_dmac_entries_get_rsp + *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + /* If msg is received from PFs(which are not mapped to CGX LMACs) + * or VF then no entries are allocated for DMAC filters at CGX level. + * So returning zero. + */ + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) { + rsp->max_dmac_filters = 0; + return 0; + } + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + rsp->max_dmac_filters = cgx_lmac_addr_max_entries_get(cgx_id, lmac_id); + return 0; +} + int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) @@ -953,3 +1035,30 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac); return 0; } + +int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_reset(cgx_id, lmac_id); +} + +int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu, + struct cgx_mac_addr_update_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d6f8210652c5..aeae37704428 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -346,6 +346,9 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf) /* Free and disable any MCAM entries used by this NIX LF */ rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf); + + /* Disable DMAC filters used */ + rvu_cgx_disable_dmac_entries(rvu, pcifunc); } int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, From dbc52debf95f8f902f74309e7ae0de38e1ed4e4c Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Wed, 30 Jun 2021 15:40:58 +0530 Subject: [PATCH 0059/1469] octeontx2-af: Debugfs support for DMAC filters Add debugfs support to display CGX/RPM DMAC filter table associated with pf. cat /sys/kernel/debug/octeontx2/cgx/cgx0/lmac0/mac_filter PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE 0002:02:00.0 PF2 ACCEPT ACCEPT UNICAST DMAC-INDEX ADDRESS 0 00:0f:b7:06:17:06 1 1a:1b:1c:1d:1e:01 2 1a:1b:1c:1d:1e:02 Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/cgx.c | 28 ++++++ .../net/ethernet/marvell/octeontx2/af/cgx.h | 3 + .../net/ethernet/marvell/octeontx2/af/rvu.h | 1 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 2 +- .../marvell/octeontx2/af/rvu_debugfs.c | 88 +++++++++++++++++-- 5 files changed, 113 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index bc413f96b430..9169849881bf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -266,6 +266,34 @@ int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr) return 0; } +u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id) +{ + struct mac_ops *mac_ops; + struct cgx *cgx = cgxd; + + if (!cgxd || !is_lmac_valid(cgxd, lmac_id)) + return 0; + + cgx = cgxd; + /* Get mac_ops to know csr offset */ + mac_ops = cgx->mac_ops; + + return cgx_read(cgxd, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); +} + +u64 cgx_read_dmac_entry(void *cgxd, int index) +{ + struct mac_ops *mac_ops; + struct cgx *cgx; + + if (!cgxd) + return 0; + + cgx = cgxd; + mac_ops = cgx->mac_ops; + return cgx_read(cgx, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 8))); +} + int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 0c613f83a41c..237ba2b56210 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -52,6 +52,7 @@ #define CGX_DMAC_BCAST_MODE BIT_ULL(0) #define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset) #define CGX_DMAC_CAM_ADDR_ENABLE BIT_ULL(48) +#define CGX_DMAC_CAM_ENTRY_LMACID GENMASK_ULL(50, 49) #define CGXX_CMRX_RX_DMAC_CAM1 0x400 #define CGX_RX_DMAC_ADR_MASK GENMASK_ULL(47, 0) #define CGXX_CMRX_TX_STAT0 0x700 @@ -172,4 +173,6 @@ unsigned long cgx_get_lmac_bmap(void *cgxd); void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val); u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset); int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index); +u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id); +u64 cgx_read_dmac_entry(void *cgxd, int index); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index bc0d24507033..10e58a5d5861 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -744,6 +744,7 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); +int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 9c6f4ba2d726..6cc8fbb7190c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -63,7 +63,7 @@ static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id]; } -static int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) +int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) { unsigned long pfmap; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 3cc3c6fd1d84..370d4ca1e5ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1971,10 +1971,9 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id) return err; } -static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) +static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id) { struct dentry *current_dir; - int err, lmac_id; char *buf; current_dir = filp->file->f_path.dentry->d_parent; @@ -1982,17 +1981,87 @@ static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) if (!buf) return -EINVAL; - err = kstrtoint(buf + 1, 10, &lmac_id); - if (!err) { - err = cgx_print_stats(filp, lmac_id); - if (err) - return err; - } + return kstrtoint(buf + 1, 10, lmac_id); +} + +static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) +{ + int lmac_id, err; + + err = rvu_dbg_derive_lmacid(filp, &lmac_id); + if (!err) + return cgx_print_stats(filp, lmac_id); + return err; } RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL); +static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id) +{ + struct pci_dev *pdev = NULL; + void *cgxd = s->private; + char *bcast, *mcast; + u16 index, domain; + u8 dmac[ETH_ALEN]; + struct rvu *rvu; + u64 cfg, mac; + int pf; + + rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_RVU_AF, NULL)); + if (!rvu) + return -ENODEV; + + pf = cgxlmac_to_pf(rvu, cgx_get_cgxid(cgxd), lmac_id); + domain = 2; + + pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0); + if (!pdev) + return 0; + + cfg = cgx_read_dmac_ctrl(cgxd, lmac_id); + bcast = cfg & CGX_DMAC_BCAST_MODE ? "ACCEPT" : "REJECT"; + mcast = cfg & CGX_DMAC_MCAST_MODE ? "ACCEPT" : "REJECT"; + + seq_puts(s, + "PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE\n"); + seq_printf(s, "%s PF%d %9s %9s", + dev_name(&pdev->dev), pf, bcast, mcast); + if (cfg & CGX_DMAC_CAM_ACCEPT) + seq_printf(s, "%12s\n\n", "UNICAST"); + else + seq_printf(s, "%16s\n\n", "PROMISCUOUS"); + + seq_puts(s, "\nDMAC-INDEX ADDRESS\n"); + + for (index = 0 ; index < 32 ; index++) { + cfg = cgx_read_dmac_entry(cgxd, index); + /* Display enabled dmac entries associated with current lmac */ + if (lmac_id == FIELD_GET(CGX_DMAC_CAM_ENTRY_LMACID, cfg) && + FIELD_GET(CGX_DMAC_CAM_ADDR_ENABLE, cfg)) { + mac = FIELD_GET(CGX_RX_DMAC_ADR_MASK, cfg); + u64_to_ether_addr(mac, dmac); + seq_printf(s, "%7d %pM\n", index, dmac); + } + } + + return 0; +} + +static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused) +{ + int err, lmac_id; + + err = rvu_dbg_derive_lmacid(filp, &lmac_id); + if (!err) + return cgx_print_dmac_flt(filp, lmac_id); + + return err; +} + +RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL); + static void rvu_dbg_cgx_init(struct rvu *rvu) { struct mac_ops *mac_ops; @@ -2029,6 +2098,9 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac, cgx, &rvu_dbg_cgx_stat_fops); + debugfs_create_file("mac_filter", 0600, + rvu->rvu_dbg.lmac, cgx, + &rvu_dbg_cgx_dmac_flt_fops); } } } From 79d2be385e9eabe4403eb85bcc7d3efc6b936a76 Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Wed, 30 Jun 2021 15:40:59 +0530 Subject: [PATCH 0060/1469] octeontx2-pf: offload DMAC filters to CGX/RPM block DMAC filtering can be achieved by either NPC MCAM rules or CGX/RPM MAC filters. Currently we are achieving this by NPC MCAM rules. This patch offloads DMAC filters to CGX/RPM MAC filters instead of NPC MCAM rules. Offloading DMAC filter to CGX/RPM block helps in reducing traffic to NPC block and save MCAM rules Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/nic/Makefile | 2 +- .../marvell/octeontx2/nic/otx2_common.c | 3 + .../marvell/octeontx2/nic/otx2_common.h | 11 + .../marvell/octeontx2/nic/otx2_dmac_flt.c | 173 +++++++++++++ .../marvell/octeontx2/nic/otx2_flows.c | 229 +++++++++++++++++- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 9 + 6 files changed, 417 insertions(+), 10 deletions(-) create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 457c94793e63..3254b02205ca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ - otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o + otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o rvu_nicvf-y := otx2_vf.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index cf7875d51d87..7cccd802c4ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -210,6 +210,9 @@ int otx2_set_mac_address(struct net_device *netdev, void *p) /* update dmac field in vlan offload rule */ if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT) otx2_install_rxvlan_offload_flow(pfvf); + /* update dmac address in ntuple and DMAC filter list */ + if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) + otx2_dmacflt_update_pfmac_flow(pfvf); } else { return -EPERM; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 20a9c69f020f..8fd58cd07f50 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -288,6 +288,9 @@ struct otx2_flow_config { u16 tc_flower_offset; u16 ntuple_max_flows; u16 tc_max_flows; + u8 dmacflt_max_flows; + u8 *bmap_to_dmacindex; + unsigned long dmacflt_bmap; struct list_head flow_list; }; @@ -329,6 +332,7 @@ struct otx2_nic { #define OTX2_FLAG_TC_FLOWER_SUPPORT BIT_ULL(11) #define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED BIT_ULL(12) #define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13) +#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14) u64 flags; struct otx2_qset qset; @@ -834,4 +838,11 @@ int otx2_init_tc(struct otx2_nic *nic); void otx2_shutdown_tc(struct otx2_nic *nic); int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data); +/* CGX/RPM DMAC filters support */ +int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf); +int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos); +int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, u8 bit_pos); +int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos); +void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf); +void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c new file mode 100644 index 000000000000..ffe3e94562d0 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 RVU Physcial Function ethernet driver + * + * Copyright (C) 2021 Marvell. + */ + +#include "otx2_common.h" + +static int otx2_dmacflt_do_add(struct otx2_nic *pf, const u8 *mac, + u8 *dmac_index) +{ + struct cgx_mac_addr_add_req *req; + struct cgx_mac_addr_add_rsp *rsp; + int err; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_add(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + ether_addr_copy(req->mac_addr, mac); + err = otx2_sync_mbox_msg(&pf->mbox); + + if (!err) { + rsp = (struct cgx_mac_addr_add_rsp *) + otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &req->hdr); + *dmac_index = rsp->index; + } + + mutex_unlock(&pf->mbox.lock); + return err; +} + +static int otx2_dmacflt_add_pfmac(struct otx2_nic *pf) +{ + struct cgx_mac_addr_set_or_get *req; + int err; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_set(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + ether_addr_copy(req->mac_addr, pf->netdev->dev_addr); + err = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos) +{ + u8 *dmacindex; + + /* Store dmacindex returned by CGX/RPM driver which will + * be used for macaddr update/remove + */ + dmacindex = &pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + + if (ether_addr_equal(mac, pf->netdev->dev_addr)) + return otx2_dmacflt_add_pfmac(pf); + else + return otx2_dmacflt_do_add(pf, mac, dmacindex); +} + +static int otx2_dmacflt_do_remove(struct otx2_nic *pfvf, const u8 *mac, + u8 dmac_index) +{ + struct cgx_mac_addr_del_req *req; + int err; + + mutex_lock(&pfvf->mbox.lock); + req = otx2_mbox_alloc_msg_cgx_mac_addr_del(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + req->index = dmac_index; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + mutex_unlock(&pfvf->mbox.lock); + + return err; +} + +static int otx2_dmacflt_remove_pfmac(struct otx2_nic *pf) +{ + struct msg_req *req; + int err; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_cgx_mac_addr_reset(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, + u8 bit_pos) +{ + u8 dmacindex = pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + + if (ether_addr_equal(mac, pf->netdev->dev_addr)) + return otx2_dmacflt_remove_pfmac(pf); + else + return otx2_dmacflt_do_remove(pf, mac, dmacindex); +} + +/* CGX/RPM blocks support max unicast entries of 32. + * on typical configuration MAC block associated + * with 4 lmacs, each lmac will have 8 dmac entries + */ +int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf) +{ + struct cgx_max_dmac_entries_get_rsp *rsp; + struct msg_req *msg; + int err; + + mutex_lock(&pf->mbox.lock); + msg = otx2_mbox_alloc_msg_cgx_mac_max_entries_get(&pf->mbox); + + if (!msg) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pf->mbox); + if (err) + goto out; + + rsp = (struct cgx_max_dmac_entries_get_rsp *) + otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &msg->hdr); + pf->flow_cfg->dmacflt_max_flows = rsp->max_dmac_filters; + +out: + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos) +{ + struct cgx_mac_addr_update_req *req; + int rc; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_update(&pf->mbox); + + if (!req) { + mutex_unlock(&pf->mbox.lock); + rc = -ENOMEM; + } + + ether_addr_copy(req->mac_addr, mac); + req->index = pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + rc = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return rc; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 8c97106bdd1c..4d9de525802d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -18,6 +18,12 @@ struct otx2_flow { bool is_vf; u8 rss_ctx_id; int vf; + bool dmac_filter; +}; + +enum dmac_req { + DMAC_ADDR_UPDATE, + DMAC_ADDR_DEL }; static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg) @@ -219,6 +225,22 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) if (!pf->mac_table) return -ENOMEM; + otx2_dmacflt_get_max_cnt(pf); + + /* DMAC filters are not allocated */ + if (!pf->flow_cfg->dmacflt_max_flows) + return 0; + + pf->flow_cfg->bmap_to_dmacindex = + devm_kzalloc(pf->dev, sizeof(u8) * + pf->flow_cfg->dmacflt_max_flows, + GFP_KERNEL); + + if (!pf->flow_cfg->bmap_to_dmacindex) + return -ENOMEM; + + pf->flags |= OTX2_FLAG_DMACFLTR_SUPPORT; + return 0; } @@ -280,6 +302,12 @@ int otx2_add_macfilter(struct net_device *netdev, const u8 *mac) { struct otx2_nic *pf = netdev_priv(netdev); + if (bitmap_weight(&pf->flow_cfg->dmacflt_bmap, + pf->flow_cfg->dmacflt_max_flows)) + netdev_warn(netdev, + "Add %pM to CGX/RPM DMAC filters list as well\n", + mac); + return otx2_do_add_macfilter(pf, mac); } @@ -351,12 +379,22 @@ static void otx2_add_flow_to_list(struct otx2_nic *pfvf, struct otx2_flow *flow) list_add(&flow->list, head); } +static int otx2_get_maxflows(struct otx2_flow_config *flow_cfg) +{ + if (flow_cfg->nr_flows == flow_cfg->ntuple_max_flows || + bitmap_weight(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows)) + return flow_cfg->ntuple_max_flows + flow_cfg->dmacflt_max_flows; + else + return flow_cfg->ntuple_max_flows; +} + int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, u32 location) { struct otx2_flow *iter; - if (location >= pfvf->flow_cfg->ntuple_max_flows) + if (location >= otx2_get_maxflows(pfvf->flow_cfg)) return -EINVAL; list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) { @@ -378,7 +416,7 @@ int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, int idx = 0; int err = 0; - nfc->data = pfvf->flow_cfg->ntuple_max_flows; + nfc->data = otx2_get_maxflows(pfvf->flow_cfg); while ((!err || err == -ENOENT) && idx < rule_cnt) { err = otx2_get_flow(pfvf, nfc, location); if (!err) @@ -760,6 +798,32 @@ int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp, return 0; } +static int otx2_is_flow_rule_dmacfilter(struct otx2_nic *pfvf, + struct ethtool_rx_flow_spec *fsp) +{ + struct ethhdr *eth_mask = &fsp->m_u.ether_spec; + struct ethhdr *eth_hdr = &fsp->h_u.ether_spec; + u64 ring_cookie = fsp->ring_cookie; + u32 flow_type; + + if (!(pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)) + return false; + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); + + /* CGX/RPM block dmac filtering configured for white listing + * check for action other than DROP + */ + if (flow_type == ETHER_FLOW && ring_cookie != RX_CLS_FLOW_DISC && + !ethtool_get_flow_spec_ring_vf(ring_cookie)) { + if (is_zero_ether_addr(eth_mask->h_dest) && + is_valid_ether_addr(eth_hdr->h_dest)) + return true; + } + + return false; +} + static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) { u64 ring_cookie = flow->flow_spec.ring_cookie; @@ -818,14 +882,46 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) return err; } +static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf, + struct otx2_flow *flow) +{ + struct otx2_flow *pf_mac; + struct ethhdr *eth_hdr; + + pf_mac = kzalloc(sizeof(*pf_mac), GFP_KERNEL); + if (!pf_mac) + return -ENOMEM; + + pf_mac->entry = 0; + pf_mac->dmac_filter = true; + pf_mac->location = pfvf->flow_cfg->ntuple_max_flows; + memcpy(&pf_mac->flow_spec, &flow->flow_spec, + sizeof(struct ethtool_rx_flow_spec)); + pf_mac->flow_spec.location = pf_mac->location; + + /* Copy PF mac address */ + eth_hdr = &pf_mac->flow_spec.h_u.ether_spec; + ether_addr_copy(eth_hdr->h_dest, pfvf->netdev->dev_addr); + + /* Install DMAC filter with PF mac address */ + otx2_dmacflt_add(pfvf, eth_hdr->h_dest, 0); + + otx2_add_flow_to_list(pfvf, pf_mac); + pfvf->flow_cfg->nr_flows++; + set_bit(0, &pfvf->flow_cfg->dmacflt_bmap); + + return 0; +} + int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct ethtool_rx_flow_spec *fsp = &nfc->fs; struct otx2_flow *flow; + struct ethhdr *eth_hdr; bool new = false; + int err = 0; u32 ring; - int err; ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT)) @@ -834,16 +930,15 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) return -EINVAL; - if (fsp->location >= flow_cfg->ntuple_max_flows) + if (fsp->location >= otx2_get_maxflows(flow_cfg)) return -EINVAL; flow = otx2_find_flow(pfvf, fsp->location); if (!flow) { - flow = kzalloc(sizeof(*flow), GFP_ATOMIC); + flow = kzalloc(sizeof(*flow), GFP_KERNEL); if (!flow) return -ENOMEM; flow->location = fsp->location; - flow->entry = flow_cfg->flow_ent[flow->location]; new = true; } /* struct copy */ @@ -852,7 +947,54 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (fsp->flow_type & FLOW_RSS) flow->rss_ctx_id = nfc->rss_context; - err = otx2_add_flow_msg(pfvf, flow); + if (otx2_is_flow_rule_dmacfilter(pfvf, &flow->flow_spec)) { + eth_hdr = &flow->flow_spec.h_u.ether_spec; + + /* Sync dmac filter table with updated fields */ + if (flow->dmac_filter) + return otx2_dmacflt_update(pfvf, eth_hdr->h_dest, + flow->entry); + + if (bitmap_full(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows)) { + netdev_warn(pfvf->netdev, + "Can't insert the rule %d as max allowed dmac filters are %d\n", + flow->location + + flow_cfg->dmacflt_max_flows, + flow_cfg->dmacflt_max_flows); + err = -EINVAL; + if (new) + kfree(flow); + return err; + } + + /* Install PF mac address to DMAC filter list */ + if (!test_bit(0, &flow_cfg->dmacflt_bmap)) + otx2_add_flow_with_pfmac(pfvf, flow); + + flow->dmac_filter = true; + flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows); + fsp->location = flow_cfg->ntuple_max_flows + flow->entry; + flow->flow_spec.location = fsp->location; + flow->location = fsp->location; + + set_bit(flow->entry, &flow_cfg->dmacflt_bmap); + otx2_dmacflt_add(pfvf, eth_hdr->h_dest, flow->entry); + + } else { + if (flow->location >= pfvf->flow_cfg->ntuple_max_flows) { + netdev_warn(pfvf->netdev, + "Can't insert non dmac ntuple rule at %d, allowed range %d-0\n", + flow->location, + flow_cfg->ntuple_max_flows - 1); + err = -EINVAL; + } else { + flow->entry = flow_cfg->flow_ent[flow->location]; + err = otx2_add_flow_msg(pfvf, flow); + } + } + if (err) { if (new) kfree(flow); @@ -890,20 +1032,70 @@ static int otx2_remove_flow_msg(struct otx2_nic *pfvf, u16 entry, bool all) return err; } +static void otx2_update_rem_pfmac(struct otx2_nic *pfvf, int req) +{ + struct otx2_flow *iter; + struct ethhdr *eth_hdr; + bool found = false; + + list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) { + if (iter->dmac_filter && iter->entry == 0) { + eth_hdr = &iter->flow_spec.h_u.ether_spec; + if (req == DMAC_ADDR_DEL) { + otx2_dmacflt_remove(pfvf, eth_hdr->h_dest, + 0); + clear_bit(0, &pfvf->flow_cfg->dmacflt_bmap); + found = true; + } else { + ether_addr_copy(eth_hdr->h_dest, + pfvf->netdev->dev_addr); + otx2_dmacflt_update(pfvf, eth_hdr->h_dest, 0); + } + break; + } + } + + if (found) { + list_del(&iter->list); + kfree(iter); + pfvf->flow_cfg->nr_flows--; + } +} + int otx2_remove_flow(struct otx2_nic *pfvf, u32 location) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct otx2_flow *flow; int err; - if (location >= flow_cfg->ntuple_max_flows) + if (location >= otx2_get_maxflows(flow_cfg)) return -EINVAL; flow = otx2_find_flow(pfvf, location); if (!flow) return -ENOENT; - err = otx2_remove_flow_msg(pfvf, flow->entry, false); + if (flow->dmac_filter) { + struct ethhdr *eth_hdr = &flow->flow_spec.h_u.ether_spec; + + /* user not allowed to remove dmac filter with interface mac */ + if (ether_addr_equal(pfvf->netdev->dev_addr, eth_hdr->h_dest)) + return -EPERM; + + err = otx2_dmacflt_remove(pfvf, eth_hdr->h_dest, + flow->entry); + clear_bit(flow->entry, &flow_cfg->dmacflt_bmap); + /* If all dmac filters are removed delete macfilter with + * interface mac address and configure CGX/RPM block in + * promiscuous mode + */ + if (bitmap_weight(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows) == 1) + otx2_update_rem_pfmac(pfvf, DMAC_ADDR_DEL); + } else { + err = otx2_remove_flow_msg(pfvf, flow->entry, false); + } + if (err) return err; @@ -1100,3 +1292,22 @@ int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable) mutex_unlock(&pf->mbox.lock); return rsp_hdr->rc; } + +void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf) +{ + struct otx2_flow *iter; + struct ethhdr *eth_hdr; + + list_for_each_entry(iter, &pf->flow_cfg->flow_list, list) { + if (iter->dmac_filter) { + eth_hdr = &iter->flow_spec.h_u.ether_spec; + otx2_dmacflt_add(pf, eth_hdr->h_dest, + iter->entry); + } + } +} + +void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf) +{ + otx2_update_rem_pfmac(pfvf, DMAC_ADDR_UPDATE); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 088c28df849d..f300b807a85b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1110,6 +1110,11 @@ static int otx2_cgx_config_loopback(struct otx2_nic *pf, bool enable) struct msg_req *msg; int err; + if (enable && bitmap_weight(&pf->flow_cfg->dmacflt_bmap, + pf->flow_cfg->dmacflt_max_flows)) + netdev_warn(pf->netdev, + "CGX/RPM internal loopback might not work as DMAC filters are active\n"); + mutex_lock(&pf->mbox.lock); if (enable) msg = otx2_mbox_alloc_msg_cgx_intlbk_enable(&pf->mbox); @@ -1644,6 +1649,10 @@ int otx2_open(struct net_device *netdev) /* Restore pause frame settings */ otx2_config_pause_frm(pf); + /* Install DMAC Filters */ + if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) + otx2_dmacflt_reinstall_flows(pf); + err = otx2_rxtx_enable(pf, true); if (err) goto err_tx_stop_queues; From 856a5c97268d474282360c8a3cf4f37f6036dbec Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:06 +0530 Subject: [PATCH 0061/1469] net: wwan: iosm: fix uevent reporting Change uevent env variable name to IOSM_EVENT & correct reporting format to key=value pair. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_uevent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.c b/drivers/net/wwan/iosm/iosm_ipc_uevent.c index 2229d752926c..d12188ffed7e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_uevent.c +++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.c @@ -37,7 +37,7 @@ void ipc_uevent_send(struct device *dev, char *uevent) /* Store the device and event information */ info->dev = dev; - snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent); + snprintf(info->uevent, MAX_UEVENT_LEN, "IOSM_EVENT=%s", uevent); /* Schedule uevent in process context using work queue */ schedule_work(&info->work); From 3bcfc0a2d3199d0a83d47ed67ad57a1c2f5a16d7 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:31 +0530 Subject: [PATCH 0062/1469] net: wwan: iosm: remove reduandant check Remove reduandant IP session id check since required checks are in place under caller. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 46f76e8aae92..e4e9461b603e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -24,15 +24,7 @@ int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) return -EIO; } - /* check for the interafce id - * if if_id 1 to 8 then create IP MUX channel sessions. - * To start MUX session from 0 as network interface id would start - * from 1 so map it to if_id = if_id - 1 - */ - if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - return ipc_mux_open_session(ipc_imem->mux, if_id - 1); - - return -EINVAL; + return ipc_mux_open_session(ipc_imem->mux, if_id - 1); } /* Release a net link to CP. */ @@ -83,13 +75,8 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, goto out; } - if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - /* Route the UL packet through IP MUX Layer */ - ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, - if_id - 1, skb); - else - dev_err(ipc_imem->dev, - "invalid if_id %d: ", if_id); + /* Route the UL packet through IP MUX Layer */ + ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id - 1, skb); out: return ret; } From 5bb4eea0c5f5b9383a543293966bdf20e54988aa Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:45 +0530 Subject: [PATCH 0063/1469] net: wwan: iosm: correct link-id handling Link ID to be kept intact with MBIM session ID Ex: ID 0 should be associated to MBIM session ID 0. Reported-by: Loic Poulain Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 6 +++--- drivers/net/wwan/iosm/iosm_ipc_imem_ops.h | 6 +++--- drivers/net/wwan/iosm/iosm_ipc_mux_codec.c | 2 +- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 4 ++-- 4 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index e4e9461b603e..0a472ce77370 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -24,7 +24,7 @@ int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) return -EIO; } - return ipc_mux_open_session(ipc_imem->mux, if_id - 1); + return ipc_mux_open_session(ipc_imem->mux, if_id); } /* Release a net link to CP. */ @@ -33,7 +33,7 @@ void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id, { if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - ipc_mux_close_session(ipc_imem->mux, if_id - 1); + ipc_mux_close_session(ipc_imem->mux, if_id); } /* Tasklet call to do uplink transfer. */ @@ -76,7 +76,7 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, } /* Route the UL packet through IP MUX Layer */ - ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id - 1, skb); + ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id, skb); out: return ret; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index fd356dafbdd6..2007fe23e9a5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -27,11 +27,11 @@ #define BOOT_CHECK_DEFAULT_TIMEOUT 400 /* IP MUX channel range */ -#define IP_MUX_SESSION_START 1 -#define IP_MUX_SESSION_END 8 +#define IP_MUX_SESSION_START 0 +#define IP_MUX_SESSION_END 7 /* Default IP MUX channel */ -#define IP_MUX_SESSION_DEFAULT 1 +#define IP_MUX_SESSION_DEFAULT 0 /** * ipc_imem_sys_port_open - Open a port link to CP. diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index e634ffc6ec08..562de275797a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -288,7 +288,7 @@ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, /* Pass the packet to the netif layer. */ dest_skb->priority = service_class; - return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1); + return ipc_wwan_receive(wwan, dest_skb, false, if_id); } /* Decode Flow Credit Table in the block */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index c999c64001f4..84e37c4b0f74 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -252,8 +252,8 @@ int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg, skb->pkt_type = PACKET_HOST; - if (if_id < (IP_MUX_SESSION_START - 1) || - if_id > (IP_MUX_SESSION_END - 1)) { + if (if_id < IP_MUX_SESSION_START || + if_id > IP_MUX_SESSION_END) { ret = -EINVAL; goto free; } From c302e3a1c86f78421d58ef564ba22519b0b039c0 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:39:17 +0530 Subject: [PATCH 0064/1469] net: wwan: iosm: fix netdev tx stats Update tx stats on successful packet consume, drop. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index 84e37c4b0f74..e0c19c59c5f6 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -107,6 +107,7 @@ static int ipc_wwan_link_transmit(struct sk_buff *skb, { struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; + unsigned int len = skb->len; int if_id = priv->if_id; int ret; @@ -123,6 +124,8 @@ static int ipc_wwan_link_transmit(struct sk_buff *skb, /* Return code of zero is success */ if (ret == 0) { + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += len; ret = NETDEV_TX_OK; } else if (ret == -EBUSY) { ret = NETDEV_TX_BUSY; @@ -140,7 +143,8 @@ exit: ret); dev_kfree_skb_any(skb); - return ret; + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; } /* Ops structure for wwan net link */ From d7340f46beae05227f5f4a1c8cb18e81e0c3fe0e Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:39:34 +0530 Subject: [PATCH 0065/1469] net: wwan: iosm: set default mtu Set netdev default mtu size to 1500. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index e0c19c59c5f6..b2357ad5d517 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -162,6 +162,7 @@ static void ipc_wwan_setup(struct net_device *iosm_dev) iosm_dev->priv_flags |= IFF_NO_QUEUE; iosm_dev->type = ARPHRD_NONE; + iosm_dev->mtu = ETH_DATA_LEN; iosm_dev->min_mtu = ETH_MIN_MTU; iosm_dev->max_mtu = ETH_MAX_MTU; From 5d43f951b1ac797450bb4d230fdc960b739bea04 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:52 +0800 Subject: [PATCH 0066/1469] ptp: add ptp virtual clock driver framework This patch is to add ptp virtual clock driver framework utilizing timecounter/cyclecounter. The patch just exports two essential APIs for PTP driver. - ptp_vclock_register() - ptp_vclock_unregister() Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/Makefile | 2 +- drivers/ptp/ptp_private.h | 15 ++++ drivers/ptp/ptp_vclock.c | 150 +++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 4 +- 4 files changed, 169 insertions(+), 2 deletions(-) create mode 100644 drivers/ptp/ptp_vclock.c diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 8673d1743faa..28a6fe342d3e 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -3,7 +3,7 @@ # Makefile for PTP 1588 clock support. # -ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o +ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o ptp_vclock.o ptp_kvm-$(CONFIG_X86) := ptp_kvm_x86.o ptp_kvm_common.o ptp_kvm-$(CONFIG_HAVE_ARM_SMCCC) := ptp_kvm_arm.o ptp_kvm_common.o obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 6b97155148f1..853b79b6b30e 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -48,6 +48,19 @@ struct ptp_clock { struct kthread_delayed_work aux_work; }; +#define info_to_vclock(d) container_of((d), struct ptp_vclock, info) +#define cc_to_vclock(d) container_of((d), struct ptp_vclock, cc) +#define dw_to_vclock(d) container_of((d), struct ptp_vclock, refresh_work) + +struct ptp_vclock { + struct ptp_clock *pclock; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct cyclecounter cc; + struct timecounter tc; + spinlock_t lock; /* protects tc/cc */ +}; + /* * The function queue_cnt() is safe for readers to call without * holding q->lock. Readers use this function to verify that the queue @@ -89,4 +102,6 @@ extern const struct attribute_group *ptp_groups[]; int ptp_populate_pin_groups(struct ptp_clock *ptp); void ptp_cleanup_pin_groups(struct ptp_clock *ptp); +struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock); +void ptp_vclock_unregister(struct ptp_vclock *vclock); #endif diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c new file mode 100644 index 000000000000..fc9205cc504d --- /dev/null +++ b/drivers/ptp/ptp_vclock.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PTP virtual clock driver + * + * Copyright 2021 NXP + */ +#include +#include "ptp_private.h" + +#define PTP_VCLOCK_CC_SHIFT 31 +#define PTP_VCLOCK_CC_MULT (1 << PTP_VCLOCK_CC_SHIFT) +#define PTP_VCLOCK_FADJ_SHIFT 9 +#define PTP_VCLOCK_FADJ_DENOMINATOR 15625ULL +#define PTP_VCLOCK_REFRESH_INTERVAL (HZ * 2) + +static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + s64 adj; + + adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT; + adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR); + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_read(&vclock->tc); + vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj; + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_adjtime(&vclock->tc, delta); + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static int ptp_vclock_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + u64 ns; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_read(&vclock->tc); + spin_unlock_irqrestore(&vclock->lock, flags); + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int ptp_vclock_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + u64 ns = timespec64_to_ns(ts); + unsigned long flags; + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_init(&vclock->tc, &vclock->cc, ns); + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static long ptp_vclock_refresh(struct ptp_clock_info *ptp) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct timespec64 ts; + + ptp_vclock_gettime(&vclock->info, &ts); + + return PTP_VCLOCK_REFRESH_INTERVAL; +} + +static const struct ptp_clock_info ptp_vclock_info = { + .owner = THIS_MODULE, + .name = "ptp virtual clock", + /* The maximum ppb value that long scaled_ppm can support */ + .max_adj = 32767999, + .adjfine = ptp_vclock_adjfine, + .adjtime = ptp_vclock_adjtime, + .gettime64 = ptp_vclock_gettime, + .settime64 = ptp_vclock_settime, + .do_aux_work = ptp_vclock_refresh, +}; + +static u64 ptp_vclock_read(const struct cyclecounter *cc) +{ + struct ptp_vclock *vclock = cc_to_vclock(cc); + struct ptp_clock *ptp = vclock->pclock; + struct timespec64 ts = {}; + + if (ptp->info->gettimex64) + ptp->info->gettimex64(ptp->info, &ts, NULL); + else + ptp->info->gettime64(ptp->info, &ts); + + return timespec64_to_ns(&ts); +} + +static const struct cyclecounter ptp_vclock_cc = { + .read = ptp_vclock_read, + .mask = CYCLECOUNTER_MASK(32), + .mult = PTP_VCLOCK_CC_MULT, + .shift = PTP_VCLOCK_CC_SHIFT, +}; + +struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) +{ + struct ptp_vclock *vclock; + + vclock = kzalloc(sizeof(*vclock), GFP_KERNEL); + if (!vclock) + return NULL; + + vclock->pclock = pclock; + vclock->info = ptp_vclock_info; + vclock->cc = ptp_vclock_cc; + + snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt", + pclock->index); + + spin_lock_init(&vclock->lock); + + vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev); + if (IS_ERR_OR_NULL(vclock->clock)) { + kfree(vclock); + return NULL; + } + + timecounter_init(&vclock->tc, &vclock->cc, 0); + ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL); + + return vclock; +} + +void ptp_vclock_unregister(struct ptp_vclock *vclock) +{ + ptp_clock_unregister(vclock->clock); + kfree(vclock); +} diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index aba237c0b3a2..b6fb771ee524 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -11,7 +11,9 @@ #include #include #include +#include +#define PTP_CLOCK_NAME_LEN 32 /** * struct ptp_clock_request - request PTP clock event * @@ -134,7 +136,7 @@ struct ptp_system_timestamp { struct ptp_clock_info { struct module *owner; - char name[16]; + char name[PTP_CLOCK_NAME_LEN]; s32 max_adj; int n_alarm; int n_ext_ts; From 73f37068d540eba5f93ba3a0019bf479d35ebd76 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:53 +0800 Subject: [PATCH 0067/1469] ptp: support ptp physical/virtual clocks conversion Support ptp physical/virtual clocks conversion via sysfs. There will be a new attribute n_vclocks under ptp physical clock sysfs. - In default, the value is 0 meaning only ptp physical clock is in use. - Setting the value can create corresponding number of ptp virtual clocks to use. But current physical clock is guaranteed to stay free running. - Setting the value back to 0 can delete virtual clocks and back use physical clock again. Another new attribute max_vclocks control the maximum number of ptp vclocks. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- Documentation/ABI/testing/sysfs-ptp | 20 ++++ drivers/ptp/ptp_clock.c | 26 ++++++ drivers/ptp/ptp_private.h | 21 +++++ drivers/ptp/ptp_sysfs.c | 138 ++++++++++++++++++++++++++++ 4 files changed, 205 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp index 2363ad810ddb..d378f57c1b73 100644 --- a/Documentation/ABI/testing/sysfs-ptp +++ b/Documentation/ABI/testing/sysfs-ptp @@ -33,6 +33,13 @@ Description: frequency adjustment value (a positive integer) in parts per billion. +What: /sys/class/ptp/ptpN/max_vclocks +Date: May 2021 +Contact: Yangbo Lu +Description: + This file contains the maximum number of ptp vclocks. + Write integer to re-configure it. + What: /sys/class/ptp/ptpN/n_alarms Date: September 2010 Contact: Richard Cochran @@ -61,6 +68,19 @@ Description: This file contains the number of programmable pins offered by the PTP hardware clock. +What: /sys/class/ptp/ptpN/n_vclocks +Date: May 2021 +Contact: Yangbo Lu +Description: + This file contains the number of virtual PTP clocks in + use. By default, the value is 0 meaning that only the + physical clock is in use. Setting the value creates + the corresponding number of virtual clocks and causes + the physical clock to become free running. Setting the + value back to 0 deletes the virtual clocks and + switches the physical clock back to normal, adjustable + operation. + What: /sys/class/ptp/ptpN/pins Date: March 2014 Contact: Richard Cochran diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index a23a37a4d5dc..7334f478dde7 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -76,6 +76,11 @@ static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp { struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + return ptp->info->settime64(ptp->info, tp); } @@ -97,6 +102,11 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) struct ptp_clock_info *ops; int err = -EOPNOTSUPP; + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + ops = ptp->info; if (tx->modes & ADJ_SETOFFSET) { @@ -161,6 +171,7 @@ static void ptp_clock_release(struct device *dev) ptp_cleanup_pin_groups(ptp); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); + mutex_destroy(&ptp->n_vclocks_mux); ida_simple_remove(&ptp_clocks_map, ptp->index); kfree(ptp); } @@ -208,6 +219,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, spin_lock_init(&ptp->tsevq.lock); mutex_init(&ptp->tsevq_mux); mutex_init(&ptp->pincfg_mux); + mutex_init(&ptp->n_vclocks_mux); init_waitqueue_head(&ptp->tsev_wq); if (ptp->info->do_aux_work) { @@ -221,6 +233,14 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, ptp->pps_source->lookup_cookie = ptp; } + /* PTP virtual clock is being registered under physical clock */ + if (parent->class && parent->class->name && + strcmp(parent->class->name, "ptp") == 0) + ptp->is_virtual_clock = true; + + if (!ptp->is_virtual_clock) + ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS; + err = ptp_populate_pin_groups(ptp); if (err) goto no_pin_groups; @@ -270,6 +290,7 @@ no_pin_groups: kworker_err: mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); + mutex_destroy(&ptp->n_vclocks_mux); ida_simple_remove(&ptp_clocks_map, index); no_slot: kfree(ptp); @@ -280,6 +301,11 @@ EXPORT_SYMBOL(ptp_clock_register); int ptp_clock_unregister(struct ptp_clock *ptp) { + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 853b79b6b30e..87cb55953b69 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -18,6 +18,7 @@ #define PTP_MAX_TIMESTAMPS 128 #define PTP_BUF_TIMESTAMPS 30 +#define PTP_DEFAULT_MAX_VCLOCKS 20 struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; @@ -46,6 +47,10 @@ struct ptp_clock { const struct attribute_group *pin_attr_groups[2]; struct kthread_worker *kworker; struct kthread_delayed_work aux_work; + unsigned int max_vclocks; + unsigned int n_vclocks; + struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */ + bool is_virtual_clock; }; #define info_to_vclock(d) container_of((d), struct ptp_vclock, info) @@ -74,6 +79,22 @@ static inline int queue_cnt(struct timestamp_event_queue *q) return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt; } +/* Check if ptp virtual clock is in use */ +static inline bool ptp_vclock_in_use(struct ptp_clock *ptp) +{ + bool in_use = false; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return true; + + if (!ptp->is_virtual_clock && ptp->n_vclocks) + in_use = true; + + mutex_unlock(&ptp->n_vclocks_mux); + + return in_use; +} + /* * see ptp_chardev.c */ diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index be076a91e20e..0b05041783a5 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -3,6 +3,7 @@ * PTP 1588 clock support - sysfs interface. * * Copyright (C) 2010 OMICRON electronics GmbH + * Copyright 2021 NXP */ #include #include @@ -148,6 +149,137 @@ out: } static DEVICE_ATTR(pps_enable, 0220, NULL, pps_enable_store); +static int unregister_vclock(struct device *dev, void *data) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + struct ptp_clock_info *info = ptp->info; + struct ptp_vclock *vclock; + u8 *num = data; + + vclock = info_to_vclock(info); + dev_info(dev->parent, "delete virtual clock ptp%d\n", + vclock->clock->index); + + ptp_vclock_unregister(vclock); + (*num)--; + + /* For break. Not error. */ + if (*num == 0) + return -EINVAL; + + return 0; +} + +static ssize_t n_vclocks_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + ssize_t size; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->n_vclocks); + + mutex_unlock(&ptp->n_vclocks_mux); + + return size; +} + +static ssize_t n_vclocks_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + struct ptp_vclock *vclock; + int err = -EINVAL; + u32 num, i; + + if (kstrtou32(buf, 0, &num)) + return err; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + if (num > ptp->max_vclocks) { + dev_err(dev, "max value is %d\n", ptp->max_vclocks); + goto out; + } + + /* Need to create more vclocks */ + if (num > ptp->n_vclocks) { + for (i = 0; i < num - ptp->n_vclocks; i++) { + vclock = ptp_vclock_register(ptp); + if (!vclock) + goto out; + + dev_info(dev, "new virtual clock ptp%d\n", + vclock->clock->index); + } + } + + /* Need to delete vclocks */ + if (num < ptp->n_vclocks) { + i = ptp->n_vclocks - num; + device_for_each_child_reverse(dev, &i, + unregister_vclock); + } + + if (num == 0) + dev_info(dev, "only physical clock in use now\n"); + else + dev_info(dev, "guarantee physical clock free running\n"); + + ptp->n_vclocks = num; + mutex_unlock(&ptp->n_vclocks_mux); + + return count; +out: + mutex_unlock(&ptp->n_vclocks_mux); + return err; +} +static DEVICE_ATTR_RW(n_vclocks); + +static ssize_t max_vclocks_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + ssize_t size; + + size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->max_vclocks); + + return size; +} + +static ssize_t max_vclocks_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + u32 max; + + if (kstrtou32(buf, 0, &max) || max == 0) + return -EINVAL; + + if (max == ptp->max_vclocks) + return count; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + if (max < ptp->n_vclocks) { + mutex_unlock(&ptp->n_vclocks_mux); + return -EINVAL; + } + + ptp->max_vclocks = max; + + mutex_unlock(&ptp->n_vclocks_mux); + + return count; +} +static DEVICE_ATTR_RW(max_vclocks); + static struct attribute *ptp_attrs[] = { &dev_attr_clock_name.attr, @@ -162,6 +294,8 @@ static struct attribute *ptp_attrs[] = { &dev_attr_fifo.attr, &dev_attr_period.attr, &dev_attr_pps_enable.attr, + &dev_attr_n_vclocks.attr, + &dev_attr_max_vclocks.attr, NULL }; @@ -183,6 +317,10 @@ static umode_t ptp_is_attribute_visible(struct kobject *kobj, } else if (attr == &dev_attr_pps_enable.attr) { if (!info->pps) mode = 0; + } else if (attr == &dev_attr_n_vclocks.attr || + attr == &dev_attr_max_vclocks.attr) { + if (ptp->is_virtual_clock) + mode = 0; } return mode; From 44c494c8e30e35713c7d11ca3c5ab332cbfabacf Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:54 +0800 Subject: [PATCH 0068/1469] ptp: track available ptp vclocks information Track available ptp vclocks information. Record index values of available ptp vclocks during registering and unregistering. This is preparation for supporting ptp vclocks info query through ethtool. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 15 ++++++++++++++- drivers/ptp/ptp_private.h | 1 + drivers/ptp/ptp_sysfs.c | 28 +++++++++++++++++++++++++--- 3 files changed, 40 insertions(+), 4 deletions(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 7334f478dde7..9205a9362a9d 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -196,6 +196,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, { struct ptp_clock *ptp; int err = 0, index, major = MAJOR(ptp_devt); + size_t size; if (info->n_alarm > PTP_MAX_ALARMS) return ERR_PTR(-EINVAL); @@ -238,9 +239,17 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, strcmp(parent->class->name, "ptp") == 0) ptp->is_virtual_clock = true; - if (!ptp->is_virtual_clock) + if (!ptp->is_virtual_clock) { ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS; + size = sizeof(int) * ptp->max_vclocks; + ptp->vclock_index = kzalloc(size, GFP_KERNEL); + if (!ptp->vclock_index) { + err = -ENOMEM; + goto no_mem_for_vclocks; + } + } + err = ptp_populate_pin_groups(ptp); if (err) goto no_pin_groups; @@ -285,6 +294,8 @@ no_clock: no_pps: ptp_cleanup_pin_groups(ptp); no_pin_groups: + kfree(ptp->vclock_index); +no_mem_for_vclocks: if (ptp->kworker) kthread_destroy_worker(ptp->kworker); kworker_err: @@ -309,6 +320,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp) ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); + kfree(ptp->vclock_index); + if (ptp->kworker) { kthread_cancel_delayed_work_sync(&ptp->aux_work); kthread_destroy_worker(ptp->kworker); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 87cb55953b69..f75fadd9b244 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -49,6 +49,7 @@ struct ptp_clock { struct kthread_delayed_work aux_work; unsigned int max_vclocks; unsigned int n_vclocks; + int *vclock_index; struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */ bool is_virtual_clock; }; diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 0b05041783a5..6a36590ca77a 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -213,6 +213,9 @@ static ssize_t n_vclocks_store(struct device *dev, if (!vclock) goto out; + *(ptp->vclock_index + ptp->n_vclocks + i) = + vclock->clock->index; + dev_info(dev, "new virtual clock ptp%d\n", vclock->clock->index); } @@ -223,6 +226,9 @@ static ssize_t n_vclocks_store(struct device *dev, i = ptp->n_vclocks - num; device_for_each_child_reverse(dev, &i, unregister_vclock); + + for (i = 1; i <= ptp->n_vclocks - num; i++) + *(ptp->vclock_index + ptp->n_vclocks - i) = -1; } if (num == 0) @@ -256,6 +262,9 @@ static ssize_t max_vclocks_store(struct device *dev, const char *buf, size_t count) { struct ptp_clock *ptp = dev_get_drvdata(dev); + unsigned int *vclock_index; + int err = -EINVAL; + size_t size; u32 max; if (kstrtou32(buf, 0, &max) || max == 0) @@ -267,16 +276,29 @@ static ssize_t max_vclocks_store(struct device *dev, if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) return -ERESTARTSYS; - if (max < ptp->n_vclocks) { - mutex_unlock(&ptp->n_vclocks_mux); - return -EINVAL; + if (max < ptp->n_vclocks) + goto out; + + size = sizeof(int) * max; + vclock_index = kzalloc(size, GFP_KERNEL); + if (!vclock_index) { + err = -ENOMEM; + goto out; } + size = sizeof(int) * ptp->n_vclocks; + memcpy(vclock_index, ptp->vclock_index, size); + + kfree(ptp->vclock_index); + ptp->vclock_index = vclock_index; ptp->max_vclocks = max; mutex_unlock(&ptp->n_vclocks_mux); return count; +out: + mutex_unlock(&ptp->n_vclocks_mux); + return err; } static DEVICE_ATTR_RW(max_vclocks); From acb288e8047b7569fbc9af6fa6e9405315345103 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:55 +0800 Subject: [PATCH 0069/1469] ptp: add kernel API ptp_get_vclocks_index() Add kernel API ptp_get_vclocks_index() to get all ptp vclocks index on pclock. This is preparation for supporting ptp vclocks info query through ethtool. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 3 ++- drivers/ptp/ptp_private.h | 2 ++ drivers/ptp/ptp_vclock.c | 35 ++++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 14 +++++++++++++ 4 files changed, 53 insertions(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 9205a9362a9d..f012fa581cf4 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -24,10 +24,11 @@ #define PTP_PPS_EVENT PPS_CAPTUREASSERT #define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC) +struct class *ptp_class; + /* private globals */ static dev_t ptp_devt; -static struct class *ptp_class; static DEFINE_IDA(ptp_clocks_map); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index f75fadd9b244..dba6be477067 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -96,6 +96,8 @@ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp) return in_use; } +extern struct class *ptp_class; + /* * see ptp_chardev.c */ diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index fc9205cc504d..cefab29a0592 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -148,3 +148,38 @@ void ptp_vclock_unregister(struct ptp_vclock *vclock) ptp_clock_unregister(vclock->clock); kfree(vclock); } + +int ptp_get_vclocks_index(int pclock_index, int **vclock_index) +{ + char name[PTP_CLOCK_NAME_LEN] = ""; + struct ptp_clock *ptp; + struct device *dev; + int num = 0; + + if (pclock_index < 0) + return num; + + snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", pclock_index); + dev = class_find_device_by_name(ptp_class, name); + if (!dev) + return num; + + ptp = dev_get_drvdata(dev); + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) { + put_device(dev); + return num; + } + + *vclock_index = kzalloc(sizeof(int) * ptp->n_vclocks, GFP_KERNEL); + if (!(*vclock_index)) + goto out; + + memcpy(*vclock_index, ptp->vclock_index, sizeof(int) * ptp->n_vclocks); + num = ptp->n_vclocks; +out: + mutex_unlock(&ptp->n_vclocks_mux); + put_device(dev); + return num; +} +EXPORT_SYMBOL(ptp_get_vclocks_index); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index b6fb771ee524..300a984fec87 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -306,6 +306,18 @@ int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); */ void ptp_cancel_worker_sync(struct ptp_clock *ptp); +/** + * ptp_get_vclocks_index() - get all vclocks index on pclock, and + * caller is responsible to free memory + * of vclock_index + * + * @pclock_index: phc index of ptp pclock. + * @vclock_index: pointer to pointer of vclock index. + * + * return number of vclocks. + */ +int ptp_get_vclocks_index(int pclock_index, int **vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -325,6 +337,8 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp, { return -EOPNOTSUPP; } static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } +static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) +{ return 0; } #endif From c156174a67070042d51d2c866146d3c934d5468c Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:56 +0800 Subject: [PATCH 0070/1469] ethtool: add a new command for getting PHC virtual clocks Add an interface for getting PHC (PTP Hardware Clock) virtual clocks, which are based on PHC physical clock providing hardware timestamp to network packets. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 22 +++++ include/linux/ethtool.h | 10 +++ include/uapi/linux/ethtool_netlink.h | 15 ++++ net/ethtool/Makefile | 2 +- net/ethtool/common.c | 13 +++ net/ethtool/netlink.c | 10 +++ net/ethtool/netlink.h | 2 + net/ethtool/phc_vclocks.c | 94 ++++++++++++++++++++ 8 files changed, 167 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/phc_vclocks.c diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 6ea91e41593f..c86628e6a235 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -212,6 +212,7 @@ Userspace to kernel: ``ETHTOOL_MSG_FEC_SET`` set FEC settings ``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET`` get standard statistics + ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info ===================================== ================================ Kernel to userspace: @@ -250,6 +251,7 @@ Kernel to userspace: ``ETHTOOL_MSG_FEC_NTF`` FEC settings ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics + ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1477,6 +1479,25 @@ Low and high bounds are inclusive, for example: etherStatsPkts512to1023Octets 512 1023 ============================= ==== ==== +PHC_VCLOCKS_GET +=============== + +Query device PHC virtual clocks information. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested reply header + ``ETHTOOL_A_PHC_VCLOCKS_NUM`` u32 PHC virtual clocks number + ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array + ==================================== ====== ========================== + Request translation =================== @@ -1575,4 +1596,5 @@ are netlink only. n/a ``ETHTOOL_MSG_CABLE_TEST_ACT`` n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` + n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` =================================== ===================================== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 29dbb603bc91..232daaec56e4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -757,6 +757,16 @@ void ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, enum ethtool_link_mode_bit_indices link_mode); +/** + * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller + * is responsible to free memory of vclock_index + * @dev: pointer to net_device structure + * @vclock_index: pointer to pointer of vclock index + * + * Return number of phc vclocks + */ +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); + /** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to start of string to update diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index c7135c9c37a5..b3b93710eff7 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -46,6 +46,7 @@ enum { ETHTOOL_MSG_FEC_SET, ETHTOOL_MSG_MODULE_EEPROM_GET, ETHTOOL_MSG_STATS_GET, + ETHTOOL_MSG_PHC_VCLOCKS_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -88,6 +89,7 @@ enum { ETHTOOL_MSG_FEC_NTF, ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, ETHTOOL_MSG_STATS_GET_REPLY, + ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -440,6 +442,19 @@ enum { ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) }; +/* PHC VCLOCKS */ + +enum { + ETHTOOL_A_PHC_VCLOCKS_UNSPEC, + ETHTOOL_A_PHC_VCLOCKS_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PHC_VCLOCKS_NUM, /* u32 */ + ETHTOOL_A_PHC_VCLOCKS_INDEX, /* array, s32 */ + + /* add new constants above here */ + __ETHTOOL_A_PHC_VCLOCKS_CNT, + ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1) +}; + /* CABLE TEST */ enum { diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 723c9a8a8cdf..0a19470efbfb 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f9dcbad84788..798231b07676 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "common.h" @@ -554,6 +555,18 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) +{ + struct ethtool_ts_info info = { }; + int num = 0; + + if (!__ethtool_get_ts_info(dev, &info)) + num = ptp_get_vclocks_index(info.phc_index, vclock_index); + + return num; +} +EXPORT_SYMBOL(ethtool_get_phc_vclocks); + const struct ethtool_phy_ops *ethtool_phy_ops; void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index a7346346114f..73e0f5b626bf 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -248,6 +248,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, + [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -958,6 +959,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_phc_vclocks_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3e25a47fd482..3fc395c86702 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,7 @@ extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; +extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -382,6 +383,7 @@ extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; +extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c new file mode 100644 index 000000000000..637b2f5297d5 --- /dev/null +++ b/net/ethtool/phc_vclocks.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 NXP + */ +#include "netlink.h" +#include "common.h" + +struct phc_vclocks_req_info { + struct ethnl_req_info base; +}; + +struct phc_vclocks_reply_data { + struct ethnl_reply_data base; + int num; + int *index; +}; + +#define PHC_VCLOCKS_REPDATA(__reply_base) \ + container_of(__reply_base, struct phc_vclocks_reply_data, base) + +const struct nla_policy ethnl_phc_vclocks_get_policy[] = { + [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->num = ethtool_get_phc_vclocks(dev, &data->index); + ethnl_ops_complete(dev); + + return ret; +} + +static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + int len = 0; + + if (data->num > 0) { + len += nla_total_size(sizeof(u32)); + len += nla_total_size(sizeof(s32) * data->num); + } + + return len; +} + +static int phc_vclocks_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + if (data->num <= 0) + return 0; + + if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) || + nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX, + sizeof(s32) * data->num, data->index)) + return -EMSGSIZE; + + return 0; +} + +static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + kfree(data->index); +} + +const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = { + .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER, + .req_info_size = sizeof(struct phc_vclocks_req_info), + .reply_data_size = sizeof(struct phc_vclocks_reply_data), + + .prepare_data = phc_vclocks_prepare_data, + .reply_size = phc_vclocks_reply_size, + .fill_reply = phc_vclocks_fill_reply, + .cleanup_data = phc_vclocks_cleanup_data, +}; From 895487a3a10fb3a177e20dcde875515d46ccd4df Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:57 +0800 Subject: [PATCH 0071/1469] ptp: add kernel API ptp_convert_timestamp() Add kernel API ptp_convert_timestamp() to convert raw hardware timestamp to a specified ptp vclock time. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_vclock.c | 34 ++++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 13 ++++++++++++ 2 files changed, 47 insertions(+) diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index cefab29a0592..e0f87c57749a 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -183,3 +183,37 @@ out: return num; } EXPORT_SYMBOL(ptp_get_vclocks_index); + +void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ + char name[PTP_CLOCK_NAME_LEN] = ""; + struct ptp_vclock *vclock; + struct ptp_clock *ptp; + unsigned long flags; + struct device *dev; + u64 ns; + + snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", vclock_index); + dev = class_find_device_by_name(ptp_class, name); + if (!dev) + return; + + ptp = dev_get_drvdata(dev); + if (!ptp->is_virtual_clock) { + put_device(dev); + return; + } + + vclock = info_to_vclock(ptp->info); + + ns = ktime_to_ns(hwtstamps->hwtstamp); + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, ns); + spin_unlock_irqrestore(&vclock->lock, flags); + + put_device(dev); + hwtstamps->hwtstamp = ns_to_ktime(ns); +} +EXPORT_SYMBOL(ptp_convert_timestamp); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 300a984fec87..71fac9237725 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -12,6 +12,7 @@ #include #include #include +#include #define PTP_CLOCK_NAME_LEN 32 /** @@ -318,6 +319,15 @@ void ptp_cancel_worker_sync(struct ptp_clock *ptp); */ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); +/** + * ptp_convert_timestamp() - convert timestamp to a ptp vclock time + * + * @hwtstamps: skb_shared_hwtstamps structure pointer + * @vclock_index: phc index of ptp vclock. + */ +void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -339,6 +349,9 @@ static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } +static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ } #endif From 6c9a0a0f2333b1e3c29fef47a8b12131fce4905b Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:58 +0800 Subject: [PATCH 0072/1469] mptcp: setsockopt: convert to mptcp_setsockopt_sol_socket_timestamping() Split timestamping handling into a new function mptcp_setsockopt_sol_socket_timestamping(). This is preparation for extending SO_TIMESTAMPING for PHC binding, since optval will no longer be integer. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- net/mptcp/sockopt.c | 57 +++++++++++++++++++++++++++++++-------------- 1 file changed, 40 insertions(+), 17 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 092d1f635d27..ea38cbcd2ad4 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -157,19 +157,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); - switch (optname) { - case SO_TIMESTAMP_OLD: - case SO_TIMESTAMP_NEW: - case SO_TIMESTAMPNS_OLD: - case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, optname, !!val); - break; - case SO_TIMESTAMPING_NEW: - case SO_TIMESTAMPING_OLD: - sock_set_timestamping(sk, optname, val); - break; - } - + sock_set_timestamp(sk, optname, !!val); unlock_sock_fast(ssk, slow); } @@ -178,7 +166,8 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam } static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, - sockptr_t optval, unsigned int optlen) + sockptr_t optval, + unsigned int optlen) { int val, ret; @@ -205,14 +194,45 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - case SO_TIMESTAMPING_OLD: - case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; } +static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, + int optname, + sockptr_t optval, + unsigned int optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + int val, ret; + + ret = mptcp_get_int_option(msk, optval, optlen, &val); + if (ret) + return ret; + + ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, + KERNEL_SOCKPTR(&val), sizeof(val)); + if (ret) + return ret; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow = lock_sock_fast(ssk); + + sock_set_timestamping(sk, optname, val); + unlock_sock_fast(ssk, slow); + } + + release_sock(sk); + + return 0; +} + static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen) { @@ -299,9 +319,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: + return mptcp_setsockopt_sol_socket_int(msk, optname, optval, + optlen); case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: - return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); + return mptcp_setsockopt_sol_socket_timestamping(msk, optname, + optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); case SO_RCVLOWAT: From d463126e23f112629edb01594141ca437a92a108 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:59 +0800 Subject: [PATCH 0073/1469] net: sock: extend SO_TIMESTAMPING for PHC binding Since PTP virtual clock support is added, there can be several PTP virtual clocks based on one PTP physical clock for timestamping. This patch is to extend SO_TIMESTAMPING API to support PHC (PTP Hardware Clock) binding by adding a new flag SOF_TIMESTAMPING_BIND_PHC. When PTP virtual clocks are in use, user space can configure to bind one for timestamping, but PTP physical clock is not supported and not needed to bind. This patch is preparation for timestamp conversion from raw timestamp to a specific PTP virtual clock time in core net. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/net/sock.h | 8 +++- include/uapi/linux/net_tstamp.h | 17 ++++++++- net/core/sock.c | 65 +++++++++++++++++++++++++++++++-- net/ethtool/common.c | 1 + net/mptcp/sockopt.c | 23 +++++++++--- 5 files changed, 101 insertions(+), 13 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 8bdd80027ffb..f23cb259b0e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,7 +316,9 @@ struct bpf_local_storage; * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only - * @sk_tsflags: SO_TIMESTAMPING socket options + * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock + * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals @@ -493,6 +495,7 @@ struct sock { seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; + int sk_bind_phc; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; @@ -2755,7 +2758,8 @@ void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_set_timestamp(struct sock *sk, int optname, bool valbool); -int sock_set_timestamping(struct sock *sk, int optname, int val); +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping); void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 7ed0b3d1c00a..fcc61c73a666 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -13,7 +13,7 @@ #include #include /* for SO_TIMESTAMPING */ -/* SO_TIMESTAMPING gets an integer bit field comprised of these values */ +/* SO_TIMESTAMPING flags */ enum { SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1), @@ -30,8 +30,9 @@ enum { SOF_TIMESTAMPING_OPT_STATS = (1<<12), SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13), SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14), + SOF_TIMESTAMPING_BIND_PHC = (1 << 15), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; @@ -46,6 +47,18 @@ enum { SOF_TIMESTAMPING_TX_SCHED | \ SOF_TIMESTAMPING_TX_ACK) +/** + * struct so_timestamping - SO_TIMESTAMPING parameter + * + * @flags: SO_TIMESTAMPING flags + * @bind_phc: Index of PTP virtual clock bound to sock. This is available + * if flag SOF_TIMESTAMPING_BIND_PHC is set. + */ +struct so_timestamping { + int flags; + int bind_phc; +}; + /** * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter * diff --git a/net/core/sock.c b/net/core/sock.c index dd9599656c40..cad107112204 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include #include +#include + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -810,8 +812,47 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool) } } -int sock_set_timestamping(struct sock *sk, int optname, int val) +static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + bool match = false; + int *vclock_index; + int i, num; + + if (sk->sk_bound_dev_if) + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + + if (!dev) { + pr_err("%s: sock not bind to device\n", __func__); + return -EOPNOTSUPP; + } + + num = ethtool_get_phc_vclocks(dev, &vclock_index); + for (i = 0; i < num; i++) { + if (*(vclock_index + i) == phc_index) { + match = true; + break; + } + } + + if (num > 0) + kfree(vclock_index); + + if (!match) + return -EINVAL; + + sk->sk_bind_phc = phc_index; + + return 0; +} + +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping) +{ + int val = timestamping.flags; + int ret; + if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; @@ -832,6 +873,12 @@ int sock_set_timestamping(struct sock *sk, int optname, int val) !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; + if (val & SOF_TIMESTAMPING_BIND_PHC) { + ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); + if (ret) + return ret; + } + sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); @@ -907,6 +954,7 @@ EXPORT_SYMBOL(sock_set_mark); int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct so_timestamping timestamping; struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; @@ -1073,7 +1121,15 @@ set_sndbuf: case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - ret = sock_set_timestamping(sk, optname, val); + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) + return -EFAULT; + } else { + memset(×tamping, 0, sizeof(timestamping)); + timestamping.flags = val; + } + ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: @@ -1348,6 +1404,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; + struct so_timestamping timestamping; } v; int lv = sizeof(int); @@ -1451,7 +1508,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING_OLD: - v.val = sk->sk_tsflags; + lv = sizeof(v.timestamping); + v.timestamping.flags = sk->sk_tsflags; + v.timestamping.bind_phc = sk->sk_bind_phc; break; case SO_RCVTIMEO_OLD: diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 798231b07676..c63e0739dc6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -398,6 +398,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats", [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", + [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index ea38cbcd2ad4..8c03afac5ca0 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -207,14 +207,25 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val, ret; + struct so_timestamping timestamping; + int ret; - ret = mptcp_get_int_option(msk, optval, optlen, &val); - if (ret) - return ret; + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) + return -EFAULT; + } else if (optlen == sizeof(int)) { + memset(×tamping, 0, sizeof(timestamping)); + + if (copy_from_sockptr(×tamping.flags, optval, sizeof(int))) + return -EFAULT; + } else { + return -EINVAL; + } ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, - KERNEL_SOCKPTR(&val), sizeof(val)); + KERNEL_SOCKPTR(×tamping), + sizeof(timestamping)); if (ret) return ret; @@ -224,7 +235,7 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); - sock_set_timestamping(sk, optname, val); + sock_set_timestamping(sk, optname, timestamping); unlock_sock_fast(ssk, slow); } From d7c08826558811e1bf88de3750a7051f27d0e25c Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:00 +0800 Subject: [PATCH 0074/1469] net: socket: support hardware timestamp conversion to PHC bound This patch is to support hardware timestamp conversion to PHC bound. This applies to both RX and TX since their skb handling (for TX, it's skb clone in error queue) all goes through __sock_recv_timestamp. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- net/socket.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/net/socket.c b/net/socket.c index bd9233da2497..0b2dad3bdf7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,6 +104,7 @@ #include #include #include +#include #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -873,12 +874,18 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { - empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && - !skb_is_err_queue(skb)) - put_ts_pktinfo(msg, skb); + !skb_is_swtx_tstamp(skb, false_tstamp)) { + if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc); + + if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp, + tss.ts + 2)) { + empty = 0; + + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb); + } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) From 2214d7032479e50ff1fa7276e6efe1df08173fbf Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:01 +0800 Subject: [PATCH 0075/1469] selftests/net: timestamping: support binding PHC Support binding PHC of PTP vclock for timestamping. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- tools/testing/selftests/net/timestamping.c | 55 ++++++++++++++-------- 1 file changed, 35 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index 21091be70688..aee631c5284e 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -47,7 +47,7 @@ static void usage(const char *error) { if (error) printf("invalid option: %s\n", error); - printf("timestamping interface option*\n\n" + printf("timestamping [bind_phc_index] [option]*\n\n" "Options:\n" " IP_MULTICAST_LOOP - looping outgoing multicasts\n" " SO_TIMESTAMP - normal software time stamping, ms resolution\n" @@ -58,6 +58,7 @@ static void usage(const char *error) " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" + " SOF_TIMESTAMPING_BIND_PHC - request to bind a PHC of PTP vclock\n" " SIOCGSTAMP - check last socket time stamp\n" " SIOCGSTAMPNS - more accurate socket time stamp\n" " PTPV2 - use PTPv2 messages\n"); @@ -311,7 +312,6 @@ static void recvpacket(int sock, int recvmsg_flags, int main(int argc, char **argv) { - int so_timestamping_flags = 0; int so_timestamp = 0; int so_timestampns = 0; int siocgstamp = 0; @@ -325,6 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; + struct so_timestamping so_timestamping_get = { 0, -1 }; + struct so_timestamping so_timestamping = { 0, -1 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; @@ -342,7 +344,12 @@ int main(int argc, char **argv) exit(1); } - for (i = 2; i < argc; i++) { + if (argc >= 3 && sscanf(argv[2], "%d", &so_timestamping.bind_phc) == 1) + val = 3; + else + val = 2; + + for (i = val; i < argc; i++) { if (!strcasecmp(argv[i], "SO_TIMESTAMP")) so_timestamp = 1; else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) @@ -356,17 +363,19 @@ int main(int argc, char **argv) else if (!strcasecmp(argv[i], "PTPV2")) ptpv2 = 1; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_TX_HARDWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_TX_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RX_HARDWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RX_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_BIND_PHC")) + so_timestamping.flags |= SOF_TIMESTAMPING_BIND_PHC; else usage(argv[i]); } @@ -385,10 +394,10 @@ int main(int argc, char **argv) hwtstamp.ifr_data = (void *)&hwconfig; memset(&hwconfig, 0, sizeof(hwconfig)); hwconfig.tx_type = - (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? + (so_timestamping.flags & SOF_TIMESTAMPING_TX_HARDWARE) ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; hwconfig.rx_filter = - (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? + (so_timestamping.flags & SOF_TIMESTAMPING_RX_HARDWARE) ? ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC : HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; hwconfig_requested = hwconfig; @@ -413,6 +422,9 @@ int main(int argc, char **argv) sizeof(struct sockaddr_in)) < 0) bail("bind"); + if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, interface, if_len)) + bail("bind device"); + /* set multicast group for outgoing packets */ inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ addr.sin_addr = iaddr; @@ -444,10 +456,9 @@ int main(int argc, char **argv) &enabled, sizeof(enabled)) < 0) bail("setsockopt SO_TIMESTAMPNS"); - if (so_timestamping_flags && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, - &so_timestamping_flags, - sizeof(so_timestamping_flags)) < 0) + if (so_timestamping.flags && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping, + sizeof(so_timestamping)) < 0) bail("setsockopt SO_TIMESTAMPING"); /* request IP_PKTINFO for debugging purposes */ @@ -468,14 +479,18 @@ int main(int argc, char **argv) else printf("SO_TIMESTAMPNS %d\n", val); - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { + len = sizeof(so_timestamping_get); + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping_get, + &len) < 0) { printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", strerror(errno)); } else { - printf("SO_TIMESTAMPING %d\n", val); - if (val != so_timestamping_flags) - printf(" not the expected value %d\n", - so_timestamping_flags); + printf("SO_TIMESTAMPING flags %d, bind phc %d\n", + so_timestamping_get.flags, so_timestamping_get.bind_phc); + if (so_timestamping_get.flags != so_timestamping.flags || + so_timestamping_get.bind_phc != so_timestamping.bind_phc) + printf(" not expected, flags %d, bind phc %d\n", + so_timestamping.flags, so_timestamping.bind_phc); } /* send packets forever every five seconds */ From 5ce15f2783332dce99ef04e2bdc927f0fa84105d Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:02 +0800 Subject: [PATCH 0076/1469] MAINTAINERS: add entry for PTP virtual clock driver Add entry for PTP virtual clock driver. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 88449b7a4c95..ca7287ee775b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14890,6 +14890,13 @@ F: drivers/net/phy/dp83640* F: drivers/ptp/* F: include/linux/ptp_cl* +PTP VIRTUAL CLOCK SUPPORT +M: Yangbo Lu +L: netdev@vger.kernel.org +S: Maintained +F: drivers/ptp/ptp_vclock.c +F: net/ethtool/phc_vclocks.c + PTRACE SUPPORT M: Oleg Nesterov S: Maintained From 4f408e1fa6e10b6da72691233369172bac7d9e9b Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 30 Jun 2021 14:36:17 -0400 Subject: [PATCH 0077/1469] ibmvnic: retry reset if there are no other resets Normally, if a reset fails due to failover or other communication error there is another reset (eg: FAILOVER) in the queue and we would process that reset. But if we are unable to communicate with PHYP or VIOS after H_FREE_CRQ, there would be no other resets in the queue and the adapter would be in an undefined state even though it was in the OPEN state earlier. While starting the reset we set the carrier to off state so we won't even get the timeout resets. If the last queued reset fails, retry it as a hard reset (after the usual 60 second settling time). Signed-off-by: Sukadev Bhattiprolu Reviewed-by: Dany Madden Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 374a75d4faea..ed77191d19f4 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2420,9 +2420,10 @@ out: static void __ibmvnic_reset(struct work_struct *work) { - struct ibmvnic_rwi *rwi; struct ibmvnic_adapter *adapter; bool saved_state = false; + struct ibmvnic_rwi *tmprwi; + struct ibmvnic_rwi *rwi; unsigned long flags; u32 reset_state; int rc = 0; @@ -2489,7 +2490,7 @@ static void __ibmvnic_reset(struct work_struct *work) } else { rc = do_reset(adapter, rwi, reset_state); } - kfree(rwi); + tmprwi = rwi; adapter->last_reset_time = jiffies; if (rc) @@ -2497,8 +2498,23 @@ static void __ibmvnic_reset(struct work_struct *work) rwi = get_next_rwi(adapter); + /* + * If there is another reset queued, free the previous rwi + * and process the new reset even if previous reset failed + * (the previous reset could have failed because of a fail + * over for instance, so process the fail over). + * + * If there are no resets queued and the previous reset failed, + * the adapter would be in an undefined state. So retry the + * previous reset as a hard reset. + */ + if (rwi) + kfree(tmprwi); + else if (rc) + rwi = tmprwi; + if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER || - rwi->reset_reason == VNIC_RESET_MOBILITY)) + rwi->reset_reason == VNIC_RESET_MOBILITY || rc)) adapter->force_reset_recovery = true; } From 09ef17863f37235fe4e65a7d991e487b9ff6e553 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 30 Jun 2021 20:18:20 -0400 Subject: [PATCH 0078/1469] Documentation: add more details in tipc.rst kernel-doc for TIPC is too simple, we need to add more information for it. This patch is to extend the abstract, and add the Features and Links items. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- Documentation/networking/tipc.rst | 121 +++++++++++++++++++++++++++++- 1 file changed, 118 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/tipc.rst b/Documentation/networking/tipc.rst index 76775f24cdc8..ab63d298cca2 100644 --- a/Documentation/networking/tipc.rst +++ b/Documentation/networking/tipc.rst @@ -4,10 +4,125 @@ Linux Kernel TIPC ================= -TIPC (Transparent Inter Process Communication) is a protocol that is -specially designed for intra-cluster communication. +Introduction +============ -For more information about TIPC, see http://tipc.sourceforge.net. +TIPC (Transparent Inter Process Communication) is a protocol that is specially +designed for intra-cluster communication. It can be configured to transmit +messages either on UDP or directly across Ethernet. Message delivery is +sequence guaranteed, loss free and flow controlled. Latency times are shorter +than with any other known protocol, while maximal throughput is comparable to +that of TCP. + +TIPC Features +------------- + +- Cluster wide IPC service + + Have you ever wished you had the convenience of Unix Domain Sockets even when + transmitting data between cluster nodes? Where you yourself determine the + addresses you want to bind to and use? Where you don't have to perform DNS + lookups and worry about IP addresses? Where you don't have to start timers + to monitor the continuous existence of peer sockets? And yet without the + downsides of that socket type, such as the risk of lingering inodes? + + Welcome to the Transparent Inter Process Communication service, TIPC in short, + which gives you all of this, and a lot more. + +- Service Addressing + + A fundamental concept in TIPC is that of Service Addressing which makes it + possible for a programmer to chose his own address, bind it to a server + socket and let client programs use only that address for sending messages. + +- Service Tracking + + A client wanting to wait for the availability of a server, uses the Service + Tracking mechanism to subscribe for binding and unbinding/close events for + sockets with the associated service address. + + The service tracking mechanism can also be used for Cluster Topology Tracking, + i.e., subscribing for availability/non-availability of cluster nodes. + + Likewise, the service tracking mechanism can be used for Cluster Connectivity + Tracking, i.e., subscribing for up/down events for individual links between + cluster nodes. + +- Transmission Modes + + Using a service address, a client can send datagram messages to a server socket. + + Using the same address type, it can establish a connection towards an accepting + server socket. + + It can also use a service address to create and join a Communication Group, + which is the TIPC manifestation of a brokerless message bus. + + Multicast with very good performance and scalability is available both in + datagram mode and in communication group mode. + +- Inter Node Links + + Communication between any two nodes in a cluster is maintained by one or two + Inter Node Links, which both guarantee data traffic integrity and monitor + the peer node's availability. + +- Cluster Scalability + + By applying the Overlapping Ring Monitoring algorithm on the inter node links + it is possible to scale TIPC clusters up to 1000 nodes with a maintained + neighbor failure discovery time of 1-2 seconds. For smaller clusters this + time can be made much shorter. + +- Neighbor Discovery + + Neighbor Node Discovery in the cluster is done by Ethernet broadcast or UDP + multicast, when any of those services are available. If not, configured peer + IP addresses can be used. + +- Configuration + + When running TIPC in single node mode no configuration whatsoever is needed. + When running in cluster mode TIPC must as a minimum be given a node address + (before Linux 4.17) and told which interface to attach to. The "tipc" + configuration tool makes is possible to add and maintain many more + configuration parameters. + +- Performance + + TIPC message transfer latency times are better than in any other known protocol. + Maximal byte throughput for inter-node connections is still somewhat lower than + for TCP, while they are superior for intra-node and inter-container throughput + on the same host. + +- Language Support + + The TIPC user API has support for C, Python, Perl, Ruby, D and Go. + +More Information +---------------- + +- How to set up TIPC: + + http://tipc.io/getting_started.html + +- How to program with TIPC: + + http://tipc.io/programming.html + +- How to contribute to TIPC: + +- http://tipc.io/contacts.html + +- More details about TIPC specification: + + http://tipc.io/protocol.html + + +Implementation +============== + +TIPC is implemented as a kernel module in net/tipc/ directory. TIPC Base Types --------------- From ca75bcf0a83b6cc7f53a593d98ec7121c4839b43 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 1 Jul 2021 10:15:09 +0200 Subject: [PATCH 0079/1469] net: remove the caif_hsi driver The caif_hsi driver relies on a cfhsi_get_ops symbol using symbol_get, but this symbol is not provided anywhere in the kernel tree. Remove this driver given that it is dead code. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/caif/Kconfig | 9 - drivers/net/caif/Makefile | 3 - drivers/net/caif/caif_hsi.c | 1454 ----------------------------------- include/net/caif/caif_hsi.h | 200 ----- 4 files changed, 1666 deletions(-) delete mode 100644 drivers/net/caif/caif_hsi.c delete mode 100644 include/net/caif/caif_hsi.h diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig index a77124bc1f4b..709660cb38f8 100644 --- a/drivers/net/caif/Kconfig +++ b/drivers/net/caif/Kconfig @@ -20,15 +20,6 @@ config CAIF_TTY identified as N_CAIF. When this ldisc is opened from user space it will redirect the TTY's traffic into the CAIF stack. -config CAIF_HSI - tristate "CAIF HSI transport driver" - depends on CAIF - default n - help - The CAIF low level driver for CAIF over HSI. - Be aware that if you enable this then you also need to - enable a low-level HSI driver. - config CAIF_VIRTIO tristate "CAIF virtio transport driver" depends on CAIF && HAS_DMA diff --git a/drivers/net/caif/Makefile b/drivers/net/caif/Makefile index b1918c8c126c..97f664f8016c 100644 --- a/drivers/net/caif/Makefile +++ b/drivers/net/caif/Makefile @@ -4,8 +4,5 @@ ccflags-$(CONFIG_CAIF_DEBUG) := -DDEBUG # Serial interface obj-$(CONFIG_CAIF_TTY) += caif_serial.o -# HSI interface -obj-$(CONFIG_CAIF_HSI) += caif_hsi.o - # Virtio interface obj-$(CONFIG_CAIF_VIRTIO) += caif_virtio.o diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c deleted file mode 100644 index 3d63b15bbaa1..000000000000 --- a/drivers/net/caif/caif_hsi.c +++ /dev/null @@ -1,1454 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson - * Dmitry.Tarnyagin / dmitry.tarnyagin@lockless.no - */ - -#define pr_fmt(fmt) KBUILD_MODNAME fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Daniel Martensson"); -MODULE_DESCRIPTION("CAIF HSI driver"); - -/* Returns the number of padding bytes for alignment. */ -#define PAD_POW2(x, pow) ((((x)&((pow)-1)) == 0) ? 0 :\ - (((pow)-((x)&((pow)-1))))) - -static const struct cfhsi_config hsi_default_config = { - - /* Inactivity timeout on HSI, ms */ - .inactivity_timeout = HZ, - - /* Aggregation timeout (ms) of zero means no aggregation is done*/ - .aggregation_timeout = 1, - - /* - * HSI link layer flow-control thresholds. - * Threshold values for the HSI packet queue. Flow-control will be - * asserted when the number of packets exceeds q_high_mark. It will - * not be de-asserted before the number of packets drops below - * q_low_mark. - * Warning: A high threshold value might increase throughput but it - * will at the same time prevent channel prioritization and increase - * the risk of flooding the modem. The high threshold should be above - * the low. - */ - .q_high_mark = 100, - .q_low_mark = 50, - - /* - * HSI padding options. - * Warning: must be a base of 2 (& operation used) and can not be zero ! - */ - .head_align = 4, - .tail_align = 4, -}; - -#define ON 1 -#define OFF 0 - -static LIST_HEAD(cfhsi_list); - -static void cfhsi_inactivity_tout(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, inactivity_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - /* Schedule power down work queue. */ - if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_down_work); -} - -static void cfhsi_update_aggregation_stats(struct cfhsi *cfhsi, - const struct sk_buff *skb, - int direction) -{ - struct caif_payload_info *info; - int hpad, tpad, len; - - info = (struct caif_payload_info *)&skb->cb; - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - len = skb->len + hpad + tpad; - - if (direction > 0) - cfhsi->aggregation_len += len; - else if (direction < 0) - cfhsi->aggregation_len -= len; -} - -static bool cfhsi_can_send_aggregate(struct cfhsi *cfhsi) -{ - int i; - - if (cfhsi->cfg.aggregation_timeout == 0) - return true; - - for (i = 0; i < CFHSI_PRIO_BEBK; ++i) { - if (cfhsi->qhead[i].qlen) - return true; - } - - /* TODO: Use aggregation_len instead */ - if (cfhsi->qhead[CFHSI_PRIO_BEBK].qlen >= CFHSI_MAX_PKTS) - return true; - - return false; -} - -static struct sk_buff *cfhsi_dequeue(struct cfhsi *cfhsi) -{ - struct sk_buff *skb; - int i; - - for (i = 0; i < CFHSI_PRIO_LAST; ++i) { - skb = skb_dequeue(&cfhsi->qhead[i]); - if (skb) - break; - } - - return skb; -} - -static int cfhsi_tx_queue_len(struct cfhsi *cfhsi) -{ - int i, len = 0; - for (i = 0; i < CFHSI_PRIO_LAST; ++i) - len += skb_queue_len(&cfhsi->qhead[i]); - return len; -} - -static void cfhsi_abort_tx(struct cfhsi *cfhsi) -{ - struct sk_buff *skb; - - for (;;) { - spin_lock_bh(&cfhsi->lock); - skb = cfhsi_dequeue(cfhsi); - if (!skb) - break; - - cfhsi->ndev->stats.tx_errors++; - cfhsi->ndev->stats.tx_dropped++; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - kfree_skb(skb); - } - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); -} - -static int cfhsi_flush_fifo(struct cfhsi *cfhsi) -{ - char buffer[32]; /* Any reasonable value */ - size_t fifo_occupancy; - int ret; - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - do { - ret = cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy); - if (ret) { - netdev_warn(cfhsi->ndev, - "%s: can't get FIFO occupancy: %d.\n", - __func__, ret); - break; - } else if (!fifo_occupancy) - /* No more data, exitting normally */ - break; - - fifo_occupancy = min(sizeof(buffer), fifo_occupancy); - set_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits); - ret = cfhsi->ops->cfhsi_rx(buffer, fifo_occupancy, - cfhsi->ops); - if (ret) { - clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits); - netdev_warn(cfhsi->ndev, - "%s: can't read data: %d.\n", - __func__, ret); - break; - } - - ret = 5 * HZ; - ret = wait_event_interruptible_timeout(cfhsi->flush_fifo_wait, - !test_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits), ret); - - if (ret < 0) { - netdev_warn(cfhsi->ndev, - "%s: can't wait for flush complete: %d.\n", - __func__, ret); - break; - } else if (!ret) { - ret = -ETIMEDOUT; - netdev_warn(cfhsi->ndev, - "%s: timeout waiting for flush complete.\n", - __func__); - break; - } - } while (1); - - return ret; -} - -static int cfhsi_tx_frm(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int nfrms = 0; - int pld_len = 0; - struct sk_buff *skb; - u8 *pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ; - - skb = cfhsi_dequeue(cfhsi); - if (!skb) - return 0; - - /* Clear offset. */ - desc->offset = 0; - - /* Check if we can embed a CAIF frame. */ - if (skb->len < CFHSI_MAX_EMB_FRM_SZ) { - struct caif_payload_info *info; - int hpad; - int tpad; - - /* Calculate needed head alignment and tail alignment. */ - info = (struct caif_payload_info *)&skb->cb; - - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - - /* Check if frame still fits with added alignment. */ - if ((skb->len + hpad + tpad) <= CFHSI_MAX_EMB_FRM_SZ) { - u8 *pemb = desc->emb_frm; - desc->offset = CFHSI_DESC_SHORT_SZ; - *pemb = (u8)(hpad - 1); - pemb += hpad; - - /* Update network statistics. */ - spin_lock_bh(&cfhsi->lock); - cfhsi->ndev->stats.tx_packets++; - cfhsi->ndev->stats.tx_bytes += skb->len; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - - /* Copy in embedded CAIF frame. */ - skb_copy_bits(skb, 0, pemb, skb->len); - - /* Consume the SKB */ - consume_skb(skb); - skb = NULL; - } - } - - /* Create payload CAIF frames. */ - while (nfrms < CFHSI_MAX_PKTS) { - struct caif_payload_info *info; - int hpad; - int tpad; - - if (!skb) - skb = cfhsi_dequeue(cfhsi); - - if (!skb) - break; - - /* Calculate needed head alignment and tail alignment. */ - info = (struct caif_payload_info *)&skb->cb; - - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - - /* Fill in CAIF frame length in descriptor. */ - desc->cffrm_len[nfrms] = hpad + skb->len + tpad; - - /* Fill head padding information. */ - *pfrm = (u8)(hpad - 1); - pfrm += hpad; - - /* Update network statistics. */ - spin_lock_bh(&cfhsi->lock); - cfhsi->ndev->stats.tx_packets++; - cfhsi->ndev->stats.tx_bytes += skb->len; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - - /* Copy in CAIF frame. */ - skb_copy_bits(skb, 0, pfrm, skb->len); - - /* Update payload length. */ - pld_len += desc->cffrm_len[nfrms]; - - /* Update frame pointer. */ - pfrm += skb->len + tpad; - - /* Consume the SKB */ - consume_skb(skb); - skb = NULL; - - /* Update number of frames. */ - nfrms++; - } - - /* Unused length fields should be zero-filled (according to SPEC). */ - while (nfrms < CFHSI_MAX_PKTS) { - desc->cffrm_len[nfrms] = 0x0000; - nfrms++; - } - - /* Check if we can piggy-back another descriptor. */ - if (cfhsi_can_send_aggregate(cfhsi)) - desc->header |= CFHSI_PIGGY_DESC; - else - desc->header &= ~CFHSI_PIGGY_DESC; - - return CFHSI_DESC_SZ + pld_len; -} - -static void cfhsi_start_tx(struct cfhsi *cfhsi) -{ - struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf; - int len, res; - - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - do { - /* Create HSI frame. */ - len = cfhsi_tx_frm(desc, cfhsi); - if (!len) { - spin_lock_bh(&cfhsi->lock); - if (unlikely(cfhsi_tx_queue_len(cfhsi))) { - spin_unlock_bh(&cfhsi->lock); - res = -EAGAIN; - continue; - } - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - /* Start inactivity timer. */ - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - break; - } - - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - } while (res < 0); -} - -static void cfhsi_tx_done(struct cfhsi *cfhsi) -{ - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* - * Send flow on if flow off has been previously signalled - * and number of packets is below low water mark. - */ - spin_lock_bh(&cfhsi->lock); - if (cfhsi->flow_off_sent && - cfhsi_tx_queue_len(cfhsi) <= cfhsi->cfg.q_low_mark && - cfhsi->cfdev.flowctrl) { - - cfhsi->flow_off_sent = 0; - cfhsi->cfdev.flowctrl(cfhsi->ndev, ON); - } - - if (cfhsi_can_send_aggregate(cfhsi)) { - spin_unlock_bh(&cfhsi->lock); - cfhsi_start_tx(cfhsi); - } else { - mod_timer(&cfhsi->aggregation_timer, - jiffies + cfhsi->cfg.aggregation_timeout); - spin_unlock_bh(&cfhsi->lock); - } - - return; -} - -static void cfhsi_tx_done_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - cfhsi_tx_done(cfhsi); -} - -static int cfhsi_rx_desc(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int xfer_sz = 0; - int nfrms = 0; - u16 *plen = NULL; - u8 *pfrm = NULL; - - if ((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n", - __func__); - return -EPROTO; - } - - /* Check for embedded CAIF frame. */ - if (desc->offset) { - struct sk_buff *skb; - int len = 0; - pfrm = ((u8 *)desc) + desc->offset; - - /* Remove offset padding. */ - pfrm += *pfrm + 1; - - /* Read length of CAIF frame (little endian). */ - len = *pfrm; - len |= ((*(pfrm+1)) << 8) & 0xFF00; - len += 2; /* Add FCS fields. */ - - /* Sanity check length of CAIF frame. */ - if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid length.\n", - __func__); - return -EPROTO; - } - - /* Allocate SKB (OK even in IRQ context). */ - skb = alloc_skb(len + 1, GFP_ATOMIC); - if (!skb) { - netdev_err(cfhsi->ndev, "%s: Out of memory !\n", - __func__); - return -ENOMEM; - } - caif_assert(skb != NULL); - - skb_put_data(skb, pfrm, len); - - skb->protocol = htons(ETH_P_CAIF); - skb_reset_mac_header(skb); - skb->dev = cfhsi->ndev; - - netif_rx_any_context(skb); - - /* Update network statistics. */ - cfhsi->ndev->stats.rx_packets++; - cfhsi->ndev->stats.rx_bytes += len; - } - - /* Calculate transfer length. */ - plen = desc->cffrm_len; - while (nfrms < CFHSI_MAX_PKTS && *plen) { - xfer_sz += *plen; - plen++; - nfrms++; - } - - /* Check for piggy-backed descriptor. */ - if (desc->header & CFHSI_PIGGY_DESC) - xfer_sz += CFHSI_DESC_SZ; - - if ((xfer_sz % 4) || (xfer_sz > (CFHSI_BUF_SZ_RX - CFHSI_DESC_SZ))) { - netdev_err(cfhsi->ndev, - "%s: Invalid payload len: %d, ignored.\n", - __func__, xfer_sz); - return -EPROTO; - } - return xfer_sz; -} - -static int cfhsi_rx_desc_len(struct cfhsi_desc *desc) -{ - int xfer_sz = 0; - int nfrms = 0; - u16 *plen; - - if ((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) { - - pr_err("Invalid descriptor. %x %x\n", desc->header, - desc->offset); - return -EPROTO; - } - - /* Calculate transfer length. */ - plen = desc->cffrm_len; - while (nfrms < CFHSI_MAX_PKTS && *plen) { - xfer_sz += *plen; - plen++; - nfrms++; - } - - if (xfer_sz % 4) { - pr_err("Invalid payload len: %d, ignored.\n", xfer_sz); - return -EPROTO; - } - return xfer_sz; -} - -static int cfhsi_rx_pld(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int rx_sz = 0; - int nfrms = 0; - u16 *plen = NULL; - u8 *pfrm = NULL; - - /* Sanity check header and offset. */ - if (WARN_ON((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ))) { - netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n", - __func__); - return -EPROTO; - } - - /* Set frame pointer to start of payload. */ - pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ; - plen = desc->cffrm_len; - - /* Skip already processed frames. */ - while (nfrms < cfhsi->rx_state.nfrms) { - pfrm += *plen; - rx_sz += *plen; - plen++; - nfrms++; - } - - /* Parse payload. */ - while (nfrms < CFHSI_MAX_PKTS && *plen) { - struct sk_buff *skb; - u8 *pcffrm = NULL; - int len; - - /* CAIF frame starts after head padding. */ - pcffrm = pfrm + *pfrm + 1; - - /* Read length of CAIF frame (little endian). */ - len = *pcffrm; - len |= ((*(pcffrm + 1)) << 8) & 0xFF00; - len += 2; /* Add FCS fields. */ - - /* Sanity check length of CAIF frames. */ - if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid length.\n", - __func__); - return -EPROTO; - } - - /* Allocate SKB (OK even in IRQ context). */ - skb = alloc_skb(len + 1, GFP_ATOMIC); - if (!skb) { - netdev_err(cfhsi->ndev, "%s: Out of memory !\n", - __func__); - cfhsi->rx_state.nfrms = nfrms; - return -ENOMEM; - } - caif_assert(skb != NULL); - - skb_put_data(skb, pcffrm, len); - - skb->protocol = htons(ETH_P_CAIF); - skb_reset_mac_header(skb); - skb->dev = cfhsi->ndev; - - netif_rx_any_context(skb); - - /* Update network statistics. */ - cfhsi->ndev->stats.rx_packets++; - cfhsi->ndev->stats.rx_bytes += len; - - pfrm += *plen; - rx_sz += *plen; - plen++; - nfrms++; - } - - return rx_sz; -} - -static void cfhsi_rx_done(struct cfhsi *cfhsi) -{ - int res; - int desc_pld_len = 0, rx_len, rx_state; - struct cfhsi_desc *desc = NULL; - u8 *rx_ptr, *rx_buf; - struct cfhsi_desc *piggy_desc = NULL; - - desc = (struct cfhsi_desc *)cfhsi->rx_buf; - - netdev_dbg(cfhsi->ndev, "%s\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Update inactivity timer if pending. */ - spin_lock_bh(&cfhsi->lock); - mod_timer_pending(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - - if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) { - desc_pld_len = cfhsi_rx_desc_len(desc); - - if (desc_pld_len < 0) - goto out_of_sync; - - rx_buf = cfhsi->rx_buf; - rx_len = desc_pld_len; - if (desc_pld_len > 0 && (desc->header & CFHSI_PIGGY_DESC)) - rx_len += CFHSI_DESC_SZ; - if (desc_pld_len == 0) - rx_buf = cfhsi->rx_flip_buf; - } else { - rx_buf = cfhsi->rx_flip_buf; - - rx_len = CFHSI_DESC_SZ; - if (cfhsi->rx_state.pld_len > 0 && - (desc->header & CFHSI_PIGGY_DESC)) { - - piggy_desc = (struct cfhsi_desc *) - (desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ + - cfhsi->rx_state.pld_len); - - cfhsi->rx_state.piggy_desc = true; - - /* Extract payload len from piggy-backed descriptor. */ - desc_pld_len = cfhsi_rx_desc_len(piggy_desc); - if (desc_pld_len < 0) - goto out_of_sync; - - if (desc_pld_len > 0) { - rx_len = desc_pld_len; - if (piggy_desc->header & CFHSI_PIGGY_DESC) - rx_len += CFHSI_DESC_SZ; - } - - /* - * Copy needed information from the piggy-backed - * descriptor to the descriptor in the start. - */ - memcpy(rx_buf, (u8 *)piggy_desc, - CFHSI_DESC_SHORT_SZ); - } - } - - if (desc_pld_len) { - rx_state = CFHSI_RX_STATE_PAYLOAD; - rx_ptr = rx_buf + CFHSI_DESC_SZ; - } else { - rx_state = CFHSI_RX_STATE_DESC; - rx_ptr = rx_buf; - rx_len = CFHSI_DESC_SZ; - } - - /* Initiate next read */ - if (test_bit(CFHSI_AWAKE, &cfhsi->bits)) { - /* Set up new transfer. */ - netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", - __func__); - - res = cfhsi->ops->cfhsi_rx(rx_ptr, rx_len, - cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: RX error %d.\n", - __func__, res); - cfhsi->ndev->stats.rx_errors++; - cfhsi->ndev->stats.rx_dropped++; - } - } - - if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) { - /* Extract payload from descriptor */ - if (cfhsi_rx_desc(desc, cfhsi) < 0) - goto out_of_sync; - } else { - /* Extract payload */ - if (cfhsi_rx_pld(desc, cfhsi) < 0) - goto out_of_sync; - if (piggy_desc) { - /* Extract any payload in piggyback descriptor. */ - if (cfhsi_rx_desc(piggy_desc, cfhsi) < 0) - goto out_of_sync; - /* Mark no embedded frame after extracting it */ - piggy_desc->offset = 0; - } - } - - /* Update state info */ - memset(&cfhsi->rx_state, 0, sizeof(cfhsi->rx_state)); - cfhsi->rx_state.state = rx_state; - cfhsi->rx_ptr = rx_ptr; - cfhsi->rx_len = rx_len; - cfhsi->rx_state.pld_len = desc_pld_len; - cfhsi->rx_state.piggy_desc = desc->header & CFHSI_PIGGY_DESC; - - if (rx_buf != cfhsi->rx_buf) - swap(cfhsi->rx_buf, cfhsi->rx_flip_buf); - return; - -out_of_sync: - netdev_err(cfhsi->ndev, "%s: Out of sync.\n", __func__); - print_hex_dump_bytes("--> ", DUMP_PREFIX_NONE, - cfhsi->rx_buf, CFHSI_DESC_SZ); - schedule_work(&cfhsi->out_of_sync_work); -} - -static void cfhsi_rx_slowpath(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, rx_slowpath_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - cfhsi_rx_done(cfhsi); -} - -static void cfhsi_rx_done_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - if (test_and_clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits)) - wake_up_interruptible(&cfhsi->flush_fifo_wait); - else - cfhsi_rx_done(cfhsi); -} - -static void cfhsi_wake_up(struct work_struct *work) -{ - struct cfhsi *cfhsi = NULL; - int res; - int len; - long ret; - - cfhsi = container_of(work, struct cfhsi, wake_up_work); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - if (unlikely(test_bit(CFHSI_AWAKE, &cfhsi->bits))) { - /* It happenes when wakeup is requested by - * both ends at the same time. */ - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - return; - } - - /* Activate wake line. */ - cfhsi->ops->cfhsi_wake_up(cfhsi->ops); - - netdev_dbg(cfhsi->ndev, "%s: Start waiting.\n", - __func__); - - /* Wait for acknowledge. */ - ret = CFHSI_WAKE_TOUT; - ret = wait_event_interruptible_timeout(cfhsi->wake_up_wait, - test_and_clear_bit(CFHSI_WAKE_UP_ACK, - &cfhsi->bits), ret); - if (unlikely(ret < 0)) { - /* Interrupted by signal. */ - netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n", - __func__, ret); - - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - return; - } else if (!ret) { - bool ca_wake = false; - size_t fifo_occupancy = 0; - - /* Wakeup timeout */ - netdev_dbg(cfhsi->ndev, "%s: Timeout.\n", - __func__); - - /* Check FIFO to check if modem has sent something. */ - WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy)); - - netdev_dbg(cfhsi->ndev, "%s: Bytes in FIFO: %u.\n", - __func__, (unsigned) fifo_occupancy); - - /* Check if we misssed the interrupt. */ - WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops, - &ca_wake)); - - if (ca_wake) { - netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n", - __func__); - - /* Clear the CFHSI_WAKE_UP_ACK bit to prevent race. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - - /* Continue execution. */ - goto wake_ack; - } - - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - return; - } -wake_ack: - netdev_dbg(cfhsi->ndev, "%s: Woken.\n", - __func__); - - /* Clear power up bit. */ - set_bit(CFHSI_AWAKE, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - - /* Resume read operation. */ - netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", __func__); - res = cfhsi->ops->cfhsi_rx(cfhsi->rx_ptr, cfhsi->rx_len, cfhsi->ops); - - if (WARN_ON(res < 0)) - netdev_err(cfhsi->ndev, "%s: RX err %d.\n", __func__, res); - - /* Clear power up acknowledment. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - - spin_lock_bh(&cfhsi->lock); - - /* Resume transmit if queues are not empty. */ - if (!cfhsi_tx_queue_len(cfhsi)) { - netdev_dbg(cfhsi->ndev, "%s: Peer wake, start timer.\n", - __func__); - /* Start inactivity timer. */ - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - return; - } - - netdev_dbg(cfhsi->ndev, "%s: Host wake.\n", - __func__); - - spin_unlock_bh(&cfhsi->lock); - - /* Create HSI frame. */ - len = cfhsi_tx_frm((struct cfhsi_desc *)cfhsi->tx_buf, cfhsi); - - if (likely(len > 0)) { - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - cfhsi_abort_tx(cfhsi); - } - } else { - netdev_err(cfhsi->ndev, - "%s: Failed to create HSI frame: %d.\n", - __func__, len); - } -} - -static void cfhsi_wake_down(struct work_struct *work) -{ - long ret; - struct cfhsi *cfhsi = NULL; - size_t fifo_occupancy = 0; - int retry = CFHSI_WAKE_TOUT; - - cfhsi = container_of(work, struct cfhsi, wake_down_work); - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Deactivate wake line. */ - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - - /* Wait for acknowledge. */ - ret = CFHSI_WAKE_TOUT; - ret = wait_event_interruptible_timeout(cfhsi->wake_down_wait, - test_and_clear_bit(CFHSI_WAKE_DOWN_ACK, - &cfhsi->bits), ret); - if (ret < 0) { - /* Interrupted by signal. */ - netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n", - __func__, ret); - return; - } else if (!ret) { - bool ca_wake = true; - - /* Timeout */ - netdev_err(cfhsi->ndev, "%s: Timeout.\n", __func__); - - /* Check if we misssed the interrupt. */ - WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops, - &ca_wake)); - if (!ca_wake) - netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n", - __func__); - } - - /* Check FIFO occupancy. */ - while (retry) { - WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy)); - - if (!fifo_occupancy) - break; - - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(1); - retry--; - } - - if (!retry) - netdev_err(cfhsi->ndev, "%s: FIFO Timeout.\n", __func__); - - /* Clear AWAKE condition. */ - clear_bit(CFHSI_AWAKE, &cfhsi->bits); - - /* Cancel pending RX requests. */ - cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops); -} - -static void cfhsi_out_of_sync(struct work_struct *work) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(work, struct cfhsi, out_of_sync_work); - - rtnl_lock(); - dev_close(cfhsi->ndev); - rtnl_unlock(); -} - -static void cfhsi_wake_up_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - set_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - wake_up_interruptible(&cfhsi->wake_up_wait); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Schedule wake up work queue if the peer initiates. */ - if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_up_work); -} - -static void cfhsi_wake_down_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - /* Initiating low power is only permitted by the host (us). */ - set_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits); - wake_up_interruptible(&cfhsi->wake_down_wait); -} - -static void cfhsi_aggregation_tout(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, aggregation_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - cfhsi_start_tx(cfhsi); -} - -static netdev_tx_t cfhsi_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct cfhsi *cfhsi = NULL; - int start_xfer = 0; - int timer_active; - int prio; - - if (!dev) - return -EINVAL; - - cfhsi = netdev_priv(dev); - - switch (skb->priority) { - case TC_PRIO_BESTEFFORT: - case TC_PRIO_FILLER: - case TC_PRIO_BULK: - prio = CFHSI_PRIO_BEBK; - break; - case TC_PRIO_INTERACTIVE_BULK: - prio = CFHSI_PRIO_VI; - break; - case TC_PRIO_INTERACTIVE: - prio = CFHSI_PRIO_VO; - break; - case TC_PRIO_CONTROL: - default: - prio = CFHSI_PRIO_CTL; - break; - } - - spin_lock_bh(&cfhsi->lock); - - /* Update aggregation statistics */ - cfhsi_update_aggregation_stats(cfhsi, skb, 1); - - /* Queue the SKB */ - skb_queue_tail(&cfhsi->qhead[prio], skb); - - /* Sanity check; xmit should not be called after unregister_netdev */ - if (WARN_ON(test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))) { - spin_unlock_bh(&cfhsi->lock); - cfhsi_abort_tx(cfhsi); - return -EINVAL; - } - - /* Send flow off if number of packets is above high water mark. */ - if (!cfhsi->flow_off_sent && - cfhsi_tx_queue_len(cfhsi) > cfhsi->cfg.q_high_mark && - cfhsi->cfdev.flowctrl) { - cfhsi->flow_off_sent = 1; - cfhsi->cfdev.flowctrl(cfhsi->ndev, OFF); - } - - if (cfhsi->tx_state == CFHSI_TX_STATE_IDLE) { - cfhsi->tx_state = CFHSI_TX_STATE_XFER; - start_xfer = 1; - } - - if (!start_xfer) { - /* Send aggregate if it is possible */ - bool aggregate_ready = - cfhsi_can_send_aggregate(cfhsi) && - del_timer(&cfhsi->aggregation_timer) > 0; - spin_unlock_bh(&cfhsi->lock); - if (aggregate_ready) - cfhsi_start_tx(cfhsi); - return NETDEV_TX_OK; - } - - /* Delete inactivity timer if started. */ - timer_active = del_timer_sync(&cfhsi->inactivity_timer); - - spin_unlock_bh(&cfhsi->lock); - - if (timer_active) { - struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf; - int len; - int res; - - /* Create HSI frame. */ - len = cfhsi_tx_frm(desc, cfhsi); - WARN_ON(!len); - - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - cfhsi_abort_tx(cfhsi); - } - } else { - /* Schedule wake up work queue if the we initiate. */ - if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_up_work); - } - - return NETDEV_TX_OK; -} - -static const struct net_device_ops cfhsi_netdevops; - -static void cfhsi_setup(struct net_device *dev) -{ - int i; - struct cfhsi *cfhsi = netdev_priv(dev); - dev->features = 0; - dev->type = ARPHRD_CAIF; - dev->flags = IFF_POINTOPOINT | IFF_NOARP; - dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ; - dev->priv_flags |= IFF_NO_QUEUE; - dev->needs_free_netdev = true; - dev->netdev_ops = &cfhsi_netdevops; - for (i = 0; i < CFHSI_PRIO_LAST; ++i) - skb_queue_head_init(&cfhsi->qhead[i]); - cfhsi->cfdev.link_select = CAIF_LINK_HIGH_BANDW; - cfhsi->cfdev.use_frag = false; - cfhsi->cfdev.use_stx = false; - cfhsi->cfdev.use_fcs = false; - cfhsi->ndev = dev; - cfhsi->cfg = hsi_default_config; -} - -static int cfhsi_open(struct net_device *ndev) -{ - struct cfhsi *cfhsi = netdev_priv(ndev); - int res; - - clear_bit(CFHSI_SHUTDOWN, &cfhsi->bits); - - /* Initialize state vaiables. */ - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - cfhsi->rx_state.state = CFHSI_RX_STATE_DESC; - - /* Set flow info */ - cfhsi->flow_off_sent = 0; - - /* - * Allocate a TX buffer with the size of a HSI packet descriptors - * and the necessary room for CAIF payload frames. - */ - cfhsi->tx_buf = kzalloc(CFHSI_BUF_SZ_TX, GFP_KERNEL); - if (!cfhsi->tx_buf) { - res = -ENODEV; - goto err_alloc_tx; - } - - /* - * Allocate a RX buffer with the size of two HSI packet descriptors and - * the necessary room for CAIF payload frames. - */ - cfhsi->rx_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL); - if (!cfhsi->rx_buf) { - res = -ENODEV; - goto err_alloc_rx; - } - - cfhsi->rx_flip_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL); - if (!cfhsi->rx_flip_buf) { - res = -ENODEV; - goto err_alloc_rx_flip; - } - - /* Initialize aggregation timeout */ - cfhsi->cfg.aggregation_timeout = hsi_default_config.aggregation_timeout; - - /* Initialize recieve vaiables. */ - cfhsi->rx_ptr = cfhsi->rx_buf; - cfhsi->rx_len = CFHSI_DESC_SZ; - - /* Initialize spin locks. */ - spin_lock_init(&cfhsi->lock); - - /* Set up the driver. */ - cfhsi->cb_ops.tx_done_cb = cfhsi_tx_done_cb; - cfhsi->cb_ops.rx_done_cb = cfhsi_rx_done_cb; - cfhsi->cb_ops.wake_up_cb = cfhsi_wake_up_cb; - cfhsi->cb_ops.wake_down_cb = cfhsi_wake_down_cb; - - /* Initialize the work queues. */ - INIT_WORK(&cfhsi->wake_up_work, cfhsi_wake_up); - INIT_WORK(&cfhsi->wake_down_work, cfhsi_wake_down); - INIT_WORK(&cfhsi->out_of_sync_work, cfhsi_out_of_sync); - - /* Clear all bit fields. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - clear_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - clear_bit(CFHSI_AWAKE, &cfhsi->bits); - - /* Create work thread. */ - cfhsi->wq = alloc_ordered_workqueue(cfhsi->ndev->name, WQ_MEM_RECLAIM); - if (!cfhsi->wq) { - netdev_err(cfhsi->ndev, "%s: Failed to create work queue.\n", - __func__); - res = -ENODEV; - goto err_create_wq; - } - - /* Initialize wait queues. */ - init_waitqueue_head(&cfhsi->wake_up_wait); - init_waitqueue_head(&cfhsi->wake_down_wait); - init_waitqueue_head(&cfhsi->flush_fifo_wait); - - /* Setup the inactivity timer. */ - timer_setup(&cfhsi->inactivity_timer, cfhsi_inactivity_tout, 0); - /* Setup the slowpath RX timer. */ - timer_setup(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath, 0); - /* Setup the aggregation timer. */ - timer_setup(&cfhsi->aggregation_timer, cfhsi_aggregation_tout, 0); - - /* Activate HSI interface. */ - res = cfhsi->ops->cfhsi_up(cfhsi->ops); - if (res) { - netdev_err(cfhsi->ndev, - "%s: can't activate HSI interface: %d.\n", - __func__, res); - goto err_activate; - } - - /* Flush FIFO */ - res = cfhsi_flush_fifo(cfhsi); - if (res) { - netdev_err(cfhsi->ndev, "%s: Can't flush FIFO: %d.\n", - __func__, res); - goto err_net_reg; - } - return res; - - err_net_reg: - cfhsi->ops->cfhsi_down(cfhsi->ops); - err_activate: - destroy_workqueue(cfhsi->wq); - err_create_wq: - kfree(cfhsi->rx_flip_buf); - err_alloc_rx_flip: - kfree(cfhsi->rx_buf); - err_alloc_rx: - kfree(cfhsi->tx_buf); - err_alloc_tx: - return res; -} - -static int cfhsi_close(struct net_device *ndev) -{ - struct cfhsi *cfhsi = netdev_priv(ndev); - u8 *tx_buf, *rx_buf, *flip_buf; - - /* going to shutdown driver */ - set_bit(CFHSI_SHUTDOWN, &cfhsi->bits); - - /* Delete timers if pending */ - del_timer_sync(&cfhsi->inactivity_timer); - del_timer_sync(&cfhsi->rx_slowpath_timer); - del_timer_sync(&cfhsi->aggregation_timer); - - /* Cancel pending RX request (if any) */ - cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops); - - /* Destroy workqueue */ - destroy_workqueue(cfhsi->wq); - - /* Store bufferes: will be freed later. */ - tx_buf = cfhsi->tx_buf; - rx_buf = cfhsi->rx_buf; - flip_buf = cfhsi->rx_flip_buf; - /* Flush transmit queues. */ - cfhsi_abort_tx(cfhsi); - - /* Deactivate interface */ - cfhsi->ops->cfhsi_down(cfhsi->ops); - - /* Free buffers. */ - kfree(tx_buf); - kfree(rx_buf); - kfree(flip_buf); - return 0; -} - -static void cfhsi_uninit(struct net_device *dev) -{ - struct cfhsi *cfhsi = netdev_priv(dev); - ASSERT_RTNL(); - symbol_put(cfhsi_get_device); - list_del(&cfhsi->list); -} - -static const struct net_device_ops cfhsi_netdevops = { - .ndo_uninit = cfhsi_uninit, - .ndo_open = cfhsi_open, - .ndo_stop = cfhsi_close, - .ndo_start_xmit = cfhsi_xmit -}; - -static void cfhsi_netlink_parms(struct nlattr *data[], struct cfhsi *cfhsi) -{ - int i; - - if (!data) { - pr_debug("no params data found\n"); - return; - } - - i = __IFLA_CAIF_HSI_INACTIVITY_TOUT; - /* - * Inactivity timeout in millisecs. Lowest possible value is 1, - * and highest possible is NEXT_TIMER_MAX_DELTA. - */ - if (data[i]) { - u32 inactivity_timeout = nla_get_u32(data[i]); - /* Pre-calculate inactivity timeout. */ - cfhsi->cfg.inactivity_timeout = inactivity_timeout * HZ / 1000; - if (cfhsi->cfg.inactivity_timeout == 0) - cfhsi->cfg.inactivity_timeout = 1; - else if (cfhsi->cfg.inactivity_timeout > NEXT_TIMER_MAX_DELTA) - cfhsi->cfg.inactivity_timeout = NEXT_TIMER_MAX_DELTA; - } - - i = __IFLA_CAIF_HSI_AGGREGATION_TOUT; - if (data[i]) - cfhsi->cfg.aggregation_timeout = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_HEAD_ALIGN; - if (data[i]) - cfhsi->cfg.head_align = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_TAIL_ALIGN; - if (data[i]) - cfhsi->cfg.tail_align = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_QHIGH_WATERMARK; - if (data[i]) - cfhsi->cfg.q_high_mark = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_QLOW_WATERMARK; - if (data[i]) - cfhsi->cfg.q_low_mark = nla_get_u32(data[i]); -} - -static int caif_hsi_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[], - struct netlink_ext_ack *extack) -{ - cfhsi_netlink_parms(data, netdev_priv(dev)); - netdev_state_change(dev); - return 0; -} - -static const struct nla_policy caif_hsi_policy[__IFLA_CAIF_HSI_MAX + 1] = { - [__IFLA_CAIF_HSI_INACTIVITY_TOUT] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_AGGREGATION_TOUT] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_HEAD_ALIGN] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_TAIL_ALIGN] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_QHIGH_WATERMARK] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_QLOW_WATERMARK] = { .type = NLA_U32, .len = 4 }, -}; - -static size_t caif_hsi_get_size(const struct net_device *dev) -{ - int i; - size_t s = 0; - for (i = __IFLA_CAIF_HSI_UNSPEC + 1; i < __IFLA_CAIF_HSI_MAX; i++) - s += nla_total_size(caif_hsi_policy[i].len); - return s; -} - -static int caif_hsi_fill_info(struct sk_buff *skb, const struct net_device *dev) -{ - struct cfhsi *cfhsi = netdev_priv(dev); - - if (nla_put_u32(skb, __IFLA_CAIF_HSI_INACTIVITY_TOUT, - cfhsi->cfg.inactivity_timeout) || - nla_put_u32(skb, __IFLA_CAIF_HSI_AGGREGATION_TOUT, - cfhsi->cfg.aggregation_timeout) || - nla_put_u32(skb, __IFLA_CAIF_HSI_HEAD_ALIGN, - cfhsi->cfg.head_align) || - nla_put_u32(skb, __IFLA_CAIF_HSI_TAIL_ALIGN, - cfhsi->cfg.tail_align) || - nla_put_u32(skb, __IFLA_CAIF_HSI_QHIGH_WATERMARK, - cfhsi->cfg.q_high_mark) || - nla_put_u32(skb, __IFLA_CAIF_HSI_QLOW_WATERMARK, - cfhsi->cfg.q_low_mark)) - return -EMSGSIZE; - - return 0; -} - -static int caif_hsi_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) -{ - struct cfhsi *cfhsi = NULL; - struct cfhsi_ops *(*get_ops)(void); - - ASSERT_RTNL(); - - cfhsi = netdev_priv(dev); - cfhsi_netlink_parms(data, cfhsi); - - get_ops = symbol_get(cfhsi_get_ops); - if (!get_ops) { - pr_err("%s: failed to get the cfhsi_ops\n", __func__); - return -ENODEV; - } - - /* Assign the HSI device. */ - cfhsi->ops = (*get_ops)(); - if (!cfhsi->ops) { - pr_err("%s: failed to get the cfhsi_ops\n", __func__); - goto err; - } - - /* Assign the driver to this HSI device. */ - cfhsi->ops->cb_ops = &cfhsi->cb_ops; - if (register_netdevice(dev)) { - pr_warn("%s: caif_hsi device registration failed\n", __func__); - goto err; - } - /* Add CAIF HSI device to list. */ - list_add_tail(&cfhsi->list, &cfhsi_list); - - return 0; -err: - symbol_put(cfhsi_get_ops); - return -ENODEV; -} - -static struct rtnl_link_ops caif_hsi_link_ops __read_mostly = { - .kind = "cfhsi", - .priv_size = sizeof(struct cfhsi), - .setup = cfhsi_setup, - .maxtype = __IFLA_CAIF_HSI_MAX, - .policy = caif_hsi_policy, - .newlink = caif_hsi_newlink, - .changelink = caif_hsi_changelink, - .get_size = caif_hsi_get_size, - .fill_info = caif_hsi_fill_info, -}; - -static void __exit cfhsi_exit_module(void) -{ - struct list_head *list_node; - struct list_head *n; - struct cfhsi *cfhsi; - - rtnl_link_unregister(&caif_hsi_link_ops); - - rtnl_lock(); - list_for_each_safe(list_node, n, &cfhsi_list) { - cfhsi = list_entry(list_node, struct cfhsi, list); - unregister_netdevice(cfhsi->ndev); - } - rtnl_unlock(); -} - -static int __init cfhsi_init_module(void) -{ - return rtnl_link_register(&caif_hsi_link_ops); -} - -module_init(cfhsi_init_module); -module_exit(cfhsi_exit_module); diff --git a/include/net/caif/caif_hsi.h b/include/net/caif/caif_hsi.h deleted file mode 100644 index 552cf68d28d2..000000000000 --- a/include/net/caif/caif_hsi.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson / daniel.martensson@stericsson.com - * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com - */ - -#ifndef CAIF_HSI_H_ -#define CAIF_HSI_H_ - -#include -#include -#include - -/* - * Maximum number of CAIF frames that can reside in the same HSI frame. - */ -#define CFHSI_MAX_PKTS 15 - -/* - * Maximum number of bytes used for the frame that can be embedded in the - * HSI descriptor. - */ -#define CFHSI_MAX_EMB_FRM_SZ 96 - -/* - * Decides if HSI buffers should be prefilled with 0xFF pattern for easier - * debugging. Both TX and RX buffers will be filled before the transfer. - */ -#define CFHSI_DBG_PREFILL 0 - -/* Structure describing a HSI packet descriptor. */ -#pragma pack(1) /* Byte alignment. */ -struct cfhsi_desc { - u8 header; - u8 offset; - u16 cffrm_len[CFHSI_MAX_PKTS]; - u8 emb_frm[CFHSI_MAX_EMB_FRM_SZ]; -}; -#pragma pack() /* Default alignment. */ - -/* Size of the complete HSI packet descriptor. */ -#define CFHSI_DESC_SZ (sizeof(struct cfhsi_desc)) - -/* - * Size of the complete HSI packet descriptor excluding the optional embedded - * CAIF frame. - */ -#define CFHSI_DESC_SHORT_SZ (CFHSI_DESC_SZ - CFHSI_MAX_EMB_FRM_SZ) - -/* - * Maximum bytes transferred in one transfer. - */ -#define CFHSI_MAX_CAIF_FRAME_SZ 4096 - -#define CFHSI_MAX_PAYLOAD_SZ (CFHSI_MAX_PKTS * CFHSI_MAX_CAIF_FRAME_SZ) - -/* Size of the complete HSI TX buffer. */ -#define CFHSI_BUF_SZ_TX (CFHSI_DESC_SZ + CFHSI_MAX_PAYLOAD_SZ) - -/* Size of the complete HSI RX buffer. */ -#define CFHSI_BUF_SZ_RX ((2 * CFHSI_DESC_SZ) + CFHSI_MAX_PAYLOAD_SZ) - -/* Bitmasks for the HSI descriptor. */ -#define CFHSI_PIGGY_DESC (0x01 << 7) - -#define CFHSI_TX_STATE_IDLE 0 -#define CFHSI_TX_STATE_XFER 1 - -#define CFHSI_RX_STATE_DESC 0 -#define CFHSI_RX_STATE_PAYLOAD 1 - -/* Bitmasks for power management. */ -#define CFHSI_WAKE_UP 0 -#define CFHSI_WAKE_UP_ACK 1 -#define CFHSI_WAKE_DOWN_ACK 2 -#define CFHSI_AWAKE 3 -#define CFHSI_WAKELOCK_HELD 4 -#define CFHSI_SHUTDOWN 5 -#define CFHSI_FLUSH_FIFO 6 - -#ifndef CFHSI_INACTIVITY_TOUT -#define CFHSI_INACTIVITY_TOUT (1 * HZ) -#endif /* CFHSI_INACTIVITY_TOUT */ - -#ifndef CFHSI_WAKE_TOUT -#define CFHSI_WAKE_TOUT (3 * HZ) -#endif /* CFHSI_WAKE_TOUT */ - -#ifndef CFHSI_MAX_RX_RETRIES -#define CFHSI_MAX_RX_RETRIES (10 * HZ) -#endif - -/* Structure implemented by the CAIF HSI driver. */ -struct cfhsi_cb_ops { - void (*tx_done_cb) (struct cfhsi_cb_ops *drv); - void (*rx_done_cb) (struct cfhsi_cb_ops *drv); - void (*wake_up_cb) (struct cfhsi_cb_ops *drv); - void (*wake_down_cb) (struct cfhsi_cb_ops *drv); -}; - -/* Structure implemented by HSI device. */ -struct cfhsi_ops { - int (*cfhsi_up) (struct cfhsi_ops *dev); - int (*cfhsi_down) (struct cfhsi_ops *dev); - int (*cfhsi_tx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_rx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_wake_up) (struct cfhsi_ops *dev); - int (*cfhsi_wake_down) (struct cfhsi_ops *dev); - int (*cfhsi_get_peer_wake) (struct cfhsi_ops *dev, bool *status); - int (*cfhsi_fifo_occupancy) (struct cfhsi_ops *dev, size_t *occupancy); - int (*cfhsi_rx_cancel)(struct cfhsi_ops *dev); - struct cfhsi_cb_ops *cb_ops; -}; - -/* Structure holds status of received CAIF frames processing */ -struct cfhsi_rx_state { - int state; - int nfrms; - int pld_len; - int retries; - bool piggy_desc; -}; - -/* Priority mapping */ -enum { - CFHSI_PRIO_CTL = 0, - CFHSI_PRIO_VI, - CFHSI_PRIO_VO, - CFHSI_PRIO_BEBK, - CFHSI_PRIO_LAST, -}; - -struct cfhsi_config { - u32 inactivity_timeout; - u32 aggregation_timeout; - u32 head_align; - u32 tail_align; - u32 q_high_mark; - u32 q_low_mark; -}; - -/* Structure implemented by CAIF HSI drivers. */ -struct cfhsi { - struct caif_dev_common cfdev; - struct net_device *ndev; - struct platform_device *pdev; - struct sk_buff_head qhead[CFHSI_PRIO_LAST]; - struct cfhsi_cb_ops cb_ops; - struct cfhsi_ops *ops; - int tx_state; - struct cfhsi_rx_state rx_state; - struct cfhsi_config cfg; - int rx_len; - u8 *rx_ptr; - u8 *tx_buf; - u8 *rx_buf; - u8 *rx_flip_buf; - spinlock_t lock; - int flow_off_sent; - struct list_head list; - struct work_struct wake_up_work; - struct work_struct wake_down_work; - struct work_struct out_of_sync_work; - struct workqueue_struct *wq; - wait_queue_head_t wake_up_wait; - wait_queue_head_t wake_down_wait; - wait_queue_head_t flush_fifo_wait; - struct timer_list inactivity_timer; - struct timer_list rx_slowpath_timer; - - /* TX aggregation */ - int aggregation_len; - struct timer_list aggregation_timer; - - unsigned long bits; -}; -extern struct platform_driver cfhsi_driver; - -/** - * enum ifla_caif_hsi - CAIF HSI NetlinkRT parameters. - * @IFLA_CAIF_HSI_INACTIVITY_TOUT: Inactivity timeout before - * taking the HSI wakeline down, in milliseconds. - * When using RT Netlink to create, destroy or configure a CAIF HSI interface, - * enum ifla_caif_hsi is used to specify the configuration attributes. - */ -enum ifla_caif_hsi { - __IFLA_CAIF_HSI_UNSPEC, - __IFLA_CAIF_HSI_INACTIVITY_TOUT, - __IFLA_CAIF_HSI_AGGREGATION_TOUT, - __IFLA_CAIF_HSI_HEAD_ALIGN, - __IFLA_CAIF_HSI_TAIL_ALIGN, - __IFLA_CAIF_HSI_QHIGH_WATERMARK, - __IFLA_CAIF_HSI_QLOW_WATERMARK, - __IFLA_CAIF_HSI_MAX -}; - -struct cfhsi_ops *cfhsi_get_ops(void); - -#endif /* CAIF_HSI_H_ */ From 71158bb1f2d2da61385c58fc1114e1a1c19984ba Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 30 Jun 2021 13:42:13 +0200 Subject: [PATCH 0080/1469] tcp: consistently disable header prediction for mptcp The MPTCP receive path is hooked only into the TCP slow-path. The DSS presence allows plain MPTCP traffic to hit that consistently. Since commit e1ff9e82e2ea ("net: mptcp: improve fallback to TCP"), when an MPTCP socket falls back to TCP, it can hit the TCP receive fast-path, and delay or stop triggering the event notification. Address the issue explicitly disabling the header prediction for MPTCP sockets. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/200 Fixes: e1ff9e82e2ea ("net: mptcp: improve fallback to TCP") Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/net/tcp.h b/include/net/tcp.h index e668f1bf780d..17df9b047ee4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -686,6 +686,10 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { + /* mptcp hooks are only on the slow path */ + if (sk_is_mptcp((struct sock *)tp)) + return; + tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); From 18a419bad63b7f68a1979e28459782518e7b6bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Jun 2021 09:42:44 -0700 Subject: [PATCH 0081/1469] udp: annotate data races around unix_sk(sk)->gso_size Accesses to unix_sk(sk)->gso_size are lockless. Add READ_ONCE()/WRITE_ONCE() around them. BUG: KCSAN: data-race in udp_lib_setsockopt / udpv6_sendmsg write to 0xffff88812d78f47c of 2 bytes by task 10849 on cpu 1: udp_lib_setsockopt+0x3b3/0x710 net/ipv4/udp.c:2696 udpv6_setsockopt+0x63/0x90 net/ipv6/udp.c:1630 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3265 __sys_setsockopt+0x18f/0x200 net/socket.c:2104 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812d78f47c of 2 bytes by task 10852 on cpu 0: udpv6_sendmsg+0x161/0x16b0 net/ipv6/udp.c:1299 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2337 ___sys_sendmsg net/socket.c:2391 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2477 __do_sys_sendmmsg net/socket.c:2506 [inline] __se_sys_sendmmsg net/socket.c:2503 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2503 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x0005 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10852 Comm: syz-executor.0 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/udp.c | 6 +++--- net/ipv6/udp.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62682807b4b2..62cd4cd52e84 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1102,7 +1102,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); - ipc.gso_size = up->gso_size; + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); @@ -2695,7 +2695,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; - up->gso_size = val; + WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: @@ -2790,7 +2790,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_SEGMENT: - val = up->gso_size; + val = READ_ONCE(up->gso_size); break; case UDP_GRO: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 368972dbd919..0cc7ba531b34 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1296,7 +1296,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); - ipc6.gso_size = up->gso_size; + ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; From b6c8801038234a6d837dfc683d79676d4022ad79 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Jul 2021 14:02:20 +0200 Subject: [PATCH 0082/1469] ARM: dts: qcom-apq8060: Correct Ethernet node name and drop bogus irq property make dtbs_check: ethernet-ebi2@2,0: $nodename:0: 'ethernet-ebi2@2,0' does not match '^ethernet(@.*)?$' ethernet-ebi2@2,0: 'smsc,irq-active-low' does not match any of the regexes: 'pinctrl-[0-9]+' There is no "smsc,irq-active-low" property, as active low is the default. Signed-off-by: Geert Uytterhoeven Reviewed-by: Linus Walleij Signed-off-by: David S. Miller --- arch/arm/boot/dts/qcom-apq8060-dragonboard.dts | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts index dace8ffeb991..0a4ffd10c484 100644 --- a/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts +++ b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts @@ -581,7 +581,7 @@ * EBI2. This has a 25MHz chrystal next to it, so no * clocking is needed. */ - ethernet-ebi2@2,0 { + ethernet@2,0 { compatible = "smsc,lan9221", "smsc,lan9115"; reg = <2 0x0 0x100>; /* @@ -598,8 +598,6 @@ phy-mode = "mii"; reg-io-width = <2>; smsc,force-external-phy; - /* IRQ on edge falling = active low */ - smsc,irq-active-low; smsc,irq-push-pull; /* From 19373d0233d04ede649eee4269922e20dd133cf2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Jul 2021 14:02:21 +0200 Subject: [PATCH 0083/1469] dt-bindings: net: sms911x: Convert to json-schema Convert the Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller Device Tree binding documentation to json-schema. Document missing properties. Make "phy-mode" not required, as many DTS files do not have it, and the Linux drivers falls back to PHY_INTERFACE_MODE_NA. Correct nodename in example. Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- .../devicetree/bindings/net/gpmc-eth.txt | 2 +- .../devicetree/bindings/net/smsc,lan9115.yaml | 110 ++++++++++++++++++ .../devicetree/bindings/net/smsc911x.txt | 43 ------- 3 files changed, 111 insertions(+), 44 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/smsc,lan9115.yaml delete mode 100644 Documentation/devicetree/bindings/net/smsc911x.txt diff --git a/Documentation/devicetree/bindings/net/gpmc-eth.txt b/Documentation/devicetree/bindings/net/gpmc-eth.txt index f7da3d73ca1b..32821066a85b 100644 --- a/Documentation/devicetree/bindings/net/gpmc-eth.txt +++ b/Documentation/devicetree/bindings/net/gpmc-eth.txt @@ -13,7 +13,7 @@ Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt For the properties relevant to the ethernet controller connected to the GPMC refer to the binding documentation of the device. For example, the documentation -for the SMSC 911x is Documentation/devicetree/bindings/net/smsc911x.txt +for the SMSC 911x is Documentation/devicetree/bindings/net/smsc,lan9115.yaml Child nodes need to specify the GPMC bus address width using the "bank-width" property but is possible that an ethernet controller also has a property to diff --git a/Documentation/devicetree/bindings/net/smsc,lan9115.yaml b/Documentation/devicetree/bindings/net/smsc,lan9115.yaml new file mode 100644 index 000000000000..f86667cbcca8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/smsc,lan9115.yaml @@ -0,0 +1,110 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/smsc,lan9115.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller + +maintainers: + - Shawn Guo + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + oneOf: + - const: smsc,lan9115 + - items: + - enum: + - smsc,lan89218 + - smsc,lan9117 + - smsc,lan9118 + - smsc,lan9220 + - smsc,lan9221 + - const: smsc,lan9115 + + reg: + maxItems: 1 + + reg-shift: true + + reg-io-width: + enum: [ 2, 4 ] + default: 2 + + interrupts: + minItems: 1 + items: + - description: + LAN interrupt line + - description: + Optional PME (power management event) interrupt that is able to wake + up the host system with a 50ms pulse on network activity + + clocks: + maxItems: 1 + + phy-mode: true + + smsc,irq-active-high: + type: boolean + description: Indicates the IRQ polarity is active-high + + smsc,irq-push-pull: + type: boolean + description: Indicates the IRQ type is push-pull + + smsc,force-internal-phy: + type: boolean + description: Forces SMSC LAN controller to use internal PHY + + smsc,force-external-phy: + type: boolean + description: Forces SMSC LAN controller to use external PHY + + smsc,save-mac-address: + type: boolean + description: + Indicates that MAC address needs to be saved before resetting the + controller + + reset-gpios: + maxItems: 1 + description: + A GPIO line connected to the RESET (active low) signal of the device. + On many systems this is wired high so the device goes out of reset at + power-on, but if it is under program control, this optional GPIO can + wake up in response to it. + + vdd33a-supply: + description: 3.3V analog power supply + + vddvario-supply: + description: IO logic power supply + +required: + - compatible + - reg + - interrupts + +# There are lots of bus-specific properties ("qcom,*", "samsung,*", "fsl,*", +# "gpmc,*", ...) to be found, that actually depend on the compatible value of +# the parent node. +additionalProperties: true + +examples: + - | + #include + + ethernet@f4000000 { + compatible = "smsc,lan9220", "smsc,lan9115"; + reg = <0xf4000000 0x2000000>; + phy-mode = "mii"; + interrupt-parent = <&gpio1>; + interrupts = <31>, <32>; + reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; + reg-io-width = <4>; + smsc,irq-push-pull; + }; diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt deleted file mode 100644 index acfafc8e143c..000000000000 --- a/Documentation/devicetree/bindings/net/smsc911x.txt +++ /dev/null @@ -1,43 +0,0 @@ -* Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller - -Required properties: -- compatible : Should be "smsc,lan", "smsc,lan9115" -- reg : Address and length of the io space for SMSC LAN -- interrupts : one or two interrupt specifiers - - The first interrupt is the SMSC LAN interrupt line - - The second interrupt (if present) is the PME (power - management event) interrupt that is able to wake up the host - system with a 50ms pulse on network activity -- phy-mode : See ethernet.txt file in the same directory - -Optional properties: -- reg-shift : Specify the quantity to shift the register offsets by -- reg-io-width : Specify the size (in bytes) of the IO accesses that - should be performed on the device. Valid value for SMSC LAN is - 2 or 4. If it's omitted or invalid, the size would be 2. -- smsc,irq-active-high : Indicates the IRQ polarity is active-high -- smsc,irq-push-pull : Indicates the IRQ type is push-pull -- smsc,force-internal-phy : Forces SMSC LAN controller to use - internal PHY -- smsc,force-external-phy : Forces SMSC LAN controller to use - external PHY -- smsc,save-mac-address : Indicates that mac address needs to be saved - before resetting the controller -- reset-gpios : a GPIO line connected to the RESET (active low) signal - of the device. On many systems this is wired high so the device goes - out of reset at power-on, but if it is under program control, this - optional GPIO can wake up in response to it. -- vdd33a-supply, vddvario-supply : 3.3V analog and IO logic power supplies - -Examples: - -lan9220@f4000000 { - compatible = "smsc,lan9220", "smsc,lan9115"; - reg = <0xf4000000 0x2000000>; - phy-mode = "mii"; - interrupt-parent = <&gpio1>; - interrupts = <31>, <32>; - reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; - reg-io-width = <4>; - smsc,irq-push-pull; -}; From 6b28a86d6c0bb02119f386ec2f56efde909e9bcb Mon Sep 17 00:00:00 2001 From: Mohammad Athari Bin Ismail Date: Wed, 30 Jun 2021 17:59:35 +0800 Subject: [PATCH 0084/1469] net: stmmac: Terminate FPE workqueue in suspend Add stmmac_fpe_stop_wq() in stmmac_suspend() to terminate FPE workqueue during suspend. So, in suspend mode, there will be no FPE workqueue available. Without this fix, new additional FPE workqueue will be created in every suspend->resume cycle. Fixes: 5a5586112b92 ("net: stmmac: support FPE link partner hand-shaking procedure") Signed-off-by: Mohammad Athari Bin Ismail Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8d9d6ecf8c63..7b8404a21544 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7171,6 +7171,7 @@ int stmmac_suspend(struct device *dev) priv->plat->rx_queues_to_use, false); stmmac_fpe_handshake(priv, false); + stmmac_fpe_stop_wq(priv); } priv->speed = SPEED_UNKNOWN; From 2342ae10d1272d411a468a85a67647dd115b344f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:18:24 +0200 Subject: [PATCH 0085/1469] gve: Fix an error handling path in 'gve_probe()' If the 'register_netdev() call fails, we must release the resources allocated by the previous 'gve_init_priv()' call, as already done in the remove function. Add a new label and the missing 'gve_teardown_priv_resources()' in the error handling path. Fixes: 893ce44df565 ("gve: Add basic driver framework for Compute Engine Virtual NIC") Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 867e87af3432..44262c9f9ec2 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1565,7 +1565,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = register_netdev(dev); if (err) - goto abort_with_wq; + goto abort_with_gve_init; dev_info(&pdev->dev, "GVE version %s\n", gve_version_str); dev_info(&pdev->dev, "GVE queue format %d\n", (int)priv->queue_format); @@ -1573,6 +1573,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) queue_work(priv->gve_wq, &priv->service_task); return 0; +abort_with_gve_init: + gve_teardown_priv_resources(priv); + abort_with_wq: destroy_workqueue(priv->gve_wq); From 6dce38b4b7ffb39539b49feca2b3ce34dbaadf02 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:18:37 +0200 Subject: [PATCH 0086/1469] gve: Propagate error codes to caller If 'gve_probe()' fails, we should propagate the error code, instead of hard coding a -ENXIO value. Make sure that all error handling paths set a correct value for 'err'. Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 44262c9f9ec2..c03984b26db4 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1469,7 +1469,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = pci_enable_device(pdev); if (err) - return -ENXIO; + return err; err = pci_request_regions(pdev, "gvnic-cfg"); if (err) @@ -1512,6 +1512,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues); if (!dev) { dev_err(&pdev->dev, "could not allocate netdev\n"); + err = -ENOMEM; goto abort_with_db_bar; } SET_NETDEV_DEV(dev, &pdev->dev); @@ -1593,7 +1594,7 @@ abort_with_pci_region: abort_with_enabled: pci_disable_device(pdev); - return -ENXIO; + return err; } static void gve_remove(struct pci_dev *pdev) From 5140aaa4604ba96685dc04b4d2dde3384bbaecef Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Jul 2021 17:44:07 +0200 Subject: [PATCH 0087/1469] s390: iucv: Avoid field over-reading memcpy() In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields. Add a wrapping struct to serve as the memcpy() source so the compiler can perform appropriate bounds checking, avoiding this future warning: In function '__fortify_memcpy', inlined from 'iucv_message_pending' at net/iucv/iucv.c:1663:4: ./include/linux/fortify-string.h:246:4: error: call to '__read_overflow2_field' declared with attribute error: detected read beyond size of field (2nd parameter) Signed-off-by: Kees Cook Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/iucv/iucv.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 349c6ac3313f..e6795d5a546a 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1635,14 +1635,16 @@ struct iucv_message_pending { u8 iptype; u32 ipmsgid; u32 iptrgcls; - union { - u32 iprmmsg1_u32; - u8 iprmmsg1[4]; - } ln1msg1; - union { - u32 ipbfln1f; - u8 iprmmsg2[4]; - } ln1msg2; + struct { + union { + u32 iprmmsg1_u32; + u8 iprmmsg1[4]; + } ln1msg1; + union { + u32 ipbfln1f; + u8 iprmmsg2[4]; + } ln1msg2; + } rmmsg; u32 res1[3]; u32 ipbfln2f; u8 ippollfg; @@ -1660,10 +1662,10 @@ static void iucv_message_pending(struct iucv_irq_data *data) msg.id = imp->ipmsgid; msg.class = imp->iptrgcls; if (imp->ipflags1 & IUCV_IPRMDATA) { - memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8); + memcpy(msg.rmmsg, &imp->rmmsg, 8); msg.length = 8; } else - msg.length = imp->ln1msg2.ipbfln1f; + msg.length = imp->rmmsg.ln1msg2.ipbfln1f; msg.reply_size = imp->ipbfln2f; path->handler->message_pending(path, &msg); } From 37d220b58d52d6da88b928e11bffd83f88c6ac79 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 24 Jun 2021 12:36:41 +0200 Subject: [PATCH 0088/1469] selftest: netfilter: add test case for unreplied tcp connections TCP connections in UNREPLIED state (only SYN seen) can be kept alive indefinitely, as each SYN re-sets the timeout. This means that even if a peer has closed its socket the entry never times out. This also prevents re-evaluation of configured NAT rules. Add a test case that sets SYN timeout to 10 seconds, then check that the nat redirection added later eventually takes effect. This is based off a repro script from Antonio Ojea. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- .../netfilter/conntrack_tcp_unreplied.sh | 167 ++++++++++++++++++ 2 files changed, 168 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index cd6430b39982..8748199ac109 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh new file mode 100755 index 000000000000..e7d7bf13cff5 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh @@ -0,0 +1,167 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check that UNREPLIED tcp conntrack will eventually timeout. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +waittime=20 +sfx=$(mktemp -u "XXXXXXXX") +ns1="ns1-$sfx" +ns2="ns2-$sfx" + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + ip netns pids $ns1 | xargs kill 2>/dev/null + ip netns pids $ns2 | xargs kill 2>/dev/null + + ip netns del $ns1 + ip netns del $ns2 +} + +ipv4() { + echo -n 192.168.$1.2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns2 nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns2 has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns2 nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +# Create test namespaces +ip netns add $ns1 || exit 1 + +trap cleanup EXIT + +ip netns add $ns2 || exit 1 + +# Connect the namespace to the host using a veth pair +ip -net $ns1 link add name veth1 type veth peer name veth2 +ip -net $ns1 link set netns $ns2 dev veth2 + +ip -net $ns1 link set up dev lo +ip -net $ns2 link set up dev lo +ip -net $ns1 link set up dev veth1 +ip -net $ns2 link set up dev veth2 + +ip -net $ns2 addr add 10.11.11.2/24 dev veth2 +ip -net $ns2 route add default via 10.11.11.1 + +ip netns exec $ns2 sysctl -q net.ipv4.conf.veth2.forwarding=1 + +# add a rule inside NS so we enable conntrack +ip netns exec $ns1 iptables -A INPUT -m state --state established,related -j ACCEPT + +ip -net $ns1 addr add 10.11.11.1/24 dev veth1 +ip -net $ns1 route add 10.99.99.99 via 10.11.11.2 + +# Check connectivity works +ip netns exec $ns1 ping -q -c 2 10.11.11.2 >/dev/null || exit 1 + +ip netns exec $ns2 nc -l -p 8080 < /dev/null & + +# however, conntrack entries are there + +ip netns exec $ns2 nft -f - < $ns2 to the virtual ip" +ip netns exec $ns1 bash -c 'while true ; do + nc -p 60000 10.99.99.99 80 + sleep 1 + done' & + +sleep 1 + +ip netns exec $ns2 nft -f - </dev/null | wc -l) +if [ $count -eq 0 ]; then + echo "ERROR: $ns2 did not pick up tcp connection from peer" + exit 1 +fi + +echo "INFO: NAT redirect added in ns $ns2, waiting for $waittime seconds for nat to take effect" +for i in $(seq 1 $waittime); do + echo -n "." + + sleep 1 + + count=$(ip netns exec $ns2 conntrack -L -p tcp --reply-port-src 8080 2>/dev/null | wc -l) + if [ $count -gt 0 ]; then + echo + echo "PASS: redirection took effect after $i seconds" + break + fi + + m=$((i%20)) + if [ $m -eq 0 ]; then + echo " waited for $i seconds" + fi +done + +expect="packets 1 bytes 60" +check_counter "$ns2" "redir" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +if [ $ret -eq 0 ];then + echo "PASS: redirection counter has expected values" +else + echo "ERROR: no tcp connection was redirected" +fi + +exit $ret From e15d4cdf27cb0c1e977270270b2cea12e0955edd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 24 Jun 2021 12:36:42 +0200 Subject: [PATCH 0089/1469] netfilter: conntrack: do not renew entry stuck in tcp SYN_SENT state Consider: client -----> conntrack ---> Host client sends a SYN, but $Host is unreachable/silent. Client eventually gives up and the conntrack entry will time out. However, if the client is restarted with same addr/port pair, it may prevent the conntrack entry from timing out. This is noticeable when the existing conntrack entry has no NAT transformation or an outdated one and port reuse happens either on client or due to a NAT middlebox. This change prevents refresh of the timeout for SYN retransmits, so entry is going away after nf_conntrack_tcp_timeout_syn_sent seconds (default: 60). Entry will be re-created on next connection attempt, but then nat rules will be evaluated again. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index f7e8baf59b51..eb4de92077a8 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1134,6 +1134,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ From 4ca041f919f13783b0b03894783deee00dbca19a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 24 Jun 2021 20:57:18 +0100 Subject: [PATCH 0090/1469] netfilter: nf_tables: Fix dereference of null pointer flow In the case where chain->flags & NFT_CHAIN_HW_OFFLOAD is false then nft_flow_rule_create is not called and flow is NULL. The subsequent error handling execution via label err_destroy_flow_rule will lead to a null pointer dereference on flow when calling nft_flow_rule_destroy. Since the error path to err_destroy_flow_rule has to cater for null and non-null flows, only call nft_flow_rule_destroy if flow is non-null to fix this issue. Addresses-Coverity: ("Explicity null dereference") Fixes: 3c5e44622011 ("netfilter: nf_tables: memleak in hw offload abort path") Signed-off-by: Colin Ian King Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 390d4466567f..de182d1f7c4e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3446,7 +3446,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: - nft_flow_rule_destroy(flow); + if (flow) + nft_flow_rule_destroy(flow); err_release_rule: nf_tables_rule_release(&ctx, rule); err_release_expr: From a23f89a9990684a0ca0cac4a2857c15d338ebe2d Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 1 Jul 2021 08:02:24 +0300 Subject: [PATCH 0091/1469] netfilter: conntrack: nf_ct_gre_keymap_flush() removal nf_ct_gre_keymap_flush() is useless. It is called from nf_conntrack_cleanup_net_list() only and tries to remove nf_ct_gre_keymap entries from pernet gre keymap list. Though: a) at this point the list should already be empty, all its entries were deleted during the conntracks cleanup, because nf_conntrack_cleanup_net_list() executes nf_ct_iterate_cleanup(kill_all) before nf_conntrack_proto_pernet_fini(): nf_conntrack_cleanup_net_list +- nf_ct_iterate_cleanup | nf_ct_put | nf_conntrack_put | nf_conntrack_destroy | destroy_conntrack | destroy_gre_conntrack | nf_ct_gre_keymap_destroy `- nf_conntrack_proto_pernet_fini nf_ct_gre_keymap_flush b) Let's say we find that the keymap list is not empty. This means netns still has a conntrack associated with gre, in which case we should not free its memory, because this will lead to a double free and related crashes. However I doubt it could have gone unnoticed for years, obviously this does not happen in real life. So I think we can remove both nf_ct_gre_keymap_flush() and nf_conntrack_proto_pernet_fini(). Signed-off-by: Vasily Averin Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 1 - net/netfilter/nf_conntrack_core.c | 1 - net/netfilter/nf_conntrack_proto.c | 7 ------- net/netfilter/nf_conntrack_proto_gre.c | 13 ------------- 4 files changed, 22 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 09f2efea0b97..13807ea94cd2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -30,7 +30,6 @@ void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); void nf_conntrack_proto_pernet_init(struct net *net); -void nf_conntrack_proto_pernet_fini(struct net *net); int nf_conntrack_proto_init(void); void nf_conntrack_proto_fini(void); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 96ba19fc8155..085a11f1eb43 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2457,7 +2457,6 @@ i_see_dead_people: } list_for_each_entry(net, net_exit_list, exit_list) { - nf_conntrack_proto_pernet_fini(net); nf_conntrack_ecache_pernet_fini(net); nf_conntrack_expect_pernet_fini(net); free_percpu(net->ct.stat); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 55647409a9be..8f7a9837349c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -697,13 +697,6 @@ void nf_conntrack_proto_pernet_init(struct net *net) #endif } -void nf_conntrack_proto_pernet_fini(struct net *net) -{ -#ifdef CONFIG_NF_CT_PROTO_GRE - nf_ct_gre_keymap_flush(net); -#endif -} - module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index db11e403d818..728eeb0aea87 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -55,19 +55,6 @@ static inline struct nf_gre_net *gre_pernet(struct net *net) return &net->ct.nf_ct_proto.gre; } -void nf_ct_gre_keymap_flush(struct net *net) -{ - struct nf_gre_net *net_gre = gre_pernet(net); - struct nf_ct_gre_keymap *km, *tmp; - - spin_lock_bh(&keymap_lock); - list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) { - list_del_rcu(&km->list); - kfree_rcu(km, rcu); - } - spin_unlock_bh(&keymap_lock); -} - static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, const struct nf_conntrack_tuple *t) { From c23a9fd209bc6f8c1fa6ee303fdf037d784a1627 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 1 Jul 2021 08:02:49 +0300 Subject: [PATCH 0092/1469] netfilter: ctnetlink: suspicious RCU usage in ctnetlink_dump_helpinfo Two patches listed below removed ctnetlink_dump_helpinfo call from under rcu_read_lock. Now its rcu_dereference generates following warning: ============================= WARNING: suspicious RCU usage 5.13.0+ #5 Not tainted ----------------------------- net/netfilter/nf_conntrack_netlink.c:221 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 stack backtrace: CPU: 1 PID: 2251 Comm: conntrack Not tainted 5.13.0+ #5 Call Trace: dump_stack+0x7f/0xa1 ctnetlink_dump_helpinfo+0x134/0x150 [nf_conntrack_netlink] ctnetlink_fill_info+0x2c2/0x390 [nf_conntrack_netlink] ctnetlink_dump_table+0x13f/0x370 [nf_conntrack_netlink] netlink_dump+0x10c/0x370 __netlink_dump_start+0x1a7/0x260 ctnetlink_get_conntrack+0x1e5/0x250 [nf_conntrack_netlink] nfnetlink_rcv_msg+0x613/0x993 [nfnetlink] netlink_rcv_skb+0x50/0x100 nfnetlink_rcv+0x55/0x120 [nfnetlink] netlink_unicast+0x181/0x260 netlink_sendmsg+0x23f/0x460 sock_sendmsg+0x5b/0x60 __sys_sendto+0xf1/0x160 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x36/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: 49ca022bccc5 ("netfilter: ctnetlink: don't dump ct extensions of unconfirmed conntracks") Fixes: 0b35f6031a00 ("netfilter: Remove duplicated rcu_read_lock.") Signed-off-by: Vasily Averin Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4e1a9dba7077..e81af33b233b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -218,6 +218,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, if (!help) return 0; + rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; @@ -233,9 +234,11 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, nla_nest_end(skb, nest_helper); out: + rcu_read_unlock(); return 0; nla_put_failure: + rcu_read_unlock(); return -1; } From eaf228263921cd15962654b539d916380a0f076e Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 2 Jul 2021 09:20:22 +0200 Subject: [PATCH 0093/1469] Revert "xfrm: policy: Read seqcount outside of rcu-read side in xfrm_policy_lookup_bytype" This reverts commit d7b0408934c749f546b01f2b33d07421a49b6f3e. This commit tried to fix a locking bug introduced by commit 77cc278f7b20 ("xfrm: policy: Use sequence counters with associated lock"). As it turned out, this patch did not really fix the bug. A proper fix for this bug is applied on top of this revert. Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9d0df2a2ab1..ce500f847b99 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2092,15 +2092,12 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - retry: - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); rcu_read_lock(); - - chain = policy_hash_direct(net, daddr, saddr, family, dir); - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); - goto retry; - } + retry: + do { + sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + chain = policy_hash_direct(net, daddr, saddr, family, dir); + } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2131,15 +2128,11 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) goto retry; - } - if (ret && !xfrm_pol_hold_rcu(ret)) { - rcu_read_unlock(); + if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; - } fail: rcu_read_unlock(); From 2580d3f40022642452dd8422bfb8c22e54cf84bb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 28 Jun 2021 15:34:28 +0200 Subject: [PATCH 0094/1469] xfrm: Fix RCU vs hash_resize_mutex lock inversion xfrm_bydst_resize() calls synchronize_rcu() while holding hash_resize_mutex. But then on PREEMPT_RT configurations, xfrm_policy_lookup_bytype() may acquire that mutex while running in an RCU read side critical section. This results in a deadlock. In fact the scope of hash_resize_mutex is way beyond the purpose of xfrm_policy_lookup_bytype() to just fetch a coherent and stable policy for a given destination/direction, along with other details. The lower level net->xfrm.xfrm_policy_lock, which among other things protects per destination/direction references to policy entries, is enough to serialize and benefit from priority inheritance against the write side. As a bonus, it makes it officially a per network namespace synchronization business where a policy table resize on namespace A shouldn't block a policy lookup on namespace B. Fixes: 77cc278f7b20 (xfrm: policy: Use sequence counters with associated lock) Cc: stable@vger.kernel.org Cc: Ahmed S. Darwish Cc: Peter Zijlstra (Intel) Cc: Varad Gautam Cc: Steffen Klassert Cc: Herbert Xu Cc: David S. Miller Signed-off-by: Frederic Weisbecker Signed-off-by: Steffen Klassert --- include/net/netns/xfrm.h | 1 + net/xfrm/xfrm_policy.c | 17 ++++++++--------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index e816b6a3ef2b..9b376b87bd54 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -74,6 +74,7 @@ struct netns_xfrm { #endif spinlock_t xfrm_state_lock; seqcount_spinlock_t xfrm_state_hash_generation; + seqcount_spinlock_t xfrm_policy_hash_generation; spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ce500f847b99..46a6d15b66d6 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -155,7 +155,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; -static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; @@ -585,7 +584,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); @@ -596,7 +595,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); @@ -1245,7 +1244,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1354,7 +1353,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2095,9 +2094,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, rcu_read_lock(); retry: do { - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); - } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2128,7 +2127,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) @@ -4084,6 +4083,7 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); + seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); rv = xfrm_statistics_init(net); @@ -4128,7 +4128,6 @@ void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); - seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP From 19d67694745c5c9ed085d0d8332fa02d835a07d0 Mon Sep 17 00:00:00 2001 From: Rodrigo Campos Date: Fri, 2 Jul 2021 17:19:27 +0200 Subject: [PATCH 0095/1469] Documentation: seccomp: Fix typo in user notification The close on exec flag is O_CLOEXEC, not O_EXEC. This patch just fixes the typo. Suggested-by: Christian Brauner Signed-off-by: Rodrigo Campos Acked-by: Christian Brauner Signed-off-by: Kees Cook Fixes: 0ae71c7720e3 ("seccomp: Support atomic "addfd + send reply"") Link: https://lore.kernel.org/r/20210702151927.263402-1-rodrigo@kinvolk.io --- Documentation/userspace-api/seccomp_filter.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index d61219889e49..539e9d4a4860 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -263,7 +263,7 @@ Userspace can also add file descriptors to the notifying process via ``ioctl(SECCOMP_IOCTL_NOTIF_ADDFD)``. The ``id`` member of ``struct seccomp_notif_addfd`` should be the same ``id`` as in ``struct seccomp_notif``. The ``newfd_flags`` flag may be used to set flags -like O_EXEC on the file descriptor in the notifying process. If the supervisor +like O_CLOEXEC on the file descriptor in the notifying process. If the supervisor wants to inject the file descriptor with a specific number, the ``SECCOMP_ADDFD_FLAG_SETFD`` flag can be used, and set the ``newfd`` member to the specific number to use. If that file descriptor is already open in the From 633fa666401c42f9a106a509b7702c58c84524e2 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Jul 2021 15:16:53 +0200 Subject: [PATCH 0096/1469] net/sched: sch_taprio: fix typo in comment I have checked that the IEEE standard 802.1Q-2018 section 8.6.9.4.5 is called AdminGateStates. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 66fe2b82af9a..07b30d0601d7 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -564,7 +564,7 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) /* if there's no entry, it means that the schedule didn't * start yet, so force all gates to be open, this is in * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 - * "AdminGateSates" + * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; From bde3c8ffdd4153a3e9f0b0d51d972b30113b35ac Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:41:19 +0200 Subject: [PATCH 0097/1469] gve: Simplify code and axe the use of a deprecated API The wrappers in include/linux/pci-dma-compat.h should go away. Replace 'pci_set_dma_mask/pci_set_consistent_dma_mask' by an equivalent and less verbose 'dma_set_mask_and_coherent()' call. Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index c03984b26db4..099a2bc5ae67 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1477,19 +1477,12 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err); goto abort_with_pci_region; } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_err(&pdev->dev, - "Failed to set consistent dma mask: err=%d\n", err); - goto abort_with_pci_region; - } - reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0); if (!reg_bar) { dev_err(&pdev->dev, "Failed to map pci bar!\n"); From 40fc3054b45820c28ea3c65e2c86d041dc244a8a Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Fri, 2 Jul 2021 02:47:00 +0300 Subject: [PATCH 0098/1469] net: ipv6: fix return value of ip6_skb_dst_mtu Commit 628a5c561890 ("[INET]: Add IP(V6)_PMTUDISC_RPOBE") introduced ip6_skb_dst_mtu with return value of signed int which is inconsistent with actually returned values. Also 2 users of this function actually assign its value to unsigned int variable and only __xfrm6_output assigns result of this function to signed variable but actually uses as unsigned in further comparisons and calls. Change this function to return unsigned int value. Fixes: 628a5c561890 ("[INET]: Add IP(V6)_PMTUDISC_RPOBE") Reviewed-by: David Ahern Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 +- net/ipv6/xfrm6_output.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f14149df5a65..625a38ccb5d9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -263,7 +263,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); -static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb) { int mtu; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 57fa27c1cdf9..d0d280077721 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -49,7 +49,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu; + unsigned int mtu; bool toobig; #ifdef CONFIG_NETFILTER From 1bfa4d0cb5adf954e0f4870a3ecb7cb19506320c Mon Sep 17 00:00:00 2001 From: Bailey Forrest Date: Thu, 1 Jul 2021 20:13:36 -0700 Subject: [PATCH 0099/1469] gve: DQO: Remove incorrect prefetch The prefetch is incorrectly using the dma address instead of the virtual address. It's supposed to be: prefetch((char *)buf_state->page_info.page_address + buf_state->page_info.page_offset) However, after correcting this mistake, there is no evidence of performance improvement. Fixes: 9b8dd5e5ea48 ("gve: DQO: Add RX path") Signed-off-by: Bailey Forrest Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 77bb8227f89b..8500621b2cd4 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -566,13 +566,6 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, return 0; } - /* Prefetch the payload header. */ - prefetch((char *)buf_state->addr + buf_state->page_info.page_offset); -#if L1_CACHE_BYTES < 128 - prefetch((char *)buf_state->addr + buf_state->page_info.page_offset + - L1_CACHE_BYTES); -#endif - if (eop && buf_len <= priv->rx_copybreak) { rx->skb_head = gve_rx_copy(priv->dev, napi, &buf_state->page_info, buf_len, 0); From 8955b90c3cdad199137809aac8ccbbb585355913 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 2 Jul 2021 11:34:31 +0800 Subject: [PATCH 0100/1469] net/sched: act_ct: fix err check for nf_conntrack_confirm The confirm operation should be checked. If there are any failed, the packet should be dropped like in ovs and netfilter. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: wenxu Signed-off-by: David S. Miller --- net/sched/act_ct.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a656baa321fe..a62f404d0e16 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1026,7 +1026,8 @@ do_nat: /* This will take care of sending queued events * even if the connection is already confirmed. */ - nf_conntrack_confirm(skb); + if (nf_conntrack_confirm(skb) != NF_ACCEPT) + goto drop; } if (!skip_add) From 561022acb1ce62e50f7a8258687a21b84282a4cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jul 2021 13:09:03 -0700 Subject: [PATCH 0101/1469] tcp: annotate data races around tp->mtu_info While tp->mtu_info is read while socket is owned, the write sides happen from err handlers (tcp_v[46]_mtu_reduced) which only own the socket spinlock. Fixes: 563d34d05786 ("tcp: dont drop MTU reduction indications") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv6/tcp_ipv6.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e66ad6bfe808..b9dc2d6197be 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -342,7 +342,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - mtu = tcp_sk(sk)->mtu_info; + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -546,7 +546,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (sk->sk_state == TCP_LISTEN) goto out; - tp->mtu_info = info; + WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 578ab6305c3f..593c32fe57ed 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -352,7 +352,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + dst = inet6_csk_update_pmtu(sk, READ_ONCE(tcp_sk(sk)->mtu_info)); if (!dst) return; @@ -443,7 +443,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - tp->mtu_info = ntohl(info); + WRITE_ONCE(tp->mtu_info, ntohl(info)); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, From 81b4a0cc7565b08cadd0d02bae3434f127d1d72a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jul 2021 07:41:01 -0700 Subject: [PATCH 0102/1469] sock: fix error in sock_setsockopt() Some tests are failing, John bisected the issue to a recent commit. sock_set_timestamp() parameters should be : 1) sk 2) optname 3) valbool Fixes: 371087aa476a ("sock: expose so_timestamp options for mptcp") Signed-off-by: Eric Dumazet Bisected-by: John Sperbeck Cc: Paolo Abeni Cc: Florian Westphal Cc: Mat Martineau Reviewed-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index cad107112204..1c4b0468bc2c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1116,7 +1116,7 @@ set_sndbuf: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, valbool, optname); + sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: From a019abd8022061b917da767cd1a66ed823724eab Mon Sep 17 00:00:00 2001 From: Wolfgang Bumiller Date: Fri, 2 Jul 2021 14:07:36 +0200 Subject: [PATCH 0103/1469] net: bridge: sync fdb to new unicast-filtering ports Since commit 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") bridges with `vlan_filtering 1` and only 1 auto-port don't set IFF_PROMISC for unicast-filtering-capable ports. Normally on port changes `br_manage_promisc` is called to update the promisc flags and unicast filters if necessary, but it cannot distinguish between *new* ports and ones losing their promisc flag, and new ports end up not receiving the MAC address list. Fix this by calling `br_fdb_sync_static` in `br_add_if` after the port promisc flags are updated and the unicast filter was supposed to have been filled. Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Signed-off-by: Wolfgang Bumiller Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_if.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f7d2f472ae24..6e4a32354a13 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; - bool changed_addr; + bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices. */ if ((dev->flags & IFF_LOOPBACK) || @@ -652,6 +652,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); + if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { + /* When updating the port count we also update all ports' + * promiscuous mode. + * A port leaving promiscuous mode normally gets the bridge's + * fdb synced to the unicast filter (if supported), however, + * `br_port_clear_promisc` does not distinguish between + * non-promiscuous ports and *new* ports, so we need to + * sync explicitly here. + */ + fdb_synced = br_fdb_sync_static(br, p) == 0; + if (!fdb_synced) + netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); + } netdev_update_features(br->dev); @@ -701,6 +714,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; err7: + if (fdb_synced) + br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); From 77ac5e40c44eb78333fbc38482d61fc2af7dda0a Mon Sep 17 00:00:00 2001 From: Louis Peens Date: Fri, 2 Jul 2021 11:21:38 +0200 Subject: [PATCH 0104/1469] net/sched: act_ct: remove and free nf_table callbacks When cleaning up the nf_table in tcf_ct_flow_table_cleanup_work there is no guarantee that the callback list, added to by nf_flow_table_offload_add_cb, is empty. This means that it is possible that the flow_block_cb memory allocated will be lost. Fix this by iterating the list and freeing the flow_block_cb entries before freeing the nf_table entry (via freeing ct_ft). Fixes: 978703f42549 ("netfilter: flowtable: Add API for registering to flow table events") Signed-off-by: Louis Peens Signed-off-by: Yinjun Zhang Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/sched/act_ct.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a62f404d0e16..1b4b3514c94f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -322,11 +322,22 @@ err_alloc: static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { + struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; + struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); + + /* Remove any remaining callbacks before cleanup */ + block = &ct_ft->nf_ft.flow_block; + down_write(&ct_ft->nf_ft.flow_block_lock); + list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } + up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); From 7cc93d888df764a13f196e3d4aef38869f7dd217 Mon Sep 17 00:00:00 2001 From: Louis Peens Date: Fri, 2 Jul 2021 11:21:39 +0200 Subject: [PATCH 0105/1469] nfp: flower-ct: remove callback delete deadlock The current location of the callback delete can lead to a race condition where deleting the callback requires a write_lock on the nf_table, but at the same time another thread from netfilter could have taken a read lock on the table before trying to offload. Since the driver is taking a rtnl_lock this can lead into a deadlock situation, where the netfilter offload will wait for the cls_flower rtnl_lock to be released, but this cannot happen since this is waiting for the nf_table read_lock to be released before it can delete the callback. Solve this by completely removing the nf_flow_table_offload_del_cb call, as this will now be cleaned up by act_ct itself when cleaning up the specific nf_table. Fixes: 62268e78145f ("nfp: flower-ct: add nft callback stubs") Signed-off-by: Louis Peens Signed-off-by: Yinjun Zhang Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/conntrack.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 273d529d43c2..128020b1573e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1141,20 +1141,7 @@ int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent) nfp_fl_ct_clean_flow_entry(ct_entry); kfree(ct_map_ent); - /* If this is the last pre_ct_rule it means that it is - * very likely that the nft table will be cleaned up next, - * as this happens on the removal of the last act_ct flow. - * However we cannot deregister the callback on the removal - * of the last nft flow as this runs into a deadlock situation. - * So deregister the callback on removal of the last pre_ct flow - * and remove any remaining nft flow entries. We also cannot - * save this state and delete the callback later since the - * nft table would already have been freed at that time. - */ if (!zt->pre_ct_count) { - nf_flow_table_offload_del_cb(zt->nft, - nfp_fl_ct_handle_nft_flow, - zt); zt->nft = NULL; nfp_fl_ct_clean_nft_entries(zt); } From b22580233d473dbf7bbfa4f6549c09e2c80e9e64 Mon Sep 17 00:00:00 2001 From: Ronak Doshi Date: Thu, 1 Jul 2021 23:44:27 -0700 Subject: [PATCH 0106/1469] vmxnet3: fix cksum offload issues for tunnels with non-default udp ports Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") added support for encapsulation offload. However, the inner offload capability is to be restricted to UDP tunnels with default Vxlan and Geneve ports. This patch fixes the issue for tunnels with non-default ports using features check capability and filtering appropriate features for such tunnels. Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") Signed-off-by: Ronak Doshi Acked-by: Guolin Yang Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_ethtool.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index c0bd9cbc43b1..1b483cf2b1ca 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -26,6 +26,10 @@ #include "vmxnet3_int.h" +#include +#include + +#define VXLAN_UDP_PORT 8472 struct vmxnet3_stat_desc { char desc[ETH_GSTRING_LEN]; @@ -262,6 +266,8 @@ netdev_features_t vmxnet3_features_check(struct sk_buff *skb, if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { u8 l4_proto = 0; + u16 port; + struct udphdr *udph; switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): @@ -274,8 +280,20 @@ netdev_features_t vmxnet3_features_check(struct sk_buff *skb, return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } - if (l4_proto != IPPROTO_UDP) + switch (l4_proto) { + case IPPROTO_UDP: + udph = udp_hdr(skb); + port = be16_to_cpu(udph->dest); + /* Check if offloaded port is supported */ + if (port != GENEVE_UDP_PORT && + port != IANA_VXLAN_UDP_PORT && + port != VXLAN_UDP_PORT) { + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + break; + default: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } } return features; } From b43c8909be52f2baca8884f967b418a88424494a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 3 Jul 2021 00:38:43 +0200 Subject: [PATCH 0107/1469] udp: properly flush normal packet at GRO time If an UDP packet enters the GRO engine but is not eligible for aggregation and is not targeting an UDP tunnel, udp_gro_receive() will not set the flush bit, and packet could delayed till the next napi flush. Fix the issue ensuring non GROed packets traverse skb_gro_flush_final(). Reported-and-tested-by: Matthias Treydte Fixes: 18f25dc39990 ("udp: skip L4 aggregation for UDP tunnel packets") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/udp_offload.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 54e06b88af69..9dde1e5fb449 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -525,8 +525,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) - pp = call_gro_receive(udp_gro_receive_segment, head, skb); - return pp; + return call_gro_receive(udp_gro_receive_segment, head, skb); + + /* no GRO, be sure flush the current packet */ + goto out; } if (NAPI_GRO_CB(skb)->encap_mark || From 6ff63a150b5556012589ae59efac1b5eeb7d32c3 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 3 Jul 2021 21:17:27 +0200 Subject: [PATCH 0108/1469] net: marvell: always set skb_shared_info in mvneta_swbm_add_rx_fragment Always set skb_shared_info data structure in mvneta_swbm_add_rx_fragment routine even if the fragment contains only the ethernet FCS. Fixes: 039fbc47f9f1 ("net: mvneta: alloc skb_shared_info on the mvneta_rx_swbm stack") Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 361bc4fbe20b..76a7777c746d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2299,19 +2299,19 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, skb_frag_off_set(frag, pp->rx_offset_correction); skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); - - /* last fragment */ - if (len == *size) { - struct skb_shared_info *sinfo; - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = xdp_sinfo->nr_frags; - memcpy(sinfo->frags, xdp_sinfo->frags, - sinfo->nr_frags * sizeof(skb_frag_t)); - } } else { page_pool_put_full_page(rxq->page_pool, page, true); } + + /* last fragment */ + if (len == *size) { + struct skb_shared_info *sinfo; + + sinfo = xdp_get_shared_info_from_buff(xdp); + sinfo->nr_frags = xdp_sinfo->nr_frags; + memcpy(sinfo->frags, xdp_sinfo->frags, + sinfo->nr_frags * sizeof(skb_frag_t)); + } *size -= len; } From 55eac20617ca84129273ab248f4d7bfe456967de Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 5 Jul 2021 16:53:06 +0800 Subject: [PATCH 0109/1469] ptp: fix NULL pointer dereference in ptp_clock_register Fix NULL pointer dereference in ptp_clock_register. The argument "parent" of ptp_clock_register may be NULL pointer. Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion") Reported-by: kernel test robot Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index f012fa581cf4..ce6d9fc85607 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -236,7 +236,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } /* PTP virtual clock is being registered under physical clock */ - if (parent->class && parent->class->name && + if (parent && parent->class && parent->class->name && strcmp(parent->class->name, "ptp") == 0) ptp->is_virtual_clock = true; From f6a175cfcc8df578adfdf06b05c82b3b8c8b5cfd Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 5 Jul 2021 17:46:17 +0800 Subject: [PATCH 0110/1469] ptp: fix format string mismatch in ptp_sysfs.c Fix format string mismatch in ptp_sysfs.c. Use %u for unsigned int. Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion") Reported-by: kernel test robot Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 6a36590ca77a..b3d96b747292 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -179,7 +179,7 @@ static ssize_t n_vclocks_show(struct device *dev, if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) return -ERESTARTSYS; - size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->n_vclocks); + size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->n_vclocks); mutex_unlock(&ptp->n_vclocks_mux); @@ -252,7 +252,7 @@ static ssize_t max_vclocks_show(struct device *dev, struct ptp_clock *ptp = dev_get_drvdata(dev); ssize_t size; - size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->max_vclocks); + size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->max_vclocks); return size; } From 81c52c42afd92b741289208c65e5063b9e23ffb4 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:53 +0800 Subject: [PATCH 0111/1469] net: stmmac: separate the tas basetime calculation function Separate the TAS basetime calculation function so that it can be called by other functions. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 3 ++ .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 38 ++++++++++++------- 2 files changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index e735134e8487..fcdb1d20389b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -349,6 +349,9 @@ void stmmac_enable_rx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_enable_tx_queue(struct stmmac_priv *priv, u32 queue); int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags); +struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, + ktime_t current_time, + u64 cycle_time); #if IS_ENABLED(CONFIG_STMMAC_SELFTESTS) void stmmac_selftest_run(struct net_device *dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 92dab609d4f8..596626c71189 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -711,6 +711,29 @@ static int tc_setup_cls(struct stmmac_priv *priv, return ret; } +struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, + ktime_t current_time, + u64 cycle_time) +{ + struct timespec64 time; + + if (ktime_after(old_base_time, current_time)) { + time = ktime_to_timespec64(old_base_time); + } else { + s64 n; + ktime_t base_time; + + n = div64_s64(ktime_sub_ns(current_time, old_base_time), + cycle_time); + base_time = ktime_add_ns(old_base_time, + (n + 1) * cycle_time); + + time = ktime_to_timespec64(base_time); + } + + return time; +} + static int tc_setup_taprio(struct stmmac_priv *priv, struct tc_taprio_qopt_offload *qopt) { @@ -814,19 +837,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv, /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); - if (ktime_after(qopt->base_time, current_time_ns)) { - time = ktime_to_timespec64(qopt->base_time); - } else { - ktime_t base_time; - s64 n; - - n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time), - qopt->cycle_time); - base_time = ktime_add_ns(qopt->base_time, - (n + 1) * qopt->cycle_time); - - time = ktime_to_timespec64(base_time); - } + time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns, + qopt->cycle_time); priv->plat->est->btr[0] = (u32)time.tv_nsec; priv->plat->est->btr[1] = (u32)time.tv_sec; From b2aae654a4794ef898ad33a179f341eb610f6b85 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:54 +0800 Subject: [PATCH 0112/1469] net: stmmac: add mutex lock to protect est parameters Add a mutex lock to protect est structure parameters so that the EST parameters can be updated by other threads. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 12 +++++++++++- include/linux/stmmac.h | 1 + 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 596626c71189..2e3cdf540168 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -796,14 +796,18 @@ static int tc_setup_taprio(struct stmmac_priv *priv, GFP_KERNEL); if (!plat->est) return -ENOMEM; + + mutex_init(&priv->plat->est->lock); } else { memset(plat->est, 0, sizeof(*plat->est)); } size = qopt->num_entries; + mutex_lock(&priv->plat->est->lock); priv->plat->est->gcl_size = size; priv->plat->est->enable = qopt->enable; + mutex_unlock(&priv->plat->est->lock); for (i = 0; i < size; i++) { s64 delta_ns = qopt->entries[i].interval; @@ -834,6 +838,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->gcl[i] = delta_ns | (gates << wid); } + mutex_lock(&priv->plat->est->lock); /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); @@ -847,8 +852,10 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC); priv->plat->est->ctr[1] = (u32)ctr; - if (fpe && !priv->dma_cap.fpesel) + if (fpe && !priv->dma_cap.fpesel) { + mutex_unlock(&priv->plat->est->lock); return -EOPNOTSUPP; + } /* Actual FPE register configuration will be done after FPE handshake * is success. @@ -857,6 +864,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); if (ret) { netdev_err(priv->dev, "failed to configure EST\n"); goto disable; @@ -872,9 +880,11 @@ static int tc_setup_taprio(struct stmmac_priv *priv, return 0; disable: + mutex_lock(&priv->plat->est->lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); priv->plat->fpe_cfg->enable = false; stmmac_fpe_configure(priv, priv->ioaddr, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d5ae621d66ba..09157b8a5810 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,6 +115,7 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { + struct mutex lock; int enable; u32 btr_offset[2]; u32 btr[2]; From e9e3720002f61cd637a49ecafae77cac230eefae Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:55 +0800 Subject: [PATCH 0113/1469] net: stmmac: ptp: update tas basetime after ptp adjust After adjusting the ptp time, the Qbv base time may be the past time of the new current time. dwmac5 hardware limited the base time cannot be set as past time. This patch add a btr_reserve to store the base time get from qopt, then calculate the base time and reset the Qbv configuration after ptp time adjust. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_ptp.c | 41 ++++++++++++++++++- .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 6 ++- include/linux/stmmac.h | 1 + 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 4e86cdf2bc9f..580cc035536b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -62,7 +62,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) u32 sec, nsec; u32 quotient, reminder; int neg_adj = 0; - bool xmac; + bool xmac, est_rst = false; + int ret; xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; @@ -75,10 +76,48 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) sec = quotient; nsec = reminder; + /* If EST is enabled, disabled it before adjust ptp time. */ + if (priv->plat->est && priv->plat->est->enable) { + est_rst = true; + mutex_lock(&priv->plat->est->lock); + priv->plat->est->enable = false; + stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, + priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); + } + spin_lock_irqsave(&priv->ptp_lock, flags); stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac); spin_unlock_irqrestore(&priv->ptp_lock, flags); + /* Caculate new basetime and re-configured EST after PTP time adjust. */ + if (est_rst) { + struct timespec64 current_time, time; + ktime_t current_time_ns, basetime; + u64 cycle_time; + + mutex_lock(&priv->plat->est->lock); + priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); + current_time_ns = timespec64_to_ktime(current_time); + time.tv_nsec = priv->plat->est->btr_reserve[0]; + time.tv_sec = priv->plat->est->btr_reserve[1]; + basetime = timespec64_to_ktime(time); + cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC + + priv->plat->est->ctr[0]; + time = stmmac_calc_tas_basetime(basetime, + current_time_ns, + cycle_time); + + priv->plat->est->btr[0] = (u32)time.tv_nsec; + priv->plat->est->btr[1] = (u32)time.tv_sec; + priv->plat->est->enable = true; + ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, + priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); + if (ret) + netdev_err(priv->dev, "failed to configure EST\n"); + } + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 2e3cdf540168..4f3b6437b114 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -739,7 +739,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, { u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep; struct plat_stmmacenet_data *plat = priv->plat; - struct timespec64 time, current_time; + struct timespec64 time, current_time, qopt_time; ktime_t current_time_ns; bool fpe = false; int i, ret = 0; @@ -848,6 +848,10 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->btr[0] = (u32)time.tv_nsec; priv->plat->est->btr[1] = (u32)time.tv_sec; + qopt_time = ktime_to_timespec64(qopt->base_time); + priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec; + priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec; + ctr = qopt->cycle_time; priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC); priv->plat->est->ctr[1] = (u32)ctr; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 09157b8a5810..a6f03b36fc4f 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -117,6 +117,7 @@ struct stmmac_axi { struct stmmac_est { struct mutex lock; int enable; + u32 btr_reserve[2]; u32 btr_offset[2]; u32 btr[2]; u32 ctr[2]; From 5a0ae9872d5cb5f27590eed168d4b3b144350ed7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 5 Jul 2021 12:38:41 +0200 Subject: [PATCH 0114/1469] bpf, samples: Add -fno-asynchronous-unwind-tables to BPF Clang invocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The samples/bpf Makefile currently compiles BPF files in a way that will produce an .eh_frame section, which will in turn confuse libbpf and produce errors when loading BPF programs, like: libbpf: elf: skipping unrecognized data section(32) .eh_frame libbpf: elf: skipping relo section(33) .rel.eh_frame for section(32) .eh_frame Fix this by instruction Clang not to produce this section, as it's useless for BPF anyway. Suggested-by: Daniel Borkmann Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210705103841.180260-1-toke@redhat.com --- samples/bpf/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 520434ea966f..036998d11ded 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -331,6 +331,7 @@ $(obj)/%.o: $(src)/%.c -Wno-gnu-variable-sized-type-not-at-end \ -Wno-address-of-packed-member -Wno-tautological-compare \ -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ + -fno-asynchronous-unwind-tables \ -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \ -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \ $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \ From 2620e92ae6ed83260eb46d214554cd308ee35d92 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Mon, 28 Jun 2021 17:18:15 +0800 Subject: [PATCH 0115/1469] bpf, samples: Fix xdpsock with '-M' parameter missing unload process Execute the following command and exit, then execute it again, the following error will be reported: $ sudo ./samples/bpf/xdpsock -i ens4f2 -M ^C $ sudo ./samples/bpf/xdpsock -i ens4f2 -M libbpf: elf: skipping unrecognized data section(16) .eh_frame libbpf: elf: skipping relo section(17) .rel.eh_frame for section(16) .eh_frame libbpf: Kernel error message: XDP program already attached ERROR: link set xdp fd failed Commit c9d27c9e8dc7 ("samples: bpf: Do not unload prog within xdpsock") removed the unloading prog code because of the presence of bpf_link. This is fine if XDP_SHARED_UMEM is disabled, but if it is enabled, unloading the prog is still needed. Fixes: c9d27c9e8dc7 ("samples: bpf: Do not unload prog within xdpsock") Signed-off-by: Wang Hai Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Cc: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20210628091815.2373487-1-wanghai38@huawei.com --- samples/bpf/xdpsock_user.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 53e300f860bb..33d0bdebbed8 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -96,6 +96,7 @@ static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; +static u32 prog_id; static bool opt_busy_poll; static bool opt_reduced_cap; @@ -461,6 +462,23 @@ static void *poller(void *arg) return NULL; } +static void remove_xdp_program(void) +{ + u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAILURE); + } + + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); +} + static void int_exit(int sig) { benchmark_done = true; @@ -471,6 +489,9 @@ static void __exit_with_error(int error, const char *file, const char *func, { fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func, line, error, strerror(error)); + + if (opt_num_xsks > 1) + remove_xdp_program(); exit(EXIT_FAILURE); } @@ -490,6 +511,9 @@ static void xdpsock_cleanup(void) if (write(sock, &cmd, sizeof(int)) < 0) exit_with_error(errno); } + + if (opt_num_xsks > 1) + remove_xdp_program(); } static void swap_mac_addresses(void *data) @@ -857,6 +881,10 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, if (ret) exit_with_error(-ret); + ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + if (ret) + exit_with_error(-ret); + xsk->app_stats.rx_empty_polls = 0; xsk->app_stats.fill_fail_polls = 0; xsk->app_stats.copy_tx_sendtos = 0; From bc832065b60f973771ff3e657214bb21b559833c Mon Sep 17 00:00:00 2001 From: Gu Shengxian Date: Mon, 5 Jul 2021 18:35:43 -0700 Subject: [PATCH 0116/1469] bpftool: Properly close va_list 'ap' by va_end() on error va_list 'ap' was opened but not closed by va_end() in error case. It should be closed by va_end() before the return. Fixes: aa52bcbe0e72 ("tools: bpftool: Fix json dump crash on powerpc") Signed-off-by: Gu Shengxian Signed-off-by: Daniel Borkmann Cc: Jiri Olsa Link: https://lore.kernel.org/bpf/20210706013543.671114-1-gushengxian507419@gmail.com --- tools/bpf/bpftool/jit_disasm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index e7e7eee9f172..24734f2249d6 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -43,11 +43,13 @@ static int fprintf_json(void *out, const char *fmt, ...) { va_list ap; char *s; + int err; va_start(ap, fmt); - if (vasprintf(&s, fmt, ap) < 0) - return -1; + err = vasprintf(&s, fmt, ap); va_end(ap); + if (err < 0) + return -1; if (!oper_count) { int i; From fb5dad4084f0ea6b6df5fe90f157531ca6e20681 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 8 Jun 2021 14:39:54 +0200 Subject: [PATCH 0117/1469] KVM: selftests: introduce P44V64 for z196 and EC12 Older machines like z196 and zEC12 do only support 44 bits of physical addresses. Make this the default and check via IBC if we are on a later machine. We then add P47V64 as an additional model. Reviewed-by: David Hildenbrand Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger Link: https://lore.kernel.org/kvm/20210701153853.33063-1-borntraeger@de.ibm.com/ Fixes: 1bc603af73dd ("KVM: selftests: introduce P47V64 for s390x") --- tools/testing/selftests/kvm/include/kvm_util.h | 3 ++- tools/testing/selftests/kvm/lib/guest_modes.c | 16 ++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++ 3 files changed, 23 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 35739567189e..74d73532fce9 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -44,6 +44,7 @@ enum vm_guest_mode { VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, NUM_VM_MODES, }; @@ -61,7 +62,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P47V64_4K +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 25bff307c71f..c330f414ef96 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -22,6 +22,22 @@ void guest_modes_append_default(void) } } #endif +#ifdef __s390x__ + { + int kvm_fd, vm_fd; + struct kvm_s390_vm_cpu_processor info; + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0); + kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info, false); + close(vm_fd); + close(kvm_fd); + /* Starting with z13 we have 47bits of physical address */ + if (info.ibc >= 0x30) + guest_mode_append(VM_MODE_P47V64_4K, true, true); + } +#endif } void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a2b732cf96ea..8606000c439e 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -176,6 +176,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", + [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -194,6 +195,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, { 47, 64, 0x1000, 12 }, + { 44, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -282,6 +284,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) case VM_MODE_P47V64_4K: vm->pgtable_levels = 5; break; + case VM_MODE_P44V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } From cd4220d23bf3f43cf720e82bdee681f383433ae2 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 1 Jul 2021 17:42:24 +0200 Subject: [PATCH 0118/1469] KVM: selftests: do not require 64GB in set_memory_region_test Unless the user sets overcommit_memory or has plenty of swap, the latest changes to the testcase will result in ENOMEM failures for hosts with less than 64GB RAM. As we do not use much of the allocated memory, we can use MAP_NORESERVE to avoid this error. Cc: Zenghui Yu Cc: vkuznets@redhat.com Cc: wanghaibin.wang@huawei.com Cc: stable@vger.kernel.org Fixes: 309505dd5685 ("KVM: selftests: Fix mapping length truncation in m{,un}map()") Tested-by: Zenghui Yu Link: https://lore.kernel.org/kvm/20210701160425.33666-1-borntraeger@de.ibm.com/ Signed-off-by: Christian Borntraeger --- tools/testing/selftests/kvm/set_memory_region_test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index d8812f27648c..d31f54ac4e98 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -377,7 +377,8 @@ static void test_add_max_memory_regions(void) (max_mem_slots - 1), MEM_REGION_SIZE >> 10); mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment, - PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0); TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host"); mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1)); From c4edc3ccbc63947e697bd2e30afca8bfaa144998 Mon Sep 17 00:00:00 2001 From: Ali Abdallah Date: Thu, 20 May 2021 12:53:11 +0200 Subject: [PATCH 0119/1469] netfilter: conntrack: improve RST handling when tuple is re-used If we receive a SYN packet in original direction on an existing connection tracking entry, we let this SYN through because conntrack might be out-of-sync. Conntrack gets back in sync when server responds with SYN/ACK and state gets updated accordingly. However, if server replies with RST, this packet might be marked as INVALID because td_maxack value reflects the *old* conntrack state and not the state of the originator of the RST. Avoid td_maxack-based checks if previous packet was a SYN. Unfortunately that is not be enough: an out of order ACK in original direction updates last_index, so we still end up marking valid RST. Thus disable the sequence check when we are not in established state and the received RST has a sequence of 0. Because marking RSTs as invalid usually leads to unwanted timeouts, also skip RST sequence checks if a conntrack entry is already closing. Such entries can already be evicted via GC in case the table is full. Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Signed-off-by: Ali Abdallah Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 53 +++++++++++++++++--------- 1 file changed, 36 insertions(+), 17 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index eb4de92077a8..b8ff67671e93 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -823,6 +823,22 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +static bool tcp_can_early_drop(const struct nf_conn *ct) +{ + switch (ct->proto.tcp.state) { + case TCP_CONNTRACK_FIN_WAIT: + case TCP_CONNTRACK_LAST_ACK: + case TCP_CONNTRACK_TIME_WAIT: + case TCP_CONNTRACK_CLOSE: + case TCP_CONNTRACK_CLOSE_WAIT: + return true; + default: + break; + } + + return false; +} + /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -1030,9 +1046,28 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (index != TCP_RST_SET) break; - if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) { + /* If we are closing, tuple might have been re-used already. + * last_index, last_ack, and all other ct fields used for + * sequence/window validation are outdated in that case. + * + * As the conntrack can already be expired by GC under pressure, + * just skip validation checks. + */ + if (tcp_can_early_drop(ct)) + goto in_window; + + /* td_maxack might be outdated if we let a SYN through earlier */ + if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && + ct->proto.tcp.last_index != TCP_SYN_SET) { u32 seq = ntohl(th->seq); + /* If we are not in established state and SEQ=0 this is most + * likely an answer to a SYN we let go through above (last_index + * can be updated due to out-of-order ACKs). + */ + if (seq == 0 && !nf_conntrack_tcp_established(ct)) + break; + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ spin_unlock_bh(&ct->lock); @@ -1165,22 +1200,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, return NF_ACCEPT; } -static bool tcp_can_early_drop(const struct nf_conn *ct) -{ - switch (ct->proto.tcp.state) { - case TCP_CONNTRACK_FIN_WAIT: - case TCP_CONNTRACK_LAST_ACK: - case TCP_CONNTRACK_TIME_WAIT: - case TCP_CONNTRACK_CLOSE: - case TCP_CONNTRACK_CLOSE_WAIT: - return true; - default: - break; - } - - return false; -} - #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include From 1da4cd82dd180224503e745ccf3220e3490d8897 Mon Sep 17 00:00:00 2001 From: Ali Abdallah Date: Thu, 27 May 2021 09:19:06 +0200 Subject: [PATCH 0120/1469] netfilter: conntrack: add new sysctl to disable RST check This patch adds a new sysctl tcp_ignore_invalid_rst to disable marking out of segments RSTs as INVALID. Signed-off-by: Ali Abdallah Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.rst | 6 ++++++ include/net/netns/conntrack.h | 1 + net/netfilter/nf_conntrack_proto_tcp.c | 6 +++++- net/netfilter/nf_conntrack_standalone.c | 10 ++++++++++ 4 files changed, 22 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 0467b30e4abe..d31ed6c1cb0d 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -110,6 +110,12 @@ nf_conntrack_tcp_be_liberal - BOOLEAN Be conservative in what you do, be liberal in what you accept from others. If it's non-zero, we mark only out of window RST segments as INVALID. +nf_conntrack_tcp_ignore_invalid_rst - BOOLEAN + - 0 - disabled (default) + - 1 - enabled + + If it's 1, we don't mark out of window RST segments as INVALID. + nf_conntrack_tcp_loose - BOOLEAN - 0 - disabled - not 0 - enabled (default) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index c3094b83a525..37e5300c7e5a 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -27,6 +27,7 @@ struct nf_tcp_net { u8 tcp_loose; u8 tcp_be_liberal; u8 tcp_max_retrans; + u8 tcp_ignore_invalid_rst; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; unsigned int offload_pickup; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b8ff67671e93..3259416f2ea4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1068,7 +1068,8 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (seq == 0 && !nf_conntrack_tcp_established(ct)) break; - if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) && + !tn->tcp_ignore_invalid_rst) { /* Invalid RST */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); @@ -1466,6 +1467,9 @@ void nf_conntrack_tcp_init_net(struct net *net) */ tn->tcp_be_liberal = 0; + /* If it's non-zero, we turn off RST sequence number check */ + tn->tcp_ignore_invalid_rst = 0; + /* Max number of the retransmitted packets without receiving an (acceptable) * ACK from the destination. If this number is reached, a shorter timer * will be started. diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index f57a951c9b5e..214d9f9e499b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -579,6 +579,7 @@ enum nf_ct_sysctl_index { #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, + NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, @@ -798,6 +799,14 @@ static struct ctl_table nf_ct_sysctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = { + .procname = "nf_conntrack_tcp_ignore_invalid_rst", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", .maxlen = sizeof(u8), @@ -1004,6 +1013,7 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, XASSIGN(LOOSE, &tn->tcp_loose); XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); + XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst); #undef XASSIGN #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) From cf4466ea47db891be785f867ca7f99e0cd9898c6 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Sun, 27 Jun 2021 18:19:18 +0200 Subject: [PATCH 0121/1469] netfilter: conntrack: Mark access for KCSAN KCSAN detected an data race with ipc/sem.c that is intentional. As nf_conntrack_lock() uses the same algorithm: Update nf_conntrack_core as well: nf_conntrack_lock() contains a1) spin_lock() a2) smp_load_acquire(nf_conntrack_locks_all). a1) actually accesses one lock from an array of locks. nf_conntrack_locks_all() contains b1) nf_conntrack_locks_all=true (normal write) b2) spin_lock() b3) spin_unlock() b2 and b3 are done for every lock. This guarantees that nf_conntrack_locks_all() prevents any concurrent nf_conntrack_lock() owners: If a thread past a1), then b2) will block until that thread releases the lock. If the threat is before a1, then b3)+a1) ensure the write b1) is visible, thus a2) is guaranteed to see the updated value. But: This is only the latest time when b1) becomes visible. It may also happen that b1) is visible an undefined amount of time before the b3). And thus KCSAN will notice a data race. In addition, the compiler might be too clever. Solution: Use WRITE_ONCE(). Signed-off-by: Manfred Spraul Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 085a11f1eb43..83c52df85870 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -149,7 +149,15 @@ static void nf_conntrack_all_lock(void) spin_lock(&nf_conntrack_locks_all_lock); - nf_conntrack_locks_all = true; + /* For nf_contrack_locks_all, only the latest time when another + * CPU will see an update is controlled, by the "release" of the + * spin_lock below. + * The earliest time is not controlled, an thus KCSAN could detect + * a race when nf_conntract_lock() reads the variable. + * WRITE_ONCE() is used to ensure the compiler will not + * optimize the write. + */ + WRITE_ONCE(nf_conntrack_locks_all, true); for (i = 0; i < CONNTRACK_LOCKS; i++) { spin_lock(&nf_conntrack_locks[i]); From 6ac4bac4ce48604cf0f4b04d61884552520ca55e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 5 Jul 2021 17:45:36 +0200 Subject: [PATCH 0122/1469] netfilter: nft_last: honor NFTA_LAST_SET on restoration NFTA_LAST_SET tells us if this expression has ever seen a packet, do not ignore this attribute when restoring the ruleset. Fixes: 836382dc2471 ("netfilter: nf_tables: add last expression") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_last.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 913ac45167f2..bbb352b64c73 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -23,15 +23,21 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); u64 last_jiffies; + u32 last_set = 0; int err; - if (tb[NFTA_LAST_MSECS]) { + if (tb[NFTA_LAST_SET]) { + last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET])); + if (last_set == 1) + priv->last_set = 1; + } + + if (last_set && tb[NFTA_LAST_MSECS]) { err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies); if (err < 0) return err; priv->last_jiffies = jiffies + (unsigned long)last_jiffies; - priv->last_set = 1; } return 0; From d1b5b80da7058883758df2b5b7f506d4d4f9a5fa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 5 Jul 2021 20:14:21 +0200 Subject: [PATCH 0123/1469] netfilter: nft_last: incorrect arithmetics when restoring last used Subtract the jiffies that have passed by to current jiffies to fix last used restoration. Fixes: 836382dc2471 ("netfilter: nf_tables: add last expression") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_last.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index bbb352b64c73..8088b99f2ee3 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -37,7 +37,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - priv->last_jiffies = jiffies + (unsigned long)last_jiffies; + priv->last_jiffies = jiffies - (unsigned long)last_jiffies; } return 0; From 8550ff8d8c75416e984d9c4b082845e57e560984 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 5 Jul 2021 13:54:51 +0300 Subject: [PATCH 0124/1469] skbuff: Release nfct refcount on napi stolen or re-used skbs When multiple SKBs are merged to a new skb under napi GRO, or SKB is re-used by napi, if nfct was set for them in the driver, it will not be released while freeing their stolen head state or on re-use. Release nfct on napi's stolen or re-used SKBs, and in gro_list_prepare, check conntrack metadata diff. Fixes: 5c6b94604744 ("net/mlx5e: CT: Handle misses after executing CT action") Reviewed-by: Roi Dayan Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- net/core/dev.c | 13 +++++++++++++ net/core/skbuff.c | 1 + 2 files changed, 14 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index c253c2aafe97..177a5aec0b6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6008,6 +6008,18 @@ static void gro_list_prepare(const struct list_head *head, diffs = memcmp(skb_mac_header(p), skb_mac_header(skb), maclen); + + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + + if (!diffs) { + struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); + struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; + } + NAPI_GRO_CB(p)->same_flow = !diffs; } } @@ -6270,6 +6282,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); skb_ext_reset(skb); + nf_reset_ct(skb); napi->skb = skb; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12aabcda6db2..f63de967ac25 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -943,6 +943,7 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_skb_free_stolen_head(struct sk_buff *skb) { + nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); napi_skb_cache_put(skb); From be5d1b61a2ad28c7e57fe8bfa277373e8ecffcdc Mon Sep 17 00:00:00 2001 From: Nguyen Dinh Phi Date: Tue, 6 Jul 2021 07:19:12 +0800 Subject: [PATCH 0125/1469] tcp: fix tcp_init_transfer() to not reset icsk_ca_initialized This commit fixes a bug (found by syzkaller) that could cause spurious double-initializations for congestion control modules, which could cause memory leaks or other problems for congestion control modules (like CDG) that allocate memory in their init functions. The buggy scenario constructed by syzkaller was something like: (1) create a TCP socket (2) initiate a TFO connect via sendto() (3) while socket is in TCP_SYN_SENT, call setsockopt(TCP_CONGESTION), which calls: tcp_set_congestion_control() -> tcp_reinit_congestion_control() -> tcp_init_congestion_control() (4) receive ACK, connection is established, call tcp_init_transfer(), set icsk_ca_initialized=0 (without first calling cc->release()), call tcp_init_congestion_control() again. Note that in this sequence tcp_init_congestion_control() is called twice without a cc->release() call in between. Thus, for CC modules that allocate memory in their init() function, e.g, CDG, a memory leak may occur. The syzkaller tool managed to find a reproducer that triggered such a leak in CDG. The bug was introduced when that commit 8919a9b31eb4 ("tcp: Only init congestion control if not initialized already") introduced icsk_ca_initialized and set icsk_ca_initialized to 0 in tcp_init_transfer(), missing the possibility for a sequence like the one above, where a process could call setsockopt(TCP_CONGESTION) in state TCP_SYN_SENT (i.e. after the connect() or TFO open sendmsg()), which would call tcp_init_congestion_control(). It did not intend to reset any initialization that the user had already explicitly made; it just missed the possibility of that particular sequence (which syzkaller managed to find). Fixes: 8919a9b31eb4 ("tcp: Only init congestion control if not initialized already") Reported-by: syzbot+f1e24a0594d4e3a895d3@syzkaller.appspotmail.com Signed-off-by: Nguyen Dinh Phi Acked-by: Neal Cardwell Tested-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e6ca5a1f3b59..a5a8d0a378b2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5922,8 +5922,8 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - icsk->icsk_ca_initialized = 0; bpf_skops_established(sk, bpf_op, skb); + /* Initialize congestion control unless BPF initialized it already: */ if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); From b648eba4c69e5819880b4907e7fcb2bb576069ab Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:06 +0000 Subject: [PATCH 0126/1469] bonding: fix suspicious RCU usage in bond_ipsec_add_sa() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Test commands: ip link add dummy0 type dummy ip link add bond0 type bond ip link set dummy0 master bond0 ip link set dummy0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 \ mode transport \ reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel \ src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp offload \ dev bond0 dir in Splat looks like: ============================= WARNING: suspicious RCU usage 5.13.0-rc3+ #1168 Not tainted ----------------------------- drivers/net/bonding/bond_main.c:411 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ip/684: #0: ffffffff9a2757c0 (&net->xfrm.xfrm_cfg_mutex){+.+.}-{3:3}, at: xfrm_netlink_rcv+0x59/0x80 [xfrm_user] 55.191733][ T684] stack backtrace: CPU: 0 PID: 684 Comm: ip Not tainted 5.13.0-rc3+ #1168 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_add_sa+0x18c/0x1f0 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? netlink_ack+0x9d0/0x9d0 ? netlink_deliver_tap+0x17c/0xa50 xfrm_netlink_rcv+0x68/0x80 [xfrm_user] netlink_unicast+0x41c/0x610 ? netlink_attachskb+0x710/0x710 netlink_sendmsg+0x6b9/0xb70 [ ... ] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0ff7567bd04f..d4d718e04dcc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -403,10 +403,12 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; + int err; if (!bond_dev) return -EINVAL; + rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); xs->xso.real_dev = slave->dev; @@ -415,10 +417,13 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) if (!(slave->dev->xfrmdev_ops && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); + rcu_read_unlock(); return -EINVAL; } - return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + rcu_read_unlock(); + return err; } /** From 105cd17a866017b45f3c45901b394c711c97bf40 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:07 +0000 Subject: [PATCH 0127/1469] bonding: fix null dereference in bond_ipsec_add_sa() If bond doesn't have real device, bond->curr_active_slave is null. But bond_ipsec_add_sa() dereferences bond->curr_active_slave without null checking. So, null-ptr-deref would occur. Test commands: ip link add bond0 type bond ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi \ 0x07 mode transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 4 PID: 680 Comm: ip Not tainted 5.13.0-rc3+ #1168 RIP: 0010:bond_ipsec_add_sa+0xc4/0x2e0 [bonding] Code: 85 21 02 00 00 4d 8b a6 48 0c 00 00 e8 75 58 44 ce 85 c0 0f 85 14 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 e2 48 c1 ea 03 <80> 3c 02 00 0f 85 fc 01 00 00 48 8d bb e0 02 00 00 4d 8b 2c 24 48 RSP: 0018:ffff88810946f508 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88810b4e8040 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffffff8fe34280 RDI: ffff888115abe100 RBP: ffff88810946f528 R08: 0000000000000003 R09: fffffbfff2287e11 R10: 0000000000000001 R11: ffff888115abe0c8 R12: 0000000000000000 R13: ffffffffc0aea9a0 R14: ffff88800d7d2000 R15: ffff88810b4e8330 FS: 00007efc5552e680(0000) GS:ffff888119c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055c2530dbf40 CR3: 0000000103056004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? netlink_ack+0x9d0/0x9d0 ? netlink_deliver_tap+0x17c/0xa50 xfrm_netlink_rcv+0x68/0x80 [xfrm_user] netlink_unicast+0x41c/0x610 ? netlink_attachskb+0x710/0x710 netlink_sendmsg+0x6b9/0xb70 [ ...] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d4d718e04dcc..5466b24ceab6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -411,6 +411,11 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); + if (!slave) { + rcu_read_unlock(); + return -ENODEV; + } + xs->xso.real_dev = slave->dev; bond->xs = xs; From 09adf7566d436322ced595b166dea48b06852efe Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:08 +0000 Subject: [PATCH 0128/1469] net: netdevsim: use xso.real_dev instead of xso.dev in callback functions of struct xfrmdev_ops There are two pointers in struct xfrm_state_offload, *dev, *real_dev. These are used in callback functions of struct xfrmdev_ops. The *dev points whether bonding interface or real interface. If bonding ipsec offload is used, it points bonding interface If not, it points real interface. And real_dev always points real interface. So, netdevsim should always use real_dev instead of dev. Of course, real_dev always not be null. Test commands: ip netns add A ip netns exec A bash modprobe netdevsim echo "1 1" > /sys/bus/netdevsim/new_device ip link add bond0 type bond mode active-backup ip link set eth0 master bond0 ip link set eth0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: BUG: spinlock bad magic on CPU#5, kworker/5:1/53 lock: 0xffff8881068c2cc8, .magic: 11121314, .owner: /-1, .owner_cpu: -235736076 CPU: 5 PID: 53 Comm: kworker/5:1 Not tainted 5.13.0-rc3+ #1168 Workqueue: events linkwatch_event Call Trace: dump_stack+0xa4/0xe5 do_raw_spin_lock+0x20b/0x270 ? rwlock_bug.part.1+0x90/0x90 _raw_spin_lock_nested+0x5f/0x70 bond_get_stats+0xe4/0x4c0 [bonding] ? rcu_read_lock_sched_held+0xc0/0xc0 ? bond_neigh_init+0x2c0/0x2c0 [bonding] ? dev_get_alias+0xe2/0x190 ? dev_get_port_parent_id+0x14a/0x360 ? rtnl_unregister+0x190/0x190 ? dev_get_phys_port_name+0xa0/0xa0 ? memset+0x1f/0x40 ? memcpy+0x38/0x60 ? rtnl_phys_switch_id_fill+0x91/0x100 dev_get_stats+0x8c/0x270 rtnl_fill_stats+0x44/0xbe0 ? nla_put+0xbe/0x140 rtnl_fill_ifinfo+0x1054/0x3ad0 [ ... ] Fixes: 272c2330adc9 ("xfrm: bail early on slave pass over skb") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/netdevsim/ipsec.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c index 3811f1bde84e..b80ed2ffd45e 100644 --- a/drivers/net/netdevsim/ipsec.c +++ b/drivers/net/netdevsim/ipsec.c @@ -85,7 +85,7 @@ static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { const char aes_gcm_name[] = "rfc4106(gcm(aes))"; - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -134,7 +134,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) u16 sa_idx; int ret; - dev = xs->xso.dev; + dev = xs->xso.real_dev; ns = netdev_priv(dev); ipsec = &ns->ipsec; @@ -194,7 +194,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) static void nsim_ipsec_del_sa(struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; u16 sa_idx; @@ -211,7 +211,7 @@ static void nsim_ipsec_del_sa(struct xfrm_state *xs) static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; ipsec->ok++; From 2de7e4f67599affc97132bd07e30e3bd59d0b777 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:09 +0000 Subject: [PATCH 0129/1469] ixgbevf: use xso.real_dev instead of xso.dev in callback functions of struct xfrmdev_ops There are two pointers in struct xfrm_state_offload, *dev, *real_dev. These are used in callback functions of struct xfrmdev_ops. The *dev points whether bonding interface or real interface. If bonding ipsec offload is used, it points bonding interface If not, it points real interface. And real_dev always points real interface. So, ixgbevf should always use real_dev instead of dev. Of course, real_dev always not be null. Test commands: ip link add bond0 type bond #eth0 is ixgbevf interface ip link set eth0 master bond0 ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 6 PID: 688 Comm: ip Not tainted 5.13.0-rc3+ #1168 RIP: 0010:ixgbevf_ipsec_find_empty_idx+0x28/0x1b0 [ixgbevf] Code: 00 00 0f 1f 44 00 00 55 53 48 89 fb 48 83 ec 08 40 84 f6 0f 84 9c 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 01 0f 8e 4c 01 00 00 66 81 3b 00 04 0f RSP: 0018:ffff8880089af390 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff8880089af4f8 R08: 0000000000000003 R09: fffffbfff4287e11 R10: 0000000000000001 R11: ffff888005de8908 R12: 0000000000000000 R13: ffff88810936a000 R14: ffff88810936a000 R15: ffff888004d78040 FS: 00007fdf9883a680(0000) GS:ffff88811a400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055bc14adbf40 CR3: 000000000b87c005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ixgbevf_ipsec_add_sa+0x1bf/0x9c0 [ixgbevf] ? rcu_read_lock_sched_held+0x91/0xc0 ? ixgbevf_ipsec_parse_proto_keys.isra.9+0x280/0x280 [ixgbevf] ? lock_acquire+0x191/0x720 ? bond_ipsec_add_sa+0x48/0x350 [bonding] ? lockdep_hardirqs_on_prepare+0x3e0/0x3e0 ? rcu_read_lock_held+0x91/0xa0 ? rcu_read_lock_sched_held+0xc0/0xc0 bond_ipsec_add_sa+0x193/0x350 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 [ ... ] Fixes: 272c2330adc9 ("xfrm: bail early on slave pass over skb") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbevf/ipsec.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index caaea2c920a6..e3e4676af9e4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -211,7 +211,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -260,12 +260,15 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, **/ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx; int ret; + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n", xs->id.proto); @@ -383,11 +386,14 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) **/ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx; + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; From a22c39b831a081da9b2c488bd970a4412d926f30 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:10 +0000 Subject: [PATCH 0130/1469] bonding: fix suspicious RCU usage in bond_ipsec_del_sa() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Test commands: ip netns add A ip netns exec A bash modprobe netdevsim echo "1 1" > /sys/bus/netdevsim/new_device ip link add bond0 type bond ip link set eth0 master bond0 ip link set eth0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in ip x s f Splat looks like: ============================= WARNING: suspicious RCU usage 5.13.0-rc3+ #1168 Not tainted ----------------------------- drivers/net/bonding/bond_main.c:448 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by ip/705: #0: ffff888106701780 (&net->xfrm.xfrm_cfg_mutex){+.+.}-{3:3}, at: xfrm_netlink_rcv+0x59/0x80 [xfrm_user] #1: ffff8880075b0098 (&x->lock){+.-.}-{2:2}, at: xfrm_state_delete+0x16/0x30 stack backtrace: CPU: 6 PID: 705 Comm: ip Not tainted 5.13.0-rc3+ #1168 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_del_sa+0x16a/0x1c0 [bonding] __xfrm_state_delete+0x51f/0x730 xfrm_state_delete+0x1e/0x30 xfrm_state_flush+0x22f/0x390 xfrm_flush_sa+0xd8/0x260 [xfrm_user] ? xfrm_flush_policy+0x290/0x290 [xfrm_user] xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 [ ... ] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5466b24ceab6..aa9c469ebbb5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -444,21 +444,24 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) if (!bond_dev) return; + rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); if (!slave) - return; + goto out; xs->xso.real_dev = slave->dev; if (!(slave->dev->xfrmdev_ops && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); - return; + goto out; } slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs); +out: + rcu_read_unlock(); } /** From b121693381b112b78c076dea171ee113e237c0e4 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:11 +0000 Subject: [PATCH 0131/1469] bonding: disallow setting nested bonding + ipsec offload bonding interface can be nested and it supports ipsec offload. So, it allows setting the nested bonding + ipsec scenario. But code does not support this scenario. So, it should be disallowed. interface graph: bond2 | bond1 | eth0 The nested bonding + ipsec offload may not a real usecase. So, disallowing this scenario is fine. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index aa9c469ebbb5..f7b89743fab9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -419,8 +419,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) xs->xso.real_dev = slave->dev; bond->xs = xs; - if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_add || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); rcu_read_unlock(); return -EINVAL; @@ -453,8 +454,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) xs->xso.real_dev = slave->dev; - if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_delete || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); goto out; } @@ -479,8 +481,9 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return true; - if (!(slave_dev->xfrmdev_ops - && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) { + if (!slave_dev->xfrmdev_ops || + !slave_dev->xfrmdev_ops->xdo_dev_offload_ok || + netif_is_bond_master(slave_dev)) { slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); return false; } From 9a5605505d9c7dbfdb89cc29a8f5fc5cf9fd2334 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:12 +0000 Subject: [PATCH 0132/1469] bonding: Add struct bond_ipesc to manage SA bonding has been supporting ipsec offload. When SA is added, bonding just passes SA to its own active real interface. But it doesn't manage SA. So, when events(add/del real interface, active real interface change, etc) occur, bonding can't handle that well because It doesn't manage SA. So some problems(panic, UAF, refcnt leak)occur. In order to make it stable, it should manage SA. That's the reason why struct bond_ipsec is added. When a new SA is added to bonding interface, it is stored in the bond_ipsec list. And the SA is passed to a current active real interface. If events occur, it uses bond_ipsec data to handle these events. bond->ipsec_list is protected by bond->ipsec_lock. If a current active real interface is changed, the following logic works. 1. delete all SAs from old active real interface 2. Add all SAs to the new active real interface. 3. If a new active real interface doesn't support ipsec offload or SA's option, it sets real_dev to NULL. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 139 +++++++++++++++++++++++++++----- include/net/bonding.h | 9 ++- 2 files changed, 127 insertions(+), 21 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f7b89743fab9..165fa55cfb38 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -401,6 +401,7 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, static int bond_ipsec_add_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; + struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; int err; @@ -416,9 +417,6 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) return -ENODEV; } - xs->xso.real_dev = slave->dev; - bond->xs = xs; - if (!slave->dev->xfrmdev_ops || !slave->dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(slave->dev)) { @@ -427,11 +425,63 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) return -EINVAL; } + ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC); + if (!ipsec) { + rcu_read_unlock(); + return -ENOMEM; + } + xs->xso.real_dev = slave->dev; + err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + if (!err) { + ipsec->xs = xs; + INIT_LIST_HEAD(&ipsec->list); + spin_lock_bh(&bond->ipsec_lock); + list_add(&ipsec->list, &bond->ipsec_list); + spin_unlock_bh(&bond->ipsec_lock); + } else { + kfree(ipsec); + } rcu_read_unlock(); return err; } +static void bond_ipsec_add_sa_all(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_ipsec *ipsec; + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (!slave) + goto out; + + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_add || + netif_is_bond_master(slave->dev)) { + spin_lock_bh(&bond->ipsec_lock); + if (!list_empty(&bond->ipsec_list)) + slave_warn(bond_dev, slave->dev, + "%s: no slave xdo_dev_state_add\n", + __func__); + spin_unlock_bh(&bond->ipsec_lock); + goto out; + } + + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + ipsec->xs->xso.real_dev = slave->dev; + if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs)) { + slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__); + ipsec->xs->xso.real_dev = NULL; + } + } + spin_unlock_bh(&bond->ipsec_lock); +out: + rcu_read_unlock(); +} + /** * bond_ipsec_del_sa - clear out this specific SA * @xs: pointer to transformer state struct @@ -439,6 +489,7 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; + struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; @@ -452,7 +503,10 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) if (!slave) goto out; - xs->xso.real_dev = slave->dev; + if (!xs->xso.real_dev) + goto out; + + WARN_ON(xs->xso.real_dev != slave->dev); if (!slave->dev->xfrmdev_ops || !slave->dev->xfrmdev_ops->xdo_dev_state_delete || @@ -463,6 +517,48 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + if (ipsec->xs == xs) { + list_del(&ipsec->list); + kfree(ipsec); + break; + } + } + spin_unlock_bh(&bond->ipsec_lock); + rcu_read_unlock(); +} + +static void bond_ipsec_del_sa_all(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_ipsec *ipsec; + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (!slave) { + rcu_read_unlock(); + return; + } + + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + if (!ipsec->xs->xso.real_dev) + continue; + + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_delete || + netif_is_bond_master(slave->dev)) { + slave_warn(bond_dev, slave->dev, + "%s: no slave xdo_dev_state_delete\n", + __func__); + } else { + slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); + } + ipsec->xs->xso.real_dev = NULL; + } + spin_unlock_bh(&bond->ipsec_lock); rcu_read_unlock(); } @@ -474,22 +570,27 @@ out: static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; - struct bonding *bond = netdev_priv(bond_dev); - struct slave *curr_active = rcu_dereference(bond->curr_active_slave); - struct net_device *slave_dev = curr_active->dev; + struct net_device *real_dev; + struct slave *curr_active; + struct bonding *bond; + + bond = netdev_priv(bond_dev); + curr_active = rcu_dereference(bond->curr_active_slave); + real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return true; - if (!slave_dev->xfrmdev_ops || - !slave_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(slave_dev)) { - slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); + if (!xs->xso.real_dev) + return false; + + if (!real_dev->xfrmdev_ops || + !real_dev->xfrmdev_ops->xdo_dev_offload_ok || + netif_is_bond_master(real_dev)) { return false; } - xs->xso.real_dev = slave_dev; - return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + return real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); } static const struct xfrmdev_ops bond_xfrmdev_ops = { @@ -1006,8 +1107,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) return; #ifdef CONFIG_XFRM_OFFLOAD - if (old_active && bond->xs) - bond_ipsec_del_sa(bond->xs); + bond_ipsec_del_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ if (new_active) { @@ -1082,10 +1182,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } #ifdef CONFIG_XFRM_OFFLOAD - if (new_active && bond->xs) { - xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true); - bond_ipsec_add_sa(bond->xs); - } + bond_ipsec_add_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ /* resend IGMP joins since active slave has changed or @@ -3343,6 +3440,7 @@ static int bond_master_netdev_event(unsigned long event, return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); + xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); @@ -4910,7 +5008,8 @@ void bond_setup(struct net_device *bond_dev) #ifdef CONFIG_XFRM_OFFLOAD /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; - bond->xs = NULL; + INIT_LIST_HEAD(&bond->ipsec_list); + spin_lock_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 15335732e166..625d9c72dee3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -201,6 +201,11 @@ struct bond_up_slave { */ #define BOND_LINK_NOCHANGE -1 +struct bond_ipsec { + struct list_head list; + struct xfrm_state *xs; +}; + /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. @@ -249,7 +254,9 @@ struct bonding { #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD - struct xfrm_state *xs; + struct list_head ipsec_list; + /* protecting ipsec_list */ + spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ }; From 955b785ec6b3b2f9b91914d6eeac8ee66ee29239 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:13 +0000 Subject: [PATCH 0133/1469] bonding: fix suspicious RCU usage in bond_ipsec_offload_ok() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Splat looks like: WARNING: suspicious RCU usage 5.13.0-rc6+ #1179 Not tainted drivers/net/bonding/bond_main.c:571 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ping/974: #0: ffff888109e7db70 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0x1303/0x2cb0 stack backtrace: CPU: 2 PID: 974 Comm: ping Not tainted 5.13.0-rc6+ #1179 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_offload_ok+0x1f4/0x260 [bonding] xfrm_output+0x179/0x890 xfrm4_output+0xfa/0x410 ? __xfrm4_output+0x4b0/0x4b0 ? __ip_make_skb+0xecc/0x2030 ? xfrm4_udp_encap_rcv+0x800/0x800 ? ip_local_out+0x21/0x3a0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x1bfd/0x2cb0 Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 165fa55cfb38..780f87869e36 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -573,24 +573,34 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; + int err; bond = netdev_priv(bond_dev); + rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); real_dev = curr_active->dev; - if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) - return true; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + err = true; + goto out; + } - if (!xs->xso.real_dev) - return false; + if (!xs->xso.real_dev) { + err = false; + goto out; + } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || netif_is_bond_master(real_dev)) { - return false; + err = false; + goto out; } - return real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); +out: + rcu_read_unlock(); + return err; } static const struct xfrmdev_ops bond_xfrmdev_ops = { From 168e696a36792a4a3b2525a06249e7472ef90186 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:14 +0000 Subject: [PATCH 0134/1469] bonding: fix incorrect return value of bond_ipsec_offload_ok() bond_ipsec_offload_ok() is called to check whether the interface supports ipsec offload or not. bonding interface support ipsec offload only in active-backup mode. So, if a bond interface is not in active-backup mode, it should return false but it returns true. Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 780f87869e36..d22d78303311 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -581,7 +581,7 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - err = true; + err = false; goto out; } From 22b6d14992b733e9421a475f4d43df24629737ab Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 4 Jun 2021 12:37:44 -0700 Subject: [PATCH 0135/1469] scftorture: Avoid false-positive warnings in scftorture_invoker() If the call to set_cpus_allowed_ptr() in scftorture_invoker() fails, a later WARN_ONCE() complains. But with the advent of 570a752b7a9b ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed"), this complaint can be drowned out by complaints from smp_processor_id(). The rationale for this change is that scftorture's kthreads are not marked with PF_NO_SETAFFINITY, which means that a system administrator could change affinity at any time. However, scftorture is a torture test, and the system administrator might well have a valid test-the-test reason for changing affinity. This commit therefore changes to raw_smp_processor_id() in order to avoid the noise, and also adds a WARN_ON_ONCE() to the call to set_cpus_allowed_ptr() in order to directly detect immediate failure. There is no WARN_ON_ONCE() within the test loop, allowing human-reflex-based affinity resetting, if desired. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 2377cbb32474..29e8fc5d91a7 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -405,15 +405,15 @@ static int scftorture_invoker(void *arg) VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu); cpu = scfp->cpu % nr_cpu_ids; - set_cpus_allowed_ptr(current, cpumask_of(cpu)); + WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(cpu))); set_user_nice(current, MAX_NICE); if (holdoff) schedule_timeout_interruptible(holdoff * HZ); - VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id()); + VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, raw_smp_processor_id()); // Make sure that the CPU is affinitized appropriately during testing. - curcpu = smp_processor_id(); + curcpu = raw_smp_processor_id(); WARN_ONCE(curcpu != scfp->cpu % nr_cpu_ids, "%s: Wanted CPU %d, running on %d, nr_cpu_ids = %d\n", __func__, scfp->cpu, curcpu, nr_cpu_ids); From 05bc276cf243d90b9f1eb6ae2962f41eeb53a741 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 10 Jun 2021 09:24:43 -0700 Subject: [PATCH 0136/1469] refscale: Avoid false-positive warnings in ref_scale_reader() If the call to set_cpus_allowed_ptr() in ref_scale_reader() fails, a later WARN_ONCE() complains. But with the advent of 570a752b7a9b ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed"), this complaint can be drowned out by complaints from smp_processor_id(). The rationale for this change is that refscale's kthreads are not marked with PF_NO_SETAFFINITY, which means that a system administrator could change affinity at any time. However, refscale is a performance/stress test, and the system administrator might well have a valid test-the-test reason for changing affinity. This commit therefore changes to raw_smp_processor_id() in order to avoid the noise, and also adds a WARN_ON_ONCE() to the call to set_cpus_allowed_ptr() in order to directly detect immediate failure. There is no WARN_ON_ONCE() within the test loop, allowing human-reflex-based affinity resetting, if desired. Signed-off-by: Paul E. McKenney --- kernel/rcu/refscale.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 313d4547cbc7..d998a76fb542 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -487,13 +487,13 @@ ref_scale_reader(void *arg) s64 duration; VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: task started", me); - set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids))); set_user_nice(current, MAX_NICE); atomic_inc(&n_init); if (holdoff) schedule_timeout_interruptible(holdoff * HZ); repeat: - VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id()); + VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, raw_smp_processor_id()); // Wait for signal that this reader can start. wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) || @@ -503,7 +503,7 @@ repeat: goto end; // Make sure that the CPU is affinitized appropriately during testing. - WARN_ON_ONCE(smp_processor_id() != me); + WARN_ON_ONCE(raw_smp_processor_id() != me); WRITE_ONCE(rt->start_reader, 0); if (!atomic_dec_return(&n_started)) From 1d10bf55d85d34eb73dd8263635f43fd72135d2d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 25 May 2021 10:12:45 -0700 Subject: [PATCH 0137/1469] rcu-tasks: Don't delete holdouts within trc_inspect_reader() As Yanfei pointed out, although invoking trc_del_holdout() is safe from the viewpoint of the integrity of the holdout list itself, the put_task_struct() invoked by trc_del_holdout() can result in use-after-free errors due to later accesses to this task_struct structure by the RCU Tasks Trace grace-period kthread. This commit therefore removes this call to trc_del_holdout() from trc_inspect_reader() in favor of the grace-period thread's existing call to trc_del_holdout(), thus eliminating that particular class of use-after-free errors. Reported-by: "Xu, Yanfei" Signed-off-by: Paul E. McKenney --- kernel/rcu/tasks.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 03a118d1c003..3d5cb6cb8a6d 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -953,10 +953,9 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) in_qs = likely(!t->trc_reader_nesting); } - // Mark as checked. Because this is called from the grace-period - // kthread, also remove the task from the holdout list. + // Mark as checked so that the grace-period kthread will + // remove it from the holdout list. t->trc_reader_checked = true; - trc_del_holdout(t); if (in_qs) return true; // Already in quiescent state, done!!! From ad1f37970875eef98eeaf478f55045f388b794a5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 6 Jul 2021 12:18:02 +0100 Subject: [PATCH 0138/1469] octeontx2-pf: Fix assigned error return value that is never used Currently when the call to otx2_mbox_alloc_msg_cgx_mac_addr_update fails the error return variable rc is being assigned -ENOMEM and does not return early. rc is then re-assigned and the error case is not handled correctly. Fix this by returning -ENOMEM rather than assigning rc. Addresses-Coverity: ("Unused value") Fixes: 79d2be385e9e ("octeontx2-pf: offload DMAC filters to CGX/RPM block") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c index ffe3e94562d0..383a6b5cb698 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c @@ -161,7 +161,7 @@ int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos) if (!req) { mutex_unlock(&pf->mbox.lock); - rc = -ENOMEM; + return -ENOMEM; } ether_addr_copy(req->mac_addr, mac); From ccd27f05ae7b8ebc40af5b004e94517a919aa862 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 6 Jul 2021 11:13:35 +0200 Subject: [PATCH 0139/1469] ipv6: fix 'disable_policy' for fwd packets The goal of commit df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") was to have the disable_policy from ipv4 available on ipv6. However, it's not exactly the same mechanism. On IPv4, all packets coming from an interface, which has disable_policy set, bypass the policy check. For ipv6, this is done only for local packets, ie for packets destinated to an address configured on the incoming interface. Let's align ipv6 with ipv4 so that the 'disable_policy' sysctl has the same effect for both protocols. My first approach was to create a new kind of route cache entries, to be able to set DST_NOPOLICY without modifying routes. This would have added a lot of code. Because the local delivery path is already handled, I choose to focus on the forwarding path to minimize code churn. Fixes: df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 984050f35c61..d4ee2169afd8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -479,7 +479,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + !idev->cnf.disable_policy && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } From a9ab9cce9367a2cc02a3c7eb57a004dc0b8f380d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 25 May 2021 11:28:40 -0700 Subject: [PATCH 0140/1469] rcu-tasks: Don't delete holdouts within trc_wait_for_one_reader() Invoking trc_del_holdout() from within trc_wait_for_one_reader() is only a performance optimization because the RCU Tasks Trace grace-period kthread will eventually do this within check_all_holdout_tasks_trace(). But it is not a particularly important performance optimization because it only applies to the grace-period kthread, of which there is but one. This commit therefore removes this invocation of trc_del_holdout() in favor of the one in check_all_holdout_tasks_trace() in the grace-period kthread. Reported-by: "Xu, Yanfei" Signed-off-by: Paul E. McKenney --- kernel/rcu/tasks.h | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 3d5cb6cb8a6d..8536c55df514 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -982,7 +982,6 @@ static void trc_wait_for_one_reader(struct task_struct *t, // The current task had better be in a quiescent state. if (t == current) { t->trc_reader_checked = true; - trc_del_holdout(t); WARN_ON_ONCE(t->trc_reader_nesting); return; } From 2a2ed5618a0e8a890d948b88b368c0459f35136c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 4 Jul 2021 13:59:35 -0700 Subject: [PATCH 0141/1469] rcu: Fix pr_info() formats and values in show_rcu_gp_kthreads() This commit changes from "%lx" to "%x" and from "0x1ffffL" to "0x1ffff" to match the change in type between the old field ->state (unsigned long) and the new field ->__state (unsigned int). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_stall.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 3f937b20814f..6c76988cc019 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -795,9 +795,9 @@ void show_rcu_gp_kthreads(void) jr = j - data_race(rcu_state.gp_req_activity); js = j - data_race(rcu_state.gp_start); jw = j - data_race(rcu_state.gp_wake_time); - pr_info("%s: wait state: %s(%d) ->state: %#lx ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n", + pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n", rcu_state.name, gp_state_getname(rcu_state.gp_state), - rcu_state.gp_state, t ? t->__state : 0x1ffffL, t ? t->rt_priority : 0xffU, + rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU, js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq), (long)data_race(rcu_state.gp_seq), (long)data_race(rcu_get_root()->gp_seq_needed), From af0efa050caa66e8f304c42c94c76cb6c480cb7e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 6 Jul 2021 14:23:55 +0200 Subject: [PATCH 0142/1469] libbpf: Restore errno return for functions that were already returning it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The update to streamline libbpf error reporting intended to change all functions to return the errno as a negative return value if LIBBPF_STRICT_DIRECT_ERRS is set. However, if the flag is *not* set, the return value changes for the two functions that were already returning a negative errno unconditionally: bpf_link__unpin() and perf_buffer__poll(). This is a user-visible API change that breaks applications; so let's revert these two functions back to unconditionally returning a negative errno value. Fixes: e9fc3ce99b34 ("libbpf: Streamline error reporting for high-level APIs") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210706122355.236082-1-toke@redhat.com --- tools/lib/bpf/libbpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1e04ce724240..6f5e2757bb3c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -10136,7 +10136,7 @@ int bpf_link__unpin(struct bpf_link *link) err = unlink(link->pin_path); if (err != 0) - return libbpf_err_errno(err); + return -errno; pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path); zfree(&link->pin_path); @@ -11197,7 +11197,7 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); if (cnt < 0) - return libbpf_err_errno(cnt); + return -errno; for (i = 0; i < cnt; i++) { struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; From c9cd752d8f3a6b13afc5332a60bea3e68f141738 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 5 Jul 2021 15:34:41 +0200 Subject: [PATCH 0143/1469] regulator: fixed: Mark regulator-fixed-domain as deprecated A power domain should not be modelled as a regulator, not even for the simplest case as recent discussions have concluded around the existing regulator-fixed-domain DT binding. Fortunately, there is only one user of the binding that was recently added. Therefore, let's mark the binding as deprecated to prevent it from being further used. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20210705133441.11344-1-ulf.hansson@linaro.org Signed-off-by: Mark Brown --- .../devicetree/bindings/regulator/fixed-regulator.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index 8850c01bd470..9b131c6facbc 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -57,12 +57,14 @@ properties: maxItems: 1 power-domains: + deprecated: true description: Power domain to use for enable control. This binding is only available if the compatible is chosen to regulator-fixed-domain. maxItems: 1 required-opps: + deprecated: true description: Performance state to use for enable control. This binding is only available if the compatible is chosen to regulator-fixed-domain. The From ea986908ccfcc53204a03bb0841227e1b26578c4 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Fri, 2 Jul 2021 22:21:40 +0800 Subject: [PATCH 0144/1469] regulator: mtk-dvfsrc: Fix wrong dev pointer for devm_regulator_register If use dev->parent, the regulator_unregister will not be called when this driver is unloaded. Fix it by using dev instead. Signed-off-by: Axel Lin Link: https://lore.kernel.org/r/20210702142140.2678130-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- drivers/regulator/mtk-dvfsrc-regulator.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/regulator/mtk-dvfsrc-regulator.c b/drivers/regulator/mtk-dvfsrc-regulator.c index d3d876198d6e..234af3a66c77 100644 --- a/drivers/regulator/mtk-dvfsrc-regulator.c +++ b/drivers/regulator/mtk-dvfsrc-regulator.c @@ -179,8 +179,7 @@ static int dvfsrc_vcore_regulator_probe(struct platform_device *pdev) for (i = 0; i < regulator_init_data->size; i++) { config.dev = dev->parent; config.driver_data = (mt_regulators + i); - rdev = devm_regulator_register(dev->parent, - &(mt_regulators + i)->desc, + rdev = devm_regulator_register(dev, &(mt_regulators + i)->desc, &config); if (IS_ERR(rdev)) { dev_err(dev, "failed to register %s\n", From 135cbd378eab336da15de9c84bbb22bf743b38a5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 3 Jul 2021 04:23:00 +0200 Subject: [PATCH 0145/1469] spi: imx: mx51-ecspi: Reinstate low-speed CONFIGREG delay MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since 00b80ac935539 ("spi: imx: mx51-ecspi: Move some initialisation to prepare_message hook."), the MX51_ECSPI_CONFIG write no longer happens in prepare_transfer hook, but rather in prepare_message hook, however the MX51_ECSPI_CONFIG delay is still left in prepare_transfer hook and thus has no effect. This leads to low bus frequency operation problems described in 6fd8b8503a0dc ("spi: spi-imx: Fix out-of-order CS/SCLK operation at low speeds") again. Move the MX51_ECSPI_CONFIG write delay into the prepare_message hook as well, thus reinstating the low bus frequency fix. Fixes: 00b80ac935539 ("spi: imx: mx51-ecspi: Move some initialisation to prepare_message hook.") Signed-off-by: Marek Vasut Cc: Uwe Kleine-König Cc: Mark Brown Link: https://lore.kernel.org/r/20210703022300.296114-1-marex@denx.de Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 39dc02e366f4..4aee3db6d6df 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -506,7 +506,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, { struct spi_device *spi = msg->spi; u32 ctrl = MX51_ECSPI_CTRL_ENABLE; - u32 testreg; + u32 testreg, delay; u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG); /* set Master or Slave mode */ @@ -567,6 +567,23 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG); + /* + * Wait until the changes in the configuration register CONFIGREG + * propagate into the hardware. It takes exactly one tick of the + * SCLK clock, but we will wait two SCLK clock just to be sure. The + * effect of the delay it takes for the hardware to apply changes + * is noticable if the SCLK clock run very slow. In such a case, if + * the polarity of SCLK should be inverted, the GPIO ChipSelect might + * be asserted before the SCLK polarity changes, which would disrupt + * the SPI communication as the device on the other end would consider + * the change of SCLK polarity as a clock tick already. + */ + delay = (2 * 1000000) / spi_imx->spi_bus_clk; + if (likely(delay < 10)) /* SCLK is faster than 100 kHz */ + udelay(delay); + else /* SCLK is _very_ slow */ + usleep_range(delay, delay + 10); + return 0; } @@ -574,7 +591,7 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, struct spi_device *spi) { u32 ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL); - u32 clk, delay; + u32 clk; /* Clear BL field and set the right value */ ctrl &= ~MX51_ECSPI_CTRL_BL_MASK; @@ -596,23 +613,6 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL); - /* - * Wait until the changes in the configuration register CONFIGREG - * propagate into the hardware. It takes exactly one tick of the - * SCLK clock, but we will wait two SCLK clock just to be sure. The - * effect of the delay it takes for the hardware to apply changes - * is noticable if the SCLK clock run very slow. In such a case, if - * the polarity of SCLK should be inverted, the GPIO ChipSelect might - * be asserted before the SCLK polarity changes, which would disrupt - * the SPI communication as the device on the other end would consider - * the change of SCLK polarity as a clock tick already. - */ - delay = (2 * 1000000) / clk; - if (likely(delay < 10)) /* SCLK is faster than 100 kHz */ - udelay(delay); - else /* SCLK is _very_ slow */ - usleep_range(delay, delay + 10); - return 0; } From e9faf53c5a5d01f6f2a09ae28ec63a3bbd6f64fd Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Mon, 5 Jul 2021 21:13:20 +0800 Subject: [PATCH 0146/1469] ieee802154: hwsim: fix GPF in hwsim_set_edge_lqi Both MAC802154_HWSIM_ATTR_RADIO_ID and MAC802154_HWSIM_ATTR_RADIO_EDGE, MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID and MAC802154_HWSIM_EDGE_ATTR_LQI must be present to fix GPF. Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb") Signed-off-by: Dongliang Mu Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20210705131321.217111-1-mudongliangabcd@gmail.com Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index ebc976b7fcc2..cae52bfb871e 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -528,14 +528,14 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) u32 v0, v1; u8 lqi; - if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] && + if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; - if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] && + if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] || !edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI]) return -EINVAL; From d322957ebfb9c21c2c72b66680f7c3ccd724e081 Mon Sep 17 00:00:00 2001 From: Duncan Roe Date: Wed, 7 Jul 2021 10:57:51 +1000 Subject: [PATCH 0147/1469] netfilter: uapi: refer to nfnetlink_conntrack.h, not nf_conntrack_netlink.h nf_conntrack_netlink.h does not exist, refer to nfnetlink_conntrack.h instead. Signed-off-by: Duncan Roe Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_log.h | 2 +- include/uapi/linux/netfilter/nfnetlink_queue.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index 45c8d3b027e0..0af9c113d665 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -61,7 +61,7 @@ enum nfulnl_attr_type { NFULA_HWTYPE, /* hardware type */ NFULA_HWHEADER, /* hardware header */ NFULA_HWLEN, /* hardware header length */ - NFULA_CT, /* nf_conntrack_netlink.h */ + NFULA_CT, /* nfnetlink_conntrack.h */ NFULA_CT_INFO, /* enum ip_conntrack_info */ NFULA_VLAN, /* nested attribute: packet vlan info */ NFULA_L2HDR, /* full L2 header */ diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index bcb2cb5d40b9..aed90c4df0c8 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -51,11 +51,11 @@ enum nfqnl_attr_type { NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */ NFQA_HWADDR, /* nfqnl_msg_packet_hw */ NFQA_PAYLOAD, /* opaque data payload */ - NFQA_CT, /* nf_conntrack_netlink.h */ + NFQA_CT, /* nfnetlink_conntrack.h */ NFQA_CT_INFO, /* enum ip_conntrack_info */ NFQA_CAP_LEN, /* __u32 length of captured packet */ NFQA_SKB_INFO, /* __u32 skb meta information */ - NFQA_EXP, /* nf_conntrack_netlink.h */ + NFQA_EXP, /* nfnetlink_conntrack.h */ NFQA_UID, /* __u32 sk uid */ NFQA_GID, /* __u32 sk gid */ NFQA_SECCTX, /* security context string */ From 54afaae34ee49e98c1c902b444b42832551d090c Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 23 Jun 2021 17:54:54 +0200 Subject: [PATCH 0148/1469] btrfs: zoned: fix types for u64 division in btrfs_reclaim_bgs_work The types in calculation of the used percentage in the reclaiming messages are both u64, though bg->length is either 1GiB (non-zoned) or the zone size in the zoned mode. The upper limit on zone size is 8GiB so this could theoretically overflow in the future, right now the values fit. Fixes: 18bb8bbf13c1 ("btrfs: zoned: automatically reclaim zones") CC: stable@vger.kernel.org # 5.13 Reviewed-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 38b127b9edfc..d4c8dc550889 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1540,7 +1540,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used", - bg->start, div_u64(bg->used * 100, bg->length)); + bg->start, div64_u64(bg->used * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); if (ret) From 5f93e776c6734cea989aeb4f2d6c97e521baa683 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 29 Jun 2021 03:16:46 +0900 Subject: [PATCH 0149/1469] btrfs: zoned: print unusable percentage when reclaiming block groups When we're automatically reclaiming a zone, because its zone_unusable value is above the reclaim threshold, we're only logging how much percent of the zone's capacity are used, but not how much of the capacity is unusable. Also print the percentage of the unusable space in the block group before we're reclaiming it. Example: BTRFS info (device sdg): reclaiming chunk 230686720 with 13% used 86% unusable CC: stable@vger.kernel.org # 5.13 Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d4c8dc550889..fec7a34b27f3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1501,6 +1501,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) mutex_lock(&fs_info->reclaim_bgs_lock); spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->reclaim_bgs)) { + u64 zone_unusable; int ret = 0; bg = list_first_entry(&fs_info->reclaim_bgs, @@ -1534,13 +1535,22 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; } + /* + * Cache the zone_unusable value before turning the block group + * to read only. As soon as the blog group is read only it's + * zone_unusable value gets moved to the block group's read-only + * bytes and isn't available for calculations anymore. + */ + zone_unusable = bg->zone_unusable; ret = inc_block_group_ro(bg, 0); up_write(&space_info->groups_sem); if (ret < 0) goto next; - btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used", - bg->start, div64_u64(bg->used * 100, bg->length)); + btrfs_info(fs_info, + "reclaiming chunk %llu with %llu%% used %llu%% unusable", + bg->start, div_u64(bg->used * 100, bg->length), + div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); if (ret) From 1cb3db1cf383a3c7dbda1aa0ce748b0958759947 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Jun 2021 14:43:05 +0100 Subject: [PATCH 0150/1469] btrfs: fix deadlock with concurrent chunk allocations involving system chunks When a task attempting to allocate a new chunk verifies that there is not currently enough free space in the system space_info and there is another task that allocated a new system chunk but it did not finish yet the creation of the respective block group, it waits for that other task to finish creating the block group. This is to avoid exhaustion of the system chunk array in the superblock, which is limited, when we have a thundering herd of tasks allocating new chunks. This problem was described and fixed by commit eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations"). However there are two very similar scenarios where this can lead to a deadlock: 1) Task B allocated a new system chunk and task A is waiting on task B to finish creation of the respective system block group. However before task B ends its transaction handle and finishes the creation of the system block group, it attempts to allocate another chunk (like a data chunk for an fallocate operation for a very large range). Task B will be unable to progress and allocate the new chunk, because task A set space_info->chunk_alloc to 1 and therefore it loops at btrfs_chunk_alloc() waiting for task A to finish its chunk allocation and set space_info->chunk_alloc to 0, but task A is waiting on task B to finish creation of the new system block group, therefore resulting in a deadlock; 2) Task B allocated a new system chunk and task A is waiting on task B to finish creation of the respective system block group. By the time that task B enter the final phase of block group allocation, which happens at btrfs_create_pending_block_groups(), when it modifies the extent tree, the device tree or the chunk tree to insert the items for some new block group, it needs to allocate a new chunk, so it ends up at btrfs_chunk_alloc() and keeps looping there because task A has set space_info->chunk_alloc to 1, but task A is waiting for task B to finish creation of the new system block group and release the reserved system space, therefore resulting in a deadlock. In short, the problem is if a task B needs to allocate a new chunk after it previously allocated a new system chunk and if another task A is currently waiting for task B to complete the allocation of the new system chunk. Unfortunately this deadlock scenario introduced by the previous fix for the system chunk array exhaustion problem does not have a simple and short fix, and requires a big change to rework the chunk allocation code so that chunk btree updates are all made in the first phase of chunk allocation. And since this deadlock regression is being frequently hit on zoned filesystems and the system chunk array exhaustion problem is triggered in more extreme cases (originally observed on PowerPC with a node size of 64K when running the fallocate tests from stress-ng), revert the changes from that commit. The next patch in the series, with a subject of "btrfs: rework chunk allocation to avoid exhaustion of the system chunk array" does the necessary changes to fix the system chunk array exhaustion problem. Reported-by: Naohiro Aota Link: https://lore.kernel.org/linux-btrfs/20210621015922.ewgbffxuawia7liz@naota-xeon/ Fixes: eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations") CC: stable@vger.kernel.org # 5.12+ Tested-by: Shin'ichiro Kawasaki Tested-by: Naohiro Aota Signed-off-by: Filipe Manana Tested-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 58 +----------------------------------------- fs/btrfs/transaction.c | 5 ---- fs/btrfs/transaction.h | 7 ----- 3 files changed, 1 insertion(+), 69 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index fec7a34b27f3..a26209f98279 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3377,7 +3377,6 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type) */ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) { - struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *info; u64 left; @@ -3392,7 +3391,6 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) lockdep_assert_held(&fs_info->chunk_mutex); info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); -again: spin_lock(&info->lock); left = info->total_bytes - btrfs_space_info_used(info, true); spin_unlock(&info->lock); @@ -3411,58 +3409,6 @@ again: if (left < thresh) { u64 flags = btrfs_system_alloc_profile(fs_info); - u64 reserved = atomic64_read(&cur_trans->chunk_bytes_reserved); - - /* - * If there's not available space for the chunk tree (system - * space) and there are other tasks that reserved space for - * creating a new system block group, wait for them to complete - * the creation of their system block group and release excess - * reserved space. We do this because: - * - * *) We can end up allocating more system chunks than necessary - * when there are multiple tasks that are concurrently - * allocating block groups, which can lead to exhaustion of - * the system array in the superblock; - * - * *) If we allocate extra and unnecessary system block groups, - * despite being empty for a long time, and possibly forever, - * they end not being added to the list of unused block groups - * because that typically happens only when deallocating the - * last extent from a block group - which never happens since - * we never allocate from them in the first place. The few - * exceptions are when mounting a filesystem or running scrub, - * which add unused block groups to the list of unused block - * groups, to be deleted by the cleaner kthread. - * And even when they are added to the list of unused block - * groups, it can take a long time until they get deleted, - * since the cleaner kthread might be sleeping or busy with - * other work (deleting subvolumes, running delayed iputs, - * defrag scheduling, etc); - * - * This is rare in practice, but can happen when too many tasks - * are allocating blocks groups in parallel (via fallocate()) - * and before the one that reserved space for a new system block - * group finishes the block group creation and releases the space - * reserved in excess (at btrfs_create_pending_block_groups()), - * other tasks end up here and see free system space temporarily - * not enough for updating the chunk tree. - * - * We unlock the chunk mutex before waiting for such tasks and - * lock it again after the wait, otherwise we would deadlock. - * It is safe to do so because allocating a system chunk is the - * first thing done while allocating a new block group. - */ - if (reserved > trans->chunk_bytes_reserved) { - const u64 min_needed = reserved - thresh; - - mutex_unlock(&fs_info->chunk_mutex); - wait_event(cur_trans->chunk_reserve_wait, - atomic64_read(&cur_trans->chunk_bytes_reserved) <= - min_needed); - mutex_lock(&fs_info->chunk_mutex); - goto again; - } /* * Ignore failure to create system chunk. We might end up not @@ -3477,10 +3423,8 @@ again: ret = btrfs_block_rsv_add(fs_info->chunk_root, &fs_info->chunk_block_rsv, thresh, BTRFS_RESERVE_NO_FLUSH); - if (!ret) { - atomic64_add(thresh, &cur_trans->chunk_bytes_reserved); + if (!ret) trans->chunk_bytes_reserved += thresh; - } } } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 50318231c1a8..443c348bc6f3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -260,7 +260,6 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans) void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_transaction *cur_trans = trans->transaction; if (!trans->chunk_bytes_reserved) return; @@ -269,8 +268,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv, trans->chunk_bytes_reserved, NULL); - atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved); - cond_wake_up(&cur_trans->chunk_reserve_wait); trans->chunk_bytes_reserved = 0; } @@ -386,8 +383,6 @@ loop: spin_lock_init(&cur_trans->dropped_roots_lock); INIT_LIST_HEAD(&cur_trans->releasing_ebs); spin_lock_init(&cur_trans->releasing_ebs_lock); - atomic64_set(&cur_trans->chunk_bytes_reserved, 0); - init_waitqueue_head(&cur_trans->chunk_reserve_wait); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 07d76029f598..a18d67796b54 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -96,13 +96,6 @@ struct btrfs_transaction { spinlock_t releasing_ebs_lock; struct list_head releasing_ebs; - - /* - * The number of bytes currently reserved, by all transaction handles - * attached to this transaction, for metadata extents of the chunk tree. - */ - atomic64_t chunk_bytes_reserved; - wait_queue_head_t chunk_reserve_wait; }; #define __TRANS_FREEZABLE (1U << 0) From 79bd37120b149532af5b21953643ed74af69654f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Jun 2021 14:43:06 +0100 Subject: [PATCH 0151/1469] btrfs: rework chunk allocation to avoid exhaustion of the system chunk array Commit eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations") fixed a problem that resulted in exhausting the system chunk array in the superblock when there are many tasks allocating chunks in parallel. Basically too many tasks enter the first phase of chunk allocation without previous tasks having finished their second phase of allocation, resulting in too many system chunks being allocated. That was originally observed when running the fallocate tests of stress-ng on a PowerPC machine, using a node size of 64K. However that commit also introduced a deadlock where a task in phase 1 of the chunk allocation waited for another task that had allocated a system chunk to finish its phase 2, but that other task was waiting on an extent buffer lock held by the first task, therefore resulting in both tasks not making any progress. That change was later reverted by a patch with the subject "btrfs: fix deadlock with concurrent chunk allocations involving system chunks", since there is no simple and short solution to address it and the deadlock is relatively easy to trigger on zoned filesystems, while the system chunk array exhaustion is not so common. This change reworks the chunk allocation to avoid the system chunk array exhaustion. It accomplishes that by making the first phase of chunk allocation do the updates of the device items in the chunk btree and the insertion of the new chunk item in the chunk btree. This is done while under the protection of the chunk mutex (fs_info->chunk_mutex), in the same critical section that checks for available system space, allocates a new system chunk if needed and reserves system chunk space. This way we do not have chunk space reserved until the second phase completes. The same logic is applied to chunk removal as well, since it keeps reserved system space long after it is done updating the chunk btree. For direct allocation of system chunks, the previous behaviour remains, because otherwise we would deadlock on extent buffers of the chunk btree. Changes to the chunk btree are by large done by chunk allocation and chunk removal, which first reserve chunk system space and then later do changes to the chunk btree. The other remaining cases are uncommon and correspond to adding a device, removing a device and resizing a device. All these other cases do not pre-reserve system space, they modify the chunk btree right away, so they don't hold reserved space for a long period like chunk allocation and chunk removal do. The diff of this change is huge, but more than half of it is just addition of comments describing both how things work regarding chunk allocation and removal, including both the new behavior and the parts of the old behavior that did not change. CC: stable@vger.kernel.org # 5.12+ Tested-by: Shin'ichiro Kawasaki Tested-by: Naohiro Aota Signed-off-by: Filipe Manana Tested-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 285 ++++++++++++++++++++++++++++---- fs/btrfs/block-group.h | 6 +- fs/btrfs/ctree.c | 67 ++------ fs/btrfs/transaction.c | 10 +- fs/btrfs/transaction.h | 2 +- fs/btrfs/volumes.c | 361 +++++++++++++++++++++++++++++++---------- fs/btrfs/volumes.h | 5 +- 7 files changed, 549 insertions(+), 187 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a26209f98279..c557327b4545 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2207,6 +2207,13 @@ error: return ret; } +/* + * This function, insert_block_group_item(), belongs to the phase 2 of chunk + * allocation. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ static int insert_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { @@ -2229,15 +2236,19 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans, return btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi)); } +/* + * This function, btrfs_create_pending_block_groups(), belongs to the phase 2 of + * chunk allocation. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *block_group; int ret = 0; - if (!trans->can_flush_pending_bgs) - return; - while (!list_empty(&trans->new_bgs)) { int index; @@ -2252,6 +2263,13 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) ret = insert_block_group_item(trans, block_group); if (ret) btrfs_abort_transaction(trans, ret); + if (!block_group->chunk_item_inserted) { + mutex_lock(&fs_info->chunk_mutex); + ret = btrfs_chunk_alloc_add_chunk_item(trans, block_group); + mutex_unlock(&fs_info->chunk_mutex); + if (ret) + btrfs_abort_transaction(trans, ret); + } ret = btrfs_finish_chunk_alloc(trans, block_group->start, block_group->length); if (ret) @@ -2275,8 +2293,9 @@ next: btrfs_trans_release_chunk_metadata(trans); } -int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, - u64 type, u64 chunk_offset, u64 size) +struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, + u64 bytes_used, u64 type, + u64 chunk_offset, u64 size) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache; @@ -2286,7 +2305,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache = btrfs_create_block_group_cache(fs_info, chunk_offset); if (!cache) - return -ENOMEM; + return ERR_PTR(-ENOMEM); cache->length = size; set_free_space_tree_thresholds(cache); @@ -2300,7 +2319,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, ret = btrfs_load_block_group_zone_info(cache, true); if (ret) { btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } ret = exclude_super_stripes(cache); @@ -2308,7 +2327,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, /* We may have excluded something, so call this just in case */ btrfs_free_excluded_extents(cache); btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } add_new_free_space(cache, chunk_offset, chunk_offset + size); @@ -2335,7 +2354,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, if (ret) { btrfs_remove_free_space_cache(cache); btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } /* @@ -2354,7 +2373,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, btrfs_update_delayed_refs_rsv(trans); set_avail_alloc_bits(fs_info, type); - return 0; + return cache; } /* @@ -3232,11 +3251,203 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } +static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +{ + struct btrfs_block_group *bg; + int ret; + + /* + * Check if we have enough space in the system space info because we + * will need to update device items in the chunk btree and insert a new + * chunk item in the chunk btree as well. This will allocate a new + * system block group if needed. + */ + check_system_chunk(trans, flags); + + bg = btrfs_alloc_chunk(trans, flags); + if (IS_ERR(bg)) { + ret = PTR_ERR(bg); + goto out; + } + + /* + * If this is a system chunk allocation then stop right here and do not + * add the chunk item to the chunk btree. This is to prevent a deadlock + * because this system chunk allocation can be triggered while COWing + * some extent buffer of the chunk btree and while holding a lock on a + * parent extent buffer, in which case attempting to insert the chunk + * item (or update the device item) would result in a deadlock on that + * parent extent buffer. In this case defer the chunk btree updates to + * the second phase of chunk allocation and keep our reservation until + * the second phase completes. + * + * This is a rare case and can only be triggered by the very few cases + * we have where we need to touch the chunk btree outside chunk allocation + * and chunk removal. These cases are basically adding a device, removing + * a device or resizing a device. + */ + if (flags & BTRFS_BLOCK_GROUP_SYSTEM) + return 0; + + ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); + /* + * Normally we are not expected to fail with -ENOSPC here, since we have + * previously reserved space in the system space_info and allocated one + * new system chunk if necessary. However there are two exceptions: + * + * 1) We may have enough free space in the system space_info but all the + * existing system block groups have a profile which can not be used + * for extent allocation. + * + * This happens when mounting in degraded mode. For example we have a + * RAID1 filesystem with 2 devices, lose one device and mount the fs + * using the other device in degraded mode. If we then allocate a chunk, + * we may have enough free space in the existing system space_info, but + * none of the block groups can be used for extent allocation since they + * have a RAID1 profile, and because we are in degraded mode with a + * single device, we are forced to allocate a new system chunk with a + * SINGLE profile. Making check_system_chunk() iterate over all system + * block groups and check if they have a usable profile and enough space + * can be slow on very large filesystems, so we tolerate the -ENOSPC and + * try again after forcing allocation of a new system chunk. Like this + * we avoid paying the cost of that search in normal circumstances, when + * we were not mounted in degraded mode; + * + * 2) We had enough free space info the system space_info, and one suitable + * block group to allocate from when we called check_system_chunk() + * above. However right after we called it, the only system block group + * with enough free space got turned into RO mode by a running scrub, + * and in this case we have to allocate a new one and retry. We only + * need do this allocate and retry once, since we have a transaction + * handle and scrub uses the commit root to search for block groups. + */ + if (ret == -ENOSPC) { + const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info); + struct btrfs_block_group *sys_bg; + + sys_bg = btrfs_alloc_chunk(trans, sys_flags); + if (IS_ERR(sys_bg)) { + ret = PTR_ERR(sys_bg); + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + } else if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } +out: + btrfs_trans_release_chunk_metadata(trans); + + return ret; +} + /* - * If force is CHUNK_ALLOC_FORCE: + * Chunk allocation is done in 2 phases: + * + * 1) Phase 1 - through btrfs_chunk_alloc() we allocate device extents for + * the chunk, the chunk mapping, create its block group and add the items + * that belong in the chunk btree to it - more specifically, we need to + * update device items in the chunk btree and add a new chunk item to it. + * + * 2) Phase 2 - through btrfs_create_pending_block_groups(), we add the block + * group item to the extent btree and the device extent items to the devices + * btree. + * + * This is done to prevent deadlocks. For example when COWing a node from the + * extent btree we are holding a write lock on the node's parent and if we + * trigger chunk allocation and attempted to insert the new block group item + * in the extent btree right way, we could deadlock because the path for the + * insertion can include that parent node. At first glance it seems impossible + * to trigger chunk allocation after starting a transaction since tasks should + * reserve enough transaction units (metadata space), however while that is true + * most of the time, chunk allocation may still be triggered for several reasons: + * + * 1) When reserving metadata, we check if there is enough free space in the + * metadata space_info and therefore don't trigger allocation of a new chunk. + * However later when the task actually tries to COW an extent buffer from + * the extent btree or from the device btree for example, it is forced to + * allocate a new block group (chunk) because the only one that had enough + * free space was just turned to RO mode by a running scrub for example (or + * device replace, block group reclaim thread, etc), so we can not use it + * for allocating an extent and end up being forced to allocate a new one; + * + * 2) Because we only check that the metadata space_info has enough free bytes, + * we end up not allocating a new metadata chunk in that case. However if + * the filesystem was mounted in degraded mode, none of the existing block + * groups might be suitable for extent allocation due to their incompatible + * profile (for e.g. mounting a 2 devices filesystem, where all block groups + * use a RAID1 profile, in degraded mode using a single device). In this case + * when the task attempts to COW some extent buffer of the extent btree for + * example, it will trigger allocation of a new metadata block group with a + * suitable profile (SINGLE profile in the example of the degraded mount of + * the RAID1 filesystem); + * + * 3) The task has reserved enough transaction units / metadata space, but when + * it attempts to COW an extent buffer from the extent or device btree for + * example, it does not find any free extent in any metadata block group, + * therefore forced to try to allocate a new metadata block group. + * This is because some other task allocated all available extents in the + * meanwhile - this typically happens with tasks that don't reserve space + * properly, either intentionally or as a bug. One example where this is + * done intentionally is fsync, as it does not reserve any transaction units + * and ends up allocating a variable number of metadata extents for log + * tree extent buffers. + * + * We also need this 2 phases setup when adding a device to a filesystem with + * a seed device - we must create new metadata and system chunks without adding + * any of the block group items to the chunk, extent and device btrees. If we + * did not do it this way, we would get ENOSPC when attempting to update those + * btrees, since all the chunks from the seed device are read-only. + * + * Phase 1 does the updates and insertions to the chunk btree because if we had + * it done in phase 2 and have a thundering herd of tasks allocating chunks in + * parallel, we risk having too many system chunks allocated by many tasks if + * many tasks reach phase 1 without the previous ones completing phase 2. In the + * extreme case this leads to exhaustion of the system chunk array in the + * superblock. This is easier to trigger if using a btree node/leaf size of 64K + * and with RAID filesystems (so we have more device items in the chunk btree). + * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of + * the system chunk array due to concurrent allocations") provides more details. + * + * For allocation of system chunks, we defer the updates and insertions into the + * chunk btree to phase 2. This is to prevent deadlocks on extent buffers because + * if the chunk allocation is triggered while COWing an extent buffer of the + * chunk btree, we are holding a lock on the parent of that extent buffer and + * doing the chunk btree updates and insertions can require locking that parent. + * This is for the very few and rare cases where we update the chunk btree that + * are not chunk allocation or chunk removal: adding a device, removing a device + * or resizing a device. + * + * The reservation of system space, done through check_system_chunk(), as well + * as all the updates and insertions into the chunk btree must be done while + * holding fs_info->chunk_mutex. This is important to guarantee that while COWing + * an extent buffer from the chunks btree we never trigger allocation of a new + * system chunk, which would result in a deadlock (trying to lock twice an + * extent buffer of the chunk btree, first time before triggering the chunk + * allocation and the second time during chunk allocation while attempting to + * update the chunks btree). The system chunk array is also updated while holding + * that mutex. The same logic applies to removing chunks - we must reserve system + * space, update the chunk btree and the system chunk array in the superblock + * while holding fs_info->chunk_mutex. + * + * This function, btrfs_chunk_alloc(), belongs to phase 1. + * + * If @force is CHUNK_ALLOC_FORCE: * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. - * If force is NOT CHUNK_ALLOC_FORCE: + * If @force is NOT CHUNK_ALLOC_FORCE: * - return 0 if it doesn't need to allocate a new chunk, * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. @@ -3253,6 +3464,13 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; + /* + * If we are removing a chunk, don't re-enter or we would deadlock. + * System space reservation and system chunk allocation is done by the + * chunk remove operation (btrfs_remove_chunk()). + */ + if (trans->removing_chunk) + return -ENOSPC; space_info = btrfs_find_space_info(fs_info, flags); ASSERT(space_info); @@ -3316,13 +3534,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - /* - * Check if we have enough space in SYSTEM chunk because we may need - * to update devices. - */ - check_system_chunk(trans, flags); - - ret = btrfs_alloc_chunk(trans, flags); + ret = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; spin_lock(&space_info->lock); @@ -3341,22 +3553,6 @@ out: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); - /* - * When we allocate a new chunk we reserve space in the chunk block - * reserve to make sure we can COW nodes/leafs in the chunk tree or - * add new nodes/leafs to it if we end up needing to do it when - * inserting the chunk item and updating device items as part of the - * second phase of chunk allocation, performed by - * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a - * large number of new block groups to create in our transaction - * handle's new_bgs list to avoid exhausting the chunk block reserve - * in extreme cases - like having a single transaction create many new - * block groups when starting to write out the free space caches of all - * the block groups that were made dirty during the lifetime of the - * transaction. - */ - if (trans->chunk_bytes_reserved >= (u64)SZ_2M) - btrfs_create_pending_block_groups(trans); return ret; } @@ -3409,14 +3605,31 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) if (left < thresh) { u64 flags = btrfs_system_alloc_profile(fs_info); + struct btrfs_block_group *bg; /* * Ignore failure to create system chunk. We might end up not * needing it, as we might not need to COW all nodes/leafs from * the paths we visit in the chunk tree (they were already COWed * or created in the current transaction for example). + * + * Also, if our caller is allocating a system chunk, do not + * attempt to insert the chunk item in the chunk btree, as we + * could deadlock on an extent buffer since our caller may be + * COWing an extent buffer from the chunk btree. */ - ret = btrfs_alloc_chunk(trans, flags); + bg = btrfs_alloc_chunk(trans, flags); + if (IS_ERR(bg)) { + ret = PTR_ERR(bg); + } else if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) { + /* + * If we fail to add the chunk item here, we end up + * trying again at phase 2 of chunk allocation, at + * btrfs_create_pending_block_groups(). So ignore + * any error here. + */ + btrfs_chunk_alloc_add_chunk_item(trans, bg); + } } if (!ret) { diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 7b927425dc71..c72a71efcb18 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -97,6 +97,7 @@ struct btrfs_block_group { unsigned int removed:1; unsigned int to_copy:1; unsigned int relocating_repair:1; + unsigned int chunk_item_inserted:1; int disk_cache_state; @@ -268,8 +269,9 @@ void btrfs_reclaim_bgs_work(struct work_struct *work); void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info); void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg); int btrfs_read_block_groups(struct btrfs_fs_info *info); -int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, - u64 type, u64 chunk_offset, u64 size); +struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, + u64 bytes_used, u64 type, + u64 chunk_offset, u64 size); void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans); int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, bool do_chunk_alloc); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 4bc3ca2cbd7d..c5c08c87e130 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -364,49 +364,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } -static struct extent_buffer *alloc_tree_block_no_bg_flush( - struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 parent_start, - const struct btrfs_disk_key *disk_key, - int level, - u64 hint, - u64 empty_size, - enum btrfs_lock_nesting nest) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct extent_buffer *ret; - - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - * For similar reasons, we also need to delay flushing pending block - * groups when splitting a leaf or node, from one of those trees, since - * we are holding a write lock on it and its parent or when inserting a - * new root node for one of those trees. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - ret = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, disk_key, level, - hint, empty_size, nest); - trans->can_flush_pending_bgs = true; - - return ret; -} - /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -455,8 +412,9 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, - level, search_start, empty_size, nest); + cow = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, &disk_key, level, + search_start, empty_size, nest); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -2458,9 +2416,9 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, - root->node->start, 0, - BTRFS_NESTING_NEW_ROOT); + c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &lower_key, level, root->node->start, 0, + BTRFS_NESTING_NEW_ROOT); if (IS_ERR(c)) return PTR_ERR(c); @@ -2589,8 +2547,9 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, - c->start, 0, BTRFS_NESTING_SPLIT); + split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &disk_key, level, c->start, 0, + BTRFS_NESTING_SPLIT); if (IS_ERR(split)) return PTR_ERR(split); @@ -3381,10 +3340,10 @@ again: * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just * use BTRFS_NESTING_NEW_ROOT. */ - right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, - l->start, 0, num_doubles ? - BTRFS_NESTING_NEW_ROOT : - BTRFS_NESTING_SPLIT); + right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &disk_key, 0, l->start, 0, + num_doubles ? BTRFS_NESTING_NEW_ROOT : + BTRFS_NESTING_SPLIT); if (IS_ERR(right)) return PTR_ERR(right); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 443c348bc6f3..14b9fdc8aaa9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -254,8 +254,11 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans) } /* - * To be called after all the new block groups attached to the transaction - * handle have been created (btrfs_create_pending_block_groups()). + * To be called after doing the chunk btree updates right after allocating a new + * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a + * chunk after all chunk btree updates and after finishing the second phase of + * chunk allocation (btrfs_create_pending_block_groups()) in case some block + * group had its chunk item insertion delayed to the second phase. */ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) { @@ -264,8 +267,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) if (!trans->chunk_bytes_reserved) return; - WARN_ON_ONCE(!list_empty(&trans->new_bgs)); - btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv, trans->chunk_bytes_reserved, NULL); trans->chunk_bytes_reserved = 0; @@ -696,7 +697,6 @@ again: h->fs_info = root->fs_info; h->type = type; - h->can_flush_pending_bgs = true; INIT_LIST_HEAD(&h->new_bgs); smp_mb(); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index a18d67796b54..ba45065f9451 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -132,7 +132,7 @@ struct btrfs_trans_handle { short aborted; bool adding_csums; bool allocating_chunk; - bool can_flush_pending_bgs; + bool removing_chunk; bool reloc_reserved; bool in_fsync; struct btrfs_root *root; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 782e16795bc4..c6c14315b1c9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1745,19 +1745,14 @@ again: extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); } else { - btrfs_handle_fs_error(fs_info, ret, "Slot search failed"); goto out; } *dev_extent_len = btrfs_dev_extent_length(leaf, extent); ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_handle_fs_error(fs_info, ret, - "Failed to remove dev extent item"); - } else { + if (ret == 0) set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags); - } out: btrfs_free_path(path); return ret; @@ -2942,7 +2937,7 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) u32 cur; struct btrfs_key key; - mutex_lock(&fs_info->chunk_mutex); + lockdep_assert_held(&fs_info->chunk_mutex); array_size = btrfs_super_sys_array_size(super_copy); ptr = super_copy->sys_chunk_array; @@ -2972,7 +2967,6 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) cur += len; } } - mutex_unlock(&fs_info->chunk_mutex); return ret; } @@ -3012,6 +3006,29 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, return em; } +static int remove_chunk_item(struct btrfs_trans_handle *trans, + struct map_lookup *map, u64 chunk_offset) +{ + int i; + + /* + * Removing chunk items and updating the device items in the chunks btree + * requires holding the chunk_mutex. + * See the comment at btrfs_chunk_alloc() for the details. + */ + lockdep_assert_held(&trans->fs_info->chunk_mutex); + + for (i = 0; i < map->num_stripes; i++) { + int ret; + + ret = btrfs_update_device(trans, map->stripes[i].dev); + if (ret) + return ret; + } + + return btrfs_free_chunk(trans, chunk_offset); +} + int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -3032,14 +3049,16 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) return PTR_ERR(em); } map = em->map_lookup; - mutex_lock(&fs_info->chunk_mutex); - check_system_chunk(trans, map->type); - mutex_unlock(&fs_info->chunk_mutex); /* - * Take the device list mutex to prevent races with the final phase of - * a device replace operation that replaces the device object associated - * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()). + * First delete the device extent items from the devices btree. + * We take the device_list_mutex to avoid racing with the finishing phase + * of a device replace operation. See the comment below before acquiring + * fs_info->chunk_mutex. Note that here we do not acquire the chunk_mutex + * because that can result in a deadlock when deleting the device extent + * items from the devices btree - COWing an extent buffer from the btree + * may result in allocating a new metadata chunk, which would attempt to + * lock again fs_info->chunk_mutex. */ mutex_lock(&fs_devices->device_list_mutex); for (i = 0; i < map->num_stripes; i++) { @@ -3061,18 +3080,73 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) btrfs_clear_space_info_full(fs_info); mutex_unlock(&fs_info->chunk_mutex); } - - ret = btrfs_update_device(trans, device); - if (ret) { - mutex_unlock(&fs_devices->device_list_mutex); - btrfs_abort_transaction(trans, ret); - goto out; - } } mutex_unlock(&fs_devices->device_list_mutex); - ret = btrfs_free_chunk(trans, chunk_offset); - if (ret) { + /* + * We acquire fs_info->chunk_mutex for 2 reasons: + * + * 1) Just like with the first phase of the chunk allocation, we must + * reserve system space, do all chunk btree updates and deletions, and + * update the system chunk array in the superblock while holding this + * mutex. This is for similar reasons as explained on the comment at + * the top of btrfs_chunk_alloc(); + * + * 2) Prevent races with the final phase of a device replace operation + * that replaces the device object associated with the map's stripes, + * because the device object's id can change at any time during that + * final phase of the device replace operation + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of + * BTRFS_DEV_REPLACE_DEVID, which would cause a failure when updating + * the device item, which does not exists on the chunk btree. + * The finishing phase of device replace acquires both the + * device_list_mutex and the chunk_mutex, in that order, so we are + * safe by just acquiring the chunk_mutex. + */ + trans->removing_chunk = true; + mutex_lock(&fs_info->chunk_mutex); + + check_system_chunk(trans, map->type); + + ret = remove_chunk_item(trans, map, chunk_offset); + /* + * Normally we should not get -ENOSPC since we reserved space before + * through the call to check_system_chunk(). + * + * Despite our system space_info having enough free space, we may not + * be able to allocate extents from its block groups, because all have + * an incompatible profile, which will force us to allocate a new system + * block group with the right profile, or right after we called + * check_system_space() above, a scrub turned the only system block group + * with enough free space into RO mode. + * This is explained with more detail at do_chunk_alloc(). + * + * So if we get -ENOSPC, allocate a new system chunk and retry once. + */ + if (ret == -ENOSPC) { + const u64 sys_flags = btrfs_system_alloc_profile(fs_info); + struct btrfs_block_group *sys_bg; + + sys_bg = btrfs_alloc_chunk(trans, sys_flags); + if (IS_ERR(sys_bg)) { + ret = PTR_ERR(sys_bg); + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = remove_chunk_item(trans, map, chunk_offset); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + } else if (ret) { btrfs_abort_transaction(trans, ret); goto out; } @@ -3087,6 +3161,15 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) } } + mutex_unlock(&fs_info->chunk_mutex); + trans->removing_chunk = false; + + /* + * We are done with chunk btree updates and deletions, so release the + * system space we previously reserved (with check_system_chunk()). + */ + btrfs_trans_release_chunk_metadata(trans); + ret = btrfs_remove_block_group(trans, chunk_offset, em); if (ret) { btrfs_abort_transaction(trans, ret); @@ -3094,6 +3177,10 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) } out: + if (trans->removing_chunk) { + mutex_unlock(&fs_info->chunk_mutex); + trans->removing_chunk = false; + } /* once for us */ free_extent_map(em); return ret; @@ -4860,13 +4947,12 @@ static int btrfs_add_system_chunk(struct btrfs_fs_info *fs_info, u32 array_size; u8 *ptr; - mutex_lock(&fs_info->chunk_mutex); + lockdep_assert_held(&fs_info->chunk_mutex); + array_size = btrfs_super_sys_array_size(super_copy); if (array_size + item_size + sizeof(disk_key) - > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { - mutex_unlock(&fs_info->chunk_mutex); + > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) return -EFBIG; - } ptr = super_copy->sys_chunk_array + array_size; btrfs_cpu_key_to_disk(&disk_key, key); @@ -4875,7 +4961,6 @@ static int btrfs_add_system_chunk(struct btrfs_fs_info *fs_info, memcpy(ptr, chunk, item_size); item_size += sizeof(disk_key); btrfs_set_super_sys_array_size(super_copy, array_size + item_size); - mutex_unlock(&fs_info->chunk_mutex); return 0; } @@ -5225,13 +5310,14 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, } } -static int create_chunk(struct btrfs_trans_handle *trans, +static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans, struct alloc_chunk_ctl *ctl, struct btrfs_device_info *devices_info) { struct btrfs_fs_info *info = trans->fs_info; struct map_lookup *map = NULL; struct extent_map_tree *em_tree; + struct btrfs_block_group *block_group; struct extent_map *em; u64 start = ctl->start; u64 type = ctl->type; @@ -5241,7 +5327,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS); if (!map) - return -ENOMEM; + return ERR_PTR(-ENOMEM); map->num_stripes = ctl->num_stripes; for (i = 0; i < ctl->ndevs; ++i) { @@ -5263,7 +5349,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, em = alloc_extent_map(); if (!em) { kfree(map); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); em->map_lookup = map; @@ -5279,12 +5365,12 @@ static int create_chunk(struct btrfs_trans_handle *trans, if (ret) { write_unlock(&em_tree->lock); free_extent_map(em); - return ret; + return ERR_PTR(ret); } write_unlock(&em_tree->lock); - ret = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size); - if (ret) + block_group = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size); + if (IS_ERR(block_group)) goto error_del_extent; for (i = 0; i < map->num_stripes; i++) { @@ -5304,7 +5390,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, check_raid56_incompat_flag(info, type); check_raid1c34_incompat_flag(info, type); - return 0; + return block_group; error_del_extent: write_lock(&em_tree->lock); @@ -5316,34 +5402,36 @@ error_del_extent: /* One for the tree reference */ free_extent_map(em); - return ret; + return block_group; } -int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type) +struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans, + u64 type) { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_fs_devices *fs_devices = info->fs_devices; struct btrfs_device_info *devices_info = NULL; struct alloc_chunk_ctl ctl; + struct btrfs_block_group *block_group; int ret; lockdep_assert_held(&info->chunk_mutex); if (!alloc_profile_is_valid(type, 0)) { ASSERT(0); - return -EINVAL; + return ERR_PTR(-EINVAL); } if (list_empty(&fs_devices->alloc_list)) { if (btrfs_test_opt(info, ENOSPC_DEBUG)) btrfs_debug(info, "%s: no writable device", __func__); - return -ENOSPC; + return ERR_PTR(-ENOSPC); } if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { btrfs_err(info, "invalid chunk type 0x%llx requested", type); ASSERT(0); - return -EINVAL; + return ERR_PTR(-EINVAL); } ctl.start = find_next_chunk(info); @@ -5353,46 +5441,43 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type) devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info), GFP_NOFS); if (!devices_info) - return -ENOMEM; + return ERR_PTR(-ENOMEM); ret = gather_device_info(fs_devices, &ctl, devices_info); - if (ret < 0) + if (ret < 0) { + block_group = ERR_PTR(ret); goto out; + } ret = decide_stripe_size(fs_devices, &ctl, devices_info); - if (ret < 0) + if (ret < 0) { + block_group = ERR_PTR(ret); goto out; + } - ret = create_chunk(trans, &ctl, devices_info); + block_group = create_chunk(trans, &ctl, devices_info); out: kfree(devices_info); - return ret; + return block_group; } /* - * Chunk allocation falls into two parts. The first part does work - * that makes the new allocated chunk usable, but does not do any operation - * that modifies the chunk tree. The second part does the work that - * requires modifying the chunk tree. This division is important for the - * bootstrap process of adding storage to a seed btrfs. + * This function, btrfs_finish_chunk_alloc(), belongs to phase 2. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. */ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, u64 chunk_offset, u64 chunk_size) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *extent_root = fs_info->extent_root; - struct btrfs_root *chunk_root = fs_info->chunk_root; - struct btrfs_key key; struct btrfs_device *device; - struct btrfs_chunk *chunk; - struct btrfs_stripe *stripe; struct extent_map *em; struct map_lookup *map; - size_t item_size; u64 dev_offset; u64 stripe_size; - int i = 0; + int i; int ret = 0; em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size); @@ -5400,53 +5485,117 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, return PTR_ERR(em); map = em->map_lookup; - item_size = btrfs_chunk_item_size(map->num_stripes); stripe_size = em->orig_block_len; - chunk = kzalloc(item_size, GFP_NOFS); - if (!chunk) { - ret = -ENOMEM; - goto out; - } - /* * Take the device list mutex to prevent races with the final phase of * a device replace operation that replaces the device object associated * with the map's stripes, because the device object's id can change * at any time during that final phase of the device replace operation - * (dev-replace.c:btrfs_dev_replace_finishing()). + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID, + * resulting in persisting a device extent item with such ID. */ mutex_lock(&fs_info->fs_devices->device_list_mutex); for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; dev_offset = map->stripes[i].physical; - ret = btrfs_update_device(trans, device); - if (ret) - break; ret = btrfs_alloc_dev_extent(trans, device, chunk_offset, dev_offset, stripe_size); if (ret) break; } - if (ret) { - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + + free_extent_map(em); + return ret; +} + +/* + * This function, btrfs_chunk_alloc_add_chunk_item(), typically belongs to the + * phase 1 of chunk allocation. It belongs to phase 2 only when allocating system + * chunks. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ +int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans, + struct btrfs_block_group *bg) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *extent_root = fs_info->extent_root; + struct btrfs_root *chunk_root = fs_info->chunk_root; + struct btrfs_key key; + struct btrfs_chunk *chunk; + struct btrfs_stripe *stripe; + struct extent_map *em; + struct map_lookup *map; + size_t item_size; + int i; + int ret; + + /* + * We take the chunk_mutex for 2 reasons: + * + * 1) Updates and insertions in the chunk btree must be done while holding + * the chunk_mutex, as well as updating the system chunk array in the + * superblock. See the comment on top of btrfs_chunk_alloc() for the + * details; + * + * 2) To prevent races with the final phase of a device replace operation + * that replaces the device object associated with the map's stripes, + * because the device object's id can change at any time during that + * final phase of the device replace operation + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID, + * which would cause a failure when updating the device item, which does + * not exists, or persisting a stripe of the chunk item with such ID. + * Here we can't use the device_list_mutex because our caller already + * has locked the chunk_mutex, and the final phase of device replace + * acquires both mutexes - first the device_list_mutex and then the + * chunk_mutex. Using any of those two mutexes protects us from a + * concurrent device replace. + */ + lockdep_assert_held(&fs_info->chunk_mutex); + + em = btrfs_get_chunk_map(fs_info, bg->start, bg->length); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + btrfs_abort_transaction(trans, ret); + return ret; + } + + map = em->map_lookup; + item_size = btrfs_chunk_item_size(map->num_stripes); + + chunk = kzalloc(item_size, GFP_NOFS); + if (!chunk) { + ret = -ENOMEM; + btrfs_abort_transaction(trans, ret); goto out; } + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_device *device = map->stripes[i].dev; + + ret = btrfs_update_device(trans, device); + if (ret) + goto out; + } + stripe = &chunk->stripe; for (i = 0; i < map->num_stripes; i++) { - device = map->stripes[i].dev; - dev_offset = map->stripes[i].physical; + struct btrfs_device *device = map->stripes[i].dev; + const u64 dev_offset = map->stripes[i].physical; btrfs_set_stack_stripe_devid(stripe, device->devid); btrfs_set_stack_stripe_offset(stripe, dev_offset); memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE); stripe++; } - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_set_stack_chunk_length(chunk, chunk_size); + btrfs_set_stack_chunk_length(chunk, bg->length); btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid); btrfs_set_stack_chunk_stripe_len(chunk, map->stripe_len); btrfs_set_stack_chunk_type(chunk, map->type); @@ -5458,15 +5607,18 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.type = BTRFS_CHUNK_ITEM_KEY; - key.offset = chunk_offset; + key.offset = bg->start; ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size); - if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) { - /* - * TODO: Cleanup of inserted chunk root in case of - * failure. - */ + if (ret) + goto out; + + bg->chunk_item_inserted = 1; + + if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) { ret = btrfs_add_system_chunk(fs_info, &key, chunk, item_size); + if (ret) + goto out; } out: @@ -5479,16 +5631,41 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; u64 alloc_profile; - int ret; + struct btrfs_block_group *meta_bg; + struct btrfs_block_group *sys_bg; + + /* + * When adding a new device for sprouting, the seed device is read-only + * so we must first allocate a metadata and a system chunk. But before + * adding the block group items to the extent, device and chunk btrees, + * we must first: + * + * 1) Create both chunks without doing any changes to the btrees, as + * otherwise we would get -ENOSPC since the block groups from the + * seed device are read-only; + * + * 2) Add the device item for the new sprout device - finishing the setup + * of a new block group requires updating the device item in the chunk + * btree, so it must exist when we attempt to do it. The previous step + * ensures this does not fail with -ENOSPC. + * + * After that we can add the block group items to their btrees: + * update existing device item in the chunk btree, add a new block group + * item to the extent btree, add a new chunk item to the chunk btree and + * finally add the new device extent items to the devices btree. + */ alloc_profile = btrfs_metadata_alloc_profile(fs_info); - ret = btrfs_alloc_chunk(trans, alloc_profile); - if (ret) - return ret; + meta_bg = btrfs_alloc_chunk(trans, alloc_profile); + if (IS_ERR(meta_bg)) + return PTR_ERR(meta_bg); alloc_profile = btrfs_system_alloc_profile(fs_info); - ret = btrfs_alloc_chunk(trans, alloc_profile); - return ret; + sys_bg = btrfs_alloc_chunk(trans, alloc_profile); + if (IS_ERR(sys_bg)) + return PTR_ERR(sys_bg); + + return 0; } static inline int btrfs_chunk_max_errors(struct map_lookup *map) @@ -7415,10 +7592,18 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) total_dev++; } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; + + /* + * We are only called at mount time, so no need to take + * fs_info->chunk_mutex. Plus, to avoid lockdep warnings, + * we always lock first fs_info->chunk_mutex before + * acquiring any locks on the chunk tree. This is a + * requirement for chunk allocation, see the comment on + * top of btrfs_chunk_alloc() for details. + */ + ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); - mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); - mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index c7fc7caf575c..55a8ba244716 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -450,7 +450,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map, struct btrfs_io_geometry *io_geom); int btrfs_read_sys_array(struct btrfs_fs_info *fs_info); int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); -int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); +struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans, + u64 type); void btrfs_mapping_tree_free(struct extent_map_tree *tree); blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num); @@ -509,6 +510,8 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, u64 logical); int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, u64 chunk_offset, u64 chunk_size); +int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans, + struct btrfs_block_group *bg); int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset); struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, u64 logical, u64 length); From abb99cfdaf0759f8a619e5fecf52ccccdf310c8c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Mon, 28 Jun 2021 17:57:28 +0900 Subject: [PATCH 0152/1469] btrfs: properly split extent_map for REQ_OP_ZONE_APPEND Damien reported a test failure with btrfs/209. The test itself ran fine, but the fsck ran afterwards reported a corrupted filesystem. The filesystem corruption happens because we're splitting an extent and then writing the extent twice. We have to split the extent though, because we're creating too large extents for a REQ_OP_ZONE_APPEND operation. When dumping the extent tree, we can see two EXTENT_ITEMs at the same start address but different lengths. $ btrfs inspect dump-tree /dev/nullb1 -t extent ... item 19 key (269484032 EXTENT_ITEM 126976) itemoff 15470 itemsize 53 refs 1 gen 7 flags DATA extent data backref root FS_TREE objectid 257 offset 786432 count 1 item 20 key (269484032 EXTENT_ITEM 262144) itemoff 15417 itemsize 53 refs 1 gen 7 flags DATA extent data backref root FS_TREE objectid 257 offset 786432 count 1 The duplicated EXTENT_ITEMs originally come from wrongly split extent_map in extract_ordered_extent(). Since extract_ordered_extent() uses create_io_em() to split an existing extent_map, we will have split->orig_start != split->start. Then, it will be logged with non-zero "extent data offset". Finally, the logged entries are replayed into a duplicated EXTENT_ITEM. Introduce and use proper splitting function for extent_map. The function is intended to be simple and specific usage for extract_ordered_extent() e.g. not supporting compression case (we do not allow splitting compressed extent_map anyway). There was a question raised by Qu, in summary why we want to split the extent map (and not the bio): The problem is not the limit on the zone end, which as you mention is the same as the block group end. The problem is that data write use zone append (ZA) operations. ZA BIOs cannot be split so a large extent may need to be processed with multiple ZA BIOs, While that is also true for regular writes, the major difference is that ZA are "nameless" write operation giving back the written sectors on completion. And ZA operations may be reordered by the block layer (not intentionally though). Combine both of these characteristics and you can see that the data for a large extent may end up being shuffled when written resulting in data corruption and the impossibility to map the extent to some start sector. To avoid this problem, zoned btrfs uses the principle "one data extent == one ZA BIO". So large extents need to be split. This is unfortunate, but we can revisit this later and optimize, e.g. merge back together the fragments of an extent once written if they actually were written sequentially in the zone. Reported-by: Damien Le Moal Fixes: d22002fd37bd ("btrfs: zoned: split ordered extent when bio is sent") CC: stable@vger.kernel.org # 5.12+ CC: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/inode.c | 147 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 118 insertions(+), 29 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e6eb20987351..8f60314c36c5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2271,13 +2271,127 @@ static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio, return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } +/* + * Split an extent_map at [start, start + len] + * + * This function is intended to be used only for extract_ordered_extent(). + */ +static int split_zoned_em(struct btrfs_inode *inode, u64 start, u64 len, + u64 pre, u64 post) +{ + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_map *em; + struct extent_map *split_pre = NULL; + struct extent_map *split_mid = NULL; + struct extent_map *split_post = NULL; + int ret = 0; + int modified; + unsigned long flags; + + /* Sanity check */ + if (pre == 0 && post == 0) + return 0; + + split_pre = alloc_extent_map(); + if (pre) + split_mid = alloc_extent_map(); + if (post) + split_post = alloc_extent_map(); + if (!split_pre || (pre && !split_mid) || (post && !split_post)) { + ret = -ENOMEM; + goto out; + } + + ASSERT(pre + post < len); + + lock_extent(&inode->io_tree, start, start + len - 1); + write_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, len); + if (!em) { + ret = -EIO; + goto out_unlock; + } + + ASSERT(em->len == len); + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE); + + flags = em->flags; + clear_bit(EXTENT_FLAG_PINNED, &em->flags); + clear_bit(EXTENT_FLAG_LOGGING, &flags); + modified = !list_empty(&em->list); + + /* First, replace the em with a new extent_map starting from * em->start */ + split_pre->start = em->start; + split_pre->len = (pre ? pre : em->len - post); + split_pre->orig_start = split_pre->start; + split_pre->block_start = em->block_start; + split_pre->block_len = split_pre->len; + split_pre->orig_block_len = split_pre->block_len; + split_pre->ram_bytes = split_pre->len; + split_pre->flags = flags; + split_pre->compress_type = em->compress_type; + split_pre->generation = em->generation; + + replace_extent_mapping(em_tree, em, split_pre, modified); + + /* + * Now we only have an extent_map at: + * [em->start, em->start + pre] if pre != 0 + * [em->start, em->start + em->len - post] if pre == 0 + */ + + if (pre) { + /* Insert the middle extent_map */ + split_mid->start = em->start + pre; + split_mid->len = em->len - pre - post; + split_mid->orig_start = split_mid->start; + split_mid->block_start = em->block_start + pre; + split_mid->block_len = split_mid->len; + split_mid->orig_block_len = split_mid->block_len; + split_mid->ram_bytes = split_mid->len; + split_mid->flags = flags; + split_mid->compress_type = em->compress_type; + split_mid->generation = em->generation; + add_extent_mapping(em_tree, split_mid, modified); + } + + if (post) { + split_post->start = em->start + em->len - post; + split_post->len = post; + split_post->orig_start = split_post->start; + split_post->block_start = em->block_start + em->len - post; + split_post->block_len = split_post->len; + split_post->orig_block_len = split_post->block_len; + split_post->ram_bytes = split_post->len; + split_post->flags = flags; + split_post->compress_type = em->compress_type; + split_post->generation = em->generation; + add_extent_mapping(em_tree, split_post, modified); + } + + /* Once for us */ + free_extent_map(em); + /* Once for the tree */ + free_extent_map(em); + +out_unlock: + write_unlock(&em_tree->lock); + unlock_extent(&inode->io_tree, start, start + len - 1); +out: + free_extent_map(split_pre); + free_extent_map(split_mid); + free_extent_map(split_post); + + return ret; +} + static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, struct bio *bio, loff_t file_offset) { struct btrfs_ordered_extent *ordered; - struct extent_map *em = NULL, *em_new = NULL; - struct extent_map_tree *em_tree = &inode->extent_tree; u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 file_len; u64 len = bio->bi_iter.bi_size; u64 end = start + len; u64 ordered_end; @@ -2317,41 +2431,16 @@ static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, goto out; } + file_len = ordered->num_bytes; pre = start - ordered->disk_bytenr; post = ordered_end - end; ret = btrfs_split_ordered_extent(ordered, pre, post); if (ret) goto out; - - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, ordered->file_offset, len); - if (!em) { - read_unlock(&em_tree->lock); - ret = -EIO; - goto out; - } - read_unlock(&em_tree->lock); - - ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); - /* - * We cannot reuse em_new here but have to create a new one, as - * unpin_extent_cache() expects the start of the extent map to be the - * logical offset of the file, which does not hold true anymore after - * splitting. - */ - em_new = create_io_em(inode, em->start + pre, len, - em->start + pre, em->block_start + pre, len, - len, len, BTRFS_COMPRESS_NONE, - BTRFS_ORDERED_REGULAR); - if (IS_ERR(em_new)) { - ret = PTR_ERR(em_new); - goto out; - } - free_extent_map(em_new); + ret = split_zoned_em(inode, file_offset, file_len, pre, post); out: - free_extent_map(em); btrfs_put_ordered_extent(ordered); return errno_to_blk_status(ret); From 9cc0b837e14ae913581ec1ea6e979a738f71b0fd Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 6 Jul 2021 01:32:38 +0900 Subject: [PATCH 0153/1469] btrfs: don't block if we can't acquire the reclaim lock If we can't acquire the reclaim_bgs_lock on block group reclaim, we block until it is free. This can potentially stall for a long time. While reclaim of block groups is necessary for a good user experience on a zoned file system, there still is no need to block as it is best effort only, just like when we're deleting unused block groups. CC: stable@vger.kernel.org # 5.13 Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c557327b4545..9e7d9d0c763d 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1498,7 +1498,15 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) return; - mutex_lock(&fs_info->reclaim_bgs_lock); + /* + * Long running balances can keep us blocked here for eternity, so + * simply skip reclaim if we're unable to get the mutex. + */ + if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) { + btrfs_exclop_finish(fs_info); + return; + } + spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->reclaim_bgs)) { u64 zone_unusable; From ea32af47f00a046a1f953370514d6d946efe0152 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 7 Jul 2021 12:23:45 +0100 Subject: [PATCH 0154/1469] btrfs: zoned: fix wrong mutex unlock on failure to allocate log root tree When syncing the log, if we fail to allocate the root node for the log root tree: 1) We are unlocking fs_info->tree_log_mutex, but at this point we have not yet locked this mutex; 2) We have locked fs_info->tree_root->log_mutex, but we end up not unlocking it; So fix this by unlocking fs_info->tree_root->log_mutex instead of fs_info->tree_log_mutex. Fixes: e75f9fd194090e ("btrfs: zoned: move log tree node allocation out of log_root_tree->log_mutex") CC: stable@vger.kernel.org # 5.13+ Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index cab451d19547..dc6eb088d73e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3173,7 +3173,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { - mutex_unlock(&fs_info->tree_log_mutex); + mutex_unlock(&fs_info->tree_root->log_mutex); goto out; } } From 7999d2555c9f879d006ea8469d74db9cdb038af0 Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Wed, 7 Jul 2021 10:27:00 +0200 Subject: [PATCH 0155/1469] spi: stm32: fixes pm_runtime calls in probe/remove Add pm_runtime calls in probe/probe error path and remove in order to be consistent in all places in ordering and ensure that pm_runtime is disabled prior to resources used by the SPI controller. This patch also fixes the 2 following warnings on driver remove: WARNING: CPU: 0 PID: 743 at drivers/clk/clk.c:594 clk_core_disable_lock+0x18/0x24 WARNING: CPU: 0 PID: 743 at drivers/clk/clk.c:476 clk_unprepare+0x24/0x2c Fixes: 038ac869c9d2 ("spi: stm32: add runtime PM support") Signed-off-by: Amelie Delaunay Signed-off-by: Alain Volmat Link: https://lore.kernel.org/r/1625646426-5826-2-git-send-email-alain.volmat@foss.st.com Signed-off-by: Mark Brown --- drivers/spi/spi-stm32.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 65b37c8dc49f..05618a618939 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -1928,6 +1928,7 @@ static int stm32_spi_probe(struct platform_device *pdev) master->can_dma = stm32_spi_can_dma; pm_runtime_set_active(&pdev->dev); + pm_runtime_get_noresume(&pdev->dev); pm_runtime_enable(&pdev->dev); ret = spi_register_master(master); @@ -1943,6 +1944,8 @@ static int stm32_spi_probe(struct platform_device *pdev) err_pm_disable: pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); err_dma_release: if (spi->dma_tx) dma_release_channel(spi->dma_tx); @@ -1959,9 +1962,14 @@ static int stm32_spi_remove(struct platform_device *pdev) struct spi_master *master = platform_get_drvdata(pdev); struct stm32_spi *spi = spi_master_get_devdata(master); + pm_runtime_get_sync(&pdev->dev); + spi_unregister_master(master); spi->cfg->disable(spi); + pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); if (master->dma_tx) dma_release_channel(master->dma_tx); if (master->dma_rx) @@ -1969,7 +1977,6 @@ static int stm32_spi_remove(struct platform_device *pdev) clk_disable_unprepare(spi->clk); - pm_runtime_disable(&pdev->dev); pinctrl_pm_select_sleep_state(&pdev->dev); From 5616e895ecc56db8ba959e53638031a21353e0e2 Mon Sep 17 00:00:00 2001 From: SanjayKumar Jeyakumar Date: Wed, 7 Jul 2021 10:59:14 +0530 Subject: [PATCH 0156/1469] tools/runqslower: Use __state instead of state Commit 2f064a59a11f ("sched: Change task_struct::state") renamed task->state to task->__state in task_struct. Fix runqslower to use the new name of the field. Fixes: 2f064a59a11f ("sched: Change task_struct::state") Signed-off-by: SanjayKumar Jeyakumar Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210707052914.21473-1-vjsanjay@gmail.com --- tools/bpf/runqslower/runqslower.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index 645530ca7e98..ab9353f2fd46 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -74,7 +74,7 @@ int handle__sched_switch(u64 *ctx) u32 pid; /* ivcsw: treat like an enqueue event and store timestamp */ - if (prev->state == TASK_RUNNING) + if (prev->__state == TASK_RUNNING) trace_enqueue(prev); pid = next->pid; From 0d472c69c6a5e22cef9e5809e2f6d0ccd5934f4a Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 7 Jul 2021 15:50:57 +0800 Subject: [PATCH 0157/1469] stmmac: dwmac-loongson: Fix unsigned comparison to zero plat->phy_interface is unsigned integer, so the condition can't be less than zero and the warning will never printed. Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index e108b0d2bd28..4c9a37dd0d3f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -49,9 +49,9 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id { struct plat_stmmacenet_data *plat; struct stmmac_resources res; - bool mdio = false; - int ret, i; struct device_node *np; + int ret, i, phy_mode; + bool mdio = false; np = dev_of_node(&pdev->dev); @@ -108,10 +108,11 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (plat->bus_id < 0) plat->bus_id = pci_dev_id(pdev); - plat->phy_interface = device_get_phy_mode(&pdev->dev); - if (plat->phy_interface < 0) + phy_mode = device_get_phy_mode(&pdev->dev); + if (phy_mode < 0) dev_err(&pdev->dev, "phy_mode not found\n"); + plat->phy_interface = phy_mode; plat->interface = PHY_INTERFACE_MODE_GMII; pci_set_master(pdev); From eca81f09145d765c21dd8fb1ba5d874ca255c32c Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 7 Jul 2021 15:53:35 +0800 Subject: [PATCH 0158/1469] stmmac: platform: Fix signedness bug in stmmac_probe_config_dt() The "plat->phy_interface" variable is an enum and in this context GCC will treat it as an unsigned int so the error handling is never triggered. Fixes: b9f0b2f634c0 ("net: stmmac: platform: fix probe for ACPI devices") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 072eff8079d0..5ca710844cc1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -397,6 +397,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + int phy_mode; void *ret; int rc; @@ -412,10 +413,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) eth_zero_addr(mac); } - plat->phy_interface = device_get_phy_mode(&pdev->dev); - if (plat->phy_interface < 0) - return ERR_PTR(plat->phy_interface); + phy_mode = device_get_phy_mode(&pdev->dev); + if (phy_mode < 0) + return ERR_PTR(phy_mode); + plat->phy_interface = phy_mode; plat->interface = stmmac_of_get_mac_mode(np); if (plat->interface < 0) plat->interface = plat->phy_interface; From 24b671aad4eae423e1abf5b7f08d9a5235458b8d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 7 Jul 2021 16:15:29 +0800 Subject: [PATCH 0159/1469] selftests: icmp_redirect: remove from checking for IPv6 route get If the kernel doesn't enable option CONFIG_IPV6_SUBTREES, the RTA_SRC info will not be exported to userspace in rt6_fill_node(). And ip cmd will not print "from ::" to the route output. So remove this check. Fixes: ec8105352869 ("selftests: Add redirect tests") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/icmp_redirect.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index c19ecc6a8614..3a111ac1edc3 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -315,7 +315,7 @@ check_exception() if [ "$with_redirect" = "yes" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ - grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}" + grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0.*${mtu}" elif [ -n "${mtu}" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -q "${mtu}" From 0e02bf5de46ae30074a2e1a8194a422a84482a1a Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 7 Jul 2021 16:15:30 +0800 Subject: [PATCH 0160/1469] selftests: icmp_redirect: IPv6 PMTU info should be cleared after redirect After redirecting, it's already a new path. So the old PMTU info should be cleared. The IPv6 test "mtu exception plus redirect" should only has redirect info without old PMTU. The IPv4 test can not be changed because of legacy. Fixes: ec8105352869 ("selftests: Add redirect tests") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/icmp_redirect.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index 3a111ac1edc3..ecbf57f264ed 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -313,9 +313,10 @@ check_exception() fi log_test $? 0 "IPv4: ${desc}" - if [ "$with_redirect" = "yes" ]; then + # No PMTU info for test "redirect" and "mtu exception plus redirect" + if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ - grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0.*${mtu}" + grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0" elif [ -n "${mtu}" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -q "${mtu}" From 1d719254c139fb62fb8056fb496b6fd007e71550 Mon Sep 17 00:00:00 2001 From: Wei Li Date: Mon, 28 Jun 2021 11:04:09 +0800 Subject: [PATCH 0161/1469] tools: bpf: Fix error in 'make -C tools/ bpf_install' make[2]: *** No rule to make target 'install'. Stop. make[1]: *** [Makefile:122: runqslower_install] Error 2 make: *** [Makefile:116: bpf_install] Error 2 There is no rule for target 'install' in tools/bpf/runqslower/Makefile, and there is no need to install it, so just remove 'runqslower_install'. Fixes: 9c01546d26d2 ("tools/bpf: Add runqslower tool to tools/bpf") Signed-off-by: Wei Li Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210628030409.3459095-1-liwei391@huawei.com --- tools/bpf/Makefile | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 39bb322707b4..b11cfc86a3d0 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -97,7 +97,7 @@ clean: bpftool_clean runqslower_clean resolve_btfids_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install runqslower_install +install: $(PROGS) bpftool_install $(call QUIET_INSTALL, bpf_jit_disasm) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin $(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm @@ -118,9 +118,6 @@ bpftool_clean: runqslower: $(call descend,runqslower) -runqslower_install: - $(call descend,runqslower,install) - runqslower_clean: $(call descend,runqslower,clean) @@ -131,5 +128,5 @@ resolve_btfids_clean: $(call descend,resolve_btfids,clean) .PHONY: all install clean bpftool bpftool_install bpftool_clean \ - runqslower runqslower_install runqslower_clean \ + runqslower runqslower_clean \ resolve_btfids resolve_btfids_clean From 271dbc31843244e5192f0f8a8be0da26995f944a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 7 Jul 2021 13:01:00 +0300 Subject: [PATCH 0162/1469] sock: unlock on error in sock_setsockopt() If copy_from_sockptr() then we need to unlock before returning. Fixes: d463126e23f1 ("net: sock: extend SO_TIMESTAMPING for PHC binding") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/core/sock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 1c4b0468bc2c..a3eea6e0b30a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1123,8 +1123,10 @@ set_sndbuf: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, - sizeof(timestamping))) - return -EFAULT; + sizeof(timestamping))) { + ret = -EFAULT; + break; + } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; From 92c4bed59bc0ef2a92b99ca1fe1c7107ffa3125c Mon Sep 17 00:00:00 2001 From: "Roy, UjjaL" Date: Wed, 7 Jul 2021 23:48:33 +0530 Subject: [PATCH 0163/1469] ipmr: Fix indentation issue Fixed indentation by removing extra spaces. Signed-off-by: Roy, UjjaL Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7b12a40dd465..2dda856ca260 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2119,7 +2119,7 @@ int ip_mr_input(struct sk_buff *skb) raw_rcv(mroute_sk, skb); return 0; } - } + } } /* already under rcu_read_lock() */ From 2e29be2e491595407087ab36a5e5a159be693f7b Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 25 May 2021 10:24:26 -0700 Subject: [PATCH 0164/1469] fs/fuse: Remove unneeded kaddr parameter fuse_dax_mem_range_init() does not need the address or the pfn of the memory requested in dax_direct_access(). It is only calling direct access to get the number of pages. Remove the unused variables and stop requesting the kaddr and pfn from dax_direct_access(). Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Reviewed-by: Vivek Goyal Link: https://lore.kernel.org/r/20210525172428.3634316-2-ira.weiny@intel.com Signed-off-by: Dan Williams --- fs/fuse/dax.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index ff99ab2a3c43..34f8a5635c7f 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1234,8 +1234,6 @@ void fuse_dax_conn_free(struct fuse_conn *fc) static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) { long nr_pages, nr_ranges; - void *kaddr; - pfn_t pfn; struct fuse_dax_mapping *range; int ret, id; size_t dax_size = -1; @@ -1247,8 +1245,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker); id = dax_read_lock(); - nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), &kaddr, - &pfn); + nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL, + NULL); dax_read_unlock(id); if (nr_pages < 0) { pr_debug("dax_direct_access() returned %ld\n", nr_pages); From 44788591c3cfb81d9315b8ee5c2076e51bfe8a39 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 25 May 2021 10:24:27 -0700 Subject: [PATCH 0165/1469] fs/dax: Clarify nr_pages to dax_direct_access() dax_direct_access() takes a number of pages. PHYS_PFN(PAGE_SIZE) is a very round about way to specify '1'. Change the nr_pages parameter to the explicit value of '1'. Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20210525172428.3634316-3-ira.weiny@intel.com Signed-off-by: Dan Williams --- fs/dax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dax.c b/fs/dax.c index 62352cbcf0f4..8ce3a7e147a8 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -721,7 +721,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL); + rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; From b05d4c576b697b9f462b9c532c997171d5c3b067 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 25 May 2021 10:24:28 -0700 Subject: [PATCH 0166/1469] dax: Ensure errno is returned from dax_direct_access If the caller specifies a negative nr_pages that is an invalid parameter. Return -EINVAL to ensure callers get an errno if they want to check it. Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20210525172428.3634316-4-ira.weiny@intel.com Signed-off-by: Dan Williams --- drivers/dax/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 5fa6ae9dbc8b..44736cbd446e 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -313,7 +313,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, return -ENXIO; if (nr_pages < 0) - return nr_pages; + return -EINVAL; avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); From 9615fe36b31d926f1c5107013b772dc226a6a7ca Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 7 Jul 2021 21:10:51 -0700 Subject: [PATCH 0167/1469] skbuff: Fix build with SKB extensions disabled We will fail to build with CONFIG_SKB_EXTENSIONS disabled after 8550ff8d8c75 ("skbuff: Release nfct refcount on napi stolen or re-used skbs") since there is an unconditionally use of skb_ext_find() without an appropriate stub. Simply build the code conditionally and properly guard against both COFNIG_SKB_EXTENSIONS as well as CONFIG_NET_TC_SKB_EXT being disabled. Fixes: Fixes: 8550ff8d8c75 ("skbuff: Release nfct refcount on napi stolen or re-used skbs") Signed-off-by: Florian Fainelli Reviewed-by: Roi Dayan Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 177a5aec0b6b..03c95a0867bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6010,7 +6010,7 @@ static void gro_list_prepare(const struct list_head *head, maclen); diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); - +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (!diffs) { struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); @@ -6019,6 +6019,7 @@ static void gro_list_prepare(const struct list_head *head, if (!diffs && unlikely(skb_ext)) diffs |= p_ext->chain ^ skb_ext->chain; } +#endif NAPI_GRO_CB(p)->same_flow = !diffs; } From 889d0e7dc68314a273627d89cbb60c09e1cc1c25 Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Wed, 7 Jul 2021 23:56:32 +0800 Subject: [PATCH 0168/1469] ieee802154: hwsim: fix GPF in hwsim_new_edge_nl Both MAC802154_HWSIM_ATTR_RADIO_ID and MAC802154_HWSIM_ATTR_RADIO_EDGE must be present to fix GPF. Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb") Signed-off-by: Dongliang Mu Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20210707155633.1486603-1-mudongliangabcd@gmail.com Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index cae52bfb871e..8caa61ec718f 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -418,7 +418,7 @@ static int hwsim_new_edge_nl(struct sk_buff *msg, struct genl_info *info) struct hwsim_edge *e; u32 v0, v1; - if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] && + if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; From c90b4503ccf42d9d367e843c223df44aa550e82a Mon Sep 17 00:00:00 2001 From: Colin Xu Date: Wed, 7 Jul 2021 08:45:31 +0800 Subject: [PATCH 0169/1469] drm/i915/gvt: Clear d3_entered on elsp cmd submission. d3_entered flag is used to mark for vgpu_reset a previous power transition from D3->D0, typically for VM resume from S3, so that gvt could skip PPGTT invalidation in current vgpu_reset during resuming. In case S0ix exit, although there is D3->D0, guest driver continue to use vgpu as normal, with d3_entered set, until next shutdown/reboot or power transition. If a reboot follows a S0ix exit, device power state transite as: D0->D3->D0->D0(reboot), while system power state transites as: S0->S0 (reboot). There is no vgpu_reset until D0(reboot), thus d3_entered won't be cleared, the vgpu_reset will skip PPGTT invalidation however those PPGTT entries are no longer valid. Err appears like: gvt: vgpu 2: vfio_pin_pages failed for gfn 0xxxxx, ret -22 gvt: vgpu 2: fail: spt xxxx guest entry 0xxxxx type 2 gvt: vgpu 2: fail: shadow page xxxx guest entry 0xxxxx type 2. Give gvt a chance to clear d3_entered on elsp cmd submission so that the states before & after S0ix enter/exit are consistent. Fixes: ba25d977571e ("drm/i915/gvt: Do not destroy ppgtt_mm during vGPU D3->D0.") Reviewed-by: Zhenyu Wang Signed-off-by: Colin Xu Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20210707004531.4873-1-colin.xu@intel.com --- drivers/gpu/drm/i915/gvt/handlers.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index dda320749c65..2358c92733b0 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1977,6 +1977,21 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, if (drm_WARN_ON(&i915->drm, !engine)) return -EINVAL; + /* + * Due to d3_entered is used to indicate skipping PPGTT invalidation on + * vGPU reset, it's set on D0->D3 on PCI config write, and cleared after + * vGPU reset if in resuming. + * In S0ix exit, the device power state also transite from D3 to D0 as + * S3 resume, but no vGPU reset (triggered by QEMU devic model). After + * S0ix exit, all engines continue to work. However the d3_entered + * remains set which will break next vGPU reset logic (miss the expected + * PPGTT invalidation). + * Engines can only work in D0. Thus the 1st elsp write gives GVT a + * chance to clear d3_entered. + */ + if (vgpu->d3_entered) + vgpu->d3_entered = false; + execlist = &vgpu->submission.execlist[engine->id]; execlist->elsp_dwords.data[3 - execlist->elsp_dwords.index] = data; From 65e2e6c1c20104ed19060a38f4edbf14e9f9a9a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:51 +0200 Subject: [PATCH 0170/1469] pwm: sprd: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to sprd_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 8aae4b02e8a6 ("pwm: sprd: Add Spreadtrum PWM support") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sprd.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index f2a85e8dd941..7004f55bbf11 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -183,13 +183,10 @@ static int sprd_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } } - if (state->period != cstate->period || - state->duty_cycle != cstate->duty_cycle) { - ret = sprd_pwm_config(spc, pwm, state->duty_cycle, - state->period); - if (ret) - return ret; - } + ret = sprd_pwm_config(spc, pwm, state->duty_cycle, + state->period); + if (ret) + return ret; sprd_pwm_write(spc, pwm->hwpwm, SPRD_PWM_ENABLE, 1); } else if (cstate->enabled) { From fe8255f80b8617bc67a58f4ca2b54b3b9b32ff84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:52 +0200 Subject: [PATCH 0171/1469] pwm: spear: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to spear_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 98761ce4b91b ("pwm: spear: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-spear.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-spear.c b/drivers/pwm/pwm-spear.c index 48c31dac2f32..54c7990967dd 100644 --- a/drivers/pwm/pwm-spear.c +++ b/drivers/pwm/pwm-spear.c @@ -177,12 +177,9 @@ static int spear_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period); - if (err) - return err; - } + err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period); + if (err) + return err; if (!pwm->state.enabled) return spear_pwm_enable(chip, pwm); From 25f70b8f3d15b8c188ecb49c6007b86f3e775c20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:53 +0200 Subject: [PATCH 0172/1469] pwm: tiecap: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to ecap_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 0ca7acd84766 ("pwm: tiecap: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tiecap.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c index dec3f1fb150c..35eb19a5a0d1 100644 --- a/drivers/pwm/pwm-tiecap.c +++ b/drivers/pwm/pwm-tiecap.c @@ -189,16 +189,13 @@ static int ecap_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - if (state->period > NSEC_PER_SEC) - return -ERANGE; + if (state->period > NSEC_PER_SEC) + return -ERANGE; - err = ecap_pwm_config(chip, pwm, state->duty_cycle, - state->period, enabled); - if (err) - return err; - } + err = ecap_pwm_config(chip, pwm, state->duty_cycle, + state->period, enabled); + if (err) + return err; if (!enabled) return ecap_pwm_enable(chip, pwm); From 7d6d4aaf2809f209c7d6bcab2f9ae76797051cfa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:54 +0200 Subject: [PATCH 0173/1469] pwm: berlin: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to berlin_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 30dffb42fcd4 ("pwm: berlin: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-berlin.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-berlin.c b/drivers/pwm/pwm-berlin.c index 5537b5f6dd5d..e157273fd2f7 100644 --- a/drivers/pwm/pwm-berlin.c +++ b/drivers/pwm/pwm-berlin.c @@ -190,12 +190,9 @@ static int berlin_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period); - if (err) - return err; - } + err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period); + if (err) + return err; if (!enabled) return berlin_pwm_enable(chip, pwm); From f4a8e31ed84ec646c158824f423cb22d1f362bbf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:55 +0200 Subject: [PATCH 0174/1469] pwm: ep93xx: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to ep93xx_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 6d45374af539 ("pwm: ep93xx: Implement .apply callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-ep93xx.c | 91 +++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 48 deletions(-) diff --git a/drivers/pwm/pwm-ep93xx.c b/drivers/pwm/pwm-ep93xx.c index 8a3d781e6514..fc3cb7d669c6 100644 --- a/drivers/pwm/pwm-ep93xx.c +++ b/drivers/pwm/pwm-ep93xx.c @@ -64,6 +64,11 @@ static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, int ret; struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip); bool enabled = state->enabled; + void __iomem *base = ep93xx_pwm->base; + unsigned long long c; + unsigned long period_cycles; + unsigned long duty_cycles; + unsigned long term; if (state->polarity != pwm->state.polarity) { if (enabled) { @@ -97,58 +102,48 @@ static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip); - void __iomem *base = ep93xx_pwm->base; - unsigned long long c; - unsigned long period_cycles; - unsigned long duty_cycles; - unsigned long term; - - /* - * The clock needs to be enabled to access the PWM registers. - * Configuration can be changed at any time. - */ - if (!pwm_is_enabled(pwm)) { - ret = clk_prepare_enable(ep93xx_pwm->clk); - if (ret) - return ret; - } - - c = clk_get_rate(ep93xx_pwm->clk); - c *= state->period; - do_div(c, 1000000000); - period_cycles = c; - - c = period_cycles; - c *= state->duty_cycle; - do_div(c, state->period); - duty_cycles = c; - - if (period_cycles < 0x10000 && duty_cycles < 0x10000) { - term = readw(base + EP93XX_PWMx_TERM_COUNT); - - /* Order is important if PWM is running */ - if (period_cycles > term) { - writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); - writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); - } else { - writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); - writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); - } - ret = 0; - } else { - ret = -EINVAL; - } - - if (!pwm_is_enabled(pwm)) - clk_disable_unprepare(ep93xx_pwm->clk); - + /* + * The clock needs to be enabled to access the PWM registers. + * Configuration can be changed at any time. + */ + if (!pwm_is_enabled(pwm)) { + ret = clk_prepare_enable(ep93xx_pwm->clk); if (ret) return ret; } + c = clk_get_rate(ep93xx_pwm->clk); + c *= state->period; + do_div(c, 1000000000); + period_cycles = c; + + c = period_cycles; + c *= state->duty_cycle; + do_div(c, state->period); + duty_cycles = c; + + if (period_cycles < 0x10000 && duty_cycles < 0x10000) { + term = readw(base + EP93XX_PWMx_TERM_COUNT); + + /* Order is important if PWM is running */ + if (period_cycles > term) { + writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); + writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); + } else { + writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); + writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); + } + ret = 0; + } else { + ret = -EINVAL; + } + + if (!pwm_is_enabled(pwm)) + clk_disable_unprepare(ep93xx_pwm->clk); + + if (ret) + return ret; + if (!enabled) { ret = clk_prepare_enable(ep93xx_pwm->clk); if (ret) From c7bb4b89033b764eb07db4e060548a6311d801ee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Jul 2021 00:21:09 -0700 Subject: [PATCH 0175/1469] ipv6: tcp: drop silly ICMPv6 packet too big messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While TCP stack scales reasonably well, there is still one part that can be used to DDOS it. IPv6 Packet too big messages have to lookup/insert a new route, and if abused by attackers, can easily put hosts under high stress, with many cpus contending on a spinlock while one is stuck in fib6_run_gc() ip6_protocol_deliver_rcu() icmpv6_rcv() icmpv6_notify() tcp_v6_err() tcp_v6_mtu_reduced() inet6_csk_update_pmtu() ip6_rt_update_pmtu() __ip6_rt_update_pmtu() ip6_rt_cache_alloc() ip6_dst_alloc() dst_alloc() ip6_dst_gc() fib6_run_gc() spin_lock_bh() ... Some of our servers have been hit by malicious ICMPv6 packets trying to _increase_ the MTU/MSS of TCP flows. We believe these ICMPv6 packets are a result of a bug in one ISP stack, since they were blindly sent back for _every_ (small) packet sent to them. These packets are for one TCP flow: 09:24:36.266491 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.266509 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.316688 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.316704 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.608151 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 TCP stack can filter some silly requests : 1) MTU below IPV6_MIN_MTU can be filtered early in tcp_v6_err() 2) tcp_v6_mtu_reduced() can drop requests trying to increase current MSS. This tests happen before the IPv6 routing stack is entered, thus removing the potential contention and route exhaustion. Note that IPv6 stack was performing these checks, but too late (ie : after the route has been added, and after the potential garbage collect war) v2: fix typo caught by Martin, thanks ! v3: exports tcp_mtu_to_mss(), caught by David, thanks ! Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Maciej Żenczykowski Cc: Martin KaFai Lau Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 1 + net/ipv6/tcp_ipv6.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bde781f46b41..29553fce8502 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1732,6 +1732,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } +EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 593c32fe57ed..323989927a0a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -348,11 +348,20 @@ failure: static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; + u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, READ_ONCE(tcp_sk(sk)->mtu_info)); + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); + + /* Drop requests trying to increase our current mss. + * Check done in __ip6_rt_update_pmtu() is too late. + */ + if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) + return; + + dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -433,6 +442,8 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (type == ICMPV6_PKT_TOOBIG) { + u32 mtu = ntohl(info); + /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). @@ -443,7 +454,11 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - WRITE_ONCE(tp->mtu_info, ntohl(info)); + if (mtu < IPV6_MIN_MTU) + goto out; + + WRITE_ONCE(tp->mtu_info, mtu); + if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, From debdd8e31895fdd1e2cfeb7a5aff1c83e49a91ba Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 8 Jul 2021 11:04:08 -0700 Subject: [PATCH 0176/1469] ptp: Relocate lookup cookie to correct block. An earlier commit set the pps_lookup cookie, but the line was somehow added to the wrong code block. Correct this. Fixes: 8602e40fc813 ("ptp: Set lookup cookie when creating a PTP PPS source.") Signed-off-by: Jonathan Lemon Signed-off-by: Dario Binacchi Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index ce6d9fc85607..4dfc52e06704 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -232,7 +232,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, pr_err("failed to create ptp aux_worker %d\n", err); goto kworker_err; } - ptp->pps_source->lookup_cookie = ptp; } /* PTP virtual clock is being registered under physical clock */ @@ -268,6 +267,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, pr_err("failed to register pps source\n"); goto no_pps; } + ptp->pps_source->lookup_cookie = ptp; } /* Initialize a new device of our class in our clock structure. */ From b9d233ea21f192702f8bbf3f5f640e2dde308b25 Mon Sep 17 00:00:00 2001 From: Gatis Peisenieks Date: Thu, 8 Jul 2021 12:49:04 +0300 Subject: [PATCH 0177/1469] atl1c: fix Mikrotik 10/25G NIC detection Since Mikrotik 10/25G NIC MDIO op emulation is not 100% reliable, on rare occasions it can happen that some physical functions of the NIC do not get initialized due to timeouted early MDIO op. This changes the atl1c probe on Mikrotik 10/25G NIC not to depend on MDIO op emulation. Signed-off-by: Gatis Peisenieks Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/atl1c/atl1c_hw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c index 7dff20350865..f19370c33444 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c @@ -594,6 +594,11 @@ int atl1c_phy_init(struct atl1c_hw *hw) int ret_val; u16 mii_bmcr_data = BMCR_RESET; + if (hw->nic_type == athr_mt) { + hw->phy_configured = true; + return 0; + } + if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) || (atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) { dev_err(&pdev->dev, "Error get phy ID\n"); From c34269041185dad1bab7a34f42ef9fab967a1684 Mon Sep 17 00:00:00 2001 From: Aaron Ma Date: Thu, 8 Jul 2021 21:17:10 +0800 Subject: [PATCH 0178/1469] mt76: mt7921: continue to probe driver when fw already downloaded When reboot system, no power cycles, firmware is already downloaded, return -EIO will break driver as error: mt7921e: probe of 0000:03:00.0 failed with error -5 Skip firmware download and continue to probe. Signed-off-by: Aaron Ma Fixes: 1c099ab44727c ("mt76: mt7921: add MCU support") Signed-off-by: David S. Miller --- drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index c2c4dc196802..cd690c64f65b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -931,7 +931,7 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY); if (ret) { dev_dbg(dev->mt76.dev, "Firmware is already download\n"); - return -EIO; + goto fw_loaded; } ret = mt7921_load_patch(dev); @@ -949,6 +949,7 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) return -EIO; } +fw_loaded: mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_FWDL], false); #ifdef CONFIG_PM From 015fe6fd29c4b9ac0f61b8c4455ef88e6018b9cc Mon Sep 17 00:00:00 2001 From: Shahjada Abul Husain Date: Thu, 8 Jul 2021 21:51:56 +0530 Subject: [PATCH 0179/1469] cxgb4: fix IRQ free race during driver unload IRQs are requested during driver's ndo_open() and then later freed up in disable_interrupts() during driver unload. A race exists where driver can set the CXGB4_FULL_INIT_DONE flag in ndo_open() after the disable_interrupts() in driver unload path checks it, and hence misses calling free_irq(). Fix by unregistering netdevice first and sync with driver's ndo_open(). This ensures disable_interrupts() checks the flag correctly and frees up the IRQs properly. Fixes: b37987e8db5f ("cxgb4: Disable interrupts and napi before unregistering netdev") Signed-off-by: Shahjada Abul Husain Signed-off-by: Raju Rangoju Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 18 ++++++++++-------- drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 3 +++ 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 9a2b166d651e..dbf9a0e6601d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2643,6 +2643,9 @@ static void detach_ulds(struct adapter *adap) { unsigned int i; + if (!is_uld(adap)) + return; + mutex_lock(&uld_mutex); list_del(&adap->list_node); @@ -7141,10 +7144,13 @@ static void remove_one(struct pci_dev *pdev) */ destroy_workqueue(adapter->workq); - if (is_uld(adapter)) { - detach_ulds(adapter); - t4_uld_clean_up(adapter); - } + detach_ulds(adapter); + + for_each_port(adapter, i) + if (adapter->port[i]->reg_state == NETREG_REGISTERED) + unregister_netdev(adapter->port[i]); + + t4_uld_clean_up(adapter); adap_free_hma_mem(adapter); @@ -7152,10 +7158,6 @@ static void remove_one(struct pci_dev *pdev) cxgb4_free_mps_ref_entries(adapter); - for_each_port(adapter, i) - if (adapter->port[i]->reg_state == NETREG_REGISTERED) - unregister_netdev(adapter->port[i]); - debugfs_remove_recursive(adapter->debugfs_root); if (!is_t4(adapter->params.chip)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index 743af9e654aa..17faac715882 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -581,6 +581,9 @@ void t4_uld_clean_up(struct adapter *adap) { unsigned int i; + if (!is_uld(adap)) + return; + mutex_lock(&uld_mutex); for (i = 0; i < CXGB4_ULD_MAX; i++) { if (!adap->uld[i].handle) From 96248d6da65744e1baaa29e5c4e5dc233e29838b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Jul 2021 10:33:10 -0700 Subject: [PATCH 0180/1469] net: microchip: sparx5: fix kconfig warning PHY_SPARX5_SERDES depends on OF so SPARX5_SWITCH should also depend on OF since 'select' does not follow any dependencies. WARNING: unmet direct dependencies detected for PHY_SPARX5_SERDES Depends on [n]: (ARCH_SPARX5 || COMPILE_TEST [=n]) && OF [=n] && HAS_IOMEM [=y] Selected by [y]: - SPARX5_SWITCH [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_MICROCHIP [=y] && NET_SWITCHDEV [=y] && HAS_IOMEM [=y] Fixes: 3cfa11bac9bb ("net: sparx5: add the basic sparx5 driver") Signed-off-by: Randy Dunlap Cc: Lars Povlsen Cc: Steen Hegelund Cc: UNGLinuxDriver@microchip.com Cc: linux-arm-kernel@lists.infradead.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/sparx5/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index a80419d8d4b5..ac403d43c74c 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -2,6 +2,7 @@ config SPARX5_SWITCH tristate "Sparx5 switch driver" depends on NET_SWITCHDEV depends on HAS_IOMEM + depends on OF select PHYLINK select PHY_SPARX5_SERDES select RESET_CONTROLLER From 27fa107d3b8d13a57cdd7c7a40bd6548d4b9cef8 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:52 +0300 Subject: [PATCH 0181/1469] net/ncsi: fix restricted cast warning of sparse Sparse reports: net/ncsi/ncsi-rsp.c:406:24: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:732:33: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:756:25: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:779:25: warning: cast to restricted __be32 Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/ncsi-manage.c | 6 +++--- net/ncsi/ncsi-rsp.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index ca04b6df1341..42b54a3da2e6 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -700,7 +700,7 @@ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN; memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN); - *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID); data[5] = NCSI_OEM_BCM_CMD_GMA; nca->data = data; @@ -724,7 +724,7 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA; u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM; @@ -747,7 +747,7 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) int ret = 0; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 888ccc2d4e34..04bc50be5c01 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -403,7 +403,7 @@ static int ncsi_rsp_handler_ev(struct ncsi_request *nr) /* Update to VLAN mode */ cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd); ncm->enable = 1; - ncm->data[0] = ntohl(cmd->mode); + ncm->data[0] = ntohl((__force __be32)cmd->mode); return 0; } From abd2fddc94a619b96bf41c60429d4c32bd118e17 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:53 +0300 Subject: [PATCH 0182/1469] net/ncsi: add NCSI Intel OEM command to keep PHY up This allows to keep PHY link up and prevents any channel resets during the host load. It is KEEP_PHY_LINK_UP option(Veto bit) in i210 datasheet which block PHY reset and power state changes. Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/Kconfig | 6 ++++++ net/ncsi/internal.h | 5 +++++ net/ncsi/ncsi-manage.c | 45 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+) diff --git a/net/ncsi/Kconfig b/net/ncsi/Kconfig index 93309081f5a4..ea1dd32b6b1f 100644 --- a/net/ncsi/Kconfig +++ b/net/ncsi/Kconfig @@ -17,3 +17,9 @@ config NCSI_OEM_CMD_GET_MAC help This allows to get MAC address from NCSI firmware and set them back to controller. +config NCSI_OEM_CMD_KEEP_PHY + bool "Keep PHY Link up" + depends on NET_NCSI + help + This allows to keep PHY link up and prevents any channel resets during + the host load. diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index cbbb0de4750a..0b6cfd3b31e0 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -78,6 +78,9 @@ enum { /* OEM Vendor Manufacture ID */ #define NCSI_OEM_MFR_MLX_ID 0x8119 #define NCSI_OEM_MFR_BCM_ID 0x113d +#define NCSI_OEM_MFR_INTEL_ID 0x157 +/* Intel specific OEM command */ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */ /* Broadcom specific OEM Command */ #define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */ /* Mellanox specific OEM Command */ @@ -86,6 +89,7 @@ enum { #define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ #define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7 #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 #define NCSI_OEM_MLX_CMD_SMAF_LEN 60 @@ -271,6 +275,7 @@ enum { ncsi_dev_state_probe_mlx_gma, ncsi_dev_state_probe_mlx_smaf, ncsi_dev_state_probe_cis, + ncsi_dev_state_probe_keep_phy, ncsi_dev_state_probe_gvi, ncsi_dev_state_probe_gc, ncsi_dev_state_probe_gls, diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 42b54a3da2e6..89c7742cd72e 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -689,6 +689,35 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + +static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) +{ + unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; + int ret = 0; + + nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN; + + memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); + + data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY; + + /* PHY Link up attribute */ + data[6] = 0x1; + + nca->data = data; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during configure\n", + nca->type); + return ret; +} + +#endif + #if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) /* NCSI OEM Command APIs */ @@ -1392,7 +1421,23 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) } nd->state = ncsi_dev_state_probe_gvi; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) + nd->state = ncsi_dev_state_probe_keep_phy; break; +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + case ncsi_dev_state_probe_keep_phy: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_keep_phy_intel(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_gvi; + break; +#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: From 163f5de509a8ec193df94a9b9afbeb1a9e3f46a6 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:54 +0300 Subject: [PATCH 0183/1469] net/ncsi: add dummy response handler for Intel boards Add the dummy response handler for Intel boards to prevent incorrect handling of OEM commands. Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/ncsi-rsp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 04bc50be5c01..d48374894817 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -699,12 +699,19 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) return 0; } +/* Response handler for Intel card */ +static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) +{ + return 0; +} + static struct ncsi_rsp_oem_handler { unsigned int mfr_id; int (*handler)(struct ncsi_request *nr); } ncsi_rsp_oem_handlers[] = { { NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx }, - { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm } + { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }, + { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel } }; /* Response handler for OEM command */ From 2b452550a203d88112eaf0ba9fc4b750a000b496 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 8 Jul 2021 18:55:32 -0700 Subject: [PATCH 0184/1469] net: bcmgenet: Ensure all TX/RX queues DMAs are disabled Make sure that we disable each of the TX and RX queues in the TDMA and RDMA control registers. This is a correctness change to be symmetrical with the code that enables the TX and RX queues. Tested-by: Maxime Ripard Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 35e9956e930c..db74241935ab 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3238,15 +3238,21 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, /* Returns a reusable dma control register value */ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) { + unsigned int i; u32 reg; u32 dma_ctrl; /* disable DMA */ dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN; + for (i = 0; i < priv->hw_params->tx_queues; i++) + dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT)); reg = bcmgenet_tdma_readl(priv, DMA_CTRL); reg &= ~dma_ctrl; bcmgenet_tdma_writel(priv, reg, DMA_CTRL); + dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN; + for (i = 0; i < priv->hw_params->rx_queues; i++) + dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT)); reg = bcmgenet_rdma_readl(priv, DMA_CTRL); reg &= ~dma_ctrl; bcmgenet_rdma_writel(priv, reg, DMA_CTRL); From f263a81451c12da5a342d90572e317e611846f2c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 7 Jul 2021 15:38:47 -0700 Subject: [PATCH 0185/1469] bpf: Track subprog poke descriptors correctly and fix use-after-free Subprograms are calling map_poke_track(), but on program release there is no hook to call map_poke_untrack(). However, on program release, the aux memory (and poke descriptor table) is freed even though we still have a reference to it in the element list of the map aux data. When we run map_poke_run(), we then end up accessing free'd memory, triggering KASAN in prog_array_map_poke_run(): [...] [ 402.824689] BUG: KASAN: use-after-free in prog_array_map_poke_run+0xc2/0x34e [ 402.824698] Read of size 4 at addr ffff8881905a7940 by task hubble-fgs/4337 [ 402.824705] CPU: 1 PID: 4337 Comm: hubble-fgs Tainted: G I 5.12.0+ #399 [ 402.824715] Call Trace: [ 402.824719] dump_stack+0x93/0xc2 [ 402.824727] print_address_description.constprop.0+0x1a/0x140 [ 402.824736] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824740] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824744] kasan_report.cold+0x7c/0xd8 [ 402.824752] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824757] prog_array_map_poke_run+0xc2/0x34e [ 402.824765] bpf_fd_array_map_update_elem+0x124/0x1a0 [...] The elements concerned are walked as follows: for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; [...] The access to size_poke_tab is a 4 byte read, verified by checking offsets in the KASAN dump: [ 402.825004] The buggy address belongs to the object at ffff8881905a7800 which belongs to the cache kmalloc-1k of size 1024 [ 402.825008] The buggy address is located 320 bytes inside of 1024-byte region [ffff8881905a7800, ffff8881905a7c00) The pahole output of bpf_prog_aux: struct bpf_prog_aux { [...] /* --- cacheline 5 boundary (320 bytes) --- */ u32 size_poke_tab; /* 320 4 */ [...] In general, subprograms do not necessarily manage their own data structures. For example, BTF func_info and linfo are just pointers to the main program structure. This allows reference counting and cleanup to be done on the latter which simplifies their management a bit. The aux->poke_tab struct, however, did not follow this logic. The initial proposed fix for this use-after-free bug further embedded poke data tracking into the subprogram with proper reference counting. However, Daniel and Alexei questioned why we were treating these objects special; I agree, its unnecessary. The fix here removes the per subprogram poke table allocation and map tracking and instead simply points the aux->poke_tab pointer at the main programs poke table. This way, map tracking is simplified to the main program and we do not need to manage them per subprogram. This also means, bpf_prog_free_deferred(), which unwinds the program reference counting and kfrees objects, needs to ensure that we don't try to double free the poke_tab when free'ing the subprog structures. This is easily solved by NULL'ing the poke_tab pointer. The second detail is to ensure that per subprogram JIT logic only does fixups on poke_tab[] entries it owns. To do this, we add a pointer in the poke structure to point at the subprogram value so JITs can easily check while walking the poke_tab structure if the current entry belongs to the current program. The aux pointer is stable and therefore suitable for such comparison. On the jit_subprogs() error path, we omit cleaning up the poke->aux field because these are only ever referenced from the JIT side, but on error we will never make it to the JIT, so its fine to leave them dangling. Removing these pointers would complicate the error path for no reason. However, we do need to untrack all poke descriptors from the main program as otherwise they could race with the freeing of JIT memory from the subprograms. Lastly, a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") had an off-by-one on the subprogram instruction index range check as it was testing 'insn_idx >= subprog_start && insn_idx <= subprog_end'. However, subprog_end is the next subprogram's start instruction. Fixes: a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210707223848.14580-2-john.fastabend@gmail.com --- arch/x86/net/bpf_jit_comp.c | 3 ++ include/linux/bpf.h | 1 + kernel/bpf/core.c | 8 ++++- kernel/bpf/verifier.c | 60 +++++++++++++------------------------ 4 files changed, 32 insertions(+), 40 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e835164189f1..4b951458c9fc 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -570,6 +570,9 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) for (i = 0; i < prog->aux->size_poke_tab; i++) { poke = &prog->aux->poke_tab[i]; + if (poke->aux && poke->aux != prog->aux) + continue; + WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable)); if (poke->reason != BPF_POKE_REASON_TAIL_CALL) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..e8e2b0393ca9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -780,6 +780,7 @@ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; + void *aux; union { struct { struct bpf_map *map; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 034ad93a1ad7..9b1577498373 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2236,8 +2236,14 @@ static void bpf_prog_free_deferred(struct work_struct *work) #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); - for (i = 0; i < aux->func_cnt; i++) + for (i = 0; i < aux->func_cnt; i++) { + /* We can just unlink the subprog poke descriptor table as + * it was originally linked to the main program and is also + * released along with it. + */ + aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); + } if (aux->func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index be38bb930bf1..42a4063de7cd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12121,33 +12121,19 @@ static int jit_subprogs(struct bpf_verifier_env *env) goto out_free; func[i]->is_func = 1; func[i]->aux->func_idx = i; - /* the btf and func_info will be freed only at prog->aux */ + /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->func_info = prog->aux->func_info; + func[i]->aux->poke_tab = prog->aux->poke_tab; + func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; for (j = 0; j < prog->aux->size_poke_tab; j++) { - u32 insn_idx = prog->aux->poke_tab[j].insn_idx; - int ret; + struct bpf_jit_poke_descriptor *poke; - if (!(insn_idx >= subprog_start && - insn_idx <= subprog_end)) - continue; - - ret = bpf_jit_add_poke_descriptor(func[i], - &prog->aux->poke_tab[j]); - if (ret < 0) { - verbose(env, "adding tail call poke descriptor failed\n"); - goto out_free; - } - - func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1; - - map_ptr = func[i]->aux->poke_tab[ret].tail_call.map; - ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux); - if (ret < 0) { - verbose(env, "tracking tail call prog failed\n"); - goto out_free; - } + poke = &prog->aux->poke_tab[j]; + if (poke->insn_idx < subprog_end && + poke->insn_idx >= subprog_start) + poke->aux = func[i]->aux; } /* Use bpf_prog_F_tag to indicate functions in stack traces. @@ -12178,18 +12164,6 @@ static int jit_subprogs(struct bpf_verifier_env *env) cond_resched(); } - /* Untrack main program's aux structs so that during map_poke_run() - * we will not stumble upon the unfilled poke descriptors; each - * of the main program's poke descs got distributed across subprogs - * and got tracked onto map, so we are sure that none of them will - * be missed after the operation below - */ - for (i = 0; i < prog->aux->size_poke_tab; i++) { - map_ptr = prog->aux->poke_tab[i].tail_call.map; - - map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); - } - /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT @@ -12267,14 +12241,22 @@ static int jit_subprogs(struct bpf_verifier_env *env) bpf_prog_jit_attempt_done(prog); return 0; out_free: + /* We failed JIT'ing, so at this point we need to unregister poke + * descriptors from subprogs, so that kernel is not attempting to + * patch it anymore as we're freeing the subprog JIT memory. + */ + for (i = 0; i < prog->aux->size_poke_tab; i++) { + map_ptr = prog->aux->poke_tab[i].tail_call.map; + map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); + } + /* At this point we're guaranteed that poke descriptors are not + * live anymore. We can just unlink its descriptor table as it's + * released with the main prog. + */ for (i = 0; i < env->subprog_cnt; i++) { if (!func[i]) continue; - - for (j = 0; j < func[i]->aux->size_poke_tab; j++) { - map_ptr = func[i]->aux->poke_tab[j].tail_call.map; - map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux); - } + func[i]->aux->poke_tab = NULL; bpf_jit_free(func[i]); } kfree(func); From 1fb5ba29ad0835c5cbfc69a27f9c2733cb65726e Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 7 Jul 2021 15:38:48 -0700 Subject: [PATCH 0186/1469] bpf: Selftest to verify mixing bpf2bpf calls and tailcalls with insn patch This adds some extra noise to the tailcall_bpf2bpf4 tests that will cause verify to patch insns. This then moves around subprog start/end insn index and poke descriptor insn index to ensure that verify and JIT will continue to track these correctly. If done correctly verifier should pass this program same as before and JIT should emit tail call logic. Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210707223848.14580-3-john.fastabend@gmail.com --- .../selftests/bpf/prog_tests/tailcalls.c | 36 +++++++++++++------ .../selftests/bpf/progs/tailcall_bpf2bpf4.c | 18 ++++++++++ 2 files changed, 44 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index ee27d68d2a1c..b5940e6ca67c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -715,6 +715,8 @@ out: bpf_object__close(obj); } +#include "tailcall_bpf2bpf4.skel.h" + /* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved * across tailcalls combined with bpf2bpf calls. for making sure that tailcall * counter behaves correctly, bpf program will go through following flow: @@ -727,10 +729,15 @@ out: * the loop begins. At the end of the test make sure that the global counter is * equal to 31, because tailcall counter includes the first two tailcalls * whereas global counter is incremented only on loop presented on flow above. + * + * The noise parameter is used to insert bpf_map_update calls into the logic + * to force verifier to patch instructions. This allows us to ensure jump + * logic remains correct with instruction movement. */ -static void test_tailcall_bpf2bpf_4(void) +static void test_tailcall_bpf2bpf_4(bool noise) { - int err, map_fd, prog_fd, main_fd, data_fd, i, val; + int err, map_fd, prog_fd, main_fd, data_fd, i; + struct tailcall_bpf2bpf4__bss val; struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; @@ -774,11 +781,6 @@ static void test_tailcall_bpf2bpf_4(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); - data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) return; @@ -787,10 +789,22 @@ static void test_tailcall_bpf2bpf_4(void) if (CHECK_FAIL(map_fd < 0)) return; + i = 0; + val.noise = noise; + val.count = 0; + err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY); + if (CHECK_FAIL(err)) + goto out; + + err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, + &duration, &retval, NULL); + CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", + err, errno, retval); + i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n", + err, errno, val.count); out: bpf_object__close(obj); @@ -815,5 +829,7 @@ void test_tailcalls(void) if (test__start_subtest("tailcall_bpf2bpf_3")) test_tailcall_bpf2bpf_3(); if (test__start_subtest("tailcall_bpf2bpf_4")) - test_tailcall_bpf2bpf_4(); + test_tailcall_bpf2bpf_4(false); + if (test__start_subtest("tailcall_bpf2bpf_5")) + test_tailcall_bpf2bpf_4(true); } diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index 77df6d4db895..e89368a50b97 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -2,6 +2,13 @@ #include #include +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} nop_table SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __uint(max_entries, 3); @@ -10,10 +17,21 @@ struct { } jmp_table SEC(".maps"); int count = 0; +int noise = 0; + +__always_inline int subprog_noise(void) +{ + __u32 key = 0; + + bpf_map_lookup_elem(&nop_table, &key); + return 0; +} __noinline int subprog_tail_2(struct __sk_buff *skb) { + if (noise) + subprog_noise(); bpf_tail_call_static(skb, &jmp_table, 2); return skb->len * 3; } From 3efe180d5105d367ae1dfadb97892ab93a89a783 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 6 Jul 2021 08:51:25 +0200 Subject: [PATCH 0187/1469] drm/qxl: add NULL check for bo->resource MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When allocations fails that can be NULL now. Signed-off-by: Christian König Reported-by: Daniel Bristot de Oliveira Tested-by: Daniel Bristot de Oliveira Tested-by: Roberto Sassu Fixes: bfa3357ef9ab ("drm/ttm: allocate resource object instead of embedding it v2") Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210708114710.8186-1-christian.koenig@amd.com --- drivers/gpu/drm/qxl/qxl_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 19fd39d9a00c..37a1b6a6ad6d 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -127,7 +127,7 @@ static void qxl_bo_move_notify(struct ttm_buffer_object *bo, struct qxl_bo *qbo; struct qxl_device *qdev; - if (!qxl_ttm_bo_is_qxl_bo(bo)) + if (!qxl_ttm_bo_is_qxl_bo(bo) || !bo->resource) return; qbo = to_qxl_bo(bo); qdev = to_qxl(qbo->tbo.base.dev); From ecef6a9effe49e8e2635c839020b9833b71e934c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Jul 2021 15:02:37 +0200 Subject: [PATCH 0188/1469] libata: fix ata_pio_sector for CONFIG_HIGHMEM Data transfers are not required to be block aligned in memory, so they span two pages. Fix this by splitting the call to >sff_data_xfer into two for that case. This has been broken since the initial libata import before the damn of git, but was uncovered by the legacy ide driver removal. Reported-by: kernel test robot Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210709130237.3730959-1-hch@lst.de Signed-off-by: Jens Axboe --- drivers/ata/libata-sff.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index ae7189d1a568..b71ea4a680b0 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -637,6 +637,20 @@ unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, } EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); +static void ata_pio_xfer(struct ata_queued_cmd *qc, struct page *page, + unsigned int offset, size_t xfer_size) +{ + bool do_write = (qc->tf.flags & ATA_TFLAG_WRITE); + unsigned char *buf; + + buf = kmap_atomic(page); + qc->ap->ops->sff_data_xfer(qc, buf + offset, xfer_size, do_write); + kunmap_atomic(buf); + + if (!do_write && !PageSlab(page)) + flush_dcache_page(page); +} + /** * ata_pio_sector - Transfer a sector of data. * @qc: Command on going @@ -648,11 +662,9 @@ EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); */ static void ata_pio_sector(struct ata_queued_cmd *qc) { - int do_write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; struct page *page; unsigned int offset; - unsigned char *buf; if (!qc->cursg) { qc->curbytes = qc->nbytes; @@ -670,13 +682,20 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); - /* do the actual data transfer */ - buf = kmap_atomic(page); - ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, do_write); - kunmap_atomic(buf); + /* + * Split the transfer when it splits a page boundary. Note that the + * split still has to be dword aligned like all ATA data transfers. + */ + WARN_ON_ONCE(offset % 4); + if (offset + qc->sect_size > PAGE_SIZE) { + unsigned int split_len = PAGE_SIZE - offset; - if (!do_write && !PageSlab(page)) - flush_dcache_page(page); + ata_pio_xfer(qc, page, offset, split_len); + ata_pio_xfer(qc, nth_page(page, 1), 0, + qc->sect_size - split_len); + } else { + ata_pio_xfer(qc, page, offset, qc->sect_size); + } qc->curbytes += qc->sect_size; qc->cursg_ofs += qc->sect_size; From 34e0fc345ae728cd974d9ee09832abf62cf054c6 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 9 Jul 2021 14:08:12 +0200 Subject: [PATCH 0189/1469] arm64: tegra: Enable audio IOMMU support on Tegra194 Add iommus and interconnects properties to the sound device tree node on Tegra194. This ensures that the correct SID is used for translation of physical to I/O virtual addresses and that the path to system memory is properly described, which in turn can impact the range of memory that the device can address. Fixes: c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194") Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index b7d532841390..0e6eeb1a1c1a 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -2469,6 +2469,11 @@ * for 8x and 11.025x sample rate streams. */ assigned-clock-rates = <258000000>; + + interconnects = <&mc TEGRA194_MEMORY_CLIENT_APEDMAR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_APEDMAW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_APE>; }; tcu: tcu { From c667dcd4dfcd515ad2c9b3953a33d742985a0b5e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 8 Jul 2021 12:39:32 +0200 Subject: [PATCH 0190/1469] arm64: tegra: Enable SMMU support for USB on Tegra194 As of commit c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194"), SMMU support is enabled system-wide on Tegra194. However, there was a bit of overlap between the SMMU enablement and the USB support addition, so the USB device tree nodes are missing the iommus and interconnects properties. This in turn leads to SMMU faults for these devices, since by default the ARM SMMU will fault. Add the iommus and interconnects properties to the XUSB and XUDC device tree nodes to restore their functionality. Fixes: c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194") Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 0e6eeb1a1c1a..076d5efc4c3d 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -948,6 +948,10 @@ <&bpmp TEGRA194_CLK_XUSB_SS>, <&bpmp TEGRA194_CLK_XUSB_FS>; clock-names = "dev", "ss", "ss_src", "fs_src"; + interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_XUSB_DEV>; power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBB>, <&bpmp TEGRA194_POWER_DOMAIN_XUSBA>; power-domain-names = "dev", "ss"; @@ -977,6 +981,10 @@ "xusb_ss", "xusb_ss_src", "xusb_hs_src", "xusb_fs_src", "pll_u_480m", "clk_m", "pll_e"; + interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_XUSB_HOST>; power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBC>, <&bpmp TEGRA194_POWER_DOMAIN_XUSBA>; From c78eaeebe855fd93f2e77142ffd0404a54070d84 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:09:53 +0300 Subject: [PATCH 0191/1469] net: moxa: fix UAF in moxart_mac_probe In case of netdev registration failure the code path will jump to init_fail label: init_fail: netdev_err(ndev, "init failed\n"); moxart_mac_free_memory(ndev); irq_map_fail: free_netdev(ndev); return ret; So, there is no need to call free_netdev() before jumping to error handling path, since it can cause UAF or double-free bug. Fixes: 6c821bd9edc9 ("net: Add MOXA ART SoCs ethernet driver") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 5249b64f4fc5..49def6934cad 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -540,10 +540,8 @@ static int moxart_mac_probe(struct platform_device *pdev) SET_NETDEV_DEV(ndev, &pdev->dev); ret = register_netdev(ndev); - if (ret) { - free_netdev(ndev); + if (ret) goto init_fail; - } netdev_dbg(ndev, "%s: IRQ=%d address=%pM\n", __func__, ndev->irq, ndev->dev_addr); From ad297cd2db8953e2202970e9504cab247b6c7cb4 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:24:18 +0300 Subject: [PATCH 0192/1469] net: qcom/emac: fix UAF in emac_remove adpt is netdev private data and it cannot be used after free_netdev() call. Using adpt after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 54e19bc74f33 ("net: qcom/emac: do not use devm on internal phy pdev") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 8543bf3c3484..ad655f0a4965 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -735,12 +735,13 @@ static int emac_remove(struct platform_device *pdev) put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); - free_netdev(netdev); if (adpt->phy.digital) iounmap(adpt->phy.digital); iounmap(adpt->phy.base); + free_netdev(netdev); + return 0; } From 0336f8ffece62f882ab3012820965a786a983f70 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:58:29 +0300 Subject: [PATCH 0193/1469] net: ti: fix UAF in tlan_remove_one priv is netdev private data and it cannot be used after free_netdev() call. Using priv after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 1e0a8b13d355 ("tlan: cancel work at remove path") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/tlan.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 0b2ce4bdc2c3..e0cb713193ea 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -313,9 +313,8 @@ static void tlan_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); #endif - free_netdev(dev); - cancel_work_sync(&priv->tlan_tqueue); + free_netdev(dev); } static void tlan_start(struct net_device *dev) From 43b90bfad34bcb81b8a5bc7dc650800f4be1787e Mon Sep 17 00:00:00 2001 From: Alexander Ovechkin Date: Fri, 9 Jul 2021 18:28:23 +0300 Subject: [PATCH 0194/1469] net: send SYNACK packet with accepted fwmark commit e05a90ec9e16 ("net: reflect mark on tcp syn ack packets") fixed IPv4 only. This part is for the IPv6 side. Fixes: e05a90ec9e16 ("net: reflect mark on tcp syn ack packets") Signed-off-by: Alexander Ovechkin Acked-by: Dmitry Yakunin Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 323989927a0a..0ce52d46e4f8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -555,7 +555,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, + err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); From 358ed624207012f03318235017ac6fb41f8af592 Mon Sep 17 00:00:00 2001 From: Talal Ahmad Date: Fri, 9 Jul 2021 11:43:06 -0400 Subject: [PATCH 0195/1469] tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path sk_wmem_schedule makes sure that sk_forward_alloc has enough bytes for charging that is going to be done by sk_mem_charge. In the transmit zerocopy path, there is sk_mem_charge but there was no call to sk_wmem_schedule. This change adds that call. Without this call to sk_wmem_schedule, sk_forward_alloc can go negetive which is a bug because sk_forward_alloc is a per-socket space that has been forward charged so this can't be negative. Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY") Signed-off-by: Talal Ahmad Reviewed-by: Willem de Bruijn Reviewed-by: Wei Wang Reviewed-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d5ab5f243640..8cb44040ec68 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1375,6 +1375,9 @@ new_segment: } pfrag->offset += copy; } else { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); From 28b34f01a73435a754956ebae826e728c03ffa38 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Fri, 9 Jul 2021 18:16:09 +0200 Subject: [PATCH 0196/1469] net: do not reuse skbuff allocated from skbuff_fclone_cache in the skb cache Some socket buffers allocated in the fclone cache (in __alloc_skb) can end-up in the following path[1]: napi_skb_finish __kfree_skb_defer napi_skb_cache_put The issue is napi_skb_cache_put is not fclone friendly and will put those skbuff in the skb cache to be reused later, although this cache only expects skbuff allocated from skbuff_head_cache. When this happens the skbuff is eventually freed using the wrong origin cache, and we can see traces similar to: [ 1223.947534] cache_from_obj: Wrong slab cache. skbuff_head_cache but object is from skbuff_fclone_cache [ 1223.948895] WARNING: CPU: 3 PID: 0 at mm/slab.h:442 kmem_cache_free+0x251/0x3e0 [ 1223.950211] Modules linked in: [ 1223.950680] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.13.0+ #474 [ 1223.951587] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-3.fc34 04/01/2014 [ 1223.953060] RIP: 0010:kmem_cache_free+0x251/0x3e0 Leading sometimes to other memory related issues. Fix this by using __kfree_skb for fclone skbuff, similar to what is done the other place __kfree_skb_defer is called. [1] At least in setups using veth pairs and tunnels. Building a kernel with KASAN we can for example see packets allocated in sk_stream_alloc_skb hit the above path and later the issue arises when the skbuff is reused. Fixes: 9243adfc311a ("skbuff: queue NAPI_MERGED_FREE skbs into NAPI cache instead of freeing") Cc: Alexander Lobakin Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 03c95a0867bb..64b21f0a2048 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6234,6 +6234,8 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); else __kfree_skb_defer(skb); break; From c26d6586e97a69ef9b429cc577ca4c9d2d2ec7cd Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Wed, 9 Jun 2021 13:23:07 -0400 Subject: [PATCH 0197/1469] drm/vmwgfx: Fix implicit declaration error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The declarations of ttm_range_man_init and ttm_range_man_fini have been moved to ttm_range_manager.h so we have to add it to the include list. Signed-off-by: Zack Rusin Reported-by: Randy Dunlap Fixes: 3eb7d96e9415 ("drm/ttm: flip over the range manager to self allocated nodes") Cc: Christian König Cc: Matthew Auld Reviewed-by: Martin Krastev Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210609172307.131929-10-zackr@vmware.com --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6f5ea00973e0..45aeeca9b8f6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include From 34bd46bcf3de72cbffcdc42d3fa67e543d1c869b Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Tue, 15 Jun 2021 14:23:35 -0400 Subject: [PATCH 0198/1469] drm/vmwgfx: Fix a bad merge in otable batch takedown Change 2ef4fb92363c ("drm/vmwgfx: Make sure bo's are unpinned before putting them back") caused a conflict in one of the drm trees and the merge commit 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") accidently re-added code that the original change was removing. Fixed by removing the incorrect buffer unpin - it has already been unpinned two lines above. Fixes: 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") Signed-off-by: Zack Rusin Reviewed-by: Martin Krastev Link: https://patchwork.freedesktop.org/patch/msgid/20210615182336.995192-4-zackr@vmware.com --- drivers/gpu/drm/vmwgfx/vmwgfx_mob.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index 5648664f71bc..f2d625415458 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -354,7 +354,6 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv, ttm_bo_unpin(bo); ttm_bo_unreserve(bo); - ttm_bo_unpin(batch->otable_bo); ttm_bo_put(batch->otable_bo); batch->otable_bo = NULL; } From 9992a078b1771da354ac1f9737e1e639b687caa2 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 9 Jul 2021 11:45:02 +0800 Subject: [PATCH 0199/1469] net: ip_tunnel: fix mtu calculation for ETHER tunnel devices Commit 28e104d00281 ("net: ip_tunnel: fix mtu calculation") removed dev->hard_header_len subtraction when calculate MTU for tunnel devices as there is an overhead for device that has header_ops. But there are ETHER tunnel devices, like gre_tap or erspan, which don't have header_ops but set dev->hard_header_len during setup. This makes pkts greater than (MTU - ETH_HLEN) could not be xmited. Fix it by subtracting the ETHER tunnel devices' dev->hard_header_len for MTU calculation. Fixes: 28e104d00281 ("net: ip_tunnel: fix mtu calculation") Reported-by: Jianlin Shi Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f6cc26de5ed3..0dca00745ac3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) } dev->needed_headroom = t_hlen + hlen; - mtu -= t_hlen; + mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; @@ -348,6 +348,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + dev->max_mtu -= dev->hard_header_len; + ip_tunnel_add(itn, nt); return nt; @@ -489,11 +492,14 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; + pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; - if (df) + if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); - else + mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; + } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); @@ -972,6 +978,9 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + max_mtu -= dev->hard_header_len; + if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1149,6 +1158,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); + if (dev->type == ARPHRD_ETHER) + max -= dev->hard_header_len; + mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } From 67a9c94317402b826fc3db32afc8f39336803d97 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 9 Jul 2021 17:35:18 +0000 Subject: [PATCH 0200/1469] net: validate lwtstate->data before returning from skb_tunnel_info() skb_tunnel_info() returns pointer of lwtstate->data as ip_tunnel_info type without validation. lwtstate->data can have various types such as mpls_iptunnel_encap, etc and these are not compatible. So skb_tunnel_info() should validate before returning that pointer. Splat looks like: BUG: KASAN: slab-out-of-bounds in vxlan_get_route+0x418/0x4b0 [vxlan] Read of size 2 at addr ffff888106ec2698 by task ping/811 CPU: 1 PID: 811 Comm: ping Not tainted 5.13.0+ #1195 Call Trace: dump_stack_lvl+0x56/0x7b print_address_description.constprop.8.cold.13+0x13/0x2ee ? vxlan_get_route+0x418/0x4b0 [vxlan] ? vxlan_get_route+0x418/0x4b0 [vxlan] kasan_report.cold.14+0x83/0xdf ? vxlan_get_route+0x418/0x4b0 [vxlan] vxlan_get_route+0x418/0x4b0 [vxlan] [ ... ] vxlan_xmit_one+0x148b/0x32b0 [vxlan] [ ... ] vxlan_xmit+0x25c5/0x4780 [vxlan] [ ... ] dev_hard_start_xmit+0x1ae/0x6e0 __dev_queue_xmit+0x1f39/0x31a0 [ ... ] neigh_xmit+0x2f9/0x940 mpls_xmit+0x911/0x1600 [mpls_iptunnel] lwtunnel_xmit+0x18f/0x450 ip_finish_output2+0x867/0x2040 [ ... ] Fixes: 61adedf3e3f1 ("route: move lwtunnel state to dst_entry") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 56cb3c38569a..14efa0ded75d 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -45,7 +45,9 @@ skb_tunnel_info(const struct sk_buff *skb) return &md_dst->u.tun_info; dst = skb_dst(skb); - if (dst && dst->lwtstate) + if (dst && dst->lwtstate && + (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || + dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; From 0c71929b5893e410e0efbe1bbeca6f19a5f19956 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:46 -0700 Subject: [PATCH 0201/1469] mptcp: fix warning in __skb_flow_dissect() when do syn cookie for subflow join I did stress test with wrk[1] and webfsd[2] with the assistance of mptcp-tools[3]: Server side: ./use_mptcp.sh webfsd -4 -R /tmp/ -p 8099 Client side: ./use_mptcp.sh wrk -c 200 -d 30 -t 4 http://192.168.174.129:8099/ and got the following warning message: [ 55.552626] TCP: request_sock_subflow: Possible SYN flooding on port 8099. Sending cookies. Check SNMP counters. [ 55.553024] ------------[ cut here ]------------ [ 55.553027] WARNING: CPU: 0 PID: 10 at net/core/flow_dissector.c:984 __skb_flow_dissect+0x280/0x1650 ... [ 55.553117] CPU: 0 PID: 10 Comm: ksoftirqd/0 Not tainted 5.12.0+ #18 [ 55.553121] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 02/27/2020 [ 55.553124] RIP: 0010:__skb_flow_dissect+0x280/0x1650 ... [ 55.553133] RSP: 0018:ffffb79580087770 EFLAGS: 00010246 [ 55.553137] RAX: 0000000000000000 RBX: ffffffff8ddb58e0 RCX: ffffb79580087888 [ 55.553139] RDX: ffffffff8ddb58e0 RSI: ffff8f7e4652b600 RDI: 0000000000000000 [ 55.553141] RBP: ffffb79580087858 R08: 0000000000000000 R09: 0000000000000008 [ 55.553143] R10: 000000008c622965 R11: 00000000d3313a5b R12: ffff8f7e4652b600 [ 55.553146] R13: ffff8f7e465c9062 R14: 0000000000000000 R15: ffffb79580087888 [ 55.553149] FS: 0000000000000000(0000) GS:ffff8f7f75e00000(0000) knlGS:0000000000000000 [ 55.553152] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 55.553154] CR2: 00007f73d1d19000 CR3: 0000000135e10004 CR4: 00000000003706f0 [ 55.553160] Call Trace: [ 55.553166] ? __sha256_final+0x67/0xd0 [ 55.553173] ? sha256+0x7e/0xa0 [ 55.553177] __skb_get_hash+0x57/0x210 [ 55.553182] subflow_init_req_cookie_join_save+0xac/0xc0 [ 55.553189] subflow_check_req+0x474/0x550 [ 55.553195] ? ip_route_output_key_hash+0x67/0x90 [ 55.553200] ? xfrm_lookup_route+0x1d/0xa0 [ 55.553207] subflow_v4_route_req+0x8e/0xd0 [ 55.553212] tcp_conn_request+0x31e/0xab0 [ 55.553218] ? selinux_socket_sock_rcv_skb+0x116/0x210 [ 55.553224] ? tcp_rcv_state_process+0x179/0x6d0 [ 55.553229] tcp_rcv_state_process+0x179/0x6d0 [ 55.553235] tcp_v4_do_rcv+0xaf/0x220 [ 55.553239] tcp_v4_rcv+0xce4/0xd80 [ 55.553243] ? ip_route_input_rcu+0x246/0x260 [ 55.553248] ip_protocol_deliver_rcu+0x35/0x1b0 [ 55.553253] ip_local_deliver_finish+0x44/0x50 [ 55.553258] ip_local_deliver+0x6c/0x110 [ 55.553262] ? ip_rcv_finish_core.isra.19+0x5a/0x400 [ 55.553267] ip_rcv+0xd1/0xe0 ... After debugging, I found in __skb_flow_dissect(), skb->dev and skb->sk are both NULL, then net is NULL, and trigger WARN_ON_ONCE(!net), actually net is always NULL in this code path, as skb->dev is set to NULL in tcp_v4_rcv(), and skb->sk is never set. Code snippet in __skb_flow_dissect() that trigger warning: 975 if (skb) { 976 if (!net) { 977 if (skb->dev) 978 net = dev_net(skb->dev); 979 else if (skb->sk) 980 net = sock_net(skb->sk); 981 } 982 } 983 984 WARN_ON_ONCE(!net); So, using seq and transport header derived hash. [1] https://github.com/wg/wrk [2] https://github.com/ourway/webfsd [3] https://github.com/pabeni/mptcp-tools Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Suggested-by: Paolo Abeni Suggested-by: Florian Westphal Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/syncookies.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index abe0fd099746..37127781aee9 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -37,7 +37,21 @@ static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net) { - u32 i = skb_get_hash(skb) ^ net_hash_mix(net); + static u32 mptcp_join_hash_secret __read_mostly; + struct tcphdr *th = tcp_hdr(skb); + u32 seq, i; + + net_get_random_once(&mptcp_join_hash_secret, + sizeof(mptcp_join_hash_secret)); + + if (th->syn) + seq = TCP_SKB_CB(skb)->seq; + else + seq = TCP_SKB_CB(skb)->seq - 1; + + i = jhash_3words(seq, net_hash_mix(net), + (__force __u32)th->source << 16 | (__force __u32)th->dest, + mptcp_join_hash_secret); return i % ARRAY_SIZE(join_entries); } From 030d37bd1cd2443a1f21db47eb301899bfa45a2a Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:47 -0700 Subject: [PATCH 0202/1469] mptcp: remove redundant req destruct in subflow_check_req() In subflow_check_req(), if subflow sport is mismatch, will put msk, destroy token, and destruct req, then return -EPERM, which can be done by subflow_req_destructor() via: tcp_conn_request() |--__reqsk_free() |--subflow_req_destructor() So we should remove these redundant code, otherwise will call tcp_v4_reqsk_destructor() twice, and may double free inet_rsk(req)->ireq_opt. Fixes: 5bc56388c74f ("mptcp: add port number check for MP_JOIN") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 66d0b1893d26..b15e2017168d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -214,11 +214,6 @@ again: ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { - sock_put((struct sock *)subflow_req->msk); - mptcp_token_destroy_request(req); - tcp_request_sock_ops.destructor(req); - subflow_req->msk = NULL; - subflow_req->mp_join = 0; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); return -EPERM; } From 8547ea5f52dd8ef19b69c25c41b1415481b3503b Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:48 -0700 Subject: [PATCH 0203/1469] mptcp: fix syncookie process if mptcp can not_accept new subflow Lots of "TCP: tcp_fin: Impossible, sk->sk_state=7" in client side when doing stress testing using wrk and webfsd. There are at least two cases may trigger this warning: 1.mptcp is in syncookie, and server recv MP_JOIN SYN request, in subflow_check_req(), the mptcp_can_accept_new_subflow() return false, so subflow_init_req_cookie_join_save() isn't called, i.e. not store the data present in the MP_JOIN syn request and the random nonce in hash table - join_entries[], but still send synack. When recv 3rd-ack, mptcp_token_join_cookie_init_state() will return false, and 3rd-ack is dropped, then if mptcp conn is closed by client, client will send a DATA_FIN and a MPTCP FIN, the DATA_FIN doesn't have MP_CAPABLE or MP_JOIN, so mptcp_subflow_init_cookie_req() will return 0, and pass the cookie check, MP_JOIN request is fallback to normal TCP. Server will send a TCP FIN if closed, in client side, when process TCP FIN, it will do reset, the code path is: tcp_data_queue()->mptcp_incoming_options() ->check_fully_established()->mptcp_subflow_reset(). mptcp_subflow_reset() will set sock state to TCP_CLOSE, so tcp_fin will hit TCP_CLOSE, and print the warning. 2.mptcp is in syncookie, and server recv 3rd-ack, in mptcp_subflow_init_cookie_req(), mptcp_can_accept_new_subflow() return false, and subflow_req->mp_join is not set to 1, so in subflow_syn_recv_sock() will not reset the MP_JOIN subflow, but fallback to normal TCP, and then the same thing happens when server will send a TCP FIN if closed. For case1, subflow_check_req() return -EPERM, then tcp_conn_request() will drop MP_JOIN SYN. For case2, let subflow_syn_recv_sock() call mptcp_can_accept_new_subflow(), and do fatal fallback, send reset. Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index b15e2017168d..966f777d35ce 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -225,6 +225,8 @@ again: if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); + else + return -EPERM; } pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, @@ -264,9 +266,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) return -EINVAL; - if (mptcp_can_accept_new_subflow(subflow_req->msk)) - subflow_req->mp_join = 1; - + subflow_req->mp_join = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; } From 6787b7e350d3552651a3422d3d8980fbc8d65368 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:49 -0700 Subject: [PATCH 0204/1469] mptcp: avoid processing packet if a subflow reset If check_fully_established() causes a subflow reset, it should not continue to process the packet in tcp_data_queue(). Add a return value to mptcp_incoming_options(), and return false if a subflow has been reset, else return true. Then drop the packet in tcp_data_queue()/tcp_rcv_state_process() if mptcp_incoming_options() return false. Fixes: d582484726c4 ("mptcp: fix fallback for MP_JOIN subflows") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/mptcp.h | 5 +++-- net/ipv4/tcp_input.c | 19 +++++++++++++++---- net/mptcp/options.c | 19 +++++++++++++------ 3 files changed, 31 insertions(+), 12 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index cb580b06152f..8b5af683a818 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -105,7 +105,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts); -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts); @@ -227,9 +227,10 @@ static inline bool mptcp_established_options(struct sock *sk, return false; } -static inline void mptcp_incoming_options(struct sock *sk, +static inline bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { + return true; } static inline void mptcp_skb_ext_move(struct sk_buff *to, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a5a8d0a378b2..149ceb5c94ff 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4247,6 +4247,9 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) { trace_tcp_receive_reset(sk); + /* mptcp can't tell us to ignore reset pkts, + * so just ignore the return value of mptcp_incoming_options(). + */ if (sk_is_mptcp(sk)) mptcp_incoming_options(sk, skb); @@ -4941,8 +4944,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) bool fragstolen; int eaten; - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not continue + * to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) { + __kfree_skb(skb); + return; + } if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); @@ -6523,8 +6531,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_CLOSING: case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not + * continue to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) + goto discard; break; } fallthrough; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b5850afea343..4452455aef7f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1035,7 +1035,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) +/* Return false if a subflow has been reset, else return true */ +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); @@ -1053,12 +1054,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) __mptcp_check_push(subflow->conn, sk); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); - return; + return true; } mptcp_get_options(sk, skb, &mp_opt); + + /* The subflow can be in close state only if check_fully_established() + * just sent a reset. If so, tell the caller to ignore the current packet. + */ if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) - return; + return sk->sk_state != TCP_CLOSE; if (mp_opt.fastclose && msk->local_key == mp_opt.rcvr_key) { @@ -1100,7 +1105,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } if (!mp_opt.dss) - return; + return true; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck @@ -1119,12 +1124,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) schedule_work(&msk->work)) sock_hold(subflow->conn); - return; + return true; } mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return; + return true; memset(mpext, 0, sizeof(*mpext)); @@ -1153,6 +1158,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) if (mpext->csum_reqd) mpext->csum = mp_opt.csum; } + + return true; } static void mptcp_set_rwin(const struct tcp_sock *tp) From a7da441621c7945fbfd43ed239c93b8073cda502 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:50 -0700 Subject: [PATCH 0205/1469] selftests: mptcp: fix case multiple subflows limited by server After patch "mptcp: fix syncookie process if mptcp can not_accept new subflow", if subflow is limited, MP_JOIN SYN is dropped, and no SYN/ACK will be replied. So in case "multiple subflows limited by server", the expected SYN/ACK number should be 1. Fixes: 00587187ad30 ("selftests: mptcp: add test cases for mptcp join tests with syn cookies") Reported-by: kernel test robot Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 9a191c1a5de8..f02f4de2f3a0 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1409,7 +1409,7 @@ syncookies_tests() ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 2 1 + chk_join_nr "subflows limited by server w cookies" 2 1 1 # test signal address with cookies reset_with_cookies From ce599c516386f09ca30848a1a4eb93d3fffbe187 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Jul 2021 17:20:51 -0700 Subject: [PATCH 0206/1469] mptcp: properly account bulk freed memory After commit 879526030c8b ("mptcp: protect the rx path with the msk socket spinlock") the rmem currently used by a given msk is really sk_rmem_alloc - rmem_released. The safety check in mptcp_data_ready() does not take the above in due account, as a result legit incoming data is kept in subflow receive queue with no reason, delaying or blocking MPTCP-level ack generation. This change addresses the issue introducing a new helper to fetch the rmem memory and using it as needed. Additionally add a MIB counter for the exceptional event described above - the peer is misbehaving. Finally, introduce the required annotation when rmem_released is updated. Fixes: 879526030c8b ("mptcp: protect the rx path with the msk socket spinlock") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/211 Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/mib.c | 1 + net/mptcp/mib.h | 1 + net/mptcp/protocol.c | 12 +++++++----- net/mptcp/protocol.h | 10 +++++++++- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 52ea2517e856..ff2cc0e3273d 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -44,6 +44,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), + SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 193466c9b549..0663cb12b448 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -37,6 +37,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ + MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7a5afa8c6866..a88924947815 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !atomic_read(&sk->sk_rmem_alloc); + rx_empty = !__mptcp_rmem(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -720,8 +720,10 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) + if (__mptcp_rmem(sk) > sk_rbuf) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); return; + } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { /* we will bulk release the skb memory later */ skb->destructor = NULL; - msk->rmem_released += skb->truesize; + WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); } @@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk) atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, msk->rmem_released); - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); } static void __mptcp_splice_receive_queue(struct sock *sk) @@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk) msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); msk->tx_pending_data = 0; msk->first = NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 426ed80fe72f..0f0c026c5f8b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -296,9 +296,17 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) return (struct mptcp_sock *)sk; } +/* the msk socket don't use the backlog, also account for the bulk + * free memory + */ +static inline int __mptcp_rmem(const struct sock *sk) +{ + return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); +} + static inline int __mptcp_space(const struct sock *sk) { - return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released); + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); } static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) From 222722bc6ebfabf5d54467070f05cf9c0a55ea8c Mon Sep 17 00:00:00 2001 From: Yunjian Wang Date: Sat, 10 Jul 2021 11:32:49 +0800 Subject: [PATCH 0207/1469] virtio_net: check virtqueue_add_sgs() return value As virtqueue_add_sgs() can fail, we should check the return value. Addresses-Coverity-ID: 1464439 ("Unchecked return value") Signed-off-by: Yunjian Wang Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b0b81458ca94..13952e2dba5e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1743,6 +1743,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, { struct scatterlist *sgs[4], hdr, stat; unsigned out_num = 0, tmp; + int ret; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); @@ -1762,7 +1763,12 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, sgs[out_num] = &stat; BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); - virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); + ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); + if (ret < 0) { + dev_warn(&vi->vdev->dev, + "Failed to add sgs for command vq: %d\n.", ret); + return false; + } if (unlikely(!virtqueue_kick(vi->cvq))) return vi->ctrl->status == VIRTIO_NET_OK; From 84f7e0bb4809f4497124b6b6904c07c8a0c73c58 Mon Sep 17 00:00:00 2001 From: kernel test robot Date: Sun, 11 Jul 2021 18:12:56 +0200 Subject: [PATCH 0208/1469] dsa: fix for_each_child.cocci warnings For_each_available_child_of_node should have of_node_put() before return around line 423. Generated by: scripts/coccinelle/iterators/for_each_child.cocci CC: Alexander Lobakin Reported-by: kernel test robot Signed-off-by: kernel test robot Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a7e5ac60baef..1542bfb8b5e5 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -419,8 +419,10 @@ int ksz_switch_register(struct ksz_device *dev, if (of_property_read_u32(port, "reg", &port_num)) continue; - if (!(dev->port_mask & BIT(port_num))) + if (!(dev->port_mask & BIT(port_num))) { + of_node_put(port); return -EINVAL; + } of_get_phy_mode(port, &dev->ports[port_num].interface); } From a5de4be0aaaa66a2fa98e8a33bdbed3bd0682804 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sun, 11 Jul 2021 18:38:15 +0200 Subject: [PATCH 0209/1469] net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It seems that we cannot differentiate 88X3310 from 88X3340 by simply looking at bit 3 of revision ID. This only works on revisions A0 and A1. On revision B0, this bit is always 1. Instead use the 3.d00d register for differentiation, since this register contains information about number of ports on the device. Fixes: 9885d016ffa9 ("net: phy: marvell10g: add separate structure for 88X3340") Signed-off-by: Marek Behún Reported-by: Matteo Croce Tested-by: Matteo Croce Signed-off-by: David S. Miller --- drivers/net/phy/marvell10g.c | 40 +++++++++++++++++++++++++++++++----- include/linux/marvell_phy.h | 6 +----- 2 files changed, 36 insertions(+), 10 deletions(-) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index bbbc6ac8fa82..53a433442803 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -78,6 +78,11 @@ enum { /* Temperature read register (88E2110 only) */ MV_PCS_TEMP = 0x8042, + /* Number of ports on the device */ + MV_PCS_PORT_INFO = 0xd00d, + MV_PCS_PORT_INFO_NPORTS_MASK = 0x0380, + MV_PCS_PORT_INFO_NPORTS_SHIFT = 7, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -966,6 +971,30 @@ static const struct mv3310_chip mv2111_type = { #endif }; +static int mv3310_get_number_of_ports(struct phy_device *phydev) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PORT_INFO); + if (ret < 0) + return ret; + + ret &= MV_PCS_PORT_INFO_NPORTS_MASK; + ret >>= MV_PCS_PORT_INFO_NPORTS_SHIFT; + + return ret + 1; +} + +static int mv3310_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 1; +} + +static int mv3340_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 4; +} + static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g) { int val; @@ -994,7 +1023,8 @@ static int mv2111_match_phy_device(struct phy_device *phydev) static struct phy_driver mv3310_drivers[] = { { .phy_id = MARVELL_PHY_ID_88X3310, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3310_match_phy_device, .name = "mv88x3310", .driver_data = &mv3310_type, .get_features = mv3310_get_features, @@ -1011,8 +1041,9 @@ static struct phy_driver mv3310_drivers[] = { .set_loopback = genphy_c45_loopback, }, { - .phy_id = MARVELL_PHY_ID_88X3340, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id = MARVELL_PHY_ID_88X3310, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3340_match_phy_device, .name = "mv88x3340", .driver_data = &mv3340_type, .get_features = mv3310_get_features, @@ -1069,8 +1100,7 @@ static struct phy_driver mv3310_drivers[] = { module_phy_driver(mv3310_drivers); static struct mdio_device_id __maybe_unused mv3310_tbl[] = { - { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_88X33X0_MASK }, - { MARVELL_PHY_ID_88X3340, MARVELL_PHY_ID_88X33X0_MASK }, + { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK }, { }, }; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index acee44b9db26..0f06c2287b52 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -22,14 +22,10 @@ #define MARVELL_PHY_ID_88E1545 0x01410ea0 #define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 +#define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 -/* PHY IDs and mask for Alaska 10G PHYs */ -#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8 -#define MARVELL_PHY_ID_88X3310 0x002b09a0 -#define MARVELL_PHY_ID_88X3340 0x002b09a8 - /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 From 04bef83a3358946bfc98a5ecebd1b0003d83d882 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 11 Jul 2021 12:56:28 +0300 Subject: [PATCH 0210/1469] net: bridge: multicast: fix PIM hello router port marking race When a PIM hello packet is received on a bridge port with multicast snooping enabled, we mark it as a router port automatically, that includes adding that port the router port list. The multicast lock protects that list, but it is not acquired in the PIM message case leading to a race condition, we need to take it to fix the race. Cc: stable@vger.kernel.org Fixes: 91b02d3d133b ("bridge: mcast: add router port on PIM hello message") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 53c3a9d80d9c..3bbbc6d7b7c3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3264,7 +3264,9 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, From 000b7287b67555fee39d39fff75229dedde0dcbf Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 11 Jul 2021 12:56:29 +0300 Subject: [PATCH 0211/1469] net: bridge: multicast: fix MRD advertisement router port marking race When an MRD advertisement is received on a bridge port with multicast snooping enabled, we mark it as a router port automatically, that includes adding that port to the router port list. The multicast lock protects that list, but it is not acquired in the MRD advertisement case leading to a race condition, we need to take it to fix the race. Cc: stable@vger.kernel.org Cc: linus.luessing@c0d3.blue Fixes: 4b3087c7e37f ("bridge: Snoop Multicast Router Advertisements") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3bbbc6d7b7c3..d0434dc8c03b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3277,7 +3277,9 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); return 0; } @@ -3345,7 +3347,9 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; + spin_lock(&br->multicast_lock); br_ip6_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge *br, From 9c6882608bce249a8918744ecdb65748534e3f17 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 10 Jul 2021 02:45:59 +0100 Subject: [PATCH 0212/1469] io_uring: use right task for exiting checks When we use delayed_work for fallback execution of requests, current will be not of the submitter task, and so checks in io_req_task_submit() may not behave as expected. Currently, it leaves inline completions not flushed, so making io_ring_exit_work() to hang. Use the submitter task for all those checks. Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/cb413c715bed0bc9c98b169059ea9c8a2c770715.1625881431.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d94fb5835a20..118215211bb2 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2016,7 +2016,7 @@ static void io_req_task_submit(struct io_kiocb *req) /* ctx stays valid until unlock, even if we drop all ours ctx->refs */ mutex_lock(&ctx->uring_lock); - if (!(current->flags & PF_EXITING) && !current->in_execve) + if (!(req->task->flags & PF_EXITING) && !req->task->in_execve) __io_queue_sqe(req); else io_req_complete_failed(req, -EFAULT); From 1b48773f9fd09f311d1166ce1dd50652ebe05218 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 11 Jul 2021 22:41:13 +0100 Subject: [PATCH 0213/1469] io_uring: fix io_drain_req() io_drain_req() return whether the request has been consumed or not, not an error code. Fix a stupid mistake slipped from optimisation patches. Reported-by: syzbot+ba6fcd859210f4e9e109@syzkaller.appspotmail.com Fixes: 76cc33d79175a ("io_uring: refactor io_req_defer()") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4d3c53c4274ffff307c8ae062fc7fda63b978df2.1626039606.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 118215211bb2..0cac361bf6b8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6019,11 +6019,13 @@ static bool io_drain_req(struct io_kiocb *req) ret = io_req_prep_async(req); if (ret) - return ret; + goto fail; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { - io_req_complete_failed(req, -ENOMEM); + ret = -ENOMEM; +fail: + io_req_complete_failed(req, ret); return true; } From 0dfc21c1a4cac321749a53c92da616d9546d00e3 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 8 Jul 2021 12:34:31 +0200 Subject: [PATCH 0214/1469] ASoC: tegra: Use ADMAIF component for DMA allocations DMA memory is currently allocated for the soundcard device, which is a virtual device added for the sole purpose of "stitching" together the audio device. It is not a real device and therefore doesn't have a DMA mask or a description of the path to and from memory of accesses. Memory accesses really originate from the ADMA controller that provides the DMA channels used by the PCM component. However, since the DMA memory is allocated up-front and the DMA channels aren't known at that point, there is no way of knowing the DMA channel provider at allocation time. The next best physical device in the memory path is the ADMAIF. Use it as the device to allocate DMA memory to. iommus and interconnects device tree properties can thus be added to the ADMAIF device tree node to describe the memory access path for audio. Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20210708103432.1690385-2-thierry.reding@gmail.com Signed-off-by: Mark Brown --- sound/soc/tegra/tegra_pcm.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/sound/soc/tegra/tegra_pcm.c b/sound/soc/tegra/tegra_pcm.c index 573374b89b10..d3276b4595af 100644 --- a/sound/soc/tegra/tegra_pcm.c +++ b/sound/soc/tegra/tegra_pcm.c @@ -213,19 +213,19 @@ snd_pcm_uframes_t tegra_pcm_pointer(struct snd_soc_component *component, } EXPORT_SYMBOL_GPL(tegra_pcm_pointer); -static int tegra_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream, +static int tegra_pcm_preallocate_dma_buffer(struct device *dev, struct snd_pcm *pcm, int stream, size_t size) { struct snd_pcm_substream *substream = pcm->streams[stream].substream; struct snd_dma_buffer *buf = &substream->dma_buffer; - buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL); + buf->area = dma_alloc_wc(dev, size, &buf->addr, GFP_KERNEL); if (!buf->area) return -ENOMEM; buf->private_data = NULL; buf->dev.type = SNDRV_DMA_TYPE_DEV; - buf->dev.dev = pcm->card->dev; + buf->dev.dev = dev; buf->bytes = size; return 0; @@ -244,31 +244,28 @@ static void tegra_pcm_deallocate_dma_buffer(struct snd_pcm *pcm, int stream) if (!buf->area) return; - dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr); + dma_free_wc(buf->dev.dev, buf->bytes, buf->area, buf->addr); buf->area = NULL; } -static int tegra_pcm_dma_allocate(struct snd_soc_pcm_runtime *rtd, +static int tegra_pcm_dma_allocate(struct device *dev, struct snd_soc_pcm_runtime *rtd, size_t size) { - struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; int ret; - ret = dma_set_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret < 0) return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { - ret = tegra_pcm_preallocate_dma_buffer(pcm, - SNDRV_PCM_STREAM_PLAYBACK, size); + ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_PLAYBACK, size); if (ret) goto err; } if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) { - ret = tegra_pcm_preallocate_dma_buffer(pcm, - SNDRV_PCM_STREAM_CAPTURE, size); + ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_CAPTURE, size); if (ret) goto err_free_play; } @@ -284,7 +281,16 @@ err: int tegra_pcm_construct(struct snd_soc_component *component, struct snd_soc_pcm_runtime *rtd) { - return tegra_pcm_dma_allocate(rtd, tegra_pcm_hardware.buffer_bytes_max); + struct device *dev = component->dev; + + /* + * Fallback for backwards-compatibility with older device trees that + * have the iommus property in the virtual, top-level "sound" node. + */ + if (!of_get_property(dev->of_node, "iommus", NULL)) + dev = rtd->card->snd_card->dev; + + return tegra_pcm_dma_allocate(dev, rtd, tegra_pcm_hardware.buffer_bytes_max); } EXPORT_SYMBOL_GPL(tegra_pcm_construct); From 2169d6a0f0721935410533281fc7e87e4e2322d1 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 8 Jul 2021 11:12:55 +0200 Subject: [PATCH 0215/1469] ASoC: tlv320aic32x4: Fix TAS2505 volume controls None of the TAS2505 outputs are stereo, do not pretend they are by implementing them using SOC*DOUBLE* macros referencing the same register twice, use SOC*SINGLE* instead. Fix volume ranges and mute control for the codec according to datasheet. Fixes: b4525b6196cd7 ("ASoC: tlv320aic32x4: add support for TAS2505") Signed-off-by: Marek Vasut Cc: Claudius Heine Cc: Mark Brown Link: https://lore.kernel.org/r/20210708091255.56502-1-marex@denx.de Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic32x4.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index c63b717040ed..dcd8aeb45cb3 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -250,8 +250,8 @@ static DECLARE_TLV_DB_SCALE(tlv_pcm, -6350, 50, 0); static DECLARE_TLV_DB_SCALE(tlv_driver_gain, -600, 100, 0); /* -12dB min, 0.5dB steps */ static DECLARE_TLV_DB_SCALE(tlv_adc_vol, -1200, 50, 0); - -static DECLARE_TLV_DB_LINEAR(tlv_spk_vol, TLV_DB_GAIN_MUTE, 0); +/* -6dB min, 1dB steps */ +static DECLARE_TLV_DB_SCALE(tlv_tas_driver_gain, -5850, 50, 0); static DECLARE_TLV_DB_SCALE(tlv_amp_vol, 0, 600, 1); static const char * const lo_cm_text[] = { @@ -1063,21 +1063,20 @@ static const struct snd_soc_component_driver soc_component_dev_aic32x4 = { }; static const struct snd_kcontrol_new aic32x4_tas2505_snd_controls[] = { - SOC_DOUBLE_R_S_TLV("PCM Playback Volume", AIC32X4_LDACVOL, - AIC32X4_LDACVOL, 0, -0x7f, 0x30, 7, 0, tlv_pcm), + SOC_SINGLE_S8_TLV("PCM Playback Volume", + AIC32X4_LDACVOL, -0x7f, 0x30, tlv_pcm), SOC_ENUM("DAC Playback PowerTune Switch", l_ptm_enum), - SOC_DOUBLE_R_S_TLV("HP Driver Playback Volume", AIC32X4_HPLGAIN, - AIC32X4_HPLGAIN, 0, -0x6, 0x1d, 5, 0, - tlv_driver_gain), - SOC_DOUBLE_R("HP DAC Playback Switch", AIC32X4_HPLGAIN, - AIC32X4_HPLGAIN, 6, 0x01, 1), + + SOC_SINGLE_TLV("HP Driver Gain Volume", + AIC32X4_HPLGAIN, 0, 0x74, 1, tlv_tas_driver_gain), + SOC_SINGLE("HP DAC Playback Switch", AIC32X4_HPLGAIN, 6, 1, 1), + + SOC_SINGLE_TLV("Speaker Driver Playback Volume", + TAS2505_SPKVOL1, 0, 0x74, 1, tlv_tas_driver_gain), + SOC_SINGLE_TLV("Speaker Amplifier Playback Volume", + TAS2505_SPKVOL2, 4, 5, 0, tlv_amp_vol), SOC_SINGLE("Auto-mute Switch", AIC32X4_DACMUTE, 4, 7, 0), - - SOC_SINGLE_RANGE_TLV("Speaker Driver Playback Volume", TAS2505_SPKVOL1, - 0, 0, 117, 1, tlv_spk_vol), - SOC_SINGLE_TLV("Speaker Amplifier Playback Volume", TAS2505_SPKVOL2, - 4, 5, 0, tlv_amp_vol), }; static const struct snd_kcontrol_new hp_output_mixer_controls[] = { From 6c621b811f99feb3941f04b386795b45f47cd771 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 7 Jul 2021 17:02:34 +0100 Subject: [PATCH 0216/1469] ASoC: tlv320aic31xx: Make regmap cache only on probe() Currently the tlv320aic31xx driver has regulator support but does not enable the regulators during probe, deferring this until something causes ASoC to make the card active. It does put the device into cache only mode but only when the component level probe is called, however if interrupts are in use the driver will access the regmap before then which if the regulators are not powered on would cause I/O problems. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210707160234.16253-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic31xx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c index 51870d50f419..b504d63385b3 100644 --- a/sound/soc/codecs/tlv320aic31xx.c +++ b/sound/soc/codecs/tlv320aic31xx.c @@ -1604,6 +1604,8 @@ static int aic31xx_i2c_probe(struct i2c_client *i2c, ret); return ret; } + regcache_cache_only(aic31xx->regmap, true); + aic31xx->dev = &i2c->dev; aic31xx->irq = i2c->irq; From 1c73daee4bf30ccdff5e86dc400daa6f74735da5 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 30 Jun 2021 17:59:59 +0800 Subject: [PATCH 0217/1469] regulator: hi6421: Fix getting wrong drvdata Since config.dev = pdev->dev.parent in current code, so dev_get_drvdata(rdev->dev.parent) call in hi6421_regulator_enable returns the drvdata of the mfd device rather than the regulator. Fix it. This was broken while converting to use simplified DT parsing because the config.dev changed from pdev->dev to pdev->dev.parent for parsing the parent's of_node. Fixes: 29dc269a85ef ("regulator: hi6421: Convert to use simplified DT parsing") Signed-off-by: Axel Lin Link: https://lore.kernel.org/r/20210630095959.2411543-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- drivers/regulator/hi6421-regulator.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/regulator/hi6421-regulator.c b/drivers/regulator/hi6421-regulator.c index bff8c515dcde..d144a4bdb76d 100644 --- a/drivers/regulator/hi6421-regulator.c +++ b/drivers/regulator/hi6421-regulator.c @@ -366,9 +366,8 @@ static struct hi6421_regulator_info static int hi6421_regulator_enable(struct regulator_dev *rdev) { - struct hi6421_regulator_pdata *pdata; + struct hi6421_regulator_pdata *pdata = rdev_get_drvdata(rdev); - pdata = dev_get_drvdata(rdev->dev.parent); /* hi6421 spec requires regulator enablement must be serialized: * - Because when BUCK, LDO switching from off to on, it will have * a huge instantaneous current; so you can not turn on two or @@ -385,9 +384,10 @@ static int hi6421_regulator_enable(struct regulator_dev *rdev) static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev) { - struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); + struct hi6421_regulator_info *info; unsigned int reg_val; + info = container_of(rdev->desc, struct hi6421_regulator_info, desc); regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val); if (reg_val & info->mode_mask) return REGULATOR_MODE_IDLE; @@ -397,9 +397,10 @@ static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev) static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev) { - struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); + struct hi6421_regulator_info *info; unsigned int reg_val; + info = container_of(rdev->desc, struct hi6421_regulator_info, desc); regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val); if (reg_val & info->mode_mask) return REGULATOR_MODE_STANDBY; @@ -410,9 +411,10 @@ static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev) static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev, unsigned int mode) { - struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); + struct hi6421_regulator_info *info; unsigned int new_mode; + info = container_of(rdev->desc, struct hi6421_regulator_info, desc); switch (mode) { case REGULATOR_MODE_NORMAL: new_mode = 0; @@ -434,9 +436,10 @@ static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev, static int hi6421_regulator_buck_set_mode(struct regulator_dev *rdev, unsigned int mode) { - struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); + struct hi6421_regulator_info *info; unsigned int new_mode; + info = container_of(rdev->desc, struct hi6421_regulator_info, desc); switch (mode) { case REGULATOR_MODE_NORMAL: new_mode = 0; @@ -459,7 +462,9 @@ static unsigned int hi6421_regulator_ldo_get_optimum_mode(struct regulator_dev *rdev, int input_uV, int output_uV, int load_uA) { - struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); + struct hi6421_regulator_info *info; + + info = container_of(rdev->desc, struct hi6421_regulator_info, desc); if (load_uA > info->eco_microamp) return REGULATOR_MODE_NORMAL; @@ -543,14 +548,13 @@ static int hi6421_regulator_probe(struct platform_device *pdev) if (!pdata) return -ENOMEM; mutex_init(&pdata->lock); - platform_set_drvdata(pdev, pdata); for (i = 0; i < ARRAY_SIZE(hi6421_regulator_info); i++) { /* assign per-regulator data */ info = &hi6421_regulator_info[i]; config.dev = pdev->dev.parent; - config.driver_data = info; + config.driver_data = pdata; config.regmap = pmic->regmap; rdev = devm_regulator_register(&pdev->dev, &info->desc, From 69e1818ad27bae167eeaaf6829d4a08900ef5153 Mon Sep 17 00:00:00 2001 From: Dan Sneddon Date: Tue, 29 Jun 2021 12:22:18 -0700 Subject: [PATCH 0218/1469] spi: atmel: Fix CS and initialization bug Commit 5fa5e6dec762 ("spi: atmel: Switch to transfer_one transfer method") switched to using transfer_one and set_cs. The core doesn't call set_cs when the chip select lines are gpios. Add the SPI_MASTER_GPIO_SS flag to the driver to ensure the calls to set_cs happen since the driver programs configuration registers there. Fixes: 5fa5e6dec762 ("spi: atmel: Switch to transfer_one transfer method") Signed-off-by: Dan Sneddon Link: https://lore.kernel.org/r/20210629192218.32125-1-dan.sneddon@microchip.com Signed-off-by: Mark Brown --- drivers/spi/spi-atmel.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 2ef74885ffa2..788dcdf25f00 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -352,8 +352,6 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi) } mr = spi_readl(as, MR); - if (spi->cs_gpiod) - gpiod_set_value(spi->cs_gpiod, 1); } else { u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0; int i; @@ -369,8 +367,6 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi) mr = spi_readl(as, MR); mr = SPI_BFINS(PCS, ~(1 << chip_select), mr); - if (spi->cs_gpiod) - gpiod_set_value(spi->cs_gpiod, 1); spi_writel(as, MR, mr); } @@ -400,8 +396,6 @@ static void cs_deactivate(struct atmel_spi *as, struct spi_device *spi) if (!spi->cs_gpiod) spi_writel(as, CR, SPI_BIT(LASTXFER)); - else - gpiod_set_value(spi->cs_gpiod, 0); } static void atmel_spi_lock(struct atmel_spi *as) __acquires(&as->lock) @@ -1483,7 +1477,8 @@ static int atmel_spi_probe(struct platform_device *pdev) master->bus_num = pdev->id; master->num_chipselect = 4; master->setup = atmel_spi_setup; - master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX); + master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX | + SPI_MASTER_GPIO_SS); master->transfer_one = atmel_spi_one_transfer; master->set_cs = atmel_spi_set_cs; master->cleanup = atmel_spi_cleanup; From 3a70dd2d050331ee4cf5ad9d5c0a32d83ead9a43 Mon Sep 17 00:00:00 2001 From: Peter Hess Date: Tue, 6 Jul 2021 14:16:09 +0200 Subject: [PATCH 0219/1469] spi: mediatek: fix fifo rx mode In FIFO mode were two problems: - RX mode was never handled and - in this case the tx_buf pointer was NULL and caused an exception fix this by handling RX mode in mtk_spi_fifo_transfer Fixes: a568231f4632 ("spi: mediatek: Add spi bus for Mediatek MT8173") Signed-off-by: Peter Hess Signed-off-by: Frank Wunderlich Link: https://lore.kernel.org/r/20210706121609.680534-1-linux@fw-web.de Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 976f73b9e299..8d5fa7f1e506 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -427,13 +427,23 @@ static int mtk_spi_fifo_transfer(struct spi_master *master, mtk_spi_setup_packet(master); cnt = xfer->len / 4; - iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt); + if (xfer->tx_buf) + iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt); + + if (xfer->rx_buf) + ioread32_rep(mdata->base + SPI_RX_DATA_REG, xfer->rx_buf, cnt); remainder = xfer->len % 4; if (remainder > 0) { reg_val = 0; - memcpy(®_val, xfer->tx_buf + (cnt * 4), remainder); - writel(reg_val, mdata->base + SPI_TX_DATA_REG); + if (xfer->tx_buf) { + memcpy(®_val, xfer->tx_buf + (cnt * 4), remainder); + writel(reg_val, mdata->base + SPI_TX_DATA_REG); + } + if (xfer->rx_buf) { + reg_val = readl(mdata->base + SPI_RX_DATA_REG); + memcpy(xfer->rx_buf + (cnt * 4), ®_val, remainder); + } } mtk_spi_enable_transfer(master); From 5937e00017f1d1dd4551e723ebfa306671f27843 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 15 Jun 2021 09:09:14 -0500 Subject: [PATCH 0220/1469] xfs: Fix multiple fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warnings by replacing /* fallthrough */ comments, and its variants, with the new pseudo-keyword macro fallthrough: fs/xfs/libxfs/xfs_attr.c:487:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:500:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:532:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:594:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:607:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1410:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1445:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1473:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Notice that Clang doesn't recognize /* fallthrough */ comments as implicit fall-through markings, so in order to globally enable -Wimplicit-fallthrough for Clang, these comments need to be replaced with fallthrough; in the whole codebase. Link: https://github.com/KSPP/linux/issues/115 Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- fs/xfs/libxfs/xfs_attr.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index d9d7d5137b73..191d51725988 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -483,7 +483,7 @@ xfs_attr_set_iter( if (error) return error; - /* fallthrough */ + fallthrough; case XFS_DAS_RM_LBLK: /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */ dac->dela_state = XFS_DAS_RM_LBLK; @@ -496,7 +496,7 @@ xfs_attr_set_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RD_LEAF: /* * This is the last step for leaf format. Read the block with @@ -528,7 +528,7 @@ xfs_attr_set_iter( return error; } - /* fallthrough */ + fallthrough; case XFS_DAS_ALLOC_NODE: /* * If there was an out-of-line value, allocate the blocks we @@ -590,7 +590,7 @@ xfs_attr_set_iter( if (error) return error; - /* fallthrough */ + fallthrough; case XFS_DAS_RM_NBLK: /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */ dac->dela_state = XFS_DAS_RM_NBLK; @@ -603,7 +603,7 @@ xfs_attr_set_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_CLR_FLAG: /* * The last state for node format. Look up the old attr and @@ -1406,7 +1406,7 @@ xfs_attr_remove_iter( state = dac->da_state; } - /* fallthrough */ + fallthrough; case XFS_DAS_RMTBLK: dac->dela_state = XFS_DAS_RMTBLK; @@ -1441,7 +1441,7 @@ xfs_attr_remove_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RM_NAME: /* * If we came here fresh from a transaction roll, reattach all @@ -1469,7 +1469,7 @@ xfs_attr_remove_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RM_SHRINK: /* * If the result is small enough, push it all into the inode. From d5c9d0a207f4c61734ccd4b51818788e8b86296a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:44:53 -0500 Subject: [PATCH 0221/1469] mt76: mt7921: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warning by explicitly adding a break statement: drivers/net/wireless/mediatek/mt76/mt7921/main.c:392:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 7fd21049ff5a..63ec140c9c37 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -389,6 +389,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, case WLAN_CIPHER_SUITE_WEP104: if (!mvif->wep_sta) return -EOPNOTSUPP; + break; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: From 4020f26b368c3e72450afedaefc2fd07ba301d20 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:47:57 -0500 Subject: [PATCH 0222/1469] nfp: flower-ct: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warning by explicitly adding a break statement: drivers/net/ethernet/netronome/nfp/flower/conntrack.c:1175:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/net/ethernet/netronome/nfp/flower/conntrack.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 273d529d43c2..684bb3efe0cf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1172,6 +1172,7 @@ int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent) nfp_ct_map_params); nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry); kfree(ct_map_ent); + break; default: break; } From 81eb1d17115fba5ea67a4939a136888a7ec05c32 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:51:03 -0500 Subject: [PATCH 0223/1469] drm/i915: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix a warning by explicitly adding a return; statement: drivers/gpu/drm/i915/gem/i915_gem_shrinker.c:65:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index f4fb68e8955a..e382b7f2353b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -62,6 +62,7 @@ static void try_to_writeback(struct drm_i915_gem_object *obj, switch (obj->mm.madv) { case I915_MADV_DONTNEED: i915_gem_object_truncate(obj); + return; case __I915_MADV_PURGED: return; } From 94b619a07655805a1622484967754f5848640456 Mon Sep 17 00:00:00 2001 From: Marco De Marco Date: Mon, 5 Jul 2021 19:44:21 +0000 Subject: [PATCH 0224/1469] USB: serial: option: add support for u-blox LARA-R6 family The patch is meant to support LARA-R6 Cat 1 module family. Module USB ID: Vendor ID: 0x05c6 Product ID: 0x90fA Interface layout: If 0: Diagnostic If 1: AT parser If 2: AT parser If 3: QMI wwan (not available in all versions) Signed-off-by: Marco De Marco Link: https://lore.kernel.org/r/49260184.kfMIbaSn9k@mars Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7608584ef4fe..0fbe253dc570 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -238,6 +238,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_UC15 0x9090 /* These u-blox products use Qualcomm's vendor ID */ #define UBLOX_PRODUCT_R410M 0x90b2 +#define UBLOX_PRODUCT_R6XX 0x90fa /* These Yuga products use Qualcomm's vendor ID */ #define YUGA_PRODUCT_CLM920_NC5 0x9625 @@ -1101,6 +1102,8 @@ static const struct usb_device_id option_ids[] = { /* u-blox products using Qualcomm vendor ID */ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M), .driver_info = RSVD(1) | RSVD(3) }, + { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R6XX), + .driver_info = RSVD(3) }, /* Quectel products using Quectel vendor ID */ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff), .driver_info = NUMEP2 }, From 2fa9fd69b3ee015a873e44f7c645ad7bcb79d290 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:35 +0100 Subject: [PATCH 0225/1469] clk: renesas: rzg2l: Add multi clock PM support Add multi clock PM support for cpg driver. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-2-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/renesas-rzg2l-cpg.c | 49 ++++++++++++++----------- 1 file changed, 28 insertions(+), 21 deletions(-) diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.c b/drivers/clk/renesas/renesas-rzg2l-cpg.c index 5009b9e48b13..1941f13bd922 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.c +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.c @@ -594,42 +594,49 @@ static int rzg2l_cpg_attach_dev(struct generic_pm_domain *unused, struct device { struct device_node *np = dev->of_node; struct of_phandle_args clkspec; + bool once = true; struct clk *clk; int error; int i = 0; while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, &clkspec)) { - if (rzg2l_cpg_is_pm_clk(&clkspec)) - goto found; + if (rzg2l_cpg_is_pm_clk(&clkspec)) { + if (once) { + once = false; + error = pm_clk_create(dev); + if (error) { + of_node_put(clkspec.np); + goto err; + } + } + clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); + if (IS_ERR(clk)) { + error = PTR_ERR(clk); + goto fail_destroy; + } - of_node_put(clkspec.np); + error = pm_clk_add_clk(dev, clk); + if (error) { + dev_err(dev, "pm_clk_add_clk failed %d\n", + error); + goto fail_put; + } + } else { + of_node_put(clkspec.np); + } i++; } return 0; -found: - clk = of_clk_get_from_provider(&clkspec); - of_node_put(clkspec.np); - - if (IS_ERR(clk)) - return PTR_ERR(clk); - - error = pm_clk_create(dev); - if (error) - goto fail_put; - - error = pm_clk_add_clk(dev, clk); - if (error) - goto fail_destroy; - - return 0; +fail_put: + clk_put(clk); fail_destroy: pm_clk_destroy(dev); -fail_put: - clk_put(clk); +err: return error; } From e93c1373613fb2f3e59db5f13271f155820e6a67 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:36 +0100 Subject: [PATCH 0226/1469] clk: renesas: r9a07g044: Rename divider table As per RZ/G2L HW Manual (Rev.0.50), CPG_PL3A_DDIV,CPG_PL3B_DDIV and CPG_PL2_DDIV(for P0) shares same divider table entries. Rename clk_div_table dtable_3b to clk_div_table dtable_1_32 so that it can be reused. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-3-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index 50b5269586a4..d5803fb1242e 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -42,12 +42,13 @@ enum clk_ids { }; /* Divider tables */ -static const struct clk_div_table dtable_3b[] = { +static const struct clk_div_table dtable_1_32[] = { {0, 1}, {1, 2}, {2, 4}, {3, 8}, {4, 32}, + {0, 0}, }; static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { @@ -72,10 +73,10 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { /* Core output clk */ DEF_FIXED("I", R9A07G044_CLK_I, CLK_PLL1, 1, 1), DEF_DIV("P0", R9A07G044_CLK_P0, CLK_PLL2_DIV16, DIVPL2A, - dtable_3b, CLK_DIVIDER_HIWORD_MASK), + dtable_1_32, CLK_DIVIDER_HIWORD_MASK), DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV8, - DIVPL3B, dtable_3b, CLK_DIVIDER_HIWORD_MASK), + DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { From fd8c3f6c36eb093039d4aeb20cceee00c7c6ba1a Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:37 +0100 Subject: [PATCH 0227/1469] clk: renesas: r9a07g044: Fix P1 Clock As per RZ/G2L HW Manual(Rev.0.50) P1 is sourced from pll3_div2_4. So fix the clock definitions for P1. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-4-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index d5803fb1242e..d895c1cef1fa 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -30,8 +30,8 @@ enum clk_ids { CLK_PLL2_DIV20, CLK_PLL3, CLK_PLL3_DIV2, + CLK_PLL3_DIV2_4, CLK_PLL3_DIV4, - CLK_PLL3_DIV8, CLK_PLL4, CLK_PLL5, CLK_PLL5_DIV2, @@ -67,15 +67,15 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED(".pll2_div20", CLK_PLL2_DIV20, CLK_PLL2, 1, 20), DEF_FIXED(".pll3_div2", CLK_PLL3_DIV2, CLK_PLL3, 1, 2), + DEF_FIXED(".pll3_div2_4", CLK_PLL3_DIV2_4, CLK_PLL3_DIV2, 1, 4), DEF_FIXED(".pll3_div4", CLK_PLL3_DIV4, CLK_PLL3, 1, 4), - DEF_FIXED(".pll3_div8", CLK_PLL3_DIV8, CLK_PLL3, 1, 8), /* Core output clk */ DEF_FIXED("I", R9A07G044_CLK_I, CLK_PLL1, 1, 1), DEF_DIV("P0", R9A07G044_CLK_P0, CLK_PLL2_DIV16, DIVPL2A, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), - DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV8, + DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV2_4, DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; From 668756f7299d2d3c75add17cb415717e247450ef Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:38 +0100 Subject: [PATCH 0228/1469] clk: renesas: r9a07g044: Add P2 Clock support Add support for P2 clock which is sourced from pll3_div2_4_2. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-5-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 4 ++++ drivers/clk/renesas/renesas-rzg2l-cpg.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index d895c1cef1fa..70df4feda417 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -31,6 +31,7 @@ enum clk_ids { CLK_PLL3, CLK_PLL3_DIV2, CLK_PLL3_DIV2_4, + CLK_PLL3_DIV2_4_2, CLK_PLL3_DIV4, CLK_PLL4, CLK_PLL5, @@ -68,6 +69,7 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED(".pll3_div2", CLK_PLL3_DIV2, CLK_PLL3, 1, 2), DEF_FIXED(".pll3_div2_4", CLK_PLL3_DIV2_4, CLK_PLL3_DIV2, 1, 4), + DEF_FIXED(".pll3_div2_4_2", CLK_PLL3_DIV2_4_2, CLK_PLL3_DIV2_4, 1, 2), DEF_FIXED(".pll3_div4", CLK_PLL3_DIV4, CLK_PLL3, 1, 4), /* Core output clk */ @@ -77,6 +79,8 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV2_4, DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), + DEF_DIV("P2", R9A07G044_CLK_P2, CLK_PLL3_DIV2_4_2, + DIVPL3A, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.h b/drivers/clk/renesas/renesas-rzg2l-cpg.h index 3948bdd8afc9..a6a3bade1985 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.h +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.h @@ -21,6 +21,7 @@ #define DDIV_PACK(offset, bitpos, size) \ (((offset) << 20) | ((bitpos) << 12) | ((size) << 8)) #define DIVPL2A DDIV_PACK(CPG_PL2_DDIV, 0, 3) +#define DIVPL3A DDIV_PACK(CPG_PL3A_DDIV, 0, 3) #define DIVPL3B DDIV_PACK(CPG_PL3A_DDIV, 4, 3) /** From c3e67ad6f5a2c698a055fb297c6f9962f5145edd Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:39 +0100 Subject: [PATCH 0229/1469] dt-bindings: clock: r9a07g044-cpg: Update clock/reset definitions Update clock and reset definitions as per RZ/G2L_clock_list_r02_02.xlsx and RZ/G2L HW(Rev.0.50) manual. Update {GIC,IA55,SCIF} clock and reset entries in the CPG driver, and separate reset from module clocks in order to handle them efficiently. Update the SCIF0 clock and reset index in the SoC DTSI. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-6-biju.das.jz@bp.renesas.com Link: https://lore.kernel.org/r/20210626081344.5783-7-biju.das.jz@bp.renesas.com Link: https://lore.kernel.org/r/20210626081344.5783-8-biju.das.jz@bp.renesas.com [geert: Squashed 3 commits] Signed-off-by: Geert Uytterhoeven --- arch/arm64/boot/dts/renesas/r9a07g044.dtsi | 4 +- drivers/clk/renesas/r9a07g044-cpg.c | 62 +++--- drivers/clk/renesas/renesas-rzg2l-cpg.c | 59 +++--- drivers/clk/renesas/renesas-rzg2l-cpg.h | 36 +++- include/dt-bindings/clock/r9a07g044-cpg.h | 236 ++++++++++++++++----- 5 files changed, 278 insertions(+), 119 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 734c8adeceba..01482d227506 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -82,10 +82,10 @@ ; interrupt-names = "eri", "rxi", "txi", "bri", "dri", "tei"; - clocks = <&cpg CPG_MOD R9A07G044_CLK_SCIF0>; + clocks = <&cpg CPG_MOD R9A07G044_SCIF0_CLK_PCK>; clock-names = "fck"; power-domains = <&cpg>; - resets = <&cpg R9A07G044_CLK_SCIF0>; + resets = <&cpg R9A07G044_SCIF0_RST_SYSTEM_N>; status = "disabled"; }; diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index 70df4feda417..ae24e0397d3c 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -84,34 +84,40 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { - DEF_MOD("gic", R9A07G044_CLK_GIC600, - R9A07G044_CLK_P1, - 0x514, BIT(0), (BIT(0) | BIT(1))), - DEF_MOD("ia55", R9A07G044_CLK_IA55, - R9A07G044_CLK_P1, - 0x518, (BIT(0) | BIT(1)), BIT(0)), - DEF_MOD("scif0", R9A07G044_CLK_SCIF0, - R9A07G044_CLK_P0, - 0x584, BIT(0), BIT(0)), - DEF_MOD("scif1", R9A07G044_CLK_SCIF1, - R9A07G044_CLK_P0, - 0x584, BIT(1), BIT(1)), - DEF_MOD("scif2", R9A07G044_CLK_SCIF2, - R9A07G044_CLK_P0, - 0x584, BIT(2), BIT(2)), - DEF_MOD("scif3", R9A07G044_CLK_SCIF3, - R9A07G044_CLK_P0, - 0x584, BIT(3), BIT(3)), - DEF_MOD("scif4", R9A07G044_CLK_SCIF4, - R9A07G044_CLK_P0, - 0x584, BIT(4), BIT(4)), - DEF_MOD("sci0", R9A07G044_CLK_SCI0, - R9A07G044_CLK_P0, - 0x588, BIT(0), BIT(0)), + DEF_MOD("gic", R9A07G044_GIC600_GICCLK, R9A07G044_CLK_P1, + 0x514, 0), + DEF_MOD("ia55_pclk", R9A07G044_IA55_PCLK, R9A07G044_CLK_P2, + 0x518, 0), + DEF_MOD("ia55_clk", R9A07G044_IA55_CLK, R9A07G044_CLK_P1, + 0x518, 1), + DEF_MOD("scif0", R9A07G044_SCIF0_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 0), + DEF_MOD("scif1", R9A07G044_SCIF1_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 1), + DEF_MOD("scif2", R9A07G044_SCIF2_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 2), + DEF_MOD("scif3", R9A07G044_SCIF3_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 3), + DEF_MOD("scif4", R9A07G044_SCIF4_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 4), + DEF_MOD("sci0", R9A07G044_SCI0_CLKP, R9A07G044_CLK_P0, + 0x588, 0), +}; + +static struct rzg2l_reset r9a07g044_resets[] = { + DEF_RST(R9A07G044_GIC600_GICRESET_N, 0x814, 0), + DEF_RST(R9A07G044_GIC600_DBG_GICRESET_N, 0x814, 1), + DEF_RST(R9A07G044_IA55_RESETN, 0x818, 0), + DEF_RST(R9A07G044_SCIF0_RST_SYSTEM_N, 0x884, 0), + DEF_RST(R9A07G044_SCIF1_RST_SYSTEM_N, 0x884, 1), + DEF_RST(R9A07G044_SCIF2_RST_SYSTEM_N, 0x884, 2), + DEF_RST(R9A07G044_SCIF3_RST_SYSTEM_N, 0x884, 3), + DEF_RST(R9A07G044_SCIF4_RST_SYSTEM_N, 0x884, 4), + DEF_RST(R9A07G044_SCI0_RST, 0x888, 0), }; static const unsigned int r9a07g044_crit_mod_clks[] __initconst = { - MOD_CLK_BASE + R9A07G044_CLK_GIC600, + MOD_CLK_BASE + R9A07G044_GIC600_GICCLK, }; const struct rzg2l_cpg_info r9a07g044_cpg_info = { @@ -128,5 +134,9 @@ const struct rzg2l_cpg_info r9a07g044_cpg_info = { /* Module Clocks */ .mod_clks = r9a07g044_mod_clks, .num_mod_clks = ARRAY_SIZE(r9a07g044_mod_clks), - .num_hw_mod_clks = R9A07G044_CLK_MIPI_DSI_PIN + 1, + .num_hw_mod_clks = R9A07G044_TSU_PCLK + 1, + + /* Resets */ + .resets = r9a07g044_resets, + .num_resets = ARRAY_SIZE(r9a07g044_resets), }; diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.c b/drivers/clk/renesas/renesas-rzg2l-cpg.c index 1941f13bd922..e7c59af2a1d8 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.c +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.c @@ -47,9 +47,9 @@ #define SDIV(val) DIV_RSMASK(val, 0, 0x7) #define CLK_ON_R(reg) (reg) -#define CLK_MON_R(reg) (0x680 - 0x500 + (reg)) -#define CLK_RST_R(reg) (0x800 - 0x500 + (reg)) -#define CLK_MRST_R(reg) (0x980 - 0x500 + (reg)) +#define CLK_MON_R(reg) (0x180 + (reg)) +#define CLK_RST_R(reg) (reg) +#define CLK_MRST_R(reg) (0x180 + (reg)) #define GET_REG_OFFSET(val) ((val >> 20) & 0xfff) #define GET_REG_SAMPLL_CLK1(val) ((val >> 22) & 0xfff) @@ -78,6 +78,7 @@ struct rzg2l_cpg_priv { struct clk **clks; unsigned int num_core_clks; unsigned int num_mod_clks; + unsigned int num_resets; unsigned int last_dt_core_clk; struct raw_notifier_head notifiers; @@ -315,15 +316,13 @@ fail: * * @hw: handle between common and hardware-specific interfaces * @off: register offset - * @onoff: ON/MON bits - * @reset: reset bits + * @bit: ON/MON bit * @priv: CPG/MSTP private data */ struct mstp_clock { struct clk_hw hw; u16 off; - u8 onoff; - u8 reset; + u8 bit; struct rzg2l_cpg_priv *priv; }; @@ -337,6 +336,7 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) struct device *dev = priv->dev; unsigned long flags; unsigned int i; + u32 bitmask = BIT(clock->bit); u32 value; if (!clock->off) { @@ -349,9 +349,9 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) spin_lock_irqsave(&priv->rmw_lock, flags); if (enable) - value = (clock->onoff << 16) | clock->onoff; + value = (bitmask << 16) | bitmask; else - value = clock->onoff << 16; + value = bitmask << 16; writel(value, priv->base + CLK_ON_R(reg)); spin_unlock_irqrestore(&priv->rmw_lock, flags); @@ -360,7 +360,7 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) return 0; for (i = 1000; i > 0; --i) { - if (((readl(priv->base + CLK_MON_R(reg))) & clock->onoff)) + if (((readl(priv->base + CLK_MON_R(reg))) & bitmask)) break; cpu_relax(); } @@ -388,6 +388,7 @@ static int rzg2l_mod_clock_is_enabled(struct clk_hw *hw) { struct mstp_clock *clock = to_mod_clock(hw); struct rzg2l_cpg_priv *priv = clock->priv; + u32 bitmask = BIT(clock->bit); u32 value; if (!clock->off) { @@ -397,7 +398,7 @@ static int rzg2l_mod_clock_is_enabled(struct clk_hw *hw) value = readl(priv->base + CLK_MON_R(clock->off)); - return !(value & clock->onoff); + return !(value & bitmask); } static const struct clk_ops rzg2l_mod_clock_ops = { @@ -457,8 +458,7 @@ rzg2l_cpg_register_mod_clk(const struct rzg2l_mod_clk *mod, init.num_parents = 1; clock->off = mod->off; - clock->onoff = mod->onoff; - clock->reset = mod->reset; + clock->bit = mod->bit; clock->priv = priv; clock->hw.init = &init; @@ -483,12 +483,11 @@ static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 dis = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 dis = BIT(info->resets[id].bit); u32 we = dis << 16; - dev_dbg(rcdev->dev, "reset name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "reset id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); /* Reset module */ writel(we, priv->base + CLK_RST_R(reg)); @@ -507,11 +506,10 @@ static int rzg2l_cpg_assert(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 value = info->mod_clks[id].reset << 16; + unsigned int reg = info->resets[id].off; + u32 value = BIT(info->resets[id].bit) << 16; - dev_dbg(rcdev->dev, "assert name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "assert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); return 0; @@ -522,12 +520,12 @@ static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 dis = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 dis = BIT(info->resets[id].bit); u32 value = (dis << 16) | dis; - dev_dbg(rcdev->dev, "deassert name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "deassert id:%ld offset:0x%x\n", id, + CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); return 0; @@ -538,8 +536,8 @@ static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 bitmask = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 bitmask = BIT(info->resets[id].bit); return !(readl(priv->base + CLK_MRST_R(reg)) & bitmask); } @@ -554,9 +552,11 @@ static const struct reset_control_ops rzg2l_cpg_reset_ops = { static int rzg2l_cpg_reset_xlate(struct reset_controller_dev *rcdev, const struct of_phandle_args *reset_spec) { + struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); + const struct rzg2l_cpg_info *info = priv->info; unsigned int id = reset_spec->args[0]; - if (id >= rcdev->nr_resets) { + if (id >= rcdev->nr_resets || !info->resets[id].off) { dev_err(rcdev->dev, "Invalid reset index %u\n", id); return -EINVAL; } @@ -571,7 +571,7 @@ static int rzg2l_cpg_reset_controller_register(struct rzg2l_cpg_priv *priv) priv->rcdev.dev = priv->dev; priv->rcdev.of_reset_n_cells = 1; priv->rcdev.of_xlate = rzg2l_cpg_reset_xlate; - priv->rcdev.nr_resets = priv->num_mod_clks; + priv->rcdev.nr_resets = priv->num_resets; return devm_reset_controller_register(priv->dev, &priv->rcdev); } @@ -699,6 +699,7 @@ static int __init rzg2l_cpg_probe(struct platform_device *pdev) priv->clks = clks; priv->num_core_clks = info->num_total_core_clks; priv->num_mod_clks = info->num_hw_mod_clks; + priv->num_resets = info->num_resets; priv->last_dt_core_clk = info->last_dt_core_clk; for (i = 0; i < nclks; i++) diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.h b/drivers/clk/renesas/renesas-rzg2l-cpg.h index a6a3bade1985..63695280ce8b 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.h +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.h @@ -77,26 +77,40 @@ enum clk_types { * @id: clock index in array containing all Core and Module Clocks * @parent: id of parent clock * @off: register offset - * @onoff: ON/MON bits - * @reset: reset bits + * @bit: ON/MON bit */ struct rzg2l_mod_clk { const char *name; unsigned int id; unsigned int parent; u16 off; - u8 onoff; - u8 reset; + u8 bit; }; -#define DEF_MOD(_name, _id, _parent, _off, _onoff, _reset) \ - [_id] = { \ +#define DEF_MOD(_name, _id, _parent, _off, _bit) \ + { \ .name = _name, \ - .id = MOD_CLK_BASE + _id, \ + .id = MOD_CLK_BASE + (_id), \ .parent = (_parent), \ .off = (_off), \ - .onoff = (_onoff), \ - .reset = (_reset) \ + .bit = (_bit), \ + } + +/** + * struct rzg2l_reset - Reset definitions + * + * @off: register offset + * @bit: reset bit + */ +struct rzg2l_reset { + u16 off; + u8 bit; +}; + +#define DEF_RST(_id, _off, _bit) \ + [_id] = { \ + .off = (_off), \ + .bit = (_bit) \ } /** @@ -127,6 +141,10 @@ struct rzg2l_cpg_info { unsigned int num_mod_clks; unsigned int num_hw_mod_clks; + /* Resets */ + const struct rzg2l_reset *resets; + unsigned int num_resets; + /* Critical Module Clocks that should not be disabled */ const unsigned int *crit_mod_clks; unsigned int num_crit_mod_clks; diff --git a/include/dt-bindings/clock/r9a07g044-cpg.h b/include/dt-bindings/clock/r9a07g044-cpg.h index 1d8986563fc5..0728ad07ff7a 100644 --- a/include/dt-bindings/clock/r9a07g044-cpg.h +++ b/include/dt-bindings/clock/r9a07g044-cpg.h @@ -32,58 +32,188 @@ #define R9A07G044_OSCCLK 21 /* R9A07G044 Module Clocks */ -#define R9A07G044_CLK_GIC600 0 -#define R9A07G044_CLK_IA55 1 -#define R9A07G044_CLK_SYC 2 -#define R9A07G044_CLK_DMAC 3 -#define R9A07G044_CLK_SYSC 4 -#define R9A07G044_CLK_MTU 5 -#define R9A07G044_CLK_GPT 6 -#define R9A07G044_CLK_ETH0 7 -#define R9A07G044_CLK_ETH1 8 -#define R9A07G044_CLK_I2C0 9 -#define R9A07G044_CLK_I2C1 10 -#define R9A07G044_CLK_I2C2 11 -#define R9A07G044_CLK_I2C3 12 -#define R9A07G044_CLK_SCIF0 13 -#define R9A07G044_CLK_SCIF1 14 -#define R9A07G044_CLK_SCIF2 15 -#define R9A07G044_CLK_SCIF3 16 -#define R9A07G044_CLK_SCIF4 17 -#define R9A07G044_CLK_SCI0 18 -#define R9A07G044_CLK_SCI1 19 -#define R9A07G044_CLK_GPIO 20 -#define R9A07G044_CLK_SDHI0 21 -#define R9A07G044_CLK_SDHI1 22 -#define R9A07G044_CLK_USB0 23 -#define R9A07G044_CLK_USB1 24 -#define R9A07G044_CLK_CANFD 25 -#define R9A07G044_CLK_SSI0 26 -#define R9A07G044_CLK_SSI1 27 -#define R9A07G044_CLK_SSI2 28 -#define R9A07G044_CLK_SSI3 29 -#define R9A07G044_CLK_MHU 30 -#define R9A07G044_CLK_OSTM0 31 -#define R9A07G044_CLK_OSTM1 32 -#define R9A07G044_CLK_OSTM2 33 -#define R9A07G044_CLK_WDT0 34 -#define R9A07G044_CLK_WDT1 35 -#define R9A07G044_CLK_WDT2 36 -#define R9A07G044_CLK_WDT_PON 37 -#define R9A07G044_CLK_GPU 38 -#define R9A07G044_CLK_ISU 39 -#define R9A07G044_CLK_H264 40 -#define R9A07G044_CLK_CRU 41 -#define R9A07G044_CLK_MIPI_DSI 42 -#define R9A07G044_CLK_LCDC 43 -#define R9A07G044_CLK_SRC 44 -#define R9A07G044_CLK_RSPI0 45 -#define R9A07G044_CLK_RSPI1 46 -#define R9A07G044_CLK_RSPI2 47 -#define R9A07G044_CLK_ADC 48 -#define R9A07G044_CLK_TSU_PCLK 49 -#define R9A07G044_CLK_SPI 50 -#define R9A07G044_CLK_MIPI_DSI_V 51 -#define R9A07G044_CLK_MIPI_DSI_PIN 52 +#define R9A07G044_CA55_SCLK 0 +#define R9A07G044_CA55_PCLK 1 +#define R9A07G044_CA55_ATCLK 2 +#define R9A07G044_CA55_GICCLK 3 +#define R9A07G044_CA55_PERICLK 4 +#define R9A07G044_CA55_ACLK 5 +#define R9A07G044_CA55_TSCLK 6 +#define R9A07G044_GIC600_GICCLK 7 +#define R9A07G044_IA55_CLK 8 +#define R9A07G044_IA55_PCLK 9 +#define R9A07G044_MHU_PCLK 10 +#define R9A07G044_SYC_CNT_CLK 11 +#define R9A07G044_DMAC_ACLK 12 +#define R9A07G044_DMAC_PCLK 13 +#define R9A07G044_OSTM0_PCLK 14 +#define R9A07G044_OSTM1_PCLK 15 +#define R9A07G044_OSTM2_PCLK 16 +#define R9A07G044_MTU_X_MCK_MTU3 17 +#define R9A07G044_POE3_CLKM_POE 18 +#define R9A07G044_GPT_PCLK 19 +#define R9A07G044_POEG_A_CLKP 20 +#define R9A07G044_POEG_B_CLKP 21 +#define R9A07G044_POEG_C_CLKP 22 +#define R9A07G044_POEG_D_CLKP 23 +#define R9A07G044_WDT0_PCLK 24 +#define R9A07G044_WDT0_CLK 25 +#define R9A07G044_WDT1_PCLK 26 +#define R9A07G044_WDT1_CLK 27 +#define R9A07G044_WDT2_PCLK 28 +#define R9A07G044_WDT2_CLK 29 +#define R9A07G044_SPI_CLK2 30 +#define R9A07G044_SPI_CLK 31 +#define R9A07G044_SDHI0_IMCLK 32 +#define R9A07G044_SDHI0_IMCLK2 33 +#define R9A07G044_SDHI0_CLK_HS 34 +#define R9A07G044_SDHI0_ACLK 35 +#define R9A07G044_SDHI1_IMCLK 36 +#define R9A07G044_SDHI1_IMCLK2 37 +#define R9A07G044_SDHI1_CLK_HS 38 +#define R9A07G044_SDHI1_ACLK 39 +#define R9A07G044_GPU_CLK 40 +#define R9A07G044_GPU_AXI_CLK 41 +#define R9A07G044_GPU_ACE_CLK 42 +#define R9A07G044_ISU_ACLK 43 +#define R9A07G044_ISU_PCLK 44 +#define R9A07G044_H264_CLK_A 45 +#define R9A07G044_H264_CLK_P 46 +#define R9A07G044_CRU_SYSCLK 47 +#define R9A07G044_CRU_VCLK 48 +#define R9A07G044_CRU_PCLK 49 +#define R9A07G044_CRU_ACLK 50 +#define R9A07G044_MIPI_DSI_PLLCLK 51 +#define R9A07G044_MIPI_DSI_SYSCLK 52 +#define R9A07G044_MIPI_DSI_ACLK 53 +#define R9A07G044_MIPI_DSI_PCLK 54 +#define R9A07G044_MIPI_DSI_VCLK 55 +#define R9A07G044_MIPI_DSI_LPCLK 56 +#define R9A07G044_LCDC_CLK_A 57 +#define R9A07G044_LCDC_CLK_P 58 +#define R9A07G044_LCDC_CLK_D 59 +#define R9A07G044_SSI0_PCLK2 60 +#define R9A07G044_SSI0_PCLK_SFR 61 +#define R9A07G044_SSI1_PCLK2 62 +#define R9A07G044_SSI1_PCLK_SFR 63 +#define R9A07G044_SSI2_PCLK2 64 +#define R9A07G044_SSI2_PCLK_SFR 65 +#define R9A07G044_SSI3_PCLK2 66 +#define R9A07G044_SSI3_PCLK_SFR 67 +#define R9A07G044_SRC_CLKP 68 +#define R9A07G044_USB_U2H0_HCLK 69 +#define R9A07G044_USB_U2H1_HCLK 70 +#define R9A07G044_USB_U2P_EXR_CPUCLK 71 +#define R9A07G044_USB_PCLK 72 +#define R9A07G044_ETH0_CLK_AXI 73 +#define R9A07G044_ETH0_CLK_CHI 74 +#define R9A07G044_ETH1_CLK_AXI 75 +#define R9A07G044_ETH1_CLK_CHI 76 +#define R9A07G044_I2C0_PCLK 77 +#define R9A07G044_I2C1_PCLK 78 +#define R9A07G044_I2C2_PCLK 79 +#define R9A07G044_I2C3_PCLK 80 +#define R9A07G044_SCIF0_CLK_PCK 81 +#define R9A07G044_SCIF1_CLK_PCK 82 +#define R9A07G044_SCIF2_CLK_PCK 83 +#define R9A07G044_SCIF3_CLK_PCK 84 +#define R9A07G044_SCIF4_CLK_PCK 85 +#define R9A07G044_SCI0_CLKP 86 +#define R9A07G044_SCI1_CLKP 87 +#define R9A07G044_IRDA_CLKP 88 +#define R9A07G044_RSPI0_CLKB 89 +#define R9A07G044_RSPI1_CLKB 90 +#define R9A07G044_RSPI2_CLKB 91 +#define R9A07G044_CANFD_PCLK 92 +#define R9A07G044_GPIO_HCLK 93 +#define R9A07G044_ADC_ADCLK 94 +#define R9A07G044_ADC_PCLK 95 +#define R9A07G044_TSU_PCLK 96 + +/* R9A07G044 Resets */ +#define R9A07G044_CA55_RST_1_0 0 +#define R9A07G044_CA55_RST_1_1 1 +#define R9A07G044_CA55_RST_3_0 2 +#define R9A07G044_CA55_RST_3_1 3 +#define R9A07G044_CA55_RST_4 4 +#define R9A07G044_CA55_RST_5 5 +#define R9A07G044_CA55_RST_6 6 +#define R9A07G044_CA55_RST_7 7 +#define R9A07G044_CA55_RST_8 8 +#define R9A07G044_CA55_RST_9 9 +#define R9A07G044_CA55_RST_10 10 +#define R9A07G044_CA55_RST_11 11 +#define R9A07G044_CA55_RST_12 12 +#define R9A07G044_GIC600_GICRESET_N 13 +#define R9A07G044_GIC600_DBG_GICRESET_N 14 +#define R9A07G044_IA55_RESETN 15 +#define R9A07G044_MHU_RESETN 16 +#define R9A07G044_DMAC_ARESETN 17 +#define R9A07G044_DMAC_RST_ASYNC 18 +#define R9A07G044_SYC_RESETN 19 +#define R9A07G044_OSTM0_PRESETZ 20 +#define R9A07G044_OSTM1_PRESETZ 21 +#define R9A07G044_OSTM2_PRESETZ 22 +#define R9A07G044_MTU_X_PRESET_MTU3 23 +#define R9A07G044_POE3_RST_M_REG 24 +#define R9A07G044_GPT_RST_C 25 +#define R9A07G044_POEG_A_RST 26 +#define R9A07G044_POEG_B_RST 27 +#define R9A07G044_POEG_C_RST 28 +#define R9A07G044_POEG_D_RST 29 +#define R9A07G044_WDT0_PRESETN 30 +#define R9A07G044_WDT1_PRESETN 31 +#define R9A07G044_WDT2_PRESETN 32 +#define R9A07G044_SPI_RST 33 +#define R9A07G044_SDHI0_IXRST 34 +#define R9A07G044_SDHI1_IXRST 35 +#define R9A07G044_GPU_RESETN 36 +#define R9A07G044_GPU_AXI_RESETN 37 +#define R9A07G044_GPU_ACE_RESETN 38 +#define R9A07G044_ISU_ARESETN 39 +#define R9A07G044_ISU_PRESETN 40 +#define R9A07G044_H264_X_RESET_VCP 41 +#define R9A07G044_H264_CP_PRESET_P 42 +#define R9A07G044_CRU_CMN_RSTB 43 +#define R9A07G044_CRU_PRESETN 44 +#define R9A07G044_CRU_ARESETN 45 +#define R9A07G044_MIPI_DSI_CMN_RSTB 46 +#define R9A07G044_MIPI_DSI_ARESET_N 47 +#define R9A07G044_MIPI_DSI_PRESET_N 48 +#define R9A07G044_LCDC_RESET_N 49 +#define R9A07G044_SSI0_RST_M2_REG 50 +#define R9A07G044_SSI1_RST_M2_REG 51 +#define R9A07G044_SSI2_RST_M2_REG 52 +#define R9A07G044_SSI3_RST_M2_REG 53 +#define R9A07G044_SRC_RST 54 +#define R9A07G044_USB_U2H0_HRESETN 55 +#define R9A07G044_USB_U2H1_HRESETN 56 +#define R9A07G044_USB_U2P_EXL_SYSRST 57 +#define R9A07G044_USB_PRESETN 58 +#define R9A07G044_ETH0_RST_HW_N 59 +#define R9A07G044_ETH1_RST_HW_N 60 +#define R9A07G044_I2C0_MRST 61 +#define R9A07G044_I2C1_MRST 62 +#define R9A07G044_I2C2_MRST 63 +#define R9A07G044_I2C3_MRST 64 +#define R9A07G044_SCIF0_RST_SYSTEM_N 65 +#define R9A07G044_SCIF1_RST_SYSTEM_N 66 +#define R9A07G044_SCIF2_RST_SYSTEM_N 67 +#define R9A07G044_SCIF3_RST_SYSTEM_N 68 +#define R9A07G044_SCIF4_RST_SYSTEM_N 69 +#define R9A07G044_SCI0_RST 70 +#define R9A07G044_SCI1_RST 71 +#define R9A07G044_IRDA_RST 72 +#define R9A07G044_RSPI0_RST 73 +#define R9A07G044_RSPI1_RST 74 +#define R9A07G044_RSPI2_RST 75 +#define R9A07G044_CANFD_RSTP_N 76 +#define R9A07G044_CANFD_RSTC_N 77 +#define R9A07G044_GPIO_RSTN 78 +#define R9A07G044_GPIO_PORT_RESETN 79 +#define R9A07G044_GPIO_SPARE_RESETN 80 +#define R9A07G044_ADC_PRESETN 81 +#define R9A07G044_ADC_ADRST_N 82 +#define R9A07G044_TSU_PRESETN 83 #endif /* __DT_BINDINGS_CLOCK_R9A07G044_CPG_H__ */ From 2e2832562c877e6530b8480982d99a4ff90c6777 Mon Sep 17 00:00:00 2001 From: Alan Young Date: Fri, 9 Jul 2021 09:48:54 +0100 Subject: [PATCH 0230/1469] ALSA: pcm: Call substream ack() method upon compat mmap commit If a 32-bit application is being used with a 64-bit kernel and is using the mmap mechanism to write data, then the SNDRV_PCM_IOCTL_SYNC_PTR ioctl results in calling snd_pcm_ioctl_sync_ptr_compat(). Make this use pcm_lib_apply_appl_ptr() so that the substream's ack() method, if defined, is called. The snd_pcm_sync_ptr() function, used in the 64-bit ioctl case, already uses snd_pcm_ioctl_sync_ptr_compat(). Fixes: 9027c4639ef1 ("ALSA: pcm: Call ack() whenever appl_ptr is updated") Signed-off-by: Alan Young Cc: Link: https://lore.kernel.org/r/c441f18c-eb2a-3bdd-299a-696ccca2de9c@gmail.com Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 14e32825c339..c88c4316c417 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3063,9 +3063,14 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, boundary = 0x7fffffff; snd_pcm_stream_lock_irq(substream); /* FIXME: we should consider the boundary for the sync from app */ - if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) - control->appl_ptr = scontrol.appl_ptr; - else + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) { + err = pcm_lib_apply_appl_ptr(substream, + scontrol.appl_ptr); + if (err < 0) { + snd_pcm_stream_unlock_irq(substream); + return err; + } + } else scontrol.appl_ptr = control->appl_ptr % boundary; if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) control->avail_min = scontrol.avail_min; From c71f78a662611fe2c67f3155da19b0eff0f29762 Mon Sep 17 00:00:00 2001 From: Maxim Schwalm Date: Mon, 12 Jul 2021 03:50:11 +0300 Subject: [PATCH 0231/1469] ASoC: rt5631: Fix regcache sync errors on resume The ALC5631 does not like multi-write accesses, avoid them. This fixes: rt5631 4-001a: Unable to sync registers 0x3a-0x3c. -121 errors on resume from suspend (and all registers after the registers in the error not being synced). Inspired by commit 2d30e9494f1e ("ASoC: rt5651: Fix regcache sync errors on resume") from Hans de Geode, which fixed the same errors on ALC5651. Signed-off-by: Maxim Schwalm Link: https://lore.kernel.org/r/20210712005011.28536-1-digetx@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5631.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c index 3000bc128b5b..38356ea2bd6e 100644 --- a/sound/soc/codecs/rt5631.c +++ b/sound/soc/codecs/rt5631.c @@ -1695,6 +1695,8 @@ static const struct regmap_config rt5631_regmap_config = { .reg_defaults = rt5631_reg, .num_reg_defaults = ARRAY_SIZE(rt5631_reg), .cache_type = REGCACHE_RBTREE, + .use_single_read = true, + .use_single_write = true, }; static int rt5631_i2c_probe(struct i2c_client *i2c, From ffe000217c5068c5da07ccb1c0f8cce7ad767435 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Thu, 24 Jun 2021 12:47:32 -0500 Subject: [PATCH 0232/1469] dma-buf/sync_file: Don't leak fences on merge failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Each add_fence() call does a dma_fence_get() on the relevant fence. In the error path, we weren't calling dma_fence_put() so all those fences got leaked. Also, in the krealloc_array failure case, we weren't freeing the fences array. Instead, ensure that i and fences are always zero-initialized and dma_fence_put() all the fences and kfree(fences) on every error path. Signed-off-by: Jason Ekstrand Reviewed-by: Christian König Fixes: a02b9dc90d84 ("dma-buf/sync_file: refactor fence storage in struct sync_file") Cc: Gustavo Padovan Cc: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210624174732.1754546-1-jason@jlekstrand.net Signed-off-by: Christian König --- drivers/dma-buf/sync_file.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 20d9bddbb985..394e6e1e9686 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -211,8 +211,8 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { struct sync_file *sync_file; - struct dma_fence **fences, **nfences, **a_fences, **b_fences; - int i, i_a, i_b, num_fences, a_num_fences, b_num_fences; + struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; + int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) @@ -236,7 +236,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, * If a sync_file can only be created with sync_file_merge * and sync_file_create, this is a reasonable assumption. */ - for (i = i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { + for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { struct dma_fence *pt_a = a_fences[i_a]; struct dma_fence *pt_b = b_fences[i_b]; @@ -277,15 +277,16 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, fences = nfences; } - if (sync_file_set_fence(sync_file, fences, i) < 0) { - kfree(fences); + if (sync_file_set_fence(sync_file, fences, i) < 0) goto err; - } strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; err: + while (i) + dma_fence_put(fences[--i]); + kfree(fences); fput(sync_file->file); return NULL; From 98f7cd23aa9563c06503991a0cd41f0cacc99f5f Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 9 Jul 2021 16:49:43 +0200 Subject: [PATCH 0233/1469] s390/vdso32: add vdso32.lds to targets This fixes a permanent rebuild of the 32 bit vdso. The RPM build process was first calling 'make bzImage' and 'make modules' as a second step. This caused a recompilation of vdso32.so, which in turn also changed the build-id of vmlinux. Fixes: 779df2248739 ("s390/vdso: add minimal compat vdso") Signed-off-by: Sven Schnelle Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens --- arch/s390/kernel/vdso32/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index b2349a3f4fa3..3457dcf10396 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -29,6 +29,7 @@ $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) obj-y += vdso32_wrapper.o +targets += vdso32.lds CPPFLAGS_vdso32.lds += -P -C -U$(ARCH) # Disable gcov profiling, ubsan and kasan for VDSO code From c30e5e9ff0c695a8bac813ff4d5216fd7fb51e4e Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 8 Jul 2021 11:41:21 +0000 Subject: [PATCH 0234/1469] s390/defconfig: allow early device mapper disks doing make install on an Ubuntu that is installed on an LVM will fail to boot. Turns out that defconfig misses 2 device mapper related configs for the Ubuntu initramfs. Signed-off-by: Christian Borntraeger Reviewed-by: Steffen Maier Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 3 ++- arch/s390/configs/defconfig | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 86afcc6b56bf..55cb846cda37 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -436,7 +436,7 @@ CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m -CONFIG_BLK_DEV_DM=m +CONFIG_BLK_DEV_DM=y CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -453,6 +453,7 @@ CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_MULTIPATH_IOA=m CONFIG_DM_DELAY=m +CONFIG_DM_INIT=y CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 71b49ea5b058..5d847ab5feaa 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -427,7 +427,7 @@ CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m -CONFIG_BLK_DEV_DM=m +CONFIG_BLK_DEV_DM=y CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -444,6 +444,7 @@ CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_MULTIPATH_IOA=m CONFIG_DM_DELAY=m +CONFIG_DM_INIT=y CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m From 5f34b1eb2f8d4bba7d6352e767ef84bee9096d97 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 12 Jul 2021 10:00:43 +0100 Subject: [PATCH 0235/1469] arm64: fix strlen() with CONFIG_KASAN_HW_TAGS When the kernel is built with CONFIG_KASAN_HW_TAGS and the CPU supports MTE, memory accesses are checked at 16-byte granularity, and out-of-bounds accesses can result in tag check faults. Our current implementation of strlen() makes unaligned 16-byte accesses (within a naturally aligned 4096-byte window), and can trigger tag check faults. This can be seen at boot time, e.g. | BUG: KASAN: invalid-access in __pi_strlen+0x14/0x150 | Read at addr f4ff0000c0028300 by task swapper/0/0 | Pointer tag: [f4], memory tag: [fe] | | CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.13.0-09550-g03c2813535a2-dirty #20 | Hardware name: linux,dummy-virt (DT) | Call trace: | dump_backtrace+0x0/0x1b0 | show_stack+0x1c/0x30 | dump_stack_lvl+0x68/0x84 | print_address_description+0x7c/0x2b4 | kasan_report+0x138/0x38c | __do_kernel_fault+0x190/0x1c4 | do_tag_check_fault+0x78/0x90 | do_mem_abort+0x44/0xb4 | el1_abort+0x40/0x60 | el1h_64_sync_handler+0xb0/0xd0 | el1h_64_sync+0x78/0x7c | __pi_strlen+0x14/0x150 | __register_sysctl_table+0x7c4/0x890 | register_leaf_sysctl_tables+0x1a4/0x210 | register_leaf_sysctl_tables+0xc8/0x210 | __register_sysctl_paths+0x22c/0x290 | register_sysctl_table+0x2c/0x40 | sysctl_init+0x20/0x30 | proc_sys_init+0x3c/0x48 | proc_root_init+0x80/0x9c | start_kernel+0x640/0x69c | __primary_switched+0xc0/0xc8 To fix this, we can reduce the (strlen-internal) MIN_PAGE_SIZE to 16 bytes when CONFIG_KASAN_HW_TAGS is selected. This will cause strlen() to align the base pointer downwards to a 16-byte boundary, and to discard the additional prefix bytes without counting them. All subsequent accesses will be 16-byte aligned 16-byte LDPs. While the comments say the body of the loop will access 32 bytes, this is performed as two 16-byte acceses, with the second made only if the first did not encounter a NUL byte, so the body of the loop will not over-read across a 16-byte boundary. No other string routines are affected. The other str*() routines will not make any access which straddles a 16-byte boundary, and the mem*() routines will only make acceses which straddle a 16-byte boundary when which is entirely within the bounds of the relevant base and size arguments. Fixes: 325a1de81287 ("arm64: Import updated version of Cortex Strings' strlen") Signed-off-by: Mark Rutland Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Marco Elver Cc: Robin Murphy Cc: Will Deacon Reviewed-by: Catalin Marinas Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210712090043.20847-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/lib/strlen.S | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 35fbdb7d6e1a..1648790e91b3 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -8,6 +8,7 @@ #include #include +#include /* Assumptions: * @@ -42,7 +43,16 @@ #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 +/* + * When KASAN_HW_TAGS is in use, memory is checked at MTE_GRANULE_SIZE + * (16-byte) granularity, and we must ensure that no access straddles this + * alignment boundary. + */ +#ifdef CONFIG_KASAN_HW_TAGS +#define MIN_PAGE_SIZE MTE_GRANULE_SIZE +#else #define MIN_PAGE_SIZE 4096 +#endif /* Since strings are short on average, we check the first 16 bytes of the string for a NUL character. In order to do an unaligned ldp From e62e074814862cffd8e60a1bdf52d6b592a03675 Mon Sep 17 00:00:00 2001 From: Carlos Bilbao Date: Thu, 8 Jul 2021 07:15:42 -0400 Subject: [PATCH 0236/1469] arm64: Add missing header in two files Add missing header on include/asm/smp_plat.h, as it calls function cpu_logical_map(). Also include it on kernel/cpufeature.c since it has calls to functions cpu_panic_kernel() and cpu_die_early(). Both files call functions defined on this header, make the header dependencies less fragile. Signed-off-by: Carlos Bilbao Acked-by: Mark Rutland Link: https://lore.kernel.org/r/4325940.LvFx2qVVIh@iron-maiden Signed-off-by: Will Deacon --- arch/arm64/include/asm/smp_plat.h | 1 + arch/arm64/kernel/cpufeature.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h index 99ad77df8f52..97ddc6c203b7 100644 --- a/arch/arm64/include/asm/smp_plat.h +++ b/arch/arm64/include/asm/smp_plat.h @@ -10,6 +10,7 @@ #include +#include #include struct mpidr_hash { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 125d5c9471ac..0ead8bfedf20 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include #include From c1132702c71f4b95db9435bac5fdc912881563e0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 12 Jul 2021 13:10:00 +0100 Subject: [PATCH 0237/1469] Revert "arm64: cache: Lower ARCH_DMA_MINALIGN to 64 (L1_CACHE_BYTES)" This reverts commit 65688d2a05deb9f0671a7e2301eadbfe7e27c9e9. Unfortunately, the original Qualcomm Kryo cores integrated into the MSM8996 SoC feature an L2 cache with 128-byte lines which sits above the Point of Coherency. Consequently, we must restore ARCH_DMA_MINALIGN to its former ugly self so that non-coherent DMA can be performed safely on devices built using this SoC. Thanks to Jeffrey Hugo for confirming this with a hardware designer. Link: https://lore.kernel.org/r/CAOCk7NqdpUZFMSXfGjw0_1NaSK5gyTLgpS9kSdZn1jmBy-QkfA@mail.gmail.com/ Reported-by: Yassine Oudjana Link: https://lore.kernel.org/r/uHgsRacR8hJ7nW-I-pIcehzg-lNIn7NJvaL7bP9tfAftFsBjsgaY2qTjG9zyBgxHkjNL1WPNrD7YVv2JVD2_Wy-a5VTbcq-1xEi8ZnwrXBo=@protonmail.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a9c0716e7440..a074459f8f2f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -47,7 +47,7 @@ * cache before the transfer is done, causing old data to be seen by * the CPU. */ -#define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_DMA_MINALIGN (128) #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) From 38e0c99249f8f12e1450234a0f7fb357a1b73843 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 24 Jun 2021 10:50:58 +0100 Subject: [PATCH 0238/1469] firmware: arm_scmi: Simplify device probe function on the bus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the driver core calls the probe callback it already checked that the devices match, so there is no need to call the match callback again. Link: https://lore.kernel.org/r/20210624095059.4010157-1-sudeep.holla@arm.com Suggested-by: Uwe Kleine-König Tested-by: Cristian Marussi Reviewed-by: Cristian Marussi Acked-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 784cf0027da3..dc113ad37ad9 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -104,11 +104,6 @@ static int scmi_dev_probe(struct device *dev) { struct scmi_driver *scmi_drv = to_scmi_driver(dev->driver); struct scmi_device *scmi_dev = to_scmi_dev(dev); - const struct scmi_device_id *id; - - id = scmi_dev_match_id(scmi_dev, scmi_drv); - if (!id) - return -ENODEV; if (!scmi_dev->handle) return -EPROBE_DEFER; From 5e469dac326555d2038d199a6329458cc82a34e5 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 24 Jun 2021 10:50:59 +0100 Subject: [PATCH 0239/1469] firmware: arm_scmi: Ensure drivers provide a probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bus probe callback calls the driver callback without further checking. Better be safe than sorry and refuse registration of a driver without a probe function to prevent a NULL pointer exception. Link: https://lore.kernel.org/r/20210624095059.4010157-2-sudeep.holla@arm.com Fixes: 933c504424a2 ("firmware: arm_scmi: add scmi protocol bus to enumerate protocol devices") Reported-by: Uwe Kleine-König Tested-by: Cristian Marussi Reviewed-by: Cristian Marussi Acked-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index dc113ad37ad9..6c7e24935eca 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -134,6 +134,9 @@ int scmi_driver_register(struct scmi_driver *driver, struct module *owner, { int retval; + if (!driver->probe) + return -EINVAL; + retval = scmi_protocol_device_request(driver->id_table); if (retval) return retval; From 7a691f16ccad05d770f813d9c4b4337a30c6d63f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 7 Jul 2021 14:50:28 +0100 Subject: [PATCH 0240/1469] firmware: arm_scmi: Fix possible scmi_linux_errmap buffer overflow The scmi_linux_errmap buffer access index is supposed to depend on the array size to prevent element out of bounds access. It uses SCMI_ERR_MAX to check bounds but that can mismatch with the array size. It also changes the success into -EIO though scmi_linux_errmap is never used in case of success, it is expected to work for success case too. It is slightly confusing code as the negative of the error code is used as index to the buffer. Fix it by negating it at the start and make it more readable. Link: https://lore.kernel.org/r/20210707135028.1869642-1-sudeep.holla@arm.com Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 66e5e694be7d..36d80661d473 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -47,7 +47,6 @@ enum scmi_error_codes { SCMI_ERR_GENERIC = -8, /* Generic Error */ SCMI_ERR_HARDWARE = -9, /* Hardware Error */ SCMI_ERR_PROTOCOL = -10,/* Protocol Error */ - SCMI_ERR_MAX }; /* List of all SCMI devices active in system */ @@ -166,8 +165,10 @@ static const int scmi_linux_errmap[] = { static inline int scmi_to_linux_errno(int errno) { - if (errno < SCMI_SUCCESS && errno > SCMI_ERR_MAX) - return scmi_linux_errmap[-errno]; + int err_idx = -errno; + + if (err_idx >= SCMI_SUCCESS && err_idx < ARRAY_SIZE(scmi_linux_errmap)) + return scmi_linux_errmap[err_idx]; return -EIO; } From 92743071464fca5acbbe812d9a0d88de3eaaad36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Jun 2021 22:16:51 +0200 Subject: [PATCH 0241/1469] firmware: arm_ffa: Ensure drivers provide a probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bus probe callback calls the driver callback without further checking. Better be safe than sorry and refuse registration of a driver without a probe function to prevent a NULL pointer exception. Link: https://lore.kernel.org/r/20210621201652.127611-1-u.kleine-koenig@pengutronix.de Fixes: e781858488b9 ("firmware: arm_ffa: Add initial FFA bus support for device enumeration") Signed-off-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 83166e02b191..d2cc24319626 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -99,6 +99,9 @@ int ffa_driver_register(struct ffa_driver *driver, struct module *owner, { int ret; + if (!driver->probe) + return -EINVAL; + driver->driver.bus = &ffa_bus_type; driver->driver.name = driver->name; driver->driver.owner = owner; From e362547addc39e4bb18ad5bdfd59ce4d512d0c08 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Jun 2021 22:16:52 +0200 Subject: [PATCH 0242/1469] firmware: arm_ffa: Simplify probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the driver core calls the probe callback it already checked that the devices match, so there is no need to call the match callback again. Link: https://lore.kernel.org/r/20210621201652.127611-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index d2cc24319626..00fe595a5bc8 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -46,9 +46,6 @@ static int ffa_device_probe(struct device *dev) struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver); struct ffa_device *ffa_dev = to_ffa_dev(dev); - if (!ffa_device_match(dev, dev->driver)) - return -ENODEV; - return ffa_drv->probe(ffa_dev); } From ba684a31d3626c86cd9097e12d6ed57d224d077d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 22 Jun 2021 17:22:02 +0100 Subject: [PATCH 0243/1469] firmware: arm_ffa: Fix the comment style clang produces the following warning: drivers/firmware/arm_ffa/driver.c:123: warning: expecting prototype for FF(). Prototype was for FFA_PAGE_SIZE() instead This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst Fix the same by removing the kernel-doc style comment here. Link: https://lore.kernel.org/r/20210622162202.3485866-1-sudeep.holla@arm.com Reported-by: kernel test robot Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b1edb4b2e94a..88b822575ac4 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -120,7 +120,7 @@ #define PACK_TARGET_INFO(s, r) \ (FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r))) -/** +/* * FF-A specification mentions explicitly about '4K pages'. This should * not be confused with the kernel PAGE_SIZE, which is the translation * granule kernel is configured and may be one among 4K, 16K and 64K. From dd925db6f07556061c11ab1fbfa4a0145ae6b438 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 7 Jul 2021 14:47:39 +0100 Subject: [PATCH 0244/1469] firmware: arm_ffa: Fix a possible ffa_linux_errmap buffer overflow The ffa_linux_errmap buffer access index is supposed to range from 0-8 but it ranges from 1-9 instead. It reads one element out of bounds. It also changes the success into -EINVAL though ffa_to_linux_errno is never used in case of success, it is expected to work for success case too. It is slightly confusing code as the negative of the error code is used as index to the buffer. Fix it by negating it at the start and make it more readable. Link: https://lore.kernel.org/r/20210707134739.1869481-1-sudeep.holla@arm.com Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 88b822575ac4..c9fb56afbcb4 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -149,8 +149,10 @@ static const int ffa_linux_errmap[] = { static inline int ffa_to_linux_errno(int errno) { - if (errno < FFA_RET_SUCCESS && errno >= -ARRAY_SIZE(ffa_linux_errmap)) - return ffa_linux_errmap[-errno]; + int err_idx = -errno; + + if (err_idx >= 0 && err_idx < ARRAY_SIZE(ffa_linux_errmap)) + return ffa_linux_errmap[err_idx]; return -EINVAL; } From f35e0cc25280cb0063b0e4481f99268fbd872ff3 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Tue, 6 Jul 2021 08:44:00 +0300 Subject: [PATCH 0245/1469] doc, af_xdp: Fix bind flags option typo Fix XDP_ZERO_COPY flag typo since it is actually named XDP_ZEROCOPY instead as per if_xdp.h uapi header. Signed-off-by: Baruch Siach Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/1656fdf94704e9e735df0f8b97667d8f26dd098b.1625550240.git.baruch@tkos.co.il --- Documentation/networking/af_xdp.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 42576880aa4a..60b217b436be 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -243,8 +243,8 @@ Configuration Flags and Socket Options These are the various configuration flags that can be used to control and monitor the behavior of AF_XDP sockets. -XDP_COPY and XDP_ZERO_COPY bind flags -------------------------------------- +XDP_COPY and XDP_ZEROCOPY bind flags +------------------------------------ When you bind to a socket, the kernel will first try to use zero-copy copy. If zero-copy is not supported, it will fall back on using copy @@ -252,7 +252,7 @@ mode, i.e. copying all packets out to user space. But if you would like to force a certain mode, you can use the following flags. If you pass the XDP_COPY flag to the bind call, the kernel will force the socket into copy mode. If it cannot use copy mode, the bind call will -fail with an error. Conversely, the XDP_ZERO_COPY flag will force the +fail with an error. Conversely, the XDP_ZEROCOPY flag will force the socket into zero-copy mode or fail. XDP_SHARED_UMEM bind flag From 5e21bb4e812566aef86fbb77c96a4ec0782286e4 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Thu, 8 Jul 2021 16:04:09 +0800 Subject: [PATCH 0246/1469] bpf, test: fix NULL pointer dereference on invalid expected_attach_type These two types of XDP progs (BPF_XDP_DEVMAP, BPF_XDP_CPUMAP) will not be executed directly in the driver, therefore we should also not directly run them from here. To run in these two situations, there must be further preparations done, otherwise these may cause a kernel panic. For more details, see also dev_xdp_attach(). [ 46.982479] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 46.984295] #PF: supervisor read access in kernel mode [ 46.985777] #PF: error_code(0x0000) - not-present page [ 46.987227] PGD 800000010dca4067 P4D 800000010dca4067 PUD 10dca6067 PMD 0 [ 46.989201] Oops: 0000 [#1] SMP PTI [ 46.990304] CPU: 7 PID: 562 Comm: a.out Not tainted 5.13.0+ #44 [ 46.992001] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/24 [ 46.995113] RIP: 0010:___bpf_prog_run+0x17b/0x1710 [ 46.996586] Code: 49 03 14 cc e8 76 f6 fe ff e9 ad fe ff ff 0f b6 43 01 48 0f bf 4b 02 48 83 c3 08 89 c2 83 e0 0f c0 ea 04 02 [ 47.001562] RSP: 0018:ffffc900005afc58 EFLAGS: 00010246 [ 47.003115] RAX: 0000000000000000 RBX: ffffc9000023f068 RCX: 0000000000000000 [ 47.005163] RDX: 0000000000000000 RSI: 0000000000000079 RDI: ffffc900005afc98 [ 47.007135] RBP: 0000000000000000 R08: ffffc9000023f048 R09: c0000000ffffdfff [ 47.009171] R10: 0000000000000001 R11: ffffc900005afb40 R12: ffffc900005afc98 [ 47.011172] R13: 0000000000000001 R14: 0000000000000001 R15: ffffffff825258a8 [ 47.013244] FS: 00007f04a5207580(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 [ 47.015705] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 47.017475] CR2: 0000000000000000 CR3: 0000000100182005 CR4: 0000000000770ee0 [ 47.019558] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 47.021595] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 47.023574] PKRU: 55555554 [ 47.024571] Call Trace: [ 47.025424] __bpf_prog_run32+0x32/0x50 [ 47.026296] ? printk+0x53/0x6a [ 47.027066] ? ktime_get+0x39/0x90 [ 47.027895] bpf_test_run.cold.28+0x23/0x123 [ 47.028866] ? printk+0x53/0x6a [ 47.029630] bpf_prog_test_run_xdp+0x149/0x1d0 [ 47.030649] __sys_bpf+0x1305/0x23d0 [ 47.031482] __x64_sys_bpf+0x17/0x20 [ 47.032316] do_syscall_64+0x3a/0x80 [ 47.033165] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 47.034254] RIP: 0033:0x7f04a51364dd [ 47.035133] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 48 [ 47.038768] RSP: 002b:00007fff8f9fc518 EFLAGS: 00000213 ORIG_RAX: 0000000000000141 [ 47.040344] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f04a51364dd [ 47.041749] RDX: 0000000000000048 RSI: 0000000020002a80 RDI: 000000000000000a [ 47.043171] RBP: 00007fff8f9fc530 R08: 0000000002049300 R09: 0000000020000100 [ 47.044626] R10: 0000000000000004 R11: 0000000000000213 R12: 0000000000401070 [ 47.046088] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 47.047579] Modules linked in: [ 47.048318] CR2: 0000000000000000 [ 47.049120] ---[ end trace 7ad34443d5be719a ]--- [ 47.050273] RIP: 0010:___bpf_prog_run+0x17b/0x1710 [ 47.051343] Code: 49 03 14 cc e8 76 f6 fe ff e9 ad fe ff ff 0f b6 43 01 48 0f bf 4b 02 48 83 c3 08 89 c2 83 e0 0f c0 ea 04 02 [ 47.054943] RSP: 0018:ffffc900005afc58 EFLAGS: 00010246 [ 47.056068] RAX: 0000000000000000 RBX: ffffc9000023f068 RCX: 0000000000000000 [ 47.057522] RDX: 0000000000000000 RSI: 0000000000000079 RDI: ffffc900005afc98 [ 47.058961] RBP: 0000000000000000 R08: ffffc9000023f048 R09: c0000000ffffdfff [ 47.060390] R10: 0000000000000001 R11: ffffc900005afb40 R12: ffffc900005afc98 [ 47.061803] R13: 0000000000000001 R14: 0000000000000001 R15: ffffffff825258a8 [ 47.063249] FS: 00007f04a5207580(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 [ 47.065070] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 47.066307] CR2: 0000000000000000 CR3: 0000000100182005 CR4: 0000000000770ee0 [ 47.067747] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 47.069217] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 47.070652] PKRU: 55555554 [ 47.071318] Kernel panic - not syncing: Fatal exception [ 47.072854] Kernel Offset: disabled [ 47.073683] ---[ end Kernel panic - not syncing: Fatal exception ]--- Fixes: 9216477449f3 ("bpf: cpumap: Add the possibility to attach an eBPF program to cpumap") Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Reported-by: Abaci Signed-off-by: Xuan Zhuo Signed-off-by: Daniel Borkmann Reviewed-by: Dust Li Acked-by: Jesper Dangaard Brouer Acked-by: David Ahern Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210708080409.73525-1-xuanzhuo@linux.alibaba.com --- net/bpf/test_run.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index aa47af349ba8..1cc75c811e24 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -701,6 +701,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; + if (prog->expected_attach_type == BPF_XDP_DEVMAP || + prog->expected_attach_type == BPF_XDP_CPUMAP) + return -EINVAL; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; From 40751c6c9bea6a5cfede7c61ee5f3cb1ab857029 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Wed, 7 Jul 2021 15:48:40 -0500 Subject: [PATCH 0247/1469] scripts/spdxcheck.py: Strictly read license files in utf-8 Commit bc41a7f36469 ("LICENSES: Add the CC-BY-4.0 license") unfortunately introduced LICENSES/dual/CC-BY-4.0 in UTF-8 Unicode text While python will barf at it with: FAIL: 'ascii' codec can't decode byte 0xe2 in position 2109: ordinal not in range(128) Traceback (most recent call last): File "scripts/spdxcheck.py", line 244, in spdx = read_spdxdata(repo) File "scripts/spdxcheck.py", line 47, in read_spdxdata for l in open(el.path).readlines(): File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode return codecs.ascii_decode(input, self.errors)[0] UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 2109: ordinal not in range(128) While it is indeed debatable if 'Licensor.' used in the license file needs unicode quotes, instead, force spdxcheck to read utf-8. Reported-by: Rahul T R Signed-off-by: Nishanth Menon Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210707204840.30891-1-nm@ti.com Signed-off-by: Jonathan Corbet --- scripts/spdxcheck.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 3e784cf9f401..ebd06ae642c9 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -44,7 +44,7 @@ def read_spdxdata(repo): continue exception = None - for l in open(el.path).readlines(): + for l in open(el.path, encoding="utf-8").readlines(): if l.startswith('Valid-License-Identifier:'): lid = l.split(':')[1].strip().upper() if lid in spdx.licenses: From 1adee589cd6da2ead7f1b5dd82419eac59a2e2b0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:03:35 -0500 Subject: [PATCH 0248/1469] kernel: debug: Fix unreachable code in gdb_serial_stub() Fix the following warning: kernel/debug/gdbstub.c:1049:4: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- kernel/debug/gdbstub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 8372897402f4..b6f28fad4307 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1045,8 +1045,8 @@ int gdb_serial_stub(struct kgdb_state *ks) gdb_cmd_detachkill(ks); return DBG_PASS_EVENT; } -#endif fallthrough; +#endif case 'C': /* Exception passing */ tmp = gdb_cmd_exception_pass(ks); if (tmp > 0) From e8865537a68bb3032f449f5eb108fa8cd76ebb6d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:09:13 -0500 Subject: [PATCH 0249/1469] fcntl: Fix unreachable code in do_fcntl() Fix the following warning: fs/fcntl.c:373:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- fs/fcntl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index dfc72f15be7f..f946bec8f1f1 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -369,8 +369,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: -#endif fallthrough; +#endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) From 1eb5f4a3ddd949af1abe947c02ad990c013dd620 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:13:49 -0500 Subject: [PATCH 0250/1469] mtd: cfi_util: Fix unreachable code issue Fix the following warning: drivers/mtd/chips/cfi_util.c:112:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) ^ drivers/mtd/chips/cfi_util.c:168:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- drivers/mtd/chips/cfi_util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c index 99b7986002f0..6a6a2a21d2ed 100644 --- a/drivers/mtd/chips/cfi_util.c +++ b/drivers/mtd/chips/cfi_util.c @@ -108,8 +108,8 @@ map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi #if BITS_PER_LONG >= 64 case 8: onecmd |= (onecmd << (chip_mode * 32)); -#endif fallthrough; +#endif case 4: onecmd |= (onecmd << (chip_mode * 16)); fallthrough; @@ -164,8 +164,8 @@ unsigned long cfi_merge_status(map_word val, struct map_info *map, #if BITS_PER_LONG >= 64 case 8: res |= (onestat >> (chip_mode * 32)); -#endif fallthrough; +#endif case 4: res |= (onestat >> (chip_mode * 16)); fallthrough; From 0c23af52ccd1605926480b5dfd1dd857ef604611 Mon Sep 17 00:00:00 2001 From: Naresh Kumar PBS Date: Sun, 11 Jul 2021 06:31:36 -0700 Subject: [PATCH 0251/1469] RDMA/bnxt_re: Fix stats counters Statistical counters are not incrementing in some adapter versions with newer FW. This is due to the stats context length mismatch between FW and driver. Since the L2 driver updates the length correctly, use the stats length from L2 driver while allocating the DMA'able memory and creating the stats context. Fixes: 9d6b648c3112 ("bnxt_en: Update firmware interface spec to 1.10.1.65.") Link: https://lore.kernel.org/r/1626010296-6076-1-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Naresh Kumar PBS Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/main.c | 4 +++- drivers/infiniband/hw/bnxt_re/qplib_res.c | 10 ++++------ drivers/infiniband/hw/bnxt_re/qplib_res.h | 1 + 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index d5674026512a..a8688a92c760 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -120,6 +120,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) if (!chip_ctx) return -ENOMEM; chip_ctx->chip_num = bp->chip_num; + chip_ctx->hw_stats_size = bp->hw_ring_stats_size; rdev->chip_ctx = chip_ctx; /* rest members to follow eventually */ @@ -550,6 +551,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, dma_addr_t dma_map, u32 *fw_stats_ctx_id) { + struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx; struct hwrm_stat_ctx_alloc_output resp = {0}; struct hwrm_stat_ctx_alloc_input req = {0}; struct bnxt_en_dev *en_dev = rdev->en_dev; @@ -566,7 +568,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(1000); req.stats_dma_addr = cpu_to_le64(dma_map); - req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext)); + req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size); req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 17f0701b3cee..44282a8cdd4f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -56,6 +56,7 @@ static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev, struct bnxt_qplib_stats *stats); static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev, + struct bnxt_qplib_chip_ctx *cctx, struct bnxt_qplib_stats *stats); /* PBL */ @@ -559,7 +560,7 @@ int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res, goto fail; stats_alloc: /* Stats */ - rc = bnxt_qplib_alloc_stats_ctx(res->pdev, &ctx->stats); + rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats); if (rc) goto fail; @@ -889,15 +890,12 @@ static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev, } static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev, + struct bnxt_qplib_chip_ctx *cctx, struct bnxt_qplib_stats *stats) { memset(stats, 0, sizeof(*stats)); stats->fw_id = -1; - /* 128 byte aligned context memory is required only for 57500. - * However making this unconditional, it does not harm previous - * generation. - */ - stats->size = ALIGN(sizeof(struct ctx_hw_stats), 128); + stats->size = cctx->hw_stats_size; stats->dma = dma_alloc_coherent(&pdev->dev, stats->size, &stats->dma_map, GFP_KERNEL); if (!stats->dma) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index c291f495ae91..91031502e8f5 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -54,6 +54,7 @@ struct bnxt_qplib_chip_ctx { u16 chip_num; u8 chip_rev; u8 chip_metal; + u16 hw_stats_size; struct bnxt_qplib_drv_modes modes; }; From 6407c69dc51fbd7cf7b6760cd8aefb105d96ff5b Mon Sep 17 00:00:00 2001 From: Tatyana Nikolova Date: Wed, 7 Jul 2021 14:14:55 -0700 Subject: [PATCH 0252/1469] RDMA/irdma: Fix unused variable total_size warning Fix the following unused variable warning: drivers/infiniband/hw/irdma/uk.c:934:6: warning: variable 'total_size' set but not used [-Wunused-but-set-variable] Link: https://lore.kernel.org/r/20210707211455.2076-1-tatyana.e.nikolova@intel.com Link: https://lkml.org/lkml/2021/7/1/726 Reported-by: kernel test robot Fixes: 551c46edc769 ("RDMA/irdma: Add user/kernel shared libraries") Signed-off-by: Mustafa Ismail Signed-off-by: Tatyana Nikolova Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/uk.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index a6d52c20091c..5fb92de1f015 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -931,7 +931,7 @@ enum irdma_status_code irdma_uk_mw_bind(struct irdma_qp_uk *qp, enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp, struct irdma_post_rq_info *info) { - u32 total_size = 0, wqe_idx, i, byte_off; + u32 wqe_idx, i, byte_off; u32 addl_frag_cnt; __le64 *wqe; u64 hdr; @@ -939,9 +939,6 @@ enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp, if (qp->max_rq_frag_cnt < info->num_sges) return IRDMA_ERR_INVALID_FRAG_COUNT; - for (i = 0; i < info->num_sges; i++) - total_size += info->sg_list[i].len; - wqe = irdma_qp_get_next_recv_wqe(qp, &wqe_idx); if (!wqe) return IRDMA_ERR_QP_TOOMANY_WRS_POSTED; From 514305ee0a1dade95c6ff1eb5735de5a329d1f89 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 1 Jul 2021 12:41:27 +0200 Subject: [PATCH 0253/1469] RDMA/irdma: Make spdxcheck.py happy Commit 48d6b3336a9f ("RDMA/irdma: Add ABI definitions") adds ./include/uapi/rdma/irdma-abi.h with an additional unneeded closing bracket at the end of the SPDX-License-Identifier line. Hence, ./scripts/spdxcheck.py complains: include/uapi/rdma/irdma-abi.h: 1:77 Syntax error: ) Remove that closing bracket to make spdxcheck.py happy. Fixes: 48d6b3336a9f ("RDMA/irdma: Add ABI definitions") Link: https://lore.kernel.org/r/20210701104127.1877-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Acked-by: Tatyana Nikolova Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/irdma-abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h index 26b638a7ad97..a7085e092d34 100644 --- a/include/uapi/rdma/irdma-abi.h +++ b/include/uapi/rdma/irdma-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB */ /* * Copyright (c) 2006 - 2021 Intel Corporation. All rights reserved. * Copyright (c) 2005 Topspin Communications. All rights reserved. From c9538831b353b96cb37092c3d3e929d67fd43c5f Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Thu, 8 Jul 2021 02:47:52 -0400 Subject: [PATCH 0254/1469] RDMA/irdma: Change the returned type to void Since the function irdma_sc_parse_fpm_commit_buf always returns 0, remove the returned value check and change the returned type to void. Fixes: 3f49d6842569 ("RDMA/irdma: Implement HW Admin Queue OPs") Link: https://lore.kernel.org/r/20210708064752.797520-1-yanjun.zhu@linux.dev Signed-off-by: Zhu Yanjun Reviewed-by: Majd Dibbiny Acked-by: Tatyana Nikolova Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/ctrl.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index b1023a7d0bd1..c3880a85e255 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -2845,7 +2845,7 @@ static u64 irdma_sc_decode_fpm_commit(struct irdma_sc_dev *dev, __le64 *buf, * parses fpm commit info and copy base value * of hmc objects in hmc_info */ -static enum irdma_status_code +static void irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf, struct irdma_hmc_obj_info *info, u32 *sd) { @@ -2915,7 +2915,6 @@ irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf, else *sd = (u32)(size >> 21); - return 0; } /** @@ -4434,9 +4433,9 @@ static enum irdma_status_code irdma_sc_cfg_iw_fpm(struct irdma_sc_dev *dev, ret_code = irdma_sc_commit_fpm_val(dev->cqp, 0, hmc_info->hmc_fn_id, &commit_fpm_mem, true, wait_type); if (!ret_code) - ret_code = irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf, - hmc_info->hmc_obj, - &hmc_info->sd_table.sd_cnt); + irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf, + hmc_info->hmc_obj, + &hmc_info->sd_table.sd_cnt); print_hex_dump_debug("HMC: COMMIT FPM BUFFER", DUMP_PREFIX_OFFSET, 16, 8, commit_fpm_mem.va, IRDMA_COMMIT_FPM_BUF_SIZE, false); From a1739c307a072e46473a2ba239eb60e6d711c96c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 11 Jul 2021 15:31:47 -0700 Subject: [PATCH 0255/1469] net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific Rename module_init & module_exit functions that are named "mod_init" and "mod_exit" so that they are unique in both the System.map file and in initcall_debug output instead of showing up as almost anonymous "mod_init". This is helpful for debugging and in determining how long certain module_init calls take to execute. Signed-off-by: Randy Dunlap Cc: Krzysztof Halasa Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Martin Schiller Cc: linux-x25@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/wan/hdlc_cisco.c | 8 ++++---- drivers/net/wan/hdlc_fr.c | 8 ++++---- drivers/net/wan/hdlc_ppp.c | 8 ++++---- drivers/net/wan/hdlc_raw.c | 8 ++++---- drivers/net/wan/hdlc_raw_eth.c | 8 ++++---- drivers/net/wan/hdlc_x25.c | 8 ++++---- 6 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 349ca18088e8..c54fdae950fb 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -364,19 +364,19 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_cisco_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_cisco_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_cisco_init); +module_exit(hdlc_cisco_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Cisco HDLC protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 72250fe0a1df..25e3564ce118 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -1279,19 +1279,19 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_fr_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_fr_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_fr_init); +module_exit(hdlc_fr_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Frame-Relay protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 834be2ae3e9e..b81ecf432a0c 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -705,20 +705,20 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_ppp_init(void) { skb_queue_head_init(&tx_queue); register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_ppp_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_ppp_init); +module_exit(hdlc_ppp_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("PPP protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_raw.c b/drivers/net/wan/hdlc_raw.c index 388fcc09b4dd..54d28496fefd 100644 --- a/drivers/net/wan/hdlc_raw.c +++ b/drivers/net/wan/hdlc_raw.c @@ -90,7 +90,7 @@ static int raw_ioctl(struct net_device *dev, struct ifreq *ifr) } -static int __init mod_init(void) +static int __init hdlc_raw_init(void) { register_hdlc_protocol(&proto); return 0; @@ -98,14 +98,14 @@ static int __init mod_init(void) -static void __exit mod_exit(void) +static void __exit hdlc_raw_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_raw_init); +module_exit(hdlc_raw_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Raw HDLC protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c index c70a518b8b47..927596276a07 100644 --- a/drivers/net/wan/hdlc_raw_eth.c +++ b/drivers/net/wan/hdlc_raw_eth.c @@ -110,7 +110,7 @@ static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr) } -static int __init mod_init(void) +static int __init hdlc_eth_init(void) { register_hdlc_protocol(&proto); return 0; @@ -118,14 +118,14 @@ static int __init mod_init(void) -static void __exit mod_exit(void) +static void __exit hdlc_eth_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_eth_init); +module_exit(hdlc_eth_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Ethernet encapsulation support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index d2bf72bf3bd7..9b7ebf8bd85c 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -365,19 +365,19 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_x25_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_x25_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_x25_init); +module_exit(hdlc_x25_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("X.25 protocol support for generic HDLC"); From 5796015fa968a3349027a27dcd04c71d95c53ba5 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 12 Jul 2021 09:45:06 +0300 Subject: [PATCH 0256/1469] ipv6: allocate enough headroom in ip6_finish_output2() When TEE target mirrors traffic to another interface, sk_buff may not have enough headroom to be processed correctly. ip_finish_output2() detect this situation for ipv4 and allocates new skb with enogh headroom. However ipv6 lacks this logic in ip_finish_output2 and it leads to skb_under_panic: skbuff: skb_under_panic: text:ffffffffc0866ad4 len:96 put:24 head:ffff97be85e31800 data:ffff97be85e317f8 tail:0x58 end:0xc0 dev:gre0 ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:110! invalid opcode: 0000 [#1] SMP PTI CPU: 2 PID: 393 Comm: kworker/2:2 Tainted: G OE 5.13.0 #13 Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.4 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x48/0x4a Call Trace: skb_push.cold.111+0x10/0x10 ipgre_header+0x24/0xf0 [ip_gre] neigh_connected_output+0xae/0xf0 ip6_finish_output2+0x1a8/0x5a0 ip6_output+0x5c/0x110 nf_dup_ipv6+0x158/0x1000 [nf_dup_ipv6] tee_tg6+0x2e/0x40 [xt_TEE] ip6t_do_table+0x294/0x470 [ip6_tables] nf_hook_slow+0x44/0xc0 nf_hook.constprop.34+0x72/0xe0 ndisc_send_skb+0x20d/0x2e0 ndisc_send_ns+0xd1/0x210 addrconf_dad_work+0x3c8/0x540 process_one_work+0x1d1/0x370 worker_thread+0x30/0x390 kthread+0x116/0x130 ret_from_fork+0x22/0x30 Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d4ee2169afd8..01bea76e3891 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,10 +60,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + unsigned int hh_len = LL_RESERVED_SPACE(dev); + int delta = hh_len - skb_headroom(skb); const struct in6_addr *nexthop; struct neighbour *neigh; int ret; + /* Be paranoid, rather than too clever. */ + if (unlikely(delta > 0) && dev->header_ops) { + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(skb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + if (!skb) { + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + return -ENOMEM; + } + } + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); From 71ce9d92fc7089f287c3e95a981bdec7545a8588 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 12 Jul 2021 15:37:50 +0100 Subject: [PATCH 0257/1469] octeontx2-pf: Fix uninitialized boolean variable pps In the case where act->id is FLOW_ACTION_POLICE and also act->police.rate_bytes_ps > 0 or act->police.rate_pkt_ps is not > 0 the boolean variable pps contains an uninitialized value when function otx2_tc_act_set_police is called. Fix this by initializing pps to false. Addresses-Coverity: ("Uninitialized scalar variable)" Fixes: 68fbff68dbea ("octeontx2-pf: Add police action for TC flower") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 905fc02a7dfe..972b202b9884 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -288,7 +288,7 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, struct otx2_nic *priv; u32 burst, mark = 0; u8 nr_police = 0; - bool pps; + bool pps = false; u64 rate; int i; From efdb6720b44b2f016d2a04b2c84e577e57ed84bd Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 11 Jul 2021 20:10:49 -0700 Subject: [PATCH 0258/1469] mm/rmap: fix munlocking Anon THP with mlocked ptes Many thanks to Kirill for reminding that PageDoubleMap cannot be relied on to warn of pte mappings in the Anon THP case; and a scan of subpages does not seem appropriate here. Note how follow_trans_huge_pmd() does not even mark an Anon THP as mlocked when compound_mapcount != 1: multiple mlocking of Anon THP is avoided, so simply return from page_mlock() in this case. Link: https://lore.kernel.org/lkml/cfa154c-d595-406-eb7d-eb9df730f944@google.com/ Fixes: d9770fcc1c0c ("mm/rmap: fix old bug: munlocking THP missed other mlocks") Reported-by: Kirill A. Shutemov Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Cc: Andrew Morton Cc: Alistair Popple Cc: Jason Gunthorpe Cc: Ralph Campbell Cc: Christoph Hellwig Cc: Yang Shi Cc: Shakeel Butt Signed-off-by: Linus Torvalds --- mm/rmap.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index 795f9d5f8386..b9eb5c12f3fe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1440,21 +1440,20 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * If the page is mlock()d, we cannot swap it out. */ - if (!(flags & TTU_IGNORE_MLOCK)) { - if (vma->vm_flags & VM_LOCKED) { - /* PTE-mapped THP are never marked as mlocked */ - if (!PageTransCompound(page) || - (PageHead(page) && !PageDoubleMap(page))) { - /* - * Holding pte lock, we do *not* need - * mmap_lock here - */ - mlock_vma_page(page); - } - ret = false; - page_vma_mapped_walk_done(&pvmw); - break; - } + if (!(flags & TTU_IGNORE_MLOCK) && + (vma->vm_flags & VM_LOCKED)) { + /* + * PTE-mapped THP are never marked as mlocked: so do + * not set it on a DoubleMap THP, nor on an Anon THP + * (which may still be PTE-mapped after DoubleMap was + * cleared). But stop unmapping even in those cases. + */ + if (!PageTransCompound(page) || (PageHead(page) && + !PageDoubleMap(page) && !PageAnon(page))) + mlock_vma_page(page); + page_vma_mapped_walk_done(&pvmw); + ret = false; + break; } /* Unexpected PMD-mapped THP? */ @@ -1986,8 +1985,10 @@ static bool page_mlock_one(struct page *page, struct vm_area_struct *vma, */ if (vma->vm_flags & VM_LOCKED) { /* - * PTE-mapped THP are never marked as mlocked, but - * this function is never called when PageDoubleMap(). + * PTE-mapped THP are never marked as mlocked; but + * this function is never called on a DoubleMap THP, + * nor on an Anon THP (which may still be PTE-mapped + * after DoubleMap was cleared). */ mlock_vma_page(page); /* @@ -2022,6 +2023,10 @@ void page_mlock(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); + /* Anon THP are only marked as mlocked when singly mapped */ + if (PageTransCompound(page) && PageAnon(page)) + return; + rmap_walk(page, &rwc); } From 79789db03fdd77510cfb35cb4b3bd52b6c50c901 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 12 Jul 2021 16:32:07 +0100 Subject: [PATCH 0259/1469] mm: Make copy_huge_page() always available Rewrite copy_huge_page() and move it into mm/util.c so it's always available. Fixes an exposure of uninitialised memory on configurations with HUGETLB and UFFD enabled and MIGRATION disabled. Fixes: 8cc5fcbb5be8 ("mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Mike Kravetz Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 ----- include/linux/mm.h | 1 + mm/migrate.c | 48 ----------------------------------------- mm/util.c | 10 +++++++++ 4 files changed, 11 insertions(+), 53 deletions(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 9b7b7cd3bae9..23dadf7aeba8 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,7 +51,6 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); -extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,10 +76,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } - -static inline void copy_huge_page(struct page *dst, struct page *src) -{ -} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/include/linux/mm.h b/include/linux/mm.h index 57453dba41b9..7ca22e6e694a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -906,6 +906,7 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); +void copy_huge_page(struct page *dst, struct page *src); /* * Compound pages have a destructor function. Provide a diff --git a/mm/migrate.c b/mm/migrate.c index 23cbd9de030b..34a9ad3e0a4f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -536,54 +536,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } -/* - * Gigantic pages are so large that we do not guarantee that page++ pointer - * arithmetic will work across the entire page. We need something more - * specialized. - */ -static void __copy_gigantic_page(struct page *dst, struct page *src, - int nr_pages) -{ - int i; - struct page *dst_base = dst; - struct page *src_base = src; - - for (i = 0; i < nr_pages; ) { - cond_resched(); - copy_highpage(dst, src); - - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); - } -} - -void copy_huge_page(struct page *dst, struct page *src) -{ - int i; - int nr_pages; - - if (PageHuge(src)) { - /* hugetlbfs page */ - struct hstate *h = page_hstate(src); - nr_pages = pages_per_huge_page(h); - - if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) { - __copy_gigantic_page(dst, src, nr_pages); - return; - } - } else { - /* thp page */ - BUG_ON(!PageTransHuge(src)); - nr_pages = thp_nr_pages(src); - } - - for (i = 0; i < nr_pages; i++) { - cond_resched(); - copy_highpage(dst + i, src + i); - } -} - /* * Copy the page to its new location */ diff --git a/mm/util.c b/mm/util.c index 99c6cc77de9e..9043d03750a7 100644 --- a/mm/util.c +++ b/mm/util.c @@ -731,6 +731,16 @@ int __page_mapcount(struct page *page) } EXPORT_SYMBOL_GPL(__page_mapcount); +void copy_huge_page(struct page *dst, struct page *src) +{ + unsigned i, nr = compound_nr(src); + + for (i = 0; i < nr; i++) { + cond_resched(); + copy_highpage(nth_page(dst, i), nth_page(src, i)); + } +} + int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; From b0863f1927323110e3d0d69f6adb6a91018a9a3c Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 12 Jul 2021 14:54:36 -0400 Subject: [PATCH 0260/1469] USB: core: Fix incorrect pipe calculation in do_proc_control() When the user submits a control URB via usbfs, the user supplies the bRequestType value and the kernel uses it to compute the pipe value. However, do_proc_control() performs this computation incorrectly in the case where the bRequestType direction bit is set to USB_DIR_IN and the URB's transfer length is 0: The pipe's direction is also set to IN but it should be OUT, which is the direction the actual transfer will use regardless of bRequestType. Commit 5cc59c418fde ("USB: core: WARN if pipe direction != setup packet direction") added a check to compare the direction bit in the pipe value to a control URB's actual direction and to WARN if they are different. This can be triggered by the incorrect computation mentioned above, as found by syzbot. This patch fixes the computation, thus avoiding the WARNing. Reported-and-tested-by: syzbot+72af3105289dcb4c055b@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/20210712185436.GB326369@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index b97464498763..9618ba622a2d 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1133,7 +1133,7 @@ static int do_proc_control(struct usb_dev_state *ps, "wIndex=%04x wLength=%04x\n", ctrl->bRequestType, ctrl->bRequest, ctrl->wValue, ctrl->wIndex, ctrl->wLength); - if (ctrl->bRequestType & 0x80) { + if ((ctrl->bRequestType & USB_DIR_IN) && ctrl->wLength) { pipe = usb_rcvctrlpipe(dev, 0); snoop_urb(dev, NULL, pipe, ctrl->wLength, tmo, SUBMIT, NULL, 0); From 7fef2edf7cc753b51f7ccc74993971b0a9c81eca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 12 Jul 2021 17:50:01 +0200 Subject: [PATCH 0261/1469] sd: don't mess with SD_MINORS for CONFIG_DEBUG_BLOCK_EXT_DEVT No need to give up the original sd minor even with this option, and if we did we'd also need to fix the number of minors for this configuration to actually work. Fixes: 7c3f828b522b0 ("block: refactor device number setup in __device_add_disk") Reported-by: Guenter Roeck Signed-off-by: Christoph Hellwig Tested-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/scsi/sd.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 6d2d63629a90..b8d55af763f9 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -98,11 +98,7 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD); MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC); -#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT) #define SD_MINORS 16 -#else -#define SD_MINORS 0 -#endif static void sd_config_discard(struct scsi_disk *, unsigned int); static void sd_config_write_same(struct scsi_disk *); From ed01ad3a2fac8fff63f441ead4f8653da053c65b Mon Sep 17 00:00:00 2001 From: Rae Moar Date: Thu, 1 Jul 2021 17:52:31 +0000 Subject: [PATCH 0262/1469] kunit: tool: Fix error messages for cases of no tests and wrong TAP header This patch addresses misleading error messages reported by kunit_tool in two cases. First, in the case of TAP output having an incorrect header format or missing a header, the parser used to output an error message of 'no tests run!'. Now the parser outputs an error message of 'could not parse test results!'. As an example: Before: $ ./tools/testing/kunit/kunit.py parse /dev/null [ERROR] no tests run! ... After: $ ./tools/testing/kunit/kunit.py parse /dev/null [ERROR] could not parse test results! ... Second, in the case of TAP output with the correct header but no tests, the parser used to output an error message of 'could not parse test results!'. Now the parser outputs an error message of 'no tests run!'. As an example: Before: $ echo -e 'TAP version 14\n1..0' | ./tools/testing/kunit/kunit.py parse [ERROR] could not parse test results! After: $ echo -e 'TAP version 14\n1..0' | ./tools/testing/kunit/kunit.py parse [ERROR] no tests run! Additionally, this patch also corrects the tests in kunit_tool_test.py and adds a test to check the error in the case of TAP output with the correct header but no tests. Signed-off-by: Rae Moar Reviewed-by: David Gow Reviewed-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_parser.py | 6 ++++-- tools/testing/kunit/kunit_tool_test.py | 16 +++++++++++++--- ...st_is_test_passed-no_tests_run_no_header.log} | 0 ...t_is_test_passed-no_tests_run_with_header.log | 2 ++ 4 files changed, 19 insertions(+), 5 deletions(-) rename tools/testing/kunit/test_data/{test_is_test_passed-no_tests_run.log => test_is_test_passed-no_tests_run_no_header.log} (100%) create mode 100644 tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index c3c524b79db8..b88db3f51dc5 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -338,9 +338,11 @@ def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus: def parse_test_result(lines: LineStream) -> TestResult: consume_non_diagnostic(lines) if not lines or not parse_tap_header(lines): - return TestResult(TestStatus.NO_TESTS, [], lines) + return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) expected_test_suite_num = parse_test_plan(lines) - if not expected_test_suite_num: + if expected_test_suite_num == 0: + return TestResult(TestStatus.NO_TESTS, [], lines) + elif expected_test_suite_num is None: return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) test_suites = [] for i in range(1, expected_test_suite_num + 1): diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index bdae0e5f6197..75045aa0f8a1 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -157,8 +157,18 @@ class KUnitParserTest(unittest.TestCase): kunit_parser.TestStatus.FAILURE, result.status) + def test_no_header(self): + empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log') + with open(empty_log) as file: + result = kunit_parser.parse_run_tests( + kunit_parser.extract_tap_lines(file.readlines())) + self.assertEqual(0, len(result.suites)) + self.assertEqual( + kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS, + result.status) + def test_no_tests(self): - empty_log = test_data_path('test_is_test_passed-no_tests_run.log') + empty_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') with open(empty_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) @@ -173,7 +183,7 @@ class KUnitParserTest(unittest.TestCase): with open(crash_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) - print_mock.assert_any_call(StrContains('no tests run!')) + print_mock.assert_any_call(StrContains('could not parse test results!')) print_mock.stop() file.close() @@ -309,7 +319,7 @@ class KUnitJsonTest(unittest.TestCase): result["sub_groups"][1]["test_cases"][0]) def test_no_tests_json(self): - result = self._json_for('test_is_test_passed-no_tests_run.log') + result = self._json_for('test_is_test_passed-no_tests_run_with_header.log') self.assertEqual(0, len(result['sub_groups'])) class StrContains(str): diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log similarity index 100% rename from tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log rename to tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log new file mode 100644 index 000000000000..5f48ee659d40 --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log @@ -0,0 +1,2 @@ +TAP version 14 +1..0 From a72fa6304342a3ad749955fd9007695f761e12d6 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Wed, 23 Jun 2021 13:17:21 -0700 Subject: [PATCH 0263/1469] Documentation: kunit: drop obsolete note about uml_abort for coverage Commit b6d5799b0b58 ("kunit: Add 'kunit_shutdown' option") changes KUnit to call kernel_halt() by default when done testing. This fixes the issue with not having .gcda files due to not calling atexit() handlers, and therefore we can stop recommending people manually tweak UML code. The need to use older versions of GCC (<=6) remains however, due to linktime issues, same as before. Note: There also might still be issues with .gcda files as well in newer versions. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/running_tips.rst | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst index 7d99386cf94a..d1626d548fa5 100644 --- a/Documentation/dev-tools/kunit/running_tips.rst +++ b/Documentation/dev-tools/kunit/running_tips.rst @@ -86,19 +86,7 @@ Generating code coverage reports under UML .. note:: TODO(brendanhiggins@google.com): There are various issues with UML and versions of gcc 7 and up. You're likely to run into missing ``.gcda`` - files or compile errors. We know one `faulty GCC commit - `_ - but not how we'd go about getting this fixed. The compile errors still - need some investigation. - -.. note:: - TODO(brendanhiggins@google.com): for recent versions of Linux - (5.10-5.12, maybe earlier), there's a bug with gcov counters not being - flushed in UML. This translates to very low (<1%) reported coverage. This is - related to the above issue and can be worked around by replacing the - one call to ``uml_abort()`` (it's in ``os_dump_core()``) with a plain - ``exit()``. - + files or compile errors. This is different from the "normal" way of getting coverage information that is documented in Documentation/dev-tools/gcov.rst. From 58c965d84e14196e762c803c50c7b207a9e352bc Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Wed, 23 Jun 2021 12:09:19 -0700 Subject: [PATCH 0264/1469] kunit: tool: remove unnecessary "annotations" import The import was working around the fact "tuple[T]" was used instead of typing.Tuple[T]. Convert it to use type.Tuple to be consistent with how the rest of the code is anotated. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_kernel.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 90bc007f1f93..2c6f916ccbaf 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,15 +6,13 @@ # Author: Felix Guo # Author: Brendan Higgins -from __future__ import annotations import importlib.util import logging import subprocess import os import shutil import signal -from typing import Iterator -from typing import Optional +from typing import Iterator, Optional, Tuple from contextlib import ExitStack @@ -208,7 +206,7 @@ def get_source_tree_ops(arch: str, cross_compile: Optional[str]) -> LinuxSourceT raise ConfigError(arch + ' is not a valid arch') def get_source_tree_ops_from_qemu_config(config_path: str, - cross_compile: Optional[str]) -> tuple[ + cross_compile: Optional[str]) -> Tuple[ str, LinuxSourceTreeOperations]: # The module name/path has very little to do with where the actual file # exists (I learned this through experimentation and could not find it From df4b0807ca1a62822342d404b863eff933d15762 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 12 Jul 2021 19:52:58 +0000 Subject: [PATCH 0265/1469] kunit: tool: Assert the version requirement Commit 87c9c1631788 ("kunit: tool: add support for QEMU") on the 'next' tree adds 'from __future__ import annotations' in 'kunit_kernel.py'. Because it is supported on only >=3.7 Python, people using older Python will get below error: Traceback (most recent call last): File "./tools/testing/kunit/kunit.py", line 20, in import kunit_kernel File "/home/sjpark/linux/tools/testing/kunit/kunit_kernel.py", line 9 from __future__ import annotations ^ SyntaxError: future feature annotations is not defined This commit adds a version assertion in 'kunit.py', so that people get more explicit error message like below: Traceback (most recent call last): File "./tools/testing/kunit/kunit.py", line 15, in assert sys.version_info >= (3, 7), "Python version is too old" AssertionError: Python version is too old Signed-off-by: SeongJae Park Acked-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index be8d8d4a4e08..6276ce0c0196 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -12,6 +12,8 @@ import sys import os import time +assert sys.version_info >= (3, 7), "Python version is too old" + from collections import namedtuple from enum import Enum, auto From 0c0f6299ba71faf610e311605e09e96331c45f28 Mon Sep 17 00:00:00 2001 From: Paolo Pisati Date: Wed, 30 Jun 2021 16:57:40 +0200 Subject: [PATCH 0266/1469] selftests: memory-hotplug: avoid spamming logs with dump_page(), ratio limit hot-remove error test While the offline memory test obey ratio limit, the same test with error injection does not and tries to offline all the hotpluggable memory, spamming system logs with hundreds of thousands of dump_page() entries, slowing system down (to the point the test itself timesout and gets terminated) and excessive fs occupation: ... [ 9784.393354] page:c00c0000007d1b40 refcount:3 mapcount:0 mapping:c0000001fc03e950 index:0xe7b [ 9784.393355] def_blk_aops [ 9784.393356] flags: 0x3ffff800002062(referenced|active|workingset|private) [ 9784.393358] raw: 003ffff800002062 c0000001b9343a68 c0000001b9343a68 c0000001fc03e950 [ 9784.393359] raw: 0000000000000e7b c000000006607b18 00000003ffffffff c00000000490d000 [ 9784.393359] page dumped because: migration failure [ 9784.393360] page->mem_cgroup:c00000000490d000 [ 9784.393416] migrating pfn 1f46d failed ret:1 ... $ grep "page dumped because: migration failure" /var/log/kern.log | wc -l 2405558 $ ls -la /var/log/kern.log -rw-r----- 1 syslog adm 2256109539 Jun 30 14:19 /var/log/kern.log Signed-off-by: Paolo Pisati Acked-by: Krzysztof Kozlowski Signed-off-by: Shuah Khan --- tools/testing/selftests/memory-hotplug/mem-on-off-test.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index b37585e6aa38..46a97f318f58 100755 --- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh @@ -282,7 +282,9 @@ done # echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error for memory in `hotpluggable_online_memory`; do - offline_memory_expect_fail $memory + if [ $((RANDOM % 100)) -lt $ratio ]; then + offline_memory_expect_fail $memory + fi done echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error From 422969bbb5af2f7226cf75cdb4aae02f46299dc2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 9 Jul 2021 13:26:20 -0700 Subject: [PATCH 0267/1469] scsi: core: Fix the documentation of the scsi_execute() time parameter The unit of the scsi_execute() timeout parameter is 1/HZ seconds instead of one second, just like the timeouts used in the block layer. Fix the documentation header above the definition of the scsi_execute() macro. Link: https://lore.kernel.org/r/20210709202638.9480-3-bvanassche@acm.org Fixes: "[SCSI] use scatter lists for all block pc requests and simplify hw handlers" # v2.6.16.28 Cc: "James E.J. Bottomley" Cc: Hannes Reinecke Cc: Ming Lei Cc: John Garry Reviewed-by: Avri Altman Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 8f9727e525aa..7456a26aef51 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -194,7 +194,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) * @bufflen: len of buffer * @sense: optional sense buffer * @sshdr: optional decoded sense header - * @timeout: request timeout in seconds + * @timeout: request timeout in HZ * @retries: number of times to retry request * @flags: flags for ->cmd_flags * @rq_flags: flags for ->rq_flags From fbf1a58701ecbf61211476277a77eaada6c091d4 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sat, 10 Jul 2021 20:36:23 -0700 Subject: [PATCH 0268/1469] scsi: fas216: Fix a build error Use SAM_STAT_GOOD instead of GOOD since GOOD has been removed. Link: https://lore.kernel.org/r/20210711033623.11267-1-bvanassche@acm.org Fixes: 3d45cefc8edd ("scsi: core: Drop obsolete Linux-specific SCSI status codes") Fixes: df1303147649 ("scsi: fas216: Use get_status_byte() to avoid using Linux-specific status codes") Cc: Hannes Reinecke Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/arm/fas216.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 30ed3d23635a..6baa9b36367d 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -2010,7 +2010,7 @@ static void fas216_rq_sns_done(FAS216_Info *info, struct scsi_cmnd *SCpnt, "request sense complete, result=0x%04x%02x%02x", result, SCpnt->SCp.Message, SCpnt->SCp.Status); - if (result != DID_OK || SCpnt->SCp.Status != GOOD) + if (result != DID_OK || SCpnt->SCp.Status != SAM_STAT_GOOD) /* * Something went wrong. Make sure that we don't * have valid data in the sense buffer that could From 93aa71ad7379900e61c8adff6a710a4c18c7c99b Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Thu, 1 Jul 2021 13:56:59 -0600 Subject: [PATCH 0269/1469] scsi: core: Fix bad pointer dereference when ehandler kthread is invalid Commit 66a834d09293 ("scsi: core: Fix error handling of scsi_host_alloc()") changed the allocation logic to call put_device() to perform host cleanup with the assumption that IDA removal and stopping the kthread would properly be performed in scsi_host_dev_release(). However, in the unlikely case that the error handler thread fails to spawn, shost->ehandler is set to ERR_PTR(-ENOMEM). The error handler cleanup code in scsi_host_dev_release() will call kthread_stop() if shost->ehandler != NULL which will always be the case whether the kthread was successfully spawned or not. In the case that it failed to spawn this has the nasty side effect of trying to dereference an invalid pointer when kthread_stop() is called. The following splat provides an example of this behavior in the wild: scsi host11: error handler thread failed to spawn, error = -4 Kernel attempted to read user page (10c) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x0000010c Faulting instruction address: 0xc00000000818e9a8 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: ibmvscsi(+) scsi_transport_srp dm_multipath dm_mirror dm_region hash dm_log dm_mod fuse overlay squashfs loop CPU: 12 PID: 274 Comm: systemd-udevd Not tainted 5.13.0-rc7 #1 NIP: c00000000818e9a8 LR: c0000000089846e8 CTR: 0000000000007ee8 REGS: c000000037d12ea0 TRAP: 0300 Not tainted (5.13.0-rc7) MSR: 800000000280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 28228228 XER: 20040001 CFAR: c0000000089846e4 DAR: 000000000000010c DSISR: 40000000 IRQMASK: 0 GPR00: c0000000089846e8 c000000037d13140 c000000009cc1100 fffffffffffffffc GPR04: 0000000000000001 0000000000000000 0000000000000000 c000000037dc0000 GPR08: 0000000000000000 c000000037dc0000 0000000000000001 00000000fffff7ff GPR12: 0000000000008000 c00000000a049000 c000000037d13d00 000000011134d5a0 GPR16: 0000000000001740 c0080000190d0000 c0080000190d1740 c000000009129288 GPR20: c000000037d13bc0 0000000000000001 c000000037d13bc0 c0080000190b7898 GPR24: c0080000190b7708 0000000000000000 c000000033bb2c48 0000000000000000 GPR28: c000000046b28280 0000000000000000 000000000000010c fffffffffffffffc NIP [c00000000818e9a8] kthread_stop+0x38/0x230 LR [c0000000089846e8] scsi_host_dev_release+0x98/0x160 Call Trace: [c000000033bb2c48] 0xc000000033bb2c48 (unreliable) [c0000000089846e8] scsi_host_dev_release+0x98/0x160 [c00000000891e960] device_release+0x60/0x100 [c0000000087e55c4] kobject_release+0x84/0x210 [c00000000891ec78] put_device+0x28/0x40 [c000000008984ea4] scsi_host_alloc+0x314/0x430 [c0080000190b38bc] ibmvscsi_probe+0x54/0xad0 [ibmvscsi] [c000000008110104] vio_bus_probe+0xa4/0x4b0 [c00000000892a860] really_probe+0x140/0x680 [c00000000892aefc] driver_probe_device+0x15c/0x200 [c00000000892b63c] device_driver_attach+0xcc/0xe0 [c00000000892b740] __driver_attach+0xf0/0x200 [c000000008926f28] bus_for_each_dev+0xa8/0x130 [c000000008929ce4] driver_attach+0x34/0x50 [c000000008928fc0] bus_add_driver+0x1b0/0x300 [c00000000892c798] driver_register+0x98/0x1a0 [c00000000810eb60] __vio_register_driver+0x80/0xe0 [c0080000190b4a30] ibmvscsi_module_init+0x9c/0xdc [ibmvscsi] [c0000000080121d0] do_one_initcall+0x60/0x2d0 [c000000008261abc] do_init_module+0x7c/0x320 [c000000008265700] load_module+0x2350/0x25b0 [c000000008265cb4] __do_sys_finit_module+0xd4/0x160 [c000000008031110] system_call_exception+0x150/0x2d0 [c00000000800d35c] system_call_common+0xec/0x278 Fix this be nulling shost->ehandler when the kthread fails to spawn. Link: https://lore.kernel.org/r/20210701195659.3185475-1-tyreld@linux.ibm.com Fixes: 66a834d09293 ("scsi: core: Fix error handling of scsi_host_alloc()") Cc: stable@vger.kernel.org Reviewed-by: Ming Lei Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/hosts.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 929a3b043ad7..3f6f14f0cafb 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -488,6 +488,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost_printk(KERN_WARNING, shost, "error handler thread failed to spawn, error = %ld\n", PTR_ERR(shost->ehandler)); + shost->ehandler = NULL; goto fail; } From 8b3bdd99c092bbaeaa7d9eecb1a3e5dc9112002b Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Fri, 2 Jul 2021 18:09:22 +0200 Subject: [PATCH 0270/1469] scsi: zfcp: Report port fc_security as unknown early during remote cable pull On remote cable pull, a zfcp_port keeps its status and only gets ZFCP_STATUS_PORT_LINK_TEST added. Only after an ADISC timeout, we would actually start port recovery and remove ZFCP_STATUS_COMMON_UNBLOCKED which zfcp_sysfs_port_fc_security_show() detected and reported as "unknown" instead of the old and possibly stale zfcp_port->connection_info. Add check for ZFCP_STATUS_PORT_LINK_TEST for timely "unknown" report. Link: https://lore.kernel.org/r/20210702160922.2667874-1-maier@linux.ibm.com Fixes: a17c78460093 ("scsi: zfcp: report FC Endpoint Security in sysfs") Cc: #5.7+ Reviewed-by: Benjamin Block Signed-off-by: Steffen Maier Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_sysfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 544efd4c42f0..b8cd75a872ee 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -487,6 +487,7 @@ static ssize_t zfcp_sysfs_port_fc_security_show(struct device *dev, if (0 == (status & ZFCP_STATUS_COMMON_OPEN) || 0 == (status & ZFCP_STATUS_COMMON_UNBLOCKED) || 0 == (status & ZFCP_STATUS_PORT_PHYS_OPEN) || + 0 != (status & ZFCP_STATUS_PORT_LINK_TEST) || 0 != (status & ZFCP_STATUS_COMMON_ERP_FAILED) || 0 != (status & ZFCP_STATUS_COMMON_ACCESS_BOXED)) i = sprintf(buf, "unknown\n"); From bb6beabf2f79ea063750bf16e78b61e5a50f2d5c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Jul 2021 09:57:23 -0700 Subject: [PATCH 0271/1469] scsi: pm8001: Clean up kernel-doc and comments Fix kernel-doc warnings then test again, wash, rinse, find more, then repeat more/again. Also fix spellos, some grammar, and some punctuation. ../drivers/scsi/pm8001/pm8001_ctl.c:557: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** pm8001_ctl_fatal_log_show - fatal error logging ../drivers/scsi/pm8001/pm8001_ctl.c:577: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** non_fatal_log_show - non fatal error logging ../drivers/scsi/pm8001/pm8001_ctl.c:622: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** pm8001_ctl_gsm_log_show - gsm dump collection Link: https://lore.kernel.org/r/20210708165723.8594-1-rdunlap@infradead.org Cc: Jack Wang Cc: linux-scsi@vger.kernel.org Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Acked-by: Jack Wang Signed-off-by: Randy Dunlap Signed-off-by: Martin K. Petersen --- drivers/scsi/pm8001/pm8001_ctl.c | 48 +++++++++++++++-------------- drivers/scsi/pm8001/pm8001_hwi.c | 18 +++++------ drivers/scsi/pm8001/pm8001_init.c | 29 +++++++++--------- drivers/scsi/pm8001/pm8001_sas.c | 41 +++++++++++++------------ drivers/scsi/pm8001/pm80xx_hwi.c | 50 +++++++++++++++---------------- 5 files changed, 97 insertions(+), 89 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_ctl.c b/drivers/scsi/pm8001/pm8001_ctl.c index 0b8802beb7ce..ec05c42e8ee6 100644 --- a/drivers/scsi/pm8001/pm8001_ctl.c +++ b/drivers/scsi/pm8001/pm8001_ctl.c @@ -77,7 +77,7 @@ DEVICE_ATTR(interface_rev, S_IRUGO, pm8001_ctl_mpi_interface_rev_show, NULL); * @attr: device attribute (unused) * @buf: the buffer returned * - * A sysfs 'read only' shost attribute. + * A sysfs 'read-only' shost attribute. */ static ssize_t controller_fatal_error_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -149,7 +149,7 @@ static ssize_t pm8001_ctl_ila_version_show(struct device *cdev, static DEVICE_ATTR(ila_version, 0444, pm8001_ctl_ila_version_show, NULL); /** - * pm8001_ctl_inactive_fw_version_show - Inacative firmware version number + * pm8001_ctl_inactive_fw_version_show - Inactive firmware version number * @cdev: pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned @@ -396,6 +396,7 @@ static DEVICE_ATTR(aap_log, S_IRUGO, pm8001_ctl_aap_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned + * * A sysfs 'read-only' shost attribute. */ static ssize_t pm8001_ctl_ib_queue_log_show(struct device *cdev, @@ -430,6 +431,7 @@ static DEVICE_ATTR(ib_log, S_IRUGO, pm8001_ctl_ib_queue_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned + * * A sysfs 'read-only' shost attribute. */ @@ -464,6 +466,7 @@ static DEVICE_ATTR(ob_log, S_IRUGO, pm8001_ctl_ob_queue_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf:the buffer returned + * * A sysfs 'read-only' shost attribute. */ static ssize_t pm8001_ctl_bios_version_show(struct device *cdev, @@ -555,13 +558,13 @@ static ssize_t pm8001_ctl_iop_log_show(struct device *cdev, static DEVICE_ATTR(iop_log, S_IRUGO, pm8001_ctl_iop_log_show, NULL); /** - ** pm8001_ctl_fatal_log_show - fatal error logging - ** @cdev:pointer to embedded class device - ** @attr: device attribute - ** @buf: the buffer returned - ** - ** A sysfs 'read-only' shost attribute. - **/ + * pm8001_ctl_fatal_log_show - fatal error logging + * @cdev:pointer to embedded class device + * @attr: device attribute + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t pm8001_ctl_fatal_log_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -575,13 +578,13 @@ static ssize_t pm8001_ctl_fatal_log_show(struct device *cdev, static DEVICE_ATTR(fatal_log, S_IRUGO, pm8001_ctl_fatal_log_show, NULL); /** - ** non_fatal_log_show - non fatal error logging - ** @cdev:pointer to embedded class device - ** @attr: device attribute - ** @buf: the buffer returned - ** - ** A sysfs 'read-only' shost attribute. - **/ + * non_fatal_log_show - non fatal error logging + * @cdev:pointer to embedded class device + * @attr: device attribute + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t non_fatal_log_show(struct device *cdev, struct device_attribute *attr, char *buf) { @@ -620,12 +623,13 @@ static ssize_t non_fatal_count_store(struct device *cdev, static DEVICE_ATTR_RW(non_fatal_count); /** - ** pm8001_ctl_gsm_log_show - gsm dump collection - ** @cdev:pointer to embedded class device - ** @attr: device attribute (unused) - ** @buf: the buffer returned - ** A sysfs 'read-only' shost attribute. - **/ + * pm8001_ctl_gsm_log_show - gsm dump collection + * @cdev:pointer to embedded class device + * @attr: device attribute (unused) + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t pm8001_ctl_gsm_log_show(struct device *cdev, struct device_attribute *attr, char *buf) { diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 33f8217577b1..17c0f26e683a 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -384,7 +384,7 @@ static void update_outbnd_queue_table(struct pm8001_hba_info *pm8001_ha, /** * pm8001_bar4_shift - function is called to shift BAR base address - * @pm8001_ha : our hba card infomation + * @pm8001_ha : our hba card information * @shiftValue : shifting value in memory bar. */ int pm8001_bar4_shift(struct pm8001_hba_info *pm8001_ha, u32 shiftValue) @@ -1151,7 +1151,7 @@ static void pm8001_hw_chip_rst(struct pm8001_hba_info *pm8001_ha) } /** - * pm8001_chip_iounmap - which maped when initialized. + * pm8001_chip_iounmap - which mapped when initialized. * @pm8001_ha: our hba card information */ void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha) @@ -1187,10 +1187,10 @@ pm8001_chip_intx_interrupt_enable(struct pm8001_hba_info *pm8001_ha) pm8001_cw32(pm8001_ha, 0, MSGU_ODCR, ODCR_CLEAR_ALL); } - /** - * pm8001_chip_intx_interrupt_disable- disable PM8001 chip interrupt - * @pm8001_ha: our hba card information - */ +/** + * pm8001_chip_intx_interrupt_disable - disable PM8001 chip interrupt + * @pm8001_ha: our hba card information + */ static void pm8001_chip_intx_interrupt_disable(struct pm8001_hba_info *pm8001_ha) { @@ -1876,8 +1876,8 @@ static void pm8001_send_read_log(struct pm8001_hba_info *pm8001_ha, * @piomb: the message contents of this outbound message. * * When FW has completed a ssp request for example a IO request, after it has - * filled the SG data with the data, it will trigger this event represent - * that he has finished the job,please check the coresponding buffer. + * filled the SG data with the data, it will trigger this event representing + * that he has finished the job; please check the corresponding buffer. * So we will tell the caller who maybe waiting the result to tell upper layer * that the task has been finished. */ @@ -3522,7 +3522,7 @@ hw_event_phy_down(struct pm8001_hba_info *pm8001_ha, void *piomb) * * when sas layer find a device it will notify LLDD, then the driver register * the domain device to FW, this event is the return device ID which the FW - * has assigned, from now,inter-communication with FW is no longer using the + * has assigned, from now, inter-communication with FW is no longer using the * SAS address, use device ID which FW assigned. */ int pm8001_mpi_reg_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 313248c7bab9..47db7e0beae6 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -233,7 +233,7 @@ static irqreturn_t pm8001_interrupt_handler_msix(int irq, void *opaque) /** * pm8001_interrupt_handler_intx - main INTx interrupt handler. * @irq: interrupt number - * @dev_id: sas_ha structure. The HBA is retrieved from sas_has structure. + * @dev_id: sas_ha structure. The HBA is retrieved from sas_ha structure. */ static irqreturn_t pm8001_interrupt_handler_intx(int irq, void *dev_id) @@ -439,9 +439,9 @@ err_out: } /** - * pm8001_ioremap - remap the pci high physical address to kernal virtual + * pm8001_ioremap - remap the pci high physical address to kernel virtual * address so that we can access them. - * @pm8001_ha:our hba structure. + * @pm8001_ha: our hba structure. */ static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha) { @@ -652,7 +652,7 @@ static void pm8001_post_sas_ha_init(struct Scsi_Host *shost, * pm8001_init_sas_add - initialize sas address * @pm8001_ha: our ha struct. * - * Currently we just set the fixed SAS address to our HBA,for manufacture, + * Currently we just set the fixed SAS address to our HBA, for manufacture, * it should read from the EEPROM */ static void pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha) @@ -790,7 +790,7 @@ struct pm8001_mpi3_phy_pg_trx_config { }; /** - * pm8001_get_internal_phy_settings : Retrieves the internal PHY settings + * pm8001_get_internal_phy_settings - Retrieves the internal PHY settings * @pm8001_ha : our adapter * @phycfg : PHY config page to populate */ @@ -810,7 +810,7 @@ void pm8001_get_internal_phy_settings(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_get_external_phy_settings : Retrieves the external PHY settings + * pm8001_get_external_phy_settings - Retrieves the external PHY settings * @pm8001_ha : our adapter * @phycfg : PHY config page to populate */ @@ -830,7 +830,7 @@ void pm8001_get_external_phy_settings(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_get_phy_mask : Retrieves the mask that denotes if a PHY is int/ext + * pm8001_get_phy_mask - Retrieves the mask that denotes if a PHY is int/ext * @pm8001_ha : our adapter * @phymask : The PHY mask */ @@ -868,7 +868,7 @@ void pm8001_get_phy_mask(struct pm8001_hba_info *pm8001_ha, int *phymask) } /** - * pm8001_set_phy_settings_ven_117c_12G() : Configure ATTO 12Gb PHY settings + * pm8001_set_phy_settings_ven_117c_12G() - Configure ATTO 12Gb PHY settings * @pm8001_ha : our adapter */ static @@ -903,7 +903,7 @@ int pm8001_set_phy_settings_ven_117c_12G(struct pm8001_hba_info *pm8001_ha) } /** - * pm8001_configure_phy_settings : Configures PHY settings based on vendor ID. + * pm8001_configure_phy_settings - Configures PHY settings based on vendor ID. * @pm8001_ha : our hba. */ static int pm8001_configure_phy_settings(struct pm8001_hba_info *pm8001_ha) @@ -1053,8 +1053,8 @@ intx: * @ent: pci device id * * This function is the main initialization function, when register a new - * pci driver it is invoked, all struct an hardware initilization should be done - * here, also, register interrupt + * pci driver it is invoked, all struct and hardware initialization should be + * done here, also, register interrupt. */ static int pm8001_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -1172,10 +1172,11 @@ err_out_enable: return rc; } -/* +/** * pm8001_init_ccb_tag - allocate memory to CCB and tag. * @pm8001_ha: our hba card information. * @shost: scsi host which has been allocated outside. + * @pdev: pci device. */ static int pm8001_init_ccb_tag(struct pm8001_hba_info *pm8001_ha, struct Scsi_Host *shost, @@ -1270,7 +1271,7 @@ static void pm8001_pci_remove(struct pci_dev *pdev) * pm8001_pci_suspend - power management suspend main entry point * @dev: Device struct * - * Returns 0 success, anything else error. + * Return: 0 on success, anything else on error. */ static int __maybe_unused pm8001_pci_suspend(struct device *dev) { @@ -1315,7 +1316,7 @@ static int __maybe_unused pm8001_pci_suspend(struct device *dev) * pm8001_pci_resume - power management resume main entry point * @dev: Device struct * - * Returns 0 success, anything else error. + * Return: 0 on success, anything else on error. */ static int __maybe_unused pm8001_pci_resume(struct device *dev) { diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 6f33d821e545..48548a95327b 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -98,14 +98,16 @@ void pm8001_tag_init(struct pm8001_hba_info *pm8001_ha) pm8001_tag_free(pm8001_ha, i); } - /** - * pm8001_mem_alloc - allocate memory for pm8001. - * @pdev: pci device. - * @virt_addr: the allocated virtual address - * @pphys_addr_hi: the physical address high byte address. - * @pphys_addr_lo: the physical address low byte address. - * @mem_size: memory size. - */ +/** + * pm8001_mem_alloc - allocate memory for pm8001. + * @pdev: pci device. + * @virt_addr: the allocated virtual address + * @pphys_addr: DMA address for this device + * @pphys_addr_hi: the physical address high byte address. + * @pphys_addr_lo: the physical address low byte address. + * @mem_size: memory size. + * @align: requested byte alignment + */ int pm8001_mem_alloc(struct pci_dev *pdev, void **virt_addr, dma_addr_t *pphys_addr, u32 *pphys_addr_hi, u32 *pphys_addr_lo, u32 mem_size, u32 align) @@ -339,7 +341,7 @@ static int pm8001_task_prep_ssp_tm(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_task_prep_ssp - the dispatcher function,prepare ssp data for ssp task + * pm8001_task_prep_ssp - the dispatcher function, prepare ssp data for ssp task * @pm8001_ha: our hba card information * @ccb: the ccb which attached to ssp task */ @@ -554,10 +556,10 @@ void pm8001_ccb_task_free(struct pm8001_hba_info *pm8001_ha, pm8001_tag_free(pm8001_ha, ccb_idx); } - /** - * pm8001_alloc_dev - find a empty pm8001_device - * @pm8001_ha: our hba card information - */ +/** + * pm8001_alloc_dev - find a empty pm8001_device + * @pm8001_ha: our hba card information + */ static struct pm8001_device *pm8001_alloc_dev(struct pm8001_hba_info *pm8001_ha) { u32 dev; @@ -705,7 +707,7 @@ static void pm8001_tmf_timedout(struct timer_list *t) * @parameter: ssp task parameter. * * when errors or exception happened, we may want to do something, for example - * abort the issued task which result in this execption, it is done by calling + * abort the issued task which result in this exception, it is done by calling * this function, note it is also with the task execute interface. */ static int pm8001_exec_internal_tmf_task(struct domain_device *dev, @@ -984,11 +986,12 @@ void pm8001_open_reject_retry( } /** - * pm8001_I_T_nexus_reset() - * Standard mandates link reset for ATA (type 0) and hard reset for - * SSP (type 1) , only for RECOVERY - * @dev: the device structure for the device to reset. - */ + * pm8001_I_T_nexus_reset() - reset the initiator/target connection + * @dev: the device structure for the device to reset. + * + * Standard mandates link reset for ATA (type 0) and hard reset for + * SSP (type 1), only for RECOVERY + */ int pm8001_I_T_nexus_reset(struct domain_device *dev) { int rc = TMF_RESP_FUNC_FAILED; diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 45ecd9639977..6ffe17b849ae 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -140,7 +140,7 @@ ssize_t pm80xx_get_fatal_dump(struct device *cdev, pm8001_ha->fatal_bar_loc = 0; } - /* Read until accum_len is retrived */ + /* Read until accum_len is retrieved */ accum_len = pm8001_mr32(fatal_table_address, MPI_FATAL_EDUMP_TABLE_ACCUM_LEN); /* Determine length of data between previously stored transfer length @@ -1011,7 +1011,7 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha) value); return -EBUSY; } - /* check the MPI-State for initialization upto 100ms*/ + /* check the MPI-State for initialization up to 100ms*/ max_wait_count = 5;/* 100 msec */ do { msleep(FW_READY_INTERVAL); @@ -1093,7 +1093,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) value = pm8001_cr32(pm8001_ha, 0, MSGU_SCRATCH_PAD_0); - /** + /* * lower 26 bits of SCRATCHPAD0 register describes offset within the * PCIe BAR where the MPI configuration table is present */ @@ -1101,7 +1101,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pm8001_dbg(pm8001_ha, DEV, "Scratchpad 0 Offset: 0x%x value 0x%x\n", offset, value); - /** + /* * Upper 6 bits describe the offset within PCI config space where BAR * is located. */ @@ -1109,7 +1109,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pcibar = get_pci_bar_index(pcilogic); pm8001_dbg(pm8001_ha, INIT, "Scratchpad 0 PCI BAR: %d\n", pcibar); - /** + /* * Make sure the offset falls inside the ioremapped PCI BAR */ if (offset > pm8001_ha->io_mem[pcibar].memsize) { @@ -1121,7 +1121,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pm8001_ha->main_cfg_tbl_addr = base_addr = pm8001_ha->io_mem[pcibar].memvirtaddr + offset; - /** + /* * Validate main configuration table address: first DWord should read * "PMCS" */ @@ -1385,7 +1385,7 @@ pm80xx_get_encrypt_info(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_encrypt_update - update flash with encryption informtion + * pm80xx_encrypt_update - update flash with encryption information * @pm8001_ha: our hba card information. */ static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha) @@ -1422,7 +1422,7 @@ static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_chip_init - the main init function that initialize whole PM8001 chip. + * pm80xx_chip_init - the main init function that initializes whole PM8001 chip. * @pm8001_ha: our hba card information */ static int pm80xx_chip_init(struct pm8001_hba_info *pm8001_ha) @@ -1541,7 +1541,7 @@ static int mpi_uninit_check(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_fatal_errors - returns non zero *ONLY* when fatal errors + * pm80xx_fatal_errors - returns non-zero *ONLY* when fatal errors * @pm8001_ha: our hba card information * * Fatal errors are recoverable only after a host reboot. @@ -1576,8 +1576,8 @@ pm80xx_fatal_errors(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that the clear all - * the FW register status to the originated status. + * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that all + * FW register status are reset to the originated status. * @pm8001_ha: our hba card information */ @@ -1895,13 +1895,13 @@ static void pm80xx_send_read_log(struct pm8001_hba_info *pm8001_ha, } /** - * mpi_ssp_completion- process the event that FW response to the SSP request. + * mpi_ssp_completion - process the event that FW response to the SSP request. * @pm8001_ha: our hba card information * @piomb: the message contents of this outbound message. * * When FW has completed a ssp request for example a IO request, after it has - * filled the SG data with the data, it will trigger this event represent - * that he has finished the job,please check the coresponding buffer. + * filled the SG data with the data, it will trigger this event representing + * that he has finished the job; please check the corresponding buffer. * So we will tell the caller who maybe waiting the result to tell upper layer * that the task has been finished. */ @@ -3217,7 +3217,7 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * pm80xx_hw_event_ack_req- For PM8001,some events need to acknowage to FW. + * pm80xx_hw_event_ack_req- For PM8001, some events need to acknowledge to FW. * @pm8001_ha: our hba card information * @Qnum: the outbound queue message number. * @SEA: source of event to ack @@ -3275,7 +3275,7 @@ static void hw_event_port_recover(struct pm8001_hba_info *pm8001_ha, } /** - * hw_event_sas_phy_up -FW tells me a SAS phy up event. + * hw_event_sas_phy_up - FW tells me a SAS phy up event. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3353,7 +3353,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * hw_event_sata_phy_up -FW tells me a SATA phy up event. + * hw_event_sata_phy_up - FW tells me a SATA phy up event. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3400,7 +3400,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * hw_event_phy_down -we should notify the libsas the phy is down. + * hw_event_phy_down - we should notify the libsas the phy is down. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3500,7 +3500,7 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * mpi_thermal_hw_event -The hw event has come. + * mpi_thermal_hw_event - a thermal hw event has come. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3530,7 +3530,7 @@ static int mpi_thermal_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * mpi_hw_event -The hw event has come. + * mpi_hw_event - The hw event has come. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -4025,7 +4025,7 @@ static void process_one_iomb(struct pm8001_hba_info *pm8001_ha, void *piomb) case OPC_OUB_SET_DEV_INFO: pm8001_dbg(pm8001_ha, MSG, "OPC_OUB_SET_DEV_INFO\n"); break; - /* spcv specifc commands */ + /* spcv specific commands */ case OPC_OUB_PHY_START_RESP: pm8001_dbg(pm8001_ha, MSG, "OPC_OUB_PHY_START_RESP opcode:%x\n", opc); @@ -4186,7 +4186,7 @@ static void build_smp_cmd(u32 deviceID, __le32 hTag, } /** - * pm80xx_chip_smp_req - send a SMP task to FW + * pm80xx_chip_smp_req - send an SMP task to FW * @pm8001_ha: our hba card information. * @ccb: the ccb information this request used. */ @@ -4346,7 +4346,7 @@ static int check_enc_sat_cmd(struct sas_task *task) } /** - * pm80xx_chip_ssp_io_req - send a SSP task to FW + * pm80xx_chip_ssp_io_req - send an SSP task to FW * @pm8001_ha: our hba card information. * @ccb: the ccb information this request used. */ @@ -4750,13 +4750,13 @@ pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE | LINKMODE_AUTO | pm8001_ha->link_rate | phy_id); /* SSC Disable and SAS Analog ST configuration */ - /** + /* payload.ase_sh_lm_slr_phyid = cpu_to_le32(SSC_DISABLE_30 | SAS_ASE | SPINHOLD_DISABLE | LINKMODE_AUTO | LINKRATE_15 | LINKRATE_30 | LINKRATE_60 | phy_id); Have to add "SAS PHY Analog Setup SPASTI 1 Byte" Based on need - **/ + */ payload.sas_identify.dev_type = SAS_END_DEVICE; payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL; From aa0dc6a73309f1fc779f4560a60ee766a3891adc Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 7 Jul 2021 13:47:56 +0530 Subject: [PATCH 0272/1469] scsi: mpi3mr: Fix W=1 compilation warnings Fix for the following W=1 compilation warning: 'strncpy' output may be truncated copying 16 bytes from a string of length 64 Link: https://lore.kernel.org/r/20210707081756.20922-1-sreekanth.reddy@broadcom.com Reported-by: kernel test robot Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_fw.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 9eceafca59bc..2dba2b0af166 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -2607,14 +2607,13 @@ static int mpi3mr_issue_iocinit(struct mpi3mr_ioc *mrioc) goto out; } drv_info->information_length = cpu_to_le32(data_len); - strncpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature)); - strncpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name)); - drv_info->os_name[sizeof(drv_info->os_name) - 1] = 0; - strncpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version)); - drv_info->os_version[sizeof(drv_info->os_version) - 1] = 0; - strncpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name)); - strncpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version)); - strncpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE, sizeof(drv_info->driver_release_date)); + strscpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature)); + strscpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name)); + strscpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version)); + strscpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name)); + strscpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version)); + strscpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE, + sizeof(drv_info->driver_release_date)); drv_info->driver_capabilities = 0; memcpy((u8 *)&mrioc->driver_info, (u8 *)drv_info, sizeof(mrioc->driver_info)); From 053c16ac89050ef0e8ab9dc1edaf157bf104c8c6 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 30 Jun 2021 17:51:17 -0700 Subject: [PATCH 0273/1469] scsi: ufs: core: Add missing host_lock in ufshcd_vops_setup_xfer_req() This patch adds a host_lock which existed before on ufshcd_vops_setup_xfer_req(). Link: https://lore.kernel.org/r/20210701005117.3846179-1-jaegeuk@kernel.org Fixes: a45f937110fa ("scsi: ufs: Optimize host lock on transfer requests send/compl paths") Cc: Stanley Chu Cc: Can Guo Cc: Bean Huo Cc: Bart Van Assche Cc: Asutosh Das Reviewed-by: Bart Van Assche Signed-off-by: Jaegeuk Kim Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index c98d540ac044..194755c9ddfe 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -1229,8 +1229,13 @@ static inline int ufshcd_vops_pwr_change_notify(struct ufs_hba *hba, static inline void ufshcd_vops_setup_xfer_req(struct ufs_hba *hba, int tag, bool is_scsi_cmd) { - if (hba->vops && hba->vops->setup_xfer_req) - return hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd); + if (hba->vops && hba->vops->setup_xfer_req) { + unsigned long flags; + + spin_lock_irqsave(hba->host->host_lock, flags); + hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd); + spin_unlock_irqrestore(hba->host->host_lock, flags); + } } static inline void ufshcd_vops_setup_task_mgmt(struct ufs_hba *hba, From e181ad43887c6b6b5995e9b191666f04242d77eb Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 21:24:07 -0500 Subject: [PATCH 0274/1469] drm/msm: Fix fall-through warning in msm_gem_new_impl() Fix the following fall-through warning: drivers/gpu/drm/msm/msm_gem.c: In function 'msm_gem_new_impl': drivers/gpu/drm/msm/msm_gem.c:1170:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 1170 | if (priv->has_cached_coherent) | ^ drivers/gpu/drm/msm/msm_gem.c:1173:2: note: here 1173 | default: | ^~~~~~~ by replacing the /* fallthrough */ comment with fallthrough; Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/msm/msm_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 141178754231..1e8a971a86f2 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1169,7 +1169,7 @@ static int msm_gem_new_impl(struct drm_device *dev, case MSM_BO_CACHED_COHERENT: if (priv->has_cached_coherent) break; - /* fallthrough */ + fallthrough; default: DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n", (flags & MSM_BO_CACHE_MASK)); From e48a12e546ecbfb0718176037eae0ad60598a29a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 13 Jul 2021 06:16:05 +0200 Subject: [PATCH 0275/1469] jump_labels: Mark __jump_label_transform() as __always_inlined to work around aggressive compiler un-inlining In randconfig testing, certain UBSAN and CC Kconfig combinations with GCC 10.3.0: CONFIG_X86_32=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_UBSAN=y # CONFIG_UBSAN_TRAP is not set # CONFIG_UBSAN_BOUNDS is not set CONFIG_UBSAN_SHIFT=y # CONFIG_UBSAN_DIV_ZERO is not set CONFIG_UBSAN_UNREACHABLE=y CONFIG_UBSAN_BOOL=y # CONFIG_UBSAN_ENUM is not set # CONFIG_UBSAN_ALIGNMENT is not set # CONFIG_UBSAN_SANITIZE_ALL is not set ... produce this build warning (and build error if CONFIG_SECTION_MISMATCH_WARN_ONLY=y is set): WARNING: modpost: vmlinux.o(.text+0x4c1cc): Section mismatch in reference from the function __jump_label_transform() to the function .init.text:text_poke_early() The function __jump_label_transform() references the function __init text_poke_early(). This is often because __jump_label_transform lacks a __init annotation or the annotation of text_poke_early is wrong. ERROR: modpost: Section mismatches detected. The problem is that __jump_label_transform() gets uninlined by GCC, despite there being only a single local scope user of the 'static inline' function. Mark the function __always_inline instead, to work around this compiler bug/artifact. Signed-off-by: Ingo Molnar --- arch/x86/kernel/jump_label.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 674906fad43b..68f091ba8443 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -79,9 +79,10 @@ __jump_label_patch(struct jump_entry *entry, enum jump_label_type type) return (struct jump_label_patch){.code = code, .size = size}; } -static inline void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static __always_inline void +__jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { const struct jump_label_patch jlp = __jump_label_patch(entry, type); From e9ba16e68cce2f85e9f5d2eba5c0453f1a741fd2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 11 Jul 2021 08:26:45 +0200 Subject: [PATCH 0276/1469] smpboot: Mark idle_init() as __always_inlined to work around aggressive compiler un-inlining While this function is a static inline, and is only used once in local scope, certain Kconfig variations may cause it to be compiled as a standalone function: 89231bf0 : 89231bf0: 83 05 60 d9 45 89 01 addl $0x1,0x8945d960 89231bf7: 55 push %ebp Resulting in this build failure: WARNING: modpost: vmlinux.o(.text.unlikely+0x7fd5): Section mismatch in reference from the function idle_init() to the function .init.text:fork_idle() The function idle_init() references the function __init fork_idle(). This is often because idle_init lacks a __init annotation or the annotation of fork_idle is wrong. ERROR: modpost: Section mismatches detected. Certain USBSAN options x86-32 builds with CONFIG_CC_OPTIMIZE_FOR_SIZE=y seem to be causing this. So mark idle_init() as __always_inline to work around this compiler bug/feature. Signed-off-by: Ingo Molnar --- kernel/smpboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/smpboot.c b/kernel/smpboot.c index e4163042c4d6..21b7953f8242 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -47,7 +47,7 @@ void __init idle_thread_set_boot_cpu(void) * * Creates the thread if it does not exist. */ -static inline void idle_init(unsigned int cpu) +static inline void __always_inline idle_init(unsigned int cpu) { struct task_struct *tsk = per_cpu(idle_threads, cpu); From 432b52eea3dcf48083bafa4b2b6ef5b054ead609 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 12 Jul 2021 12:16:57 +0200 Subject: [PATCH 0277/1469] ARM: shmobile: defconfig: Restore graphical consoles As of commit f611b1e7624ccdbd ("drm: Avoid circular dependencies for CONFIG_FB"), CONFIG_FB is no longer auto-enabled. While CONFIG_FB may be considered unneeded for systems where graphics is provided by a DRM driver, R-Mobile A1 still relies on a frame buffer device driver for graphics support. Restore support for graphics on R-Mobile A1 and graphical consoles on DRM-based systems by explicitly enabling CONFIG_FB in the defconfig for Renesas ARM systems. Fixes: f611b1e7624ccdbd ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/2a4474be1d2c00c6ca97c2714844ea416a9ea9a9.1626084948.git.geert+renesas@glider.be --- arch/arm/configs/shmobile_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 66c8b0980a0a..d9a27e4e0914 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -135,6 +135,7 @@ CONFIG_DRM_SII902X=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_I2C_ADV7511=y CONFIG_DRM_I2C_ADV7511_AUDIO=y +CONFIG_FB=y CONFIG_FB_SH_MOBILE_LCDC=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_AS3711=y From 8b43ced64d2baca72a13caf2a7182f2853e054bd Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Tue, 13 Jul 2021 11:31:56 +0200 Subject: [PATCH 0278/1469] nvme-tcp: use __dev_get_by_name instead dev_get_by_name for OPT_HOST_IFACE dev_get_by_name() finds network device by name but it also increases the reference count. If a nvme-tcp queue is present and the network device driver is removed before nvme_tcp, we will face the following continuous log: "kernel:unregister_netdevice: waiting for to become free. Usage count = 2" And rmmod further halts. Similar case arises during reboot/shutdown with nvme-tcp queue present and both never completes. To fix this, use __dev_get_by_name() which finds network device by name without increasing any reference counter. Fixes: 3ede8f72a9a2 ("nvme-tcp: allow selecting the network interface for connections") Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Prabhakar Kushwaha Reviewed-by: Sagi Grimberg [hch: remove the ->ndev member entirely] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 12acfe05cd68..8cb15ee5b249 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -123,7 +123,6 @@ struct nvme_tcp_ctrl { struct blk_mq_tag_set admin_tag_set; struct sockaddr_storage addr; struct sockaddr_storage src_addr; - struct net_device *ndev; struct nvme_ctrl ctrl; struct work_struct err_work; @@ -2533,8 +2532,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, } if (opts->mask & NVMF_OPT_HOST_IFACE) { - ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface); - if (!ctrl->ndev) { + if (!__dev_get_by_name(&init_net, opts->host_iface)) { pr_err("invalid interface passed: %s\n", opts->host_iface); ret = -ENODEV; From e4b9852a0f4afe40604afb442e3af4452722050a Mon Sep 17 00:00:00 2001 From: Casey Chen Date: Wed, 7 Jul 2021 14:14:31 -0700 Subject: [PATCH 0279/1469] nvme-pci: fix multiple races in nvme_setup_io_queues Below two paths could overlap each other if we power off a drive quickly after powering it on. There are multiple races in nvme_setup_io_queues() because of shutdown_lock missing and improper use of NVMEQ_ENABLED bit. nvme_reset_work() nvme_remove() nvme_setup_io_queues() nvme_dev_disable() ... ... A1 clear NVMEQ_ENABLED bit for admin queue lock retry: B1 nvme_suspend_io_queues() A2 pci_free_irq() admin queue B2 nvme_suspend_queue() admin queue A3 pci_free_irq_vectors() nvme_pci_disable() A4 nvme_setup_irqs(); B3 pci_free_irq_vectors() ... unlock A5 queue_request_irq() for admin queue set NVMEQ_ENABLED bit ... nvme_create_io_queues() A6 result = queue_request_irq(); set NVMEQ_ENABLED bit ... fail to allocate enough IO queues: A7 nvme_suspend_io_queues() goto retry If B3 runs in between A1 and A2, it will crash if irqaction haven't been freed by A2. B2 is supposed to free admin queue IRQ but it simply can't fulfill the job as A1 has cleared NVMEQ_ENABLED bit. Fix: combine A1 A2 so IRQ get freed as soon as the NVMEQ_ENABLED bit gets cleared. After solved #1, A2 could race with B3 if A2 is freeing IRQ while B3 is checking irqaction. A3 also could race with B2 if B2 is freeing IRQ while A3 is checking irqaction. Fix: A2 and A3 take lock for mutual exclusion. A3 could race with B3 since they could run free_msi_irqs() in parallel. Fix: A3 takes lock for mutual exclusion. A4 could fail to allocate all needed IRQ vectors if A3 and A4 are interrupted by B3. Fix: A4 takes lock for mutual exclusion. If A5/A6 happened after B2/B1, B3 will crash since irqaction is not NULL. They are just allocated by A5/A6. Fix: Lock queue_request_irq() and setting of NVMEQ_ENABLED bit. A7 could get chance to pci_free_irq() for certain IO queue while B3 is checking irqaction. Fix: A7 takes lock. nvme_dev->online_queues need to be protected by shutdown_lock. Since it is not atomic, both paths could modify it using its own copy. Co-developed-by: Yuanyuan Zhong Signed-off-by: Casey Chen Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 66 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 58 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d3c5086673bc..46698cabef81 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1554,6 +1554,28 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) wmb(); /* ensure the first interrupt sees the initialization */ } +/* + * Try getting shutdown_lock while setting up IO queues. + */ +static int nvme_setup_io_queues_trylock(struct nvme_dev *dev) +{ + /* + * Give up if the lock is being held by nvme_dev_disable. + */ + if (!mutex_trylock(&dev->shutdown_lock)) + return -ENODEV; + + /* + * Controller is in wrong state, fail early. + */ + if (dev->ctrl.state != NVME_CTRL_CONNECTING) { + mutex_unlock(&dev->shutdown_lock); + return -ENODEV; + } + + return 0; +} + static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) { struct nvme_dev *dev = nvmeq->dev; @@ -1582,8 +1604,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) goto release_cq; nvmeq->cq_vector = vector; - nvme_init_queue(nvmeq, qid); + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; + nvme_init_queue(nvmeq, qid); if (!polled) { result = queue_request_irq(nvmeq); if (result < 0) @@ -1591,10 +1616,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) } set_bit(NVMEQ_ENABLED, &nvmeq->flags); + mutex_unlock(&dev->shutdown_lock); return result; release_sq: dev->online_queues--; + mutex_unlock(&dev->shutdown_lock); adapter_delete_sq(dev, qid); release_cq: adapter_delete_cq(dev, qid); @@ -2167,7 +2194,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) if (nr_io_queues == 0) return 0; - clear_bit(NVMEQ_ENABLED, &adminq->flags); + /* + * Free IRQ resources as soon as NVMEQ_ENABLED bit transitions + * from set to unset. If there is a window to it is truely freed, + * pci_free_irq_vectors() jumping into this window will crash. + * And take lock to avoid racing with pci_free_irq_vectors() in + * nvme_dev_disable() path. + */ + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; + if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags)) + pci_free_irq(pdev, 0, adminq); if (dev->cmb_use_sqes) { result = nvme_cmb_qdepth(dev, nr_io_queues, @@ -2183,14 +2221,17 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) result = nvme_remap_bar(dev, size); if (!result) break; - if (!--nr_io_queues) - return -ENOMEM; + if (!--nr_io_queues) { + result = -ENOMEM; + goto out_unlock; + } } while (1); adminq->q_db = dev->dbs; retry: /* Deregister the admin queue's interrupt */ - pci_free_irq(pdev, 0, adminq); + if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags)) + pci_free_irq(pdev, 0, adminq); /* * If we enable msix early due to not intx, disable it again before @@ -2199,8 +2240,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) pci_free_irq_vectors(pdev); result = nvme_setup_irqs(dev, nr_io_queues); - if (result <= 0) - return -EIO; + if (result <= 0) { + result = -EIO; + goto out_unlock; + } dev->num_vecs = result; result = max(result - 1, 1); @@ -2214,8 +2257,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) */ result = queue_request_irq(adminq); if (result) - return result; + goto out_unlock; set_bit(NVMEQ_ENABLED, &adminq->flags); + mutex_unlock(&dev->shutdown_lock); result = nvme_create_io_queues(dev); if (result || dev->online_queues < 2) @@ -2224,6 +2268,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) if (dev->online_queues - 1 < dev->max_qid) { nr_io_queues = dev->online_queues - 1; nvme_disable_io_queues(dev); + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; nvme_suspend_io_queues(dev); goto retry; } @@ -2232,6 +2279,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) dev->io_queues[HCTX_TYPE_READ], dev->io_queues[HCTX_TYPE_POLL]); return 0; +out_unlock: + mutex_unlock(&dev->shutdown_lock); + return result; } static void nvme_del_queue_end(struct request *req, blk_status_t error) From 251ef6f71be2adfd09546a26643426fe62585173 Mon Sep 17 00:00:00 2001 From: Casey Chen Date: Wed, 7 Jul 2021 14:14:32 -0700 Subject: [PATCH 0280/1469] nvme-pci: do not call nvme_dev_remove_admin from nvme_remove nvme_dev_remove_admin could free dev->admin_q and the admin_tagset while they are being accessed by nvme_dev_disable(), which can be called by nvme_reset_work via nvme_remove_dead_ctrl. Commit cb4bfda62afa ("nvme-pci: fix hot removal during error handling") intended to avoid requests being stuck on a removed controller by killing the admin queue. But the later fix c8e9e9b7646e ("nvme-pci: unquiesce admin queue on shutdown"), together with nvme_dev_disable(dev, true) right before nvme_dev_remove_admin() could help dispatch requests and fail them early, so we don't need nvme_dev_remove_admin() any more. Fixes: cb4bfda62afa ("nvme-pci: fix hot removal during error handling") Signed-off-by: Casey Chen Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 46698cabef81..320051f5a3dd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3012,7 +3012,6 @@ static void nvme_remove(struct pci_dev *pdev) if (!pci_device_is_present(pdev)) { nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD); nvme_dev_disable(dev, true); - nvme_dev_remove_admin(dev); } flush_work(&dev->ctrl.reset_work); From 52f83955aaf91b22f46765b007b4404ce85b2133 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 14:08:01 +0100 Subject: [PATCH 0281/1469] firmware: arm_scmi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'fast_switch_possible' not described in 'scmi_perf_proto_ops' | Function parameter or member 'power_scale_mw_get' not described in 'scmi_perf_proto_ops' | cannot understand function prototype: 'struct scmi_sensor_reading ' | cannot understand function prototype: 'struct scmi_range_attrs ' | cannot understand function prototype: 'struct scmi_sensor_axis_info ' | cannot understand function prototype: 'struct scmi_sensor_intervals_info ' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-2-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 79d0a1237e6c..80e781c51ddc 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -101,6 +101,10 @@ struct scmi_clk_proto_ops { * to sustained performance level mapping * @est_power_get: gets the estimated power cost for a given performance domain * at a given frequency + * @fast_switch_possible: indicates if fast DVFS switching is possible or not + * for a given device + * @power_scale_mw_get: indicates if the power values provided are in milliWatts + * or in some other (abstract) scale */ struct scmi_perf_proto_ops { int (*limits_set)(const struct scmi_protocol_handle *ph, u32 domain, @@ -153,7 +157,7 @@ struct scmi_power_proto_ops { }; /** - * scmi_sensor_reading - represent a timestamped read + * struct scmi_sensor_reading - represent a timestamped read * * Used by @reading_get_timestamped method. * @@ -167,7 +171,7 @@ struct scmi_sensor_reading { }; /** - * scmi_range_attrs - specifies a sensor or axis values' range + * struct scmi_range_attrs - specifies a sensor or axis values' range * @min_range: The minimum value which can be represented by the sensor/axis. * @max_range: The maximum value which can be represented by the sensor/axis. */ @@ -177,7 +181,7 @@ struct scmi_range_attrs { }; /** - * scmi_sensor_axis_info - describes one sensor axes + * struct scmi_sensor_axis_info - describes one sensor axes * @id: The axes ID. * @type: Axes type. Chosen amongst one of @enum scmi_sensor_class. * @scale: Power-of-10 multiplier applied to the axis unit. @@ -205,8 +209,8 @@ struct scmi_sensor_axis_info { }; /** - * scmi_sensor_intervals_info - describes number and type of available update - * intervals + * struct scmi_sensor_intervals_info - describes number and type of available + * update intervals * @segmented: Flag for segmented intervals' representation. When True there * will be exactly 3 intervals in @desc, with each entry * representing a member of a segment in this order: From 5ff6319d46cee22c9cd6f39a377e32c444f9a7b0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 11:27:48 +0100 Subject: [PATCH 0282/1469] firmware: arm_scpi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'device_domain_id' not described in 'scpi_ops' | Function parameter or member 'get_transition_latency' not described in 'scpi_ops' | Function parameter or member 'add_opps_to_device' not described in 'scpi_ops' | Function parameter or member 'sensor_get_capability' not described in 'scpi_ops' | Function parameter or member 'sensor_get_info' not described in 'scpi_ops' | Function parameter or member 'sensor_get_value' not described in 'scpi_ops' | Function parameter or member 'device_get_power_state' not described in 'scpi_ops' | Function parameter or member 'device_set_power_state' not described in 'scpi_ops' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-1-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index afbf8037d8db..d2176a56828a 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -51,6 +51,14 @@ struct scpi_sensor_info { * OPP is an index to the list return by @dvfs_get_info * @dvfs_get_info: returns the DVFS capabilities of the given power * domain. It includes the OPP list and the latency information + * @device_domain_id: gets the scpi domain id for a given device + * @get_transition_latency: gets the DVFS transition latency for a given device + * @add_opps_to_device: adds all the OPPs for a given device + * @sensor_get_capability: get the list of capabilities for the sensors + * @sensor_get_info: get the information of the specified sensor + * @sensor_get_value: gets the current value of the sensor + * @device_get_power_state: gets the power state of a power domain + * @device_set_power_state: sets the power state of a power domain */ struct scpi_ops { u32 (*get_version)(void); From b98cf55ec0bd88bdba725845c743e94ecaf57b7e Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 12 Jul 2021 15:35:04 +0100 Subject: [PATCH 0283/1469] firmware: arm_scmi: Fix kernel doc warnings about return values Kernel doc validation script still complains about the following: |No description found for return value of 'scmi_get_protocol_device' |No description found for return value of 'scmi_devm_notifier_register' |No description found for return value of 'scmi_devm_notifier_unregister' Fix adding missing Return kernel-doc statements. Link: https://lore.kernel.org/r/20210712143504.33541-1-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 2 ++ drivers/firmware/arm_scmi/notify.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 36d80661d473..1cbd2b06e523 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1138,6 +1138,8 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) * @proto_id and @name: if device was still not existent it is created as a * child of the specified SCMI instance @info and its transport properly * initialized as usual. + * + * Return: A properly initialized scmi device, NULL otherwise. */ static inline struct scmi_device * scmi_get_protocol_device(struct device_node *np, struct scmi_info *info, diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index d860bebd984a..0efd20cd9d69 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -1457,6 +1457,8 @@ static void scmi_devm_release_notifier(struct device *dev, void *res) * * Generic devres managed helper to register a notifier_block against a * protocol event. + * + * Return: 0 on Success */ static int scmi_devm_notifier_register(struct scmi_device *sdev, u8 proto_id, u8 evt_id, @@ -1523,6 +1525,8 @@ static int scmi_devm_notifier_match(struct device *dev, void *res, void *data) * Generic devres managed helper to explicitly un-register a notifier_block * against a protocol event, which was previously registered using the above * @scmi_devm_notifier_register. + * + * Return: 0 on Success */ static int scmi_devm_notifier_unregister(struct scmi_device *sdev, u8 proto_id, u8 evt_id, From 187a002b07e8089f0b5657eafec50b5d05625569 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 28 Jun 2021 18:00:42 +0100 Subject: [PATCH 0284/1469] firmware: arm_scmi: Avoid padding in sensor message structure scmi_resp_sensor_reading_complete structure is meant to represent an SCMI asynchronous reading complete message. The readings field with a 64bit type forces padding and breaks reads in scmi_sensor_reading_get. Split it in two adjacent 32bit readings_low/high subfields to avoid the padding within the structure. Alternatively we could to mark the structure packed. Link: https://lore.kernel.org/r/20210628170042.34105-1-cristian.marussi@arm.com Fixes: e2083d3673916 ("firmware: arm_scmi: Add SCMI v3.0 sensors timestamped reads") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/sensors.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index 2c88aa221559..308471586381 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -166,7 +166,8 @@ struct scmi_msg_sensor_reading_get { struct scmi_resp_sensor_reading_complete { __le32 id; - __le64 readings; + __le32 readings_low; + __le32 readings_high; }; struct scmi_sensor_reading_resp { @@ -717,7 +718,8 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph, resp = t->rx.buf; if (le32_to_cpu(resp->id) == sensor_id) - *value = get_unaligned_le64(&resp->readings); + *value = + get_unaligned_le64(&resp->readings_low); else ret = -EPROTO; } From bdb8742dc6f7c599c3d61959234fe4c23638727b Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 12 Jul 2021 15:18:18 +0100 Subject: [PATCH 0285/1469] firmware: arm_scmi: Fix range check for the maximum number of pending messages SCMI message headers carry a sequence number and such field is sized to allow for MSG_TOKEN_MAX distinct numbers; moreover zero is not really an acceptable maximum number of pending in-flight messages. Fix accordingly the checks performed on the value exported by transports in scmi_desc.max_msg Link: https://lore.kernel.org/r/20210712141833.6628-3-cristian.marussi@arm.com Reported-by: Vincent Guittot Signed-off-by: Cristian Marussi [sudeep.holla: updated the patch title and error message] Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 1cbd2b06e523..9b2e8d42a992 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1026,8 +1026,9 @@ static int __scmi_xfer_info_init(struct scmi_info *sinfo, const struct scmi_desc *desc = sinfo->desc; /* Pre-allocated messages, no more than what hdr.seq can support */ - if (WARN_ON(desc->max_msg >= MSG_TOKEN_MAX)) { - dev_err(dev, "Maximum message of %d exceeds supported %ld\n", + if (WARN_ON(!desc->max_msg || desc->max_msg > MSG_TOKEN_MAX)) { + dev_err(dev, + "Invalid maximum messages %d, not in range [1 - %lu]\n", desc->max_msg, MSG_TOKEN_MAX); return -EINVAL; } From 0af778269a522c988ef0b4188556aba97fb420cc Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 12 Jul 2021 16:55:44 +0800 Subject: [PATCH 0286/1469] fbmem: Do not delete the mode that is still in use The execution of fb_delete_videomode() is not based on the result of the previous fbcon_mode_deleted(). As a result, the mode is directly deleted, regardless of whether it is still in use, which may cause UAF. ================================================================== BUG: KASAN: use-after-free in fb_mode_is_equal+0x36e/0x5e0 \ drivers/video/fbdev/core/modedb.c:924 Read of size 4 at addr ffff88807e0ddb1c by task syz-executor.0/18962 CPU: 2 PID: 18962 Comm: syz-executor.0 Not tainted 5.10.45-rc1+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ... Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x137/0x1be lib/dump_stack.c:118 print_address_description+0x6c/0x640 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report+0x13d/0x1e0 mm/kasan/report.c:562 fb_mode_is_equal+0x36e/0x5e0 drivers/video/fbdev/core/modedb.c:924 fbcon_mode_deleted+0x16a/0x220 drivers/video/fbdev/core/fbcon.c:2746 fb_set_var+0x1e1/0xdb0 drivers/video/fbdev/core/fbmem.c:975 do_fb_ioctl+0x4d9/0x6e0 drivers/video/fbdev/core/fbmem.c:1108 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 18960: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x3d/0x70 mm/kasan/common.c:56 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0x108/0x140 mm/kasan/common.c:422 slab_free_hook mm/slub.c:1541 [inline] slab_free_freelist_hook+0xd6/0x1a0 mm/slub.c:1574 slab_free mm/slub.c:3139 [inline] kfree+0xca/0x3d0 mm/slub.c:4121 fb_delete_videomode+0x56a/0x820 drivers/video/fbdev/core/modedb.c:1104 fb_set_var+0x1f3/0xdb0 drivers/video/fbdev/core/fbmem.c:978 do_fb_ioctl+0x4d9/0x6e0 drivers/video/fbdev/core/fbmem.c:1108 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 13ff178ccd6d ("fbcon: Call fbcon_mode_deleted/new_modelist directly") Signed-off-by: Zhen Lei Cc: # v5.3+ Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210712085544.2828-1-thunder.leizhen@huawei.com --- drivers/video/fbdev/core/fbmem.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 98f193078c05..1c855145711b 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -970,13 +970,11 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var) fb_var_to_videomode(&mode2, &info->var); /* make sure we don't delete the videomode of current var */ ret = fb_mode_is_equal(&mode1, &mode2); - - if (!ret) - fbcon_mode_deleted(info, &mode1); - - if (!ret) - fb_delete_videomode(&mode1, &info->modelist); - + if (!ret) { + ret = fbcon_mode_deleted(info, &mode1); + if (!ret) + fb_delete_videomode(&mode1, &info->modelist); + } return ret ? -EINVAL : 0; } From 5dd0a6b8582ffbfa88351949d50eccd5b6694ade Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 12 Jul 2021 22:57:35 +0200 Subject: [PATCH 0287/1469] bpf: Fix tail_call_reachable rejection for interpreter when jit failed During testing of f263a81451c1 ("bpf: Track subprog poke descriptors correctly and fix use-after-free") under various failure conditions, for example, when jit_subprogs() fails and tries to clean up the program to be run under the interpreter, we ran into the following freeze: [...] #127/8 tailcall_bpf2bpf_3:FAIL [...] [ 92.041251] BUG: KASAN: slab-out-of-bounds in ___bpf_prog_run+0x1b9d/0x2e20 [ 92.042408] Read of size 8 at addr ffff88800da67f68 by task test_progs/682 [ 92.043707] [ 92.044030] CPU: 1 PID: 682 Comm: test_progs Tainted: G O 5.13.0-53301-ge6c08cb33a30-dirty #87 [ 92.045542] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1 04/01/2014 [ 92.046785] Call Trace: [ 92.047171] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.047773] ? __bpf_prog_run_args32+0x8b/0xb0 [ 92.048389] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.049019] ? ktime_get+0x117/0x130 [...] // few hundred [similar] lines more [ 92.659025] ? ktime_get+0x117/0x130 [ 92.659845] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.660738] ? __bpf_prog_run_args32+0x8b/0xb0 [ 92.661528] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.662378] ? print_usage_bug+0x50/0x50 [ 92.663221] ? print_usage_bug+0x50/0x50 [ 92.664077] ? bpf_ksym_find+0x9c/0xe0 [ 92.664887] ? ktime_get+0x117/0x130 [ 92.665624] ? kernel_text_address+0xf5/0x100 [ 92.666529] ? __kernel_text_address+0xe/0x30 [ 92.667725] ? unwind_get_return_address+0x2f/0x50 [ 92.668854] ? ___bpf_prog_run+0x15d4/0x2e20 [ 92.670185] ? ktime_get+0x117/0x130 [ 92.671130] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.672020] ? __bpf_prog_run_args32+0x8b/0xb0 [ 92.672860] ? __bpf_prog_run_args64+0xc0/0xc0 [ 92.675159] ? ktime_get+0x117/0x130 [ 92.677074] ? lock_is_held_type+0xd5/0x130 [ 92.678662] ? ___bpf_prog_run+0x15d4/0x2e20 [ 92.680046] ? ktime_get+0x117/0x130 [ 92.681285] ? __bpf_prog_run32+0x6b/0x90 [ 92.682601] ? __bpf_prog_run64+0x90/0x90 [ 92.683636] ? lock_downgrade+0x370/0x370 [ 92.684647] ? mark_held_locks+0x44/0x90 [ 92.685652] ? ktime_get+0x117/0x130 [ 92.686752] ? lockdep_hardirqs_on+0x79/0x100 [ 92.688004] ? ktime_get+0x117/0x130 [ 92.688573] ? __cant_migrate+0x2b/0x80 [ 92.689192] ? bpf_test_run+0x2f4/0x510 [ 92.689869] ? bpf_test_timer_continue+0x1c0/0x1c0 [ 92.690856] ? rcu_read_lock_bh_held+0x90/0x90 [ 92.691506] ? __kasan_slab_alloc+0x61/0x80 [ 92.692128] ? eth_type_trans+0x128/0x240 [ 92.692737] ? __build_skb+0x46/0x50 [ 92.693252] ? bpf_prog_test_run_skb+0x65e/0xc50 [ 92.693954] ? bpf_prog_test_run_raw_tp+0x2d0/0x2d0 [ 92.694639] ? __fget_light+0xa1/0x100 [ 92.695162] ? bpf_prog_inc+0x23/0x30 [ 92.695685] ? __sys_bpf+0xb40/0x2c80 [ 92.696324] ? bpf_link_get_from_fd+0x90/0x90 [ 92.697150] ? mark_held_locks+0x24/0x90 [ 92.698007] ? lockdep_hardirqs_on_prepare+0x124/0x220 [ 92.699045] ? finish_task_switch+0xe6/0x370 [ 92.700072] ? lockdep_hardirqs_on+0x79/0x100 [ 92.701233] ? finish_task_switch+0x11d/0x370 [ 92.702264] ? __switch_to+0x2c0/0x740 [ 92.703148] ? mark_held_locks+0x24/0x90 [ 92.704155] ? __x64_sys_bpf+0x45/0x50 [ 92.705146] ? do_syscall_64+0x35/0x80 [ 92.706953] ? entry_SYSCALL_64_after_hwframe+0x44/0xae [...] Turns out that the program rejection from e411901c0b77 ("bpf: allow for tailcalls in BPF subprograms for x64 JIT") is buggy since env->prog->aux->tail_call_reachable is never true. Commit ebf7d1f508a7 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT") added a tracker into check_max_stack_depth() which propagates the tail_call_reachable condition throughout the subprograms. This info is then assigned to the subprogram's func[i]->aux->tail_call_reachable. However, in the case of the rejection check upon JIT failure, env->prog->aux->tail_call_reachable is used. func[0]->aux->tail_call_reachable which represents the main program's information did not propagate this to the outer env->prog->aux, though. Add this propagation into check_max_stack_depth() where it needs to belong so that the check can be done reliably. Fixes: ebf7d1f508a7 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT") Fixes: e411901c0b77 ("bpf: allow for tailcalls in BPF subprograms for x64 JIT") Co-developed-by: John Fastabend Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Acked-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/618c34e3163ad1a36b1e82377576a6081e182f25.1626123173.git.daniel@iogearbox.net --- kernel/bpf/verifier.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42a4063de7cd..9de3c9c3267c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3677,6 +3677,8 @@ continue_func: if (tail_call_reachable) for (j = 0; j < frame; j++) subprog[ret_prog[j]].tail_call_reachable = true; + if (subprog[0].tail_call_reachable) + env->prog->aux->tail_call_reachable = true; /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT From 5acc7d3e8d342858405fbbc671221f676b547ce7 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Sat, 10 Jul 2021 11:16:35 +0800 Subject: [PATCH 0288/1469] xdp, net: Fix use-after-free in bpf_xdp_link_release The problem occurs between dev_get_by_index() and dev_xdp_attach_link(). At this point, dev_xdp_uninstall() is called. Then xdp link will not be detached automatically when dev is released. But link->dev already points to dev, when xdp link is released, dev will still be accessed, but dev has been released. dev_get_by_index() | link->dev = dev | | rtnl_lock() | unregister_netdevice_many() | dev_xdp_uninstall() | rtnl_unlock() rtnl_lock(); | dev_xdp_attach_link() | rtnl_unlock(); | | netdev_run_todo() // dev released bpf_xdp_link_release() | /* access dev. | use-after-free */ | [ 45.966867] BUG: KASAN: use-after-free in bpf_xdp_link_release+0x3b8/0x3d0 [ 45.967619] Read of size 8 at addr ffff00000f9980c8 by task a.out/732 [ 45.968297] [ 45.968502] CPU: 1 PID: 732 Comm: a.out Not tainted 5.13.0+ #22 [ 45.969222] Hardware name: linux,dummy-virt (DT) [ 45.969795] Call trace: [ 45.970106] dump_backtrace+0x0/0x4c8 [ 45.970564] show_stack+0x30/0x40 [ 45.970981] dump_stack_lvl+0x120/0x18c [ 45.971470] print_address_description.constprop.0+0x74/0x30c [ 45.972182] kasan_report+0x1e8/0x200 [ 45.972659] __asan_report_load8_noabort+0x2c/0x50 [ 45.973273] bpf_xdp_link_release+0x3b8/0x3d0 [ 45.973834] bpf_link_free+0xd0/0x188 [ 45.974315] bpf_link_put+0x1d0/0x218 [ 45.974790] bpf_link_release+0x3c/0x58 [ 45.975291] __fput+0x20c/0x7e8 [ 45.975706] ____fput+0x24/0x30 [ 45.976117] task_work_run+0x104/0x258 [ 45.976609] do_notify_resume+0x894/0xaf8 [ 45.977121] work_pending+0xc/0x328 [ 45.977575] [ 45.977775] The buggy address belongs to the page: [ 45.978369] page:fffffc00003e6600 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x4f998 [ 45.979522] flags: 0x7fffe0000000000(node=0|zone=0|lastcpupid=0x3ffff) [ 45.980349] raw: 07fffe0000000000 fffffc00003e6708 ffff0000dac3c010 0000000000000000 [ 45.981309] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 45.982259] page dumped because: kasan: bad access detected [ 45.982948] [ 45.983153] Memory state around the buggy address: [ 45.983753] ffff00000f997f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 45.984645] ffff00000f998000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.985533] >ffff00000f998080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.986419] ^ [ 45.987112] ffff00000f998100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.988006] ffff00000f998180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.988895] ================================================================== [ 45.989773] Disabling lock debugging due to kernel taint [ 45.990552] Kernel panic - not syncing: panic_on_warn set ... [ 45.991166] CPU: 1 PID: 732 Comm: a.out Tainted: G B 5.13.0+ #22 [ 45.991929] Hardware name: linux,dummy-virt (DT) [ 45.992448] Call trace: [ 45.992753] dump_backtrace+0x0/0x4c8 [ 45.993208] show_stack+0x30/0x40 [ 45.993627] dump_stack_lvl+0x120/0x18c [ 45.994113] dump_stack+0x1c/0x34 [ 45.994530] panic+0x3a4/0x7d8 [ 45.994930] end_report+0x194/0x198 [ 45.995380] kasan_report+0x134/0x200 [ 45.995850] __asan_report_load8_noabort+0x2c/0x50 [ 45.996453] bpf_xdp_link_release+0x3b8/0x3d0 [ 45.997007] bpf_link_free+0xd0/0x188 [ 45.997474] bpf_link_put+0x1d0/0x218 [ 45.997942] bpf_link_release+0x3c/0x58 [ 45.998429] __fput+0x20c/0x7e8 [ 45.998833] ____fput+0x24/0x30 [ 45.999247] task_work_run+0x104/0x258 [ 45.999731] do_notify_resume+0x894/0xaf8 [ 46.000236] work_pending+0xc/0x328 [ 46.000697] SMP: stopping secondary CPUs [ 46.001226] Dumping ftrace buffer: [ 46.001663] (ftrace buffer empty) [ 46.002110] Kernel Offset: disabled [ 46.002545] CPU features: 0x00000001,23202c00 [ 46.003080] Memory Limit: none Fixes: aa8d3a716b59db6c ("bpf, xdp: Add bpf_link-based XDP attachment API") Reported-by: Abaci Signed-off-by: Xuan Zhuo Signed-off-by: Alexei Starovoitov Reviewed-by: Dust Li Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210710031635.41649-1-xuanzhuo@linux.alibaba.com --- net/core/dev.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 64b21f0a2048..7da8d1215328 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9700,14 +9700,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) struct net_device *dev; int err, fd; + rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); - if (!dev) + if (!dev) { + rtnl_unlock(); return -EINVAL; + } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; - goto out_put_dev; + goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); @@ -9717,14 +9720,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); - goto out_put_dev; + goto unlock; } - rtnl_lock(); err = dev_xdp_attach_link(dev, NULL, link); rtnl_unlock(); if (err) { + link->dev = NULL; bpf_link_cleanup(&link_primer); goto out_put_dev; } @@ -9734,6 +9737,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) dev_put(dev); return fd; +unlock: + rtnl_unlock(); + out_put_dev: dev_put(dev); return err; From 8cdd23c23c3d481a43b4aa03dcb5738812831115 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 12 Jul 2021 14:46:37 -0700 Subject: [PATCH 0289/1469] arm64: Restrict ARM64_BTI_KERNEL to clang 12.0.0 and newer Commit 97fed779f2a6 ("arm64: bti: Provide Kconfig for kernel mode BTI") disabled CONFIG_ARM64_BTI_KERNEL when CONFIG_GCOV_KERNEL was enabled and compiling with clang because of warnings that were seen with allmodconfig because LLVM was not emitting PAC/BTI instructions for compiler generated functions: | warning: some functions compiled with BTI and some compiled without BTI | warning: not setting BTI in feature flags This dependency was fine for avoiding the warnings with allmodconfig until commit 51c2ee6d121c ("Kconfig: Introduce ARCH_WANTS_NO_INSTR and CC_HAS_NO_PROFILE_FN_ATTR"), which prevents CONFIG_GCOV_KERNEL from being enabled with clang 12.0.0 or older because those versions do not support the no_profile_instrument_function attribute. As a result, CONFIG_ARM64_BTI_KERNEL gets enabled with allmodconfig and there are more warnings like the ones above due to CONFIG_KASAN, which suffers from the same problem as CONFIG_GCOV_KERNEL. This was most likely not noticed at the time because allmodconfig + CONFIG_GCOV_KERNEL=n was not tested. defconfig + CONFIG_KASAN=y is enough to reproduce the same warnings as above. The root cause of the warnings was resolved in LLVM during the 12.0.0 release so rather than play whack-a-mole with the dependencies, just update CONFIG_ARM64_BTI_KERNEL to require clang 12.0.0, which will have all of the issues ironed out. Link: https://github.com/ClangBuiltLinux/linux/issues/1428 Link: https://github.com/ClangBuiltLinux/continuous-integration2/runs/3010034706?check_suite_focus=true Link: https://github.com/ClangBuiltLinux/continuous-integration2/runs/3010035725?check_suite_focus=true Link: https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20210712214636.3134425-1-nathan@kernel.org Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e07e7de9ac49..b5b13a932561 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1605,7 +1605,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 - depends on !(CC_IS_CLANG && GCOV_KERNEL) + # https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9 + depends on !CC_IS_CLANG || CLANG_VERSION >= 120000 depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help Build the kernel with Branch Target Identification annotations From 798c511548b946ae9ec123b0dfe197a5f29e63ec Mon Sep 17 00:00:00 2001 From: Jingwen Chen Date: Thu, 1 Jul 2021 10:19:17 +0800 Subject: [PATCH 0290/1469] drm/amdgpu: SRIOV flr_work should take write_lock [Why] If flr_work takes read_lock, then other threads who takes read_lock can access hardware when host is doing vf flr. [How] flr_work should take write_lock to avoid this case. Signed-off-by: Jingwen Chen Reviewed-by: Monk Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 3ee481557fc9..ff2307d7ee0f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -252,7 +252,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 48e588d3c409..9f7aac435d69 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -273,7 +273,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -289,7 +289,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) From 43a44c5322d1030d8f36ad679307c61f5b4e3716 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Fri, 2 Jul 2021 18:35:14 -0400 Subject: [PATCH 0291/1469] drm/amdgpu: Return error if no RAS In amdgpu_ras_query_error_count() return an error if the device doesn't support RAS. This prevents that function from having to always set the values of the integer pointers (if set), and thus prevents function side effects--always to have to set values of integers if integer pointers set, regardless of whether RAS is supported or not--with this change this side effect is mitigated. Also, if no pointers are set, don't count, since we've no way of reporting the counts. Also, give this function a kernel-doc. Cc: Alexander Deucher Cc: John Clements Cc: Hawking Zhang Reported-by: Tom Rix Fixes: a46751fbcde505 ("drm/amdgpu: Fix RAS function interface") Signed-off-by: Luben Tuikov Reviewed-by: Alexander Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 49 ++++++++++++++++++------- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 6 +-- 2 files changed, 38 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index c13b02caf8c3..fc66aca28594 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -809,7 +809,7 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev, /* query/inject/cure begin */ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, - struct ras_query_if *info) + struct ras_query_if *info) { struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); struct ras_err_data err_data = {0, 0, 0, NULL}; @@ -1043,17 +1043,32 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, return ret; } -/* get the total error counts on all IPs */ -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count) +/** + * amdgpu_ras_query_error_count -- Get error counts of all IPs + * adev: pointer to AMD GPU device + * ce_count: pointer to an integer to be set to the count of correctible errors. + * ue_count: pointer to an integer to be set to the count of uncorrectible + * errors. + * + * If set, @ce_count or @ue_count, count and return the corresponding + * error counts in those integer pointers. Return 0 if the device + * supports RAS. Return -EOPNOTSUPP if the device doesn't support RAS. + */ +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; unsigned long ce, ue; if (!adev->ras_enabled || !con) - return; + return -EOPNOTSUPP; + + /* Don't count since no reporting. + */ + if (!ce_count && !ue_count) + return 0; ce = 0; ue = 0; @@ -1061,9 +1076,11 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, struct ras_query_if info = { .head = obj->head, }; + int res; - if (amdgpu_ras_query_error_status(adev, &info)) - return; + res = amdgpu_ras_query_error_status(adev, &info); + if (res) + return res; ce += info.ce_count; ue += info.ue_count; @@ -1074,6 +1091,8 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, if (ue_count) *ue_count = ue; + + return 0; } /* query/inject/cure end */ @@ -2137,9 +2156,10 @@ static void amdgpu_ras_counte_dw(struct work_struct *work) /* Cache new values. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } pm_runtime_mark_last_busy(dev->dev); Out: @@ -2312,9 +2332,10 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, /* Those are the cached values at init. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } return 0; cleanup: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 256cea5d34f2..b504ed8c9b50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -490,9 +490,9 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev, void amdgpu_ras_resume(struct amdgpu_device *adev); void amdgpu_ras_suspend(struct amdgpu_device *adev); -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count); +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count); /* error handling functions */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, From e9cfe00ba8bd437da149a3c52712d4a73e249f45 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 16 Jun 2021 17:11:12 -0400 Subject: [PATCH 0292/1469] drm/amd/display: Fix updating infoframe for DCN3.1 eDP [Why] We're only treating TMDS as a valid target for infoframe updates which results in PSR being unable to transition from state 4 to state 5. [How] Also allow infoframe updates for DCN3.1 - following how we handle this path for earlier ASIC as well. Signed-off-by: Nicholas Kazlauskas Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index fc1fc1a4bf8b..836864a5a5dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -390,7 +390,7 @@ void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) is_hdmi_tmds = dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal); is_dp = dc_is_dp_signal(pipe_ctx->stream->signal); - if (!is_hdmi_tmds) + if (!is_hdmi_tmds && !is_dp) return; if (is_hdmi_tmds) From dce9d910eb9e54c97e830637f4e3383a11bb7556 Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Wed, 16 Jun 2021 16:11:23 -0400 Subject: [PATCH 0293/1469] Revert "drm/amd/display: Always write repeater mode regardless of LTTPR" This reverts commit 2b7605d73b97e2fa28e0817242e66ca968d2a7cb Some displays are not lighting up when put in LTTPR Transparent Mode Signed-off-by: Wesley Chalmers Reviewed-by: Jun Lei Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index b8832bdde2bc..6860827159ba 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1620,11 +1620,12 @@ enum dc_status dpcd_configure_lttpr_mode(struct dc_link *link, struct link_train { enum dc_status status = DC_OK; - if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) - status = configure_lttpr_mode_non_transparent(link, lt_settings); - else + if (lt_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) status = configure_lttpr_mode_transparent(link); + else if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + status = configure_lttpr_mode_non_transparent(link, lt_settings); + return status; } From 9849e71ac0793c956883da3ca780484d3a226316 Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Tue, 15 Jun 2021 15:11:31 -0400 Subject: [PATCH 0294/1469] drm/amd/display: remove faulty assert Signed-off-by: Dmytro Laktyushkin Reviewed-by: Wenjing Liu Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 6860827159ba..6da226bf11d5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1785,7 +1785,6 @@ bool perform_link_training_with_retries( link_enc = stream->link_enc; else link_enc = link->link_enc; - ASSERT(link_enc); /* We need to do this before the link training to ensure the idle pattern in SST * mode will be sent right after the link training From 21cf0293d500f198ad886cbdcd3ff65f82b35edf Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Thu, 1 Jul 2021 14:09:18 +0800 Subject: [PATCH 0295/1469] drm/amd/pm: drop smu_v13_0_1.c|h files for yellow carp Since there's nothing special in smu implementation for yellow carp, it's better to reuse the common smu_v13_0 interfaces and drop the specific smu_v13_0_1.c|h files. v2: remove the duplicate register offset and shift mask header files as well. Signed-off-by: Xiaomeng Hou Reviewed-by: Lijo Lazar Reviewed-by: Kevin Wang Signed-off-by: Alex Deucher --- .../include/asic_reg/mp/mp_13_0_1_offset.h | 355 ------------ .../include/asic_reg/mp/mp_13_0_1_sh_mask.h | 531 ------------------ drivers/gpu/drm/amd/pm/inc/smu_v13_0.h | 1 + drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h | 57 -- drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile | 2 +- .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 24 + .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c | 311 ---------- .../drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 39 +- 8 files changed, 57 insertions(+), 1263 deletions(-) delete mode 100644 drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h delete mode 100644 drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h delete mode 100644 drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h delete mode 100644 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h deleted file mode 100644 index dfacc6b5d89d..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h +++ /dev/null @@ -1,355 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_OFFSET_HEADER -#define _mp_13_0_1_OFFSET_HEADER - - - -// addressBlock: mp_SmuMp0_SmnDec -// base address: 0x0 -#define regMP0_SMN_C2PMSG_32 0x0060 -#define regMP0_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_33 0x0061 -#define regMP0_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_34 0x0062 -#define regMP0_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_35 0x0063 -#define regMP0_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_36 0x0064 -#define regMP0_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_37 0x0065 -#define regMP0_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_38 0x0066 -#define regMP0_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_39 0x0067 -#define regMP0_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_40 0x0068 -#define regMP0_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_41 0x0069 -#define regMP0_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_42 0x006a -#define regMP0_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_43 0x006b -#define regMP0_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_44 0x006c -#define regMP0_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_45 0x006d -#define regMP0_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_46 0x006e -#define regMP0_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_47 0x006f -#define regMP0_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_48 0x0070 -#define regMP0_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_49 0x0071 -#define regMP0_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_50 0x0072 -#define regMP0_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_51 0x0073 -#define regMP0_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_52 0x0074 -#define regMP0_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_53 0x0075 -#define regMP0_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_54 0x0076 -#define regMP0_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_55 0x0077 -#define regMP0_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_56 0x0078 -#define regMP0_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_57 0x0079 -#define regMP0_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_58 0x007a -#define regMP0_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_59 0x007b -#define regMP0_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_60 0x007c -#define regMP0_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_61 0x007d -#define regMP0_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_62 0x007e -#define regMP0_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_63 0x007f -#define regMP0_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_64 0x0080 -#define regMP0_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_65 0x0081 -#define regMP0_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_66 0x0082 -#define regMP0_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_67 0x0083 -#define regMP0_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_68 0x0084 -#define regMP0_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_69 0x0085 -#define regMP0_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_70 0x0086 -#define regMP0_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_71 0x0087 -#define regMP0_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_72 0x0088 -#define regMP0_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_73 0x0089 -#define regMP0_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_74 0x008a -#define regMP0_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_75 0x008b -#define regMP0_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_76 0x008c -#define regMP0_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_77 0x008d -#define regMP0_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_78 0x008e -#define regMP0_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_79 0x008f -#define regMP0_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_80 0x0090 -#define regMP0_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_81 0x0091 -#define regMP0_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_82 0x0092 -#define regMP0_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_83 0x0093 -#define regMP0_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_84 0x0094 -#define regMP0_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_85 0x0095 -#define regMP0_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_86 0x0096 -#define regMP0_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_87 0x0097 -#define regMP0_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_88 0x0098 -#define regMP0_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_89 0x0099 -#define regMP0_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_90 0x009a -#define regMP0_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_91 0x009b -#define regMP0_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_92 0x009c -#define regMP0_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_93 0x009d -#define regMP0_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_94 0x009e -#define regMP0_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_95 0x009f -#define regMP0_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_96 0x00a0 -#define regMP0_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_97 0x00a1 -#define regMP0_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_98 0x00a2 -#define regMP0_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_99 0x00a3 -#define regMP0_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_100 0x00a4 -#define regMP0_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_101 0x00a5 -#define regMP0_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_102 0x00a6 -#define regMP0_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_103 0x00a7 -#define regMP0_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP0_SMN_IH_CREDIT 0x00c1 -#define regMP0_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT 0x00c2 -#define regMP0_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT_CTRL 0x00c3 -#define regMP0_SMN_IH_SW_INT_CTRL_BASE_IDX 0 - - -// addressBlock: mp_SmuMp1_SmnDec -// base address: 0x0 -#define regMP1_SMN_C2PMSG_32 0x0260 -#define regMP1_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_33 0x0261 -#define regMP1_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_34 0x0262 -#define regMP1_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_35 0x0263 -#define regMP1_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_36 0x0264 -#define regMP1_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_37 0x0265 -#define regMP1_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_38 0x0266 -#define regMP1_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_39 0x0267 -#define regMP1_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_40 0x0268 -#define regMP1_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_41 0x0269 -#define regMP1_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_42 0x026a -#define regMP1_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_43 0x026b -#define regMP1_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_44 0x026c -#define regMP1_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_45 0x026d -#define regMP1_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_46 0x026e -#define regMP1_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_47 0x026f -#define regMP1_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_48 0x0270 -#define regMP1_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_49 0x0271 -#define regMP1_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_50 0x0272 -#define regMP1_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_51 0x0273 -#define regMP1_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_52 0x0274 -#define regMP1_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_53 0x0275 -#define regMP1_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_54 0x0276 -#define regMP1_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_55 0x0277 -#define regMP1_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_56 0x0278 -#define regMP1_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_57 0x0279 -#define regMP1_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_58 0x027a -#define regMP1_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_59 0x027b -#define regMP1_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_60 0x027c -#define regMP1_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_61 0x027d -#define regMP1_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_62 0x027e -#define regMP1_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_63 0x027f -#define regMP1_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_64 0x0280 -#define regMP1_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_65 0x0281 -#define regMP1_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_66 0x0282 -#define regMP1_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_67 0x0283 -#define regMP1_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_68 0x0284 -#define regMP1_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_69 0x0285 -#define regMP1_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_70 0x0286 -#define regMP1_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_71 0x0287 -#define regMP1_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_72 0x0288 -#define regMP1_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_73 0x0289 -#define regMP1_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_74 0x028a -#define regMP1_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_75 0x028b -#define regMP1_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_76 0x028c -#define regMP1_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_77 0x028d -#define regMP1_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_78 0x028e -#define regMP1_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_79 0x028f -#define regMP1_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_80 0x0290 -#define regMP1_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_81 0x0291 -#define regMP1_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_82 0x0292 -#define regMP1_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_83 0x0293 -#define regMP1_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_84 0x0294 -#define regMP1_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_85 0x0295 -#define regMP1_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_86 0x0296 -#define regMP1_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_87 0x0297 -#define regMP1_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_88 0x0298 -#define regMP1_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_89 0x0299 -#define regMP1_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_90 0x029a -#define regMP1_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_91 0x029b -#define regMP1_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_92 0x029c -#define regMP1_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_93 0x029d -#define regMP1_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_94 0x029e -#define regMP1_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_95 0x029f -#define regMP1_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_96 0x02a0 -#define regMP1_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_97 0x02a1 -#define regMP1_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_98 0x02a2 -#define regMP1_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_99 0x02a3 -#define regMP1_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_100 0x02a4 -#define regMP1_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_101 0x02a5 -#define regMP1_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_102 0x02a6 -#define regMP1_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_103 0x02a7 -#define regMP1_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP1_SMN_IH_CREDIT 0x02c1 -#define regMP1_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT 0x02c2 -#define regMP1_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT_CTRL 0x02c3 -#define regMP1_SMN_IH_SW_INT_CTRL_BASE_IDX 0 -#define regMP1_SMN_FPS_CNT 0x02c4 -#define regMP1_SMN_FPS_CNT_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH0 0x0340 -#define regMP1_SMN_EXT_SCRATCH0_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH1 0x0341 -#define regMP1_SMN_EXT_SCRATCH1_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH2 0x0342 -#define regMP1_SMN_EXT_SCRATCH2_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH3 0x0343 -#define regMP1_SMN_EXT_SCRATCH3_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH4 0x0344 -#define regMP1_SMN_EXT_SCRATCH4_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH5 0x0345 -#define regMP1_SMN_EXT_SCRATCH5_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH6 0x0346 -#define regMP1_SMN_EXT_SCRATCH6_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH7 0x0347 -#define regMP1_SMN_EXT_SCRATCH7_BASE_IDX 0 - - -#endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h deleted file mode 100644 index 2d5e8b58e693..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h +++ /dev/null @@ -1,531 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_SH_MASK_HEADER -#define _mp_13_0_1_SH_MASK_HEADER - - -// addressBlock: mp_SmuMp0_SmnDec -//MP0_SMN_C2PMSG_32 -#define MP0_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_33 -#define MP0_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_34 -#define MP0_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_35 -#define MP0_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_36 -#define MP0_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_37 -#define MP0_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_38 -#define MP0_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_39 -#define MP0_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_40 -#define MP0_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_41 -#define MP0_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_42 -#define MP0_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_43 -#define MP0_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_44 -#define MP0_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_45 -#define MP0_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_46 -#define MP0_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_47 -#define MP0_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_48 -#define MP0_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_49 -#define MP0_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_50 -#define MP0_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_51 -#define MP0_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_52 -#define MP0_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_53 -#define MP0_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_54 -#define MP0_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_55 -#define MP0_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_56 -#define MP0_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_57 -#define MP0_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_58 -#define MP0_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_59 -#define MP0_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_60 -#define MP0_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_61 -#define MP0_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_62 -#define MP0_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_63 -#define MP0_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_64 -#define MP0_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_65 -#define MP0_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_66 -#define MP0_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_67 -#define MP0_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_68 -#define MP0_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_69 -#define MP0_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_70 -#define MP0_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_71 -#define MP0_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_72 -#define MP0_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_73 -#define MP0_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_74 -#define MP0_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_75 -#define MP0_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_76 -#define MP0_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_77 -#define MP0_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_78 -#define MP0_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_79 -#define MP0_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_80 -#define MP0_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_81 -#define MP0_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_82 -#define MP0_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_83 -#define MP0_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_84 -#define MP0_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_85 -#define MP0_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_86 -#define MP0_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_87 -#define MP0_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_88 -#define MP0_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_89 -#define MP0_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_90 -#define MP0_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_91 -#define MP0_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_92 -#define MP0_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_93 -#define MP0_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_94 -#define MP0_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_95 -#define MP0_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_96 -#define MP0_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_97 -#define MP0_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_98 -#define MP0_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_99 -#define MP0_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_100 -#define MP0_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_101 -#define MP0_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_102 -#define MP0_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_103 -#define MP0_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_IH_CREDIT -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP0_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP0_SMN_IH_SW_INT -#define MP0_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP0_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP0_SMN_IH_SW_INT_CTRL -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L - - -// addressBlock: mp_SmuMp1Pub_CruDec -//MP1_FIRMWARE_FLAGS -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT 0x0 -#define MP1_FIRMWARE_FLAGS__RESERVED__SHIFT 0x1 -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK 0x00000001L -#define MP1_FIRMWARE_FLAGS__RESERVED_MASK 0xFFFFFFFEL - - -// addressBlock: mp_SmuMp1_SmnDec -//MP1_SMN_C2PMSG_32 -#define MP1_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_33 -#define MP1_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_34 -#define MP1_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_35 -#define MP1_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_36 -#define MP1_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_37 -#define MP1_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_38 -#define MP1_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_39 -#define MP1_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_40 -#define MP1_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_41 -#define MP1_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_42 -#define MP1_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_43 -#define MP1_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_44 -#define MP1_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_45 -#define MP1_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_46 -#define MP1_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_47 -#define MP1_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_48 -#define MP1_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_49 -#define MP1_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_50 -#define MP1_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_51 -#define MP1_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_52 -#define MP1_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_53 -#define MP1_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_54 -#define MP1_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_55 -#define MP1_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_56 -#define MP1_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_57 -#define MP1_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_58 -#define MP1_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_59 -#define MP1_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_60 -#define MP1_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_61 -#define MP1_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_62 -#define MP1_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_63 -#define MP1_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_64 -#define MP1_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_65 -#define MP1_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_66 -#define MP1_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_67 -#define MP1_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_68 -#define MP1_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_69 -#define MP1_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_70 -#define MP1_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_71 -#define MP1_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_72 -#define MP1_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_73 -#define MP1_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_74 -#define MP1_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_75 -#define MP1_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_76 -#define MP1_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_77 -#define MP1_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_78 -#define MP1_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_79 -#define MP1_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_80 -#define MP1_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_81 -#define MP1_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_82 -#define MP1_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_83 -#define MP1_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_84 -#define MP1_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_85 -#define MP1_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_86 -#define MP1_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_87 -#define MP1_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_88 -#define MP1_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_89 -#define MP1_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_90 -#define MP1_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_91 -#define MP1_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_92 -#define MP1_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_93 -#define MP1_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_94 -#define MP1_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_95 -#define MP1_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_96 -#define MP1_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_97 -#define MP1_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_98 -#define MP1_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_99 -#define MP1_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_100 -#define MP1_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_101 -#define MP1_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_102 -#define MP1_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_103 -#define MP1_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_IH_CREDIT -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP1_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP1_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP1_SMN_IH_SW_INT -#define MP1_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP1_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP1_SMN_IH_SW_INT_CTRL -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L -//MP1_SMN_FPS_CNT -#define MP1_SMN_FPS_CNT__COUNT__SHIFT 0x0 -#define MP1_SMN_FPS_CNT__COUNT_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH0 -#define MP1_SMN_EXT_SCRATCH0__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH0__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH1 -#define MP1_SMN_EXT_SCRATCH1__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH1__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH2 -#define MP1_SMN_EXT_SCRATCH2__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH2__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH3 -#define MP1_SMN_EXT_SCRATCH3__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH3__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH4 -#define MP1_SMN_EXT_SCRATCH4__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH4__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH5 -#define MP1_SMN_EXT_SCRATCH5__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH5__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH6 -#define MP1_SMN_EXT_SCRATCH6__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH6__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH7 -#define MP1_SMN_EXT_SCRATCH7__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH7__DATA_MASK 0xFFFFFFFFL - - -#endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index 6119a36b2cba..3fea2430dec0 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -26,6 +26,7 @@ #include "amdgpu_smu.h" #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF +#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x03 #define SMU13_DRIVER_IF_VERSION_ALDE 0x07 /* MP Apertures */ diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h deleted file mode 100644 index b6c976a4d578..000000000000 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h +++ /dev/null @@ -1,57 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#ifndef __SMU_V13_0_1_H__ -#define __SMU_V13_0_1_H__ - -#include "amdgpu_smu.h" - -#define SMU13_0_1_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP 0x3 - -/* MP Apertures */ -#define MP0_Public 0x03800000 -#define MP0_SRAM 0x03900000 -#define MP1_Public 0x03b00000 -#define MP1_SRAM 0x03c00004 - -/* address block */ -#define smnMP1_FIRMWARE_FLAGS 0x3010024 - - -#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) - -int smu_v13_0_1_check_fw_status(struct smu_context *smu); - -int smu_v13_0_1_check_fw_version(struct smu_context *smu); - -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu); - -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu); - -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu); - -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu); - -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable); -#endif -#endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile index 9b3a8503f5cd..d4c4c495762c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'smu manager' sub-component of powerplay. # It provides the smu management services for the driver. -SMU13_MGR = smu_v13_0.o aldebaran_ppt.o smu_v13_0_1.o yellow_carp_ppt.o +SMU13_MGR = smu_v13_0.o aldebaran_ppt.o yellow_carp_ppt.o AMD_SWSMU_SMU13MGR = $(addprefix $(AMD_SWSMU_PATH)/smu13/,$(SMU13_MGR)) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index a3dc7194aaf8..a421ba85bd6d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -210,6 +210,9 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) case CHIP_ALDEBARAN: smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE; break; + case CHIP_YELLOW_CARP: + smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_YELLOW_CARP; + break; default: dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_INV; @@ -694,6 +697,27 @@ failed: return ret; } +int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable) +{ + int ret = 0; + struct amdgpu_device *adev = smu->adev; + + switch (adev->asic_type) { + case CHIP_YELLOW_CARP: + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) + return 0; + if (enable) + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); + else + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); + break; + default: + break; + } + + return ret; +} + int smu_v13_0_system_features_control(struct smu_context *smu, bool en) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c deleted file mode 100644 index 61917b49f2bf..000000000000 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c +++ /dev/null @@ -1,311 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -//#include - -#define SWSMU_CODE_LAYER_L3 - -#include "amdgpu.h" -#include "amdgpu_smu.h" -#include "smu_v13_0_1.h" -#include "soc15_common.h" -#include "smu_cmn.h" -#include "atomfirmware.h" -#include "amdgpu_atomfirmware.h" -#include "amdgpu_atombios.h" -#include "atom.h" - -#include "asic_reg/mp/mp_13_0_1_offset.h" -#include "asic_reg/mp/mp_13_0_1_sh_mask.h" - -/* - * DO NOT use these for err/warn/info/debug messages. - * Use dev_err, dev_warn, dev_info and dev_dbg instead. - * They are more MGPU friendly. - */ -#undef pr_err -#undef pr_warn -#undef pr_info -#undef pr_debug - -int smu_v13_0_1_check_fw_status(struct smu_context *smu) -{ - struct amdgpu_device *adev = smu->adev; - uint32_t mp1_fw_flags; - - mp1_fw_flags = RREG32_PCIE(MP1_Public | - (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); - - if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >> - MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT) - return 0; - - return -EIO; -} - -int smu_v13_0_1_check_fw_version(struct smu_context *smu) -{ - uint32_t if_version = 0xff, smu_version = 0xff; - uint16_t smu_major; - uint8_t smu_minor, smu_debug; - int ret = 0; - - ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); - if (ret) - return ret; - - smu_major = (smu_version >> 16) & 0xffff; - smu_minor = (smu_version >> 8) & 0xff; - smu_debug = (smu_version >> 0) & 0xff; - - switch (smu->adev->asic_type) { - case CHIP_YELLOW_CARP: - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP; - break; - - default: - dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_INV; - break; - } - - dev_info(smu->adev->dev, "smu fw reported version = 0x%08x (%d.%d.%d)\n", - smu_version, smu_major, smu_minor, smu_debug); - - /* - * 1. if_version mismatch is not critical as our fw is designed - * to be backward compatible. - * 2. New fw usually brings some optimizations. But that's visible - * only on the paired driver. - * Considering above, we just leave user a warning message instead - * of halt driver loading. - */ - if (if_version != smu->smc_driver_if_version) { - dev_info(smu->adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, " - "smu fw version = 0x%08x (%d.%d.%d)\n", - smu->smc_driver_if_version, if_version, - smu_version, smu_major, smu_minor, smu_debug); - dev_warn(smu->adev->dev, "SMU driver if version not matched\n"); - } - - return ret; -} - -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - kfree(smu_table->clocks_table); - smu_table->clocks_table = NULL; - - kfree(smu_table->metrics_table); - smu_table->metrics_table = NULL; - - kfree(smu_table->watermarks_table); - smu_table->watermarks_table = NULL; - - return 0; -} - -static int smu_v13_0_1_atom_get_smu_clockinfo(struct amdgpu_device *adev, - uint8_t clk_id, - uint8_t syspll_id, - uint32_t *clk_freq) -{ - struct atom_get_smu_clock_info_parameters_v3_1 input = {0}; - struct atom_get_smu_clock_info_output_parameters_v3_1 *output; - int ret, index; - - input.clk_id = clk_id; - input.syspll_id = syspll_id; - input.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ; - index = get_index_into_master_table(atom_master_list_of_command_functions_v2_1, - getsmuclockinfo); - - ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, - (uint32_t *)&input); - if (ret) - return -EINVAL; - - output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&input; - *clk_freq = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000; - - return 0; -} - -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu) -{ - int ret, index; - uint16_t size; - uint8_t frev, crev; - struct atom_common_table_header *header; - struct atom_firmware_info_v3_4 *v_3_4; - struct atom_firmware_info_v3_3 *v_3_3; - struct atom_firmware_info_v3_1 *v_3_1; - - index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, - firmwareinfo); - - ret = amdgpu_atombios_get_data_table(smu->adev, index, &size, &frev, &crev, - (uint8_t **)&header); - if (ret) - return ret; - - if (header->format_revision != 3) { - dev_err(smu->adev->dev, "unknown atom_firmware_info version! for smu13\n"); - return -EINVAL; - } - - switch (header->content_revision) { - case 0: - case 1: - case 2: - v_3_1 = (struct atom_firmware_info_v3_1 *)header; - smu->smu_table.boot_values.revision = v_3_1->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_1->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_1->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_1->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_1->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_1->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_1->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_1->coolingsolution_id; - break; - case 3: - v_3_3 = (struct atom_firmware_info_v3_3 *)header; - smu->smu_table.boot_values.revision = v_3_3->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_3->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_3->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_3->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_3->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_3->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_3->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_3->coolingsolution_id; - break; - case 4: - default: - v_3_4 = (struct atom_firmware_info_v3_4 *)header; - smu->smu_table.boot_values.revision = v_3_4->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_4->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_4->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_4->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_4->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_4->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_4->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_4->coolingsolution_id; - break; - } - - smu->smu_table.boot_values.format_revision = header->format_revision; - smu->smu_table.boot_values.content_revision = header->content_revision; - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_SOCCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.socclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCEFCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dcefclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_ECLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.eclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_VCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.vclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dclk); - - if ((smu->smu_table.boot_values.format_revision == 3) && - (smu->smu_table.boot_values.content_revision >= 2)) - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL1_0_FCLK_ID, - (uint8_t)SMU11_SYSPLL1_2_ID, - &smu->smu_table.boot_values.fclk); - - return 0; -} - -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); -} - -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu) -{ - struct smu_table *driver_table = &smu->smu_table.driver_table; - int ret = 0; - - if (!driver_table->mc_address) - return 0; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrHigh, - upper_32_bits(driver_table->mc_address), - NULL); - - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrLow, - lower_32_bits(driver_table->mc_address), - NULL); - - return ret; -} - -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable) -{ - int ret = 0; - struct amdgpu_device *adev = smu->adev; - - switch (adev->asic_type) { - case CHIP_YELLOW_CARP: - if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) - return 0; - if (enable) - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); - else - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); - break; - default: - break; - } - - return ret; -} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 18a1ffdca227..de92f713a911 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -25,7 +25,7 @@ #include "amdgpu.h" #include "amdgpu_smu.h" -#include "smu_v13_0_1.h" +#include "smu_v13_0.h" #include "smu13_driver_if_yellow_carp.h" #include "yellow_carp_ppt.h" #include "smu_v13_0_1_ppsmc.h" @@ -186,6 +186,22 @@ err0_out: return -ENOMEM; } +static int yellow_carp_fini_smc_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + kfree(smu_table->clocks_table); + smu_table->clocks_table = NULL; + + kfree(smu_table->metrics_table); + smu_table->metrics_table = NULL; + + kfree(smu_table->watermarks_table); + smu_table->watermarks_table = NULL; + + return 0; +} + static int yellow_carp_system_features_control(struct smu_context *smu, bool en) { struct smu_feature *feature = &smu->smu_feature; @@ -659,6 +675,13 @@ static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_1); } +static int yellow_carp_set_default_dpm_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); +} + static int yellow_carp_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type, long input[], uint32_t size) { @@ -1203,17 +1226,17 @@ static int yellow_carp_set_fine_grain_gfx_freq_parameters(struct smu_context *sm } static const struct pptable_funcs yellow_carp_ppt_funcs = { - .check_fw_status = smu_v13_0_1_check_fw_status, - .check_fw_version = smu_v13_0_1_check_fw_version, + .check_fw_status = smu_v13_0_check_fw_status, + .check_fw_version = smu_v13_0_check_fw_version, .init_smc_tables = yellow_carp_init_smc_tables, - .fini_smc_tables = smu_v13_0_1_fini_smc_tables, - .get_vbios_bootup_values = smu_v13_0_1_get_vbios_bootup_values, + .fini_smc_tables = yellow_carp_fini_smc_tables, + .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .system_features_control = yellow_carp_system_features_control, .send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param, .send_smc_msg = smu_cmn_send_smc_msg, .dpm_set_vcn_enable = yellow_carp_dpm_set_vcn_enable, .dpm_set_jpeg_enable = yellow_carp_dpm_set_jpeg_enable, - .set_default_dpm_table = smu_v13_0_1_set_default_dpm_tables, + .set_default_dpm_table = yellow_carp_set_default_dpm_tables, .read_sensor = yellow_carp_read_sensor, .is_dpm_running = yellow_carp_is_dpm_running, .set_watermarks_table = yellow_carp_set_watermarks_table, @@ -1222,8 +1245,8 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = { .get_gpu_metrics = yellow_carp_get_gpu_metrics, .get_enabled_mask = smu_cmn_get_enabled_32_bits_mask, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, - .set_driver_table_location = smu_v13_0_1_set_driver_table_location, - .gfx_off_control = smu_v13_0_1_gfx_off_control, + .set_driver_table_location = smu_v13_0_set_driver_table_location, + .gfx_off_control = smu_v13_0_gfx_off_control, .post_init = yellow_carp_post_smu_init, .mode2_reset = yellow_carp_mode2_reset, .get_dpm_ultimate_freq = yellow_carp_get_dpm_ultimate_freq, From 834b8245d6bbd57900ca6c79d7f9e0279a8d51c2 Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Wed, 7 Jul 2021 16:50:01 +0800 Subject: [PATCH 0296/1469] drm/amd/display: update header file name Update the register header file name. Signed-off-by: Xiaomeng Hou Reviewed-by: Aaron Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c index 66db5e988bc1..dad4a4c18bcf 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -31,8 +31,8 @@ #include "dcn31_smu.h" #include "yellow_carp_offset.h" -#include "mp/mp_13_0_1_offset.h" -#include "mp/mp_13_0_1_sh_mask.h" +#include "mp/mp_13_0_2_offset.h" +#include "mp/mp_13_0_2_sh_mask.h" #define REG(reg_name) \ (MP0_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name) From fa8f311e9e3aa1d41f31f8b28f975c65f0b25c03 Mon Sep 17 00:00:00 2001 From: Emily Deng Date: Tue, 12 May 2020 18:27:21 +0800 Subject: [PATCH 0297/1469] drm/amdgpu: Correct the irq numbers for virtual crtc The irq number should be decided by num_crtc, and the num_crtc could change by parameter. Signed-off-by: Emily Deng Reviewed by: Monk Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/dce_virtual.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 33324427b555..7e0d8c092c7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -766,7 +766,7 @@ static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = { static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev) { - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VBLANK6 + 1; + adev->crtc_irq.num_types = adev->mode_info.num_crtc; adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs; } From 5017bf8214d929f6ff45c46ec21cd3c1bfc03dad Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Wed, 7 Jul 2021 12:42:34 -0400 Subject: [PATCH 0298/1469] drm/amdkfd: handle fault counters on invalid address prange is NULL if vm fault retry on invalid address, for this case, can not use prange to get pdd, use adev to get gpuidx and then get pdd instead, then increase pdd vm fault counter. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 30 +++++++++++++++++----------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9a71d8919bd6..c7b364e4a287 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2375,21 +2375,27 @@ static bool svm_range_skip_recover(struct svm_range *prange) static void svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p, - struct svm_range *prange, int32_t gpuidx) + int32_t gpuidx) { struct kfd_process_device *pdd; - if (gpuidx == MAX_GPU_INSTANCE) - /* fault is on different page of same range - * or fault is skipped to recover later - */ - pdd = svm_range_get_pdd_by_adev(prange, adev); - else - /* fault recovered - * or fault cannot recover because GPU no access on the range - */ - pdd = kfd_process_device_from_gpuidx(p, gpuidx); + /* fault is on different page of same range + * or fault is skipped to recover later + * or fault is on invalid virtual address + */ + if (gpuidx == MAX_GPU_INSTANCE) { + uint32_t gpuid; + int r; + r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpuidx); + if (r < 0) + return; + } + + /* fault is recovered + * or fault cannot recover because GPU no access on the range + */ + pdd = kfd_process_device_from_gpuidx(p, gpuidx); if (pdd) WRITE_ONCE(pdd->faults, pdd->faults + 1); } @@ -2525,7 +2531,7 @@ out_unlock_svms: mutex_unlock(&svms->lock); mmap_read_unlock(mm); - svm_range_count_fault(adev, p, prange, gpuidx); + svm_range_count_fault(adev, p, gpuidx); mmput(mm); out: From c010efb7f0bc0c3cb2cd26b000f71d4bd0c427cd Mon Sep 17 00:00:00 2001 From: Zhan Liu Date: Thu, 8 Jul 2021 00:51:52 -0400 Subject: [PATCH 0299/1469] drm/amdgpu/display - only update eDP's backlight level when necessary [Why] The original logic is to update eDP's backlight level on every amdgpu dm atomic commit, which causes excessive DMUB write. As a result, when playing game or moving window around, DMUB timeout and system lagging are observed. [How] We only need to update eDP's backlight level when current level doesn't match requested level. Signed-off-by: Zhan Liu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 01e1062dc235..d3a2a5ff57e9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9191,7 +9191,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) /* restore the backlight level */ - if (dm->backlight_dev) + if (dm->backlight_dev && (amdgpu_dm_backlight_get_level(dm) != dm->brightness[0])) amdgpu_dm_backlight_set_level(dm, dm->brightness[0]); #endif /* From 99e7d65cccc8f54581eb961a50da676b79c966d0 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 7 Jul 2021 17:55:55 -0400 Subject: [PATCH 0300/1469] drm/amdkfd: Allow CPU access for all VRAM BOs The thunk needs to mmap all BOs for CPU access to allow the debugger to access them. Invisible ones are mapped with PROT_NONE. Fixes: 71df0368e9b6 ("drm/amdgpu: Implement mmap as GEM object function") Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 3b8e1ee8c475..eb82739b3080 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1393,8 +1393,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM; alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ? - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; + AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0; } else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT; alloc_flags = 0; From 9be26ddf88de5621f071a1e4f7725ce1015b5036 Mon Sep 17 00:00:00 2001 From: "Emily.Deng" Date: Thu, 1 Oct 2020 12:41:50 +0800 Subject: [PATCH 0301/1469] drm/amdgpu: Restore msix after FLR After FLR, the msix will be cleared, so need to re-enable it. Signed-off-by: Peng Ju Zhou Signed-off-by: Emily.Deng Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 32ce0e679dc7..83af307e97cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -278,6 +278,21 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev) return true; } +static void amdgpu_restore_msix(struct amdgpu_device *adev) +{ + u16 ctrl; + + pci_read_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl); + if (!(ctrl & PCI_MSIX_FLAGS_ENABLE)) + return; + + /* VF FLR */ + ctrl &= ~PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); + ctrl |= PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); +} + /** * amdgpu_irq_init - initialize interrupt handling * @@ -569,6 +584,9 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev) { int i, j, k; + if (amdgpu_sriov_vf(adev)) + amdgpu_restore_msix(adev); + for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) { if (!adev->irq.client[i].sources) continue; From 06055d2e1ce83ba02b0073ff6f4fdb883fdb05c0 Mon Sep 17 00:00:00 2001 From: Chengming Gui Date: Fri, 9 Jul 2021 16:23:48 +0800 Subject: [PATCH 0302/1469] drm/amd/pm: Fix BACO state setting for Beige_Goby Correct BACO state setting for Beige_Goby Signed-off-by: Chengming Gui Reviewed-by: Jiansong Chen Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 388c5cb5c647..0a5d46ac9ccd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1528,6 +1528,7 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: + case CHIP_BEIGE_GOBY: if (amdgpu_runtime_pm == 2) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, From f5cc09acece432d536c2e62c791b52760a25fa5c Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:51:34 -0400 Subject: [PATCH 0303/1469] Revert "drm/amdkfd: Add memory sync before TLB flush on unmap" This reverts commit 3be4dca197010d1328df8b11febc8c40491be498. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 67541c30327a..a10e3823b660 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1566,29 +1566,13 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, i, args->n_devices); goto unmap_memory_from_gpu_failed; } + kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); args->n_success = i+1; } - mutex_unlock(&p->mutex); - - err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd, (struct kgd_mem *) mem, true); - if (err) { - pr_debug("Sync memory failed, wait interrupted by user signal\n"); - goto sync_memory_failed; - } - - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer = kfd_device_by_id(devices_arr[i]); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } - kfree(devices_arr); + mutex_unlock(&p->mutex); + return 0; bind_process_to_device_failed: @@ -1596,7 +1580,6 @@ get_mem_obj_from_handle_failed: unmap_memory_from_gpu_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr); return err; } From 22762e376612be51a47c96d977bdc103c7a4436c Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:55:03 -0400 Subject: [PATCH 0304/1469] Revert "drm/amdgpu: Fix warning of Function parameter or member not described" This reverts commit 7a68d188d1c4a9d947369acaa19040a58baaaeda. Reason for revert: the related commit is reverted. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 79cfa2d68487..6b43ebab68a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1816,7 +1816,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * @adev: amdgpu_device pointer * @bo_va: requested BO and VM object * @clear: if true clear the entries - * @table_freed: return true if page table is freed * * Fill in the page table entries for @bo_va. * From c37387c354c81eaf17bdc463727dcad1c951c0db Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:57:11 -0400 Subject: [PATCH 0305/1469] Revert "drm/amdkfd: Make TLB flush conditional on mapping" This reverts commit 31f33243788dcbae8bd2819ed83923a73f7dfd30. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 +- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 19 +++++++-------- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 23 ++++++++----------- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 3 +-- 4 files changed, 20 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index db16b3e83694..cf62f43a03da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -269,7 +269,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, uint64_t *size); int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed); + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index eb82739b3080..4fb15750b9bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1057,8 +1057,7 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, static int update_gpuvm_pte(struct kgd_mem *mem, struct kfd_mem_attachment *entry, - struct amdgpu_sync *sync, - bool *table_freed) + struct amdgpu_sync *sync) { struct amdgpu_bo_va *bo_va = entry->bo_va; struct amdgpu_device *adev = entry->adev; @@ -1069,7 +1068,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, return ret; /* Update the page tables */ - ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed); + ret = amdgpu_vm_bo_update(adev, bo_va, false); if (ret) { pr_err("amdgpu_vm_bo_update failed\n"); return ret; @@ -1081,8 +1080,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, static int map_bo_to_gpuvm(struct kgd_mem *mem, struct kfd_mem_attachment *entry, struct amdgpu_sync *sync, - bool no_update_pte, - bool *table_freed) + bool no_update_pte) { int ret; @@ -1099,7 +1097,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, if (no_update_pte) return 0; - ret = update_gpuvm_pte(mem, entry, sync, table_freed); + ret = update_gpuvm_pte(mem, entry, sync); if (ret) { pr_err("update_gpuvm_pte() failed\n"); goto update_gpuvm_pte_failed; @@ -1596,8 +1594,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, - void *drm_priv, bool *table_freed) + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv) { struct amdgpu_device *adev = get_amdgpu_device(kgd); struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv); @@ -1685,7 +1682,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( entry->va, entry->va + bo_size, entry); ret = map_bo_to_gpuvm(mem, entry, ctx.sync, - is_invalid_userptr, table_freed); + is_invalid_userptr); if (ret) { pr_err("Failed to map bo to gpuvm\n"); goto out_unreserve; @@ -2135,7 +2132,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync); if (ret) { pr_err("%s: update PTE failed\n", __func__); /* make sure this gets validated again */ @@ -2341,7 +2338,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync_obj); if (ret) { pr_debug("Memory eviction: update PTE failed. Try again\n"); goto validate_map_fail; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a10e3823b660..84894cd81ced 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1393,7 +1393,6 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, long err = 0; int i; uint32_t *devices_arr = NULL; - bool table_freed = false; dev = kfd_device_by_id(GET_GPU_ID(args->handle)); if (!dev) @@ -1451,8 +1450,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, goto get_mem_obj_from_handle_failed; } err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - peer->kgd, (struct kgd_mem *)mem, - peer_pdd->drm_priv, &table_freed); + peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv); if (err) { pr_err("Failed to map to gpu %d/%d\n", i, args->n_devices); @@ -1470,17 +1468,16 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, } /* Flush TLBs after waiting for the page table updates to complete */ - if (table_freed) { - for (i = 0; i < args->n_devices; i++) { - peer = kfd_device_by_id(devices_arr[i]); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); - } + for (i = 0; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (WARN_ON_ONCE(!peer)) + continue; + peer_pdd = kfd_get_process_device_data(peer, p); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); } + kfree(devices_arr); return err; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 21ec8a18cad2..8a2c6fc438c0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -714,8 +714,7 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd, if (err) goto err_alloc_mem; - err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, - pdd->drm_priv, NULL); + err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv); if (err) goto err_map_mem; From d605094394ee35afd22f8adbe4a4b7b5f0c143a2 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:58:16 -0400 Subject: [PATCH 0306/1469] Revert "drm/amdgpu: Add table_freed parameter to amdgpu_vm_bo_update" This reverts commit 075e8080c1a7571563171a07fa9ce47c4bc80044. Reason for revert: the related commit is reverted. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 76fe5b71e35d..30fa1f61e0e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -781,7 +781,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL); + r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false); if (r) return r; @@ -792,7 +792,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) { bo_va = fpriv->csa_va; BUG_ON(!bo_va); - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; @@ -811,7 +811,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (bo_va == NULL) continue; - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index b3404c43a911..d0d9bc445d7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -612,7 +612,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (operation == AMDGPU_VA_OP_MAP || operation == AMDGPU_VA_OP_REPLACE) { - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) goto error; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6b43ebab68a1..078c068937fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1758,7 +1758,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit(¶ms, fence); if (table_freed) - *table_freed = *table_freed || params.table_freed; + *table_freed = params.table_freed; error_unlock: amdgpu_vm_eviction_unlock(vm); @@ -1823,7 +1823,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * 0 for success, -EINVAL for failure. */ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed) + bool clear) { struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; @@ -1902,7 +1902,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, resv, mapping->start, mapping->last, update_flags, mapping->offset, mem, - pages_addr, last_update, table_freed); + pages_addr, last_update, NULL); if (r) return r; } @@ -2154,7 +2154,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { /* Per VM BOs never need to bo cleared in the page tables */ - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; } @@ -2173,7 +2173,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, else clear = true; - r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, clear); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index ddb85a85cbba..f8fa653d4da7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -406,7 +406,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, struct dma_fence **fence, bool *free_table); int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed); + bool clear); bool amdgpu_vm_evictable(struct amdgpu_bo *bo); void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, struct amdgpu_bo *bo, bool evicted); From 5adcd7458a78120dddec6b53c9619acd8f4d5931 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:59:20 -0400 Subject: [PATCH 0307/1469] Revert "drm/amdkfd: Add heavy-weight TLB flush after unmapping" This reverts commit 1098d658bef05e5fee634aab0b6a1fa590cfca24. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 84894cd81ced..e48acdd03c1a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1563,7 +1563,6 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, i, args->n_devices); goto unmap_memory_from_gpu_failed; } - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); args->n_success = i+1; } kfree(devices_arr); From adefab4ef308f43c80537bd28e059eed7f3517e4 Mon Sep 17 00:00:00 2001 From: Aaron Liu Date: Tue, 13 Jul 2021 14:54:47 +0800 Subject: [PATCH 0308/1469] drm/amd/pm: Add waiting for response of mode-reset message for yellow carp Remove mdelay process and use smu_cmn_send_smc_msg_with_param to send mode-reset message to SMC. Signed-off-by: Aaron Liu Reviewed-by: Evan Quan Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index de92f713a911..0cfeb9fc7c03 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -298,13 +298,9 @@ static int yellow_carp_mode_reset(struct smu_context *smu, int type) if (index < 0) return index == -EACCES ? 0 : index; - mutex_lock(&smu->message_lock); - - ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, type); - - mutex_unlock(&smu->message_lock); - - mdelay(10); + ret = smu_cmn_send_smc_msg_with_param(smu, (uint16_t)index, type, NULL); + if (ret) + dev_err(smu->adev->dev, "Failed to mode reset!\n"); return ret; } From 01757f536ac825e3614d583fee9acb48c64ed084 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Tue, 13 Jul 2021 10:48:24 +0800 Subject: [PATCH 0309/1469] net: Use nlmsg_unicast() instead of netlink_unicast() It has 'if (err >0 )' statement in nlmsg_unicast(), so use nlmsg_unicast() instead of netlink_unicast(), this looks more concise. v2: remove the change in netfilter. Signed-off-by: Yajun Deng Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 2 +- net/ipv4/inet_diag.c | 5 +---- net/ipv4/raw_diag.c | 7 ++----- net/ipv4/udp_diag.c | 6 ++---- net/mptcp/mptcp_diag.c | 6 ++---- net/netlink/af_netlink.c | 2 +- net/sctp/diag.c | 6 ++---- net/unix/diag.c | 6 ++---- 8 files changed, 13 insertions(+), 27 deletions(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a933bd6345b1..9fe13e4f5d08 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1376,7 +1376,7 @@ static void nl_fib_input(struct sk_buff *skb) portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ - netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); + nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e65f4ef024a4..ef7897226f08 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -580,10 +580,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, nlmsg_free(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 1b5b8af27aaf..ccacbde30a2c 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -119,11 +119,8 @@ static int raw_diag_dump_one(struct netlink_callback *cb, return err; } - err = netlink_unicast(net->diag_nlsk, rep, - NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + return err; } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index b2cee9a307d4..1ed8c4d78e5c 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -77,10 +77,8 @@ static int udp_dump_one(struct udp_table *tbl, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 8f88ddeab6a2..f48eb6315bbb 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -57,10 +57,8 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: sock_put(sk); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d233ac4a91b6..380f95aacdec 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2471,7 +2471,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); - netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); + nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 493fc01e5d2b..760b367644c1 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -284,10 +284,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: return err; } diff --git a/net/unix/diag.c b/net/unix/diag.c index 9ff64f9df1f3..7e7d7f45685a 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -295,10 +295,8 @@ again: goto again; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); From e56c6bbd98dc1cefb6f9c5d795fd29016e4f2fe7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:33:50 +0300 Subject: [PATCH 0310/1469] net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload The point with a *dev and a *brport_dev is that when we have a LAG net device that is a bridge port, *dev is an ocelot net device and *brport_dev is the bonding/team net device. The ocelot net device beneath the LAG does not exist from the bridge's perspective, so we need to sync the switchdev objects belonging to the brport_dev and not to the dev. Fixes: e4bd44e89dcf ("net: ocelot: replay switchdev events when joining bridge") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot_net.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 3e89e34f86d5..e9d260d84bf3 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1298,6 +1298,7 @@ static int ocelot_netdevice_lag_leave(struct net_device *dev, } static int ocelot_netdevice_changeupper(struct net_device *dev, + struct net_device *brport_dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; @@ -1307,11 +1308,11 @@ static int ocelot_netdevice_changeupper(struct net_device *dev, if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) - err = ocelot_netdevice_bridge_join(dev, dev, + err = ocelot_netdevice_bridge_join(dev, brport_dev, info->upper_dev, extack); else - err = ocelot_netdevice_bridge_leave(dev, dev, + err = ocelot_netdevice_bridge_leave(dev, brport_dev, info->upper_dev); } if (netif_is_lag_master(info->upper_dev)) { @@ -1346,7 +1347,7 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev, if (ocelot_port->bond != dev) return NOTIFY_OK; - err = ocelot_netdevice_changeupper(lower, info); + err = ocelot_netdevice_changeupper(lower, dev, info); if (err) return notifier_from_errno(err); } @@ -1385,7 +1386,7 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct netdev_notifier_changeupper_info *info = ptr; if (ocelot_netdevice_dev_check(dev)) - return ocelot_netdevice_changeupper(dev, info); + return ocelot_netdevice_changeupper(dev, dev, info); if (netif_is_lag_master(dev)) return ocelot_netdevice_lag_changeupper(dev, info); From b0b33b048dcfbd7da82c3cde4fab02751dfab4d6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:37:19 +0300 Subject: [PATCH 0311/1469] net: dsa: sja1105: fix address learning getting disabled on the CPU port In May 2019 when commit 640f763f98c2 ("net: dsa: sja1105: Add support for Spanning Tree Protocol") was introduced, the comment that "STP does not get called for the CPU port" was true. This changed after commit 0394a63acfe2 ("net: dsa: enable and disable all ports") in August 2019 and went largely unnoticed, because the sja1105_bridge_stp_state_set() method did nothing different compared to the static setup done by sja1105_init_mac_settings(). With the ability to turn address learning off introduced by the blamed commit, there is a new priv->learn_ena port mask in the driver. When sja1105_bridge_stp_state_set() gets called and we are in BR_STATE_LEARNING or later, address learning is enabled or not depending on priv->learn_ena & BIT(port). So what happens is that priv->learn_ena is not being set from anywhere for the CPU port, and the static configuration done by sja1105_init_mac_settings() is being overwritten. To solve this, acknowledge that the static configuration of STP state is no longer necessary because the STP state is being set by the DSA core now, but what is necessary is to set priv->learn_ena for the CPU port. Fixes: 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to device") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 4f0545605f6b..ced8c9cb29c2 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -122,14 +122,12 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) for (i = 0; i < ds->num_ports; i++) { mac[i] = default_mac; - if (i == dsa_upstream_port(priv->ds, i)) { - /* STP doesn't get called for CPU port, so we need to - * set the I/O parameters statically. - */ - mac[i].dyn_learn = true; - mac[i].ingress = true; - mac[i].egress = true; - } + + /* Let sja1105_bridge_stp_state_set() keep address learning + * enabled for the CPU port. + */ + if (dsa_is_cpu_port(ds, i)) + priv->learn_ena |= BIT(i); } return 0; From deb7178eb940e2c5caca1b1db084a69b2e59b4c9 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 13 Jul 2021 13:58:53 +0300 Subject: [PATCH 0312/1469] net: fddi: fix UAF in fza_probe fp is netdev private data and it cannot be used after free_netdev() call. Using fp after free_netdev() can cause UAF bug. Fix it by moving free_netdev() after error message. Fixes: 61414f5ec983 ("FDDI: defza: Add support for DEC FDDIcontroller 700 TURBOchannel adapter") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 14f07050b6b1..0de2c4552f5e 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1504,9 +1504,8 @@ err_out_resource: release_mem_region(start, len); err_out_kfree: - free_netdev(dev); - pr_err("%s: initialization failure, aborting!\n", fp->name); + free_netdev(dev); return ret; } From 2e7ea96924acc502929c3ffa0fcbdaeec00b2208 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 11:51:58 -0500 Subject: [PATCH 0313/1469] cpufreq: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix a fallthrough warning by simply dropping the empty default case at the bottom. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/cpufreq/longhaul.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 182a4dbca095..c538a153ee82 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -942,8 +942,6 @@ static int __init longhaul_init(void) return cpufreq_register_driver(&longhaul_driver); case 10: pr_err("Use acpi-cpufreq driver for VIA C7\n"); - default: - ; } return -ENODEV; From f28100cb9c9645c07cbd22431278ac9492f6a01c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:27 +0200 Subject: [PATCH 0314/1469] sfc: fix lack of XDP TX queues - error XDP TX failed (-22) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes: e26ca4b53582 sfc: reduce the number of requested xdp ev queues The buggy commit intended to allocate less channels for XDP in order to be more unlikely to reach the limit of 32 channels of the driver. The idea was to use each IRQ/eventqeue for more XDP TX queues than before, calculating which is the maximum number of TX queues that one event queue can handle. For example, in EF10 each event queue could handle up to 8 queues, better than the 4 they were handling before the change. This way, it would have to allocate half of channels than before for XDP TX. The problem is that the TX queues are also contained inside the channel structs, and there are only 4 queues per channel. Reducing the number of channels means also reducing the number of queues, resulting in not having the desired number of 1 queue per CPU. This leads to getting errors on XDP_TX and XDP_REDIRECT if they're executed from a high numbered CPU, because there only exist queues for the low half of CPUs, actually. If XDP_TX/REDIRECT is executed in a low numbered CPU, the error doesn't happen. This is the error in the logs (repeated many times, even rate limited): sfc 0000:5e:00.0 ens3f0np0: XDP TX failed (-22) This errors happens in function efx_xdp_tx_buffers, where it expects to have a dedicated XDP TX queue per CPU. Reverting the change makes again more likely to reach the limit of 32 channels in machines with many CPUs. If this happen, no XDP_TX/REDIRECT will be possible at all, and we will have this log error messages: At interface probe: sfc 0000:5e:00.0: Insufficient resources for 12 XDP event queues (24 other channels, max 32) At every subsequent XDP_TX/REDIRECT failure, rate limited: sfc 0000:5e:00.0 ens3f0np0: XDP TX failed (-22) However, without reverting the change, it makes the user to think that everything is OK at probe time, but later it fails in an unpredictable way, depending on the CPU that handles the packet. It is better to restore the predictable behaviour. If the user sees the error message at probe time, he/she can try to configure the best way it fits his/her needs. At least, he/she will have 2 options: - Accept that XDP_TX/REDIRECT is not available (he/she may not need it) - Load sfc module with modparam 'rss_cpus' with a lower number, thus creating less normal RX queues/channels, letting more free resources for XDP, with some performance penalty. Anyway, let the calculation of maximum TX queues that can be handled by a single event queue, and use it only if it's less than the number of TX queues per channel. This doesn't happen in practice, but could happen if some constant values are tweaked in the future, such us EFX_MAX_TXQ_PER_CHANNEL, EFX_MAX_EVQ_SIZE or EFX_MAX_DMAQ_SIZE. Related mailing list thread: https://lore.kernel.org/bpf/20201215104327.2be76156@carbon/ Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index a3ca406a3561..5b71f8a03a6d 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -152,6 +152,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, * maximum size. */ tx_per_ev = EFX_MAX_EVQ_SIZE / EFX_TXQ_MAX_ENT(efx); + tx_per_ev = min(tx_per_ev, EFX_MAX_TXQ_PER_CHANNEL); n_xdp_tx = num_possible_cpus(); n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, tx_per_ev); @@ -181,7 +182,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, efx->xdp_tx_queue_count = 0; } else { efx->n_xdp_channels = n_xdp_ev; - efx->xdp_tx_per_channel = EFX_MAX_TXQ_PER_CHANNEL; + efx->xdp_tx_per_channel = tx_per_ev; efx->xdp_tx_queue_count = n_xdp_tx; n_channels += n_xdp_ev; netif_dbg(efx, drv, efx->net_dev, From 788bc000d4c2f25232db19ab3a0add0ba4e27671 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:28 +0200 Subject: [PATCH 0315/1469] sfc: ensure correct number of XDP queues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 99ba0ea616aa ("sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues") intended to fix a problem caused by a round up when calculating the number of XDP channels and queues. However, this was not the real problem. The real problem was that the number of XDP TX queues had been reduced to half in commit e26ca4b53582 ("sfc: reduce the number of requested xdp ev queues"), but the variable xdp_tx_queue_count had remained the same. Once the correct number of XDP TX queues is created again in the previous patch of this series, this also can be reverted since the error doesn't actually exist. Only in the case that there is a bug in the code we can have different values in xdp_queue_number and efx->xdp_tx_queue_count. Because of this, and per Edward Cree's suggestion, I add instead a WARN_ON to catch if it happens again in the future. Note that the number of allocated queues can be higher than the number of used ones due to the round up, as explained in the existing comment in the code. That's why we also have to stop increasing xdp_queue_number beyond efx->xdp_tx_queue_count. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 5b71f8a03a6d..bb48a139dd15 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -892,18 +892,20 @@ int efx_set_channels(struct efx_nic *efx) if (efx_channel_is_xdp_tx(channel)) { efx_for_each_channel_tx_queue(tx_queue, channel) { tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); + /* We may have a few left-over XDP TX * queues owing to xdp_tx_queue_count * not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL. * We still allocate and probe those * TXQs, but never use them. */ - if (xdp_queue_number < efx->xdp_tx_queue_count) + if (xdp_queue_number < efx->xdp_tx_queue_count) { + netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", + channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - xdp_queue_number++; + xdp_queue_number++; + } } } else { efx_for_each_channel_tx_queue(tx_queue, channel) { @@ -915,8 +917,7 @@ int efx_set_channels(struct efx_nic *efx) } } } - if (xdp_queue_number) - efx->xdp_tx_queue_count = xdp_queue_number; + WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) From d2a16bde77322fca6b6f36ebe19097a1c3c46f74 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:29 +0200 Subject: [PATCH 0316/1469] sfc: add logs explaining XDP_TX/REDIRECT is not available MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If it's not possible to allocate enough channels for XDP, XDP_TX and XDP_REDIRECT don't work. However, only a message saying that not enough channels were available was shown, but not saying what are the consequences in that case. The user didn't know if he/she can use XDP or not, if the performance is reduced, or what. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index bb48a139dd15..e5b0d795c301 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -170,6 +170,8 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", n_xdp_ev, n_channels, max_channels); + netif_err(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will not work on this interface"); efx->n_xdp_channels = 0; efx->xdp_tx_per_channel = 0; efx->xdp_tx_queue_count = 0; @@ -177,6 +179,8 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", n_xdp_tx, n_channels, efx->max_vis); + netif_err(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will not work on this interface"); efx->n_xdp_channels = 0; efx->xdp_tx_per_channel = 0; efx->xdp_tx_queue_count = 0; From 4377d9ab1f162e58e0e5ae89c9a5fd7b4d8a6bdb Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Fri, 9 Jul 2021 09:17:27 +0200 Subject: [PATCH 0317/1469] iio: accel: fxls8962af: fix potential use of uninitialized symbol Fix this warning from kernel test robot: smatch warnings: drivers/iio/accel/fxls8962af-core.c:640 fxls8962af_i2c_raw_read_errata3() error: uninitialized symbol 'ret'. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Sean Nyekjaer Fixes: af959b7b96b8 ("iio: accel: fxls8962af: fix errata bug E3 - I2C burst reads") Link: https://lore.kernel.org/r/20210709071727.2453536-1-sean@geanix.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/fxls8962af-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 078d87865fde..0019f1ea7df2 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -637,7 +637,7 @@ static int fxls8962af_i2c_raw_read_errata3(struct fxls8962af_data *data, return ret; } - return ret; + return 0; } static int fxls8962af_fifo_transfer(struct fxls8962af_data *data, From 420405ecde061fde76d67bd3a67577a563ea758e Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 13 Jul 2021 10:49:26 -0700 Subject: [PATCH 0318/1469] configfs: fix the read and write iterators Commit 7fe1e79b59ba ("configfs: implement the .read_iter and .write_iter methods") changed the simple_read_from_buffer() calls into copy_to_iter() calls and the simple_write_to_buffer() calls into copy_from_iter() calls. The simple*buffer() methods update the file offset (*ppos) but the read and write iterators not yet. Make the read and write iterators update the file offset (iocb->ki_pos). This patch has been tested as follows: # modprobe target_core_user # dd if=/sys/kernel/config/target/dbroot bs=1 /var/target 12+0 records in 12+0 records out 12 bytes copied, 9.5539e-05 s, 126 kB/s # cd /sys/kernel/config/acpi/table # mkdir test # cd test # dmesg -c >/dev/null; printf 'SSDT\x8\0\0\0abcdefghijklmnopqrstuvwxyz' | dd of=aml bs=1; dmesg -c 34+0 records in 34+0 records out 34 bytes copied, 0.010627 s, 3.2 kB/s [ 261.056551] ACPI configfs: invalid table length Reported-by: Yanko Kaneti Cc: Yanko Kaneti Fixes: 7fe1e79b59ba ("configfs: implement the .read_iter and .write_iter methods") Signed-off-by: Bart Van Assche Signed-off-by: Christoph Hellwig --- fs/configfs/file.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 2f63bf3a7325..5a0be9985bae 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -91,7 +91,10 @@ static ssize_t configfs_read_iter(struct kiocb *iocb, struct iov_iter *to) } pr_debug("%s: count = %zd, pos = %lld, buf = %s\n", __func__, iov_iter_count(to), iocb->ki_pos, buffer->page); - retval = copy_to_iter(buffer->page, buffer->count, to); + if (iocb->ki_pos >= buffer->count) + goto out; + retval = copy_to_iter(buffer->page + iocb->ki_pos, + buffer->count - iocb->ki_pos, to); iocb->ki_pos += retval; if (retval == 0) retval = -EFAULT; @@ -162,7 +165,10 @@ static ssize_t configfs_bin_read_iter(struct kiocb *iocb, struct iov_iter *to) buffer->needs_read_fill = 0; } - retval = copy_to_iter(buffer->bin_buffer, buffer->bin_buffer_size, to); + if (iocb->ki_pos >= buffer->bin_buffer_size) + goto out; + retval = copy_to_iter(buffer->bin_buffer + iocb->ki_pos, + buffer->bin_buffer_size - iocb->ki_pos, to); iocb->ki_pos += retval; if (retval == 0) retval = -EFAULT; @@ -171,21 +177,28 @@ out: return retval; } -static int fill_write_buffer(struct configfs_buffer *buffer, +/* Fill [buffer, buffer + pos) with data coming from @from. */ +static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos, struct iov_iter *from) { + loff_t to_copy; int copied; + u8 *to; if (!buffer->page) buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); if (!buffer->page) return -ENOMEM; - copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from); + to_copy = SIMPLE_ATTR_SIZE - 1 - pos; + if (to_copy <= 0) + return 0; + to = buffer->page + pos; + copied = copy_from_iter(to, to_copy, from); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, * so e.g. sscanf() can scan the string easily */ - buffer->page[copied] = 0; + to[copied] = 0; return copied ? : -EFAULT; } @@ -217,7 +230,7 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t len; mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, from); + len = fill_write_buffer(buffer, iocb->ki_pos, from); if (len > 0) len = flush_write_buffer(file, buffer, len); if (len > 0) @@ -272,7 +285,9 @@ static ssize_t configfs_bin_write_iter(struct kiocb *iocb, buffer->bin_buffer_size = end_offset; } - len = copy_from_iter(buffer->bin_buffer, buffer->bin_buffer_size, from); + len = copy_from_iter(buffer->bin_buffer + iocb->ki_pos, + buffer->bin_buffer_size - iocb->ki_pos, from); + iocb->ki_pos += len; out: mutex_unlock(&buffer->mutex); return len ? : -EFAULT; From f336a009f8e3dd0b47168565584608a4a62cbbb4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:09:06 -0500 Subject: [PATCH 0319/1469] math-emu: Fix fall-through warning Fix the following fallthrough warning (nds32-randconfig with GCC): include/math-emu/op-common.h:332:8: warning: this statement may fall through [-Wimplicit-fallthrough=] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- include/math-emu/op-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index 143568d64b20..4b57bbba588a 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -338,7 +338,7 @@ do { \ FP_SET_EXCEPTION(FP_EX_INVALID | FP_EX_INVALID_ISI); \ break; \ } \ - /* FALLTHRU */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \ From c8698340e0e5897c30811f8e7e86bcebe53e0519 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:13:40 -0500 Subject: [PATCH 0320/1469] video: fbdev: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/video/fbdev/xilinxfb.c:244:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/video/fbdev/xilinxfb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/fbdev/xilinxfb.c b/drivers/video/fbdev/xilinxfb.c index ffbf900648d9..438e2c78142f 100644 --- a/drivers/video/fbdev/xilinxfb.c +++ b/drivers/video/fbdev/xilinxfb.c @@ -241,6 +241,8 @@ xilinx_fb_blank(int blank_mode, struct fb_info *fbi) case FB_BLANK_POWERDOWN: /* turn off panel */ xilinx_fb_out32(drvdata, REG_CTRL, 0); + break; + default: break; } From 223fa873facce6eef165009294d01e18c191c609 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:18:14 -0500 Subject: [PATCH 0321/1469] scsi: libsas: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/scsi/libsas/sas_discover.c:467:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/scsi/libsas/sas_discover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 9f5068f3bcfb..dd205414e505 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -461,7 +461,7 @@ static void sas_discover_domain(struct work_struct *work) break; #else pr_notice("ATA device seen but CONFIG_SCSI_SAS_ATA=N so cannot attach\n"); - /* Fall through */ + fallthrough; #endif /* Fall through - only for the #else condition above. */ default: From 54325d0849d60ed52ee9316f76d116b52b53669b Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:21:22 -0500 Subject: [PATCH 0322/1469] PCI: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/pci/proc.c:234:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/pci/proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 9bab07302bbf..d32fbfc93ea9 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -230,8 +230,8 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, break; } /* If arch decided it can't, fall through... */ -#endif /* HAVE_PCI_MMAP */ fallthrough; +#endif /* HAVE_PCI_MMAP */ default: ret = -EINVAL; break; From f95deaeca8e106af891061e5f9c745dc7dc172c0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:23:21 -0500 Subject: [PATCH 0323/1469] mmc: jz4740: Fix fall-through warning for Clang Fix the following fallthrough warning (mips-randconfig with Clang): drivers/mmc/host/jz4740_mmc.c:792:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/mmc/host/jz4740_mmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 0db17bcc9c16..cb1a64a5c256 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -789,6 +789,8 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid) break; } } + fallthrough; + case JZ4740_MMC_STATE_DONE: break; } From 5a1ab5c0299a7b3b9e7ec52c327f44d98b8e001d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:25:06 -0500 Subject: [PATCH 0324/1469] iommu/arm-smmu-v3: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c:382:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index dd20b01771c4..235f9bdaeaf2 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -379,6 +379,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) switch (idx) { case CMDQ_ERR_CERROR_ABT_IDX: dev_err(smmu->dev, "retrying command fetch\n"); + return; case CMDQ_ERR_CERROR_NONE_IDX: return; case CMDQ_ERR_CERROR_ATC_INV_IDX: From 41614014a7afbbce5b61bfce5ce89ee3455143e7 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:27:08 -0500 Subject: [PATCH 0325/1469] dmaengine: ipu: Fix fall-through warning for Clang Fix the following fallthrough warnings (arm64-randconfig): drivers/dma/ipu/ipu_idmac.c:621:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] rivers/dma/ipu/ipu_idmac.c:981:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/dma/ipu/ipu_idmac.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index 104ad420abbe..baab1ca9f621 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -618,6 +618,7 @@ static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan) case IDMAC_SDC_1: case IDMAC_IC_7: ipu_channel_set_priority(ipu, channel, true); + break; default: break; } @@ -978,6 +979,7 @@ static int ipu_init_channel(struct idmac *idmac, struct idmac_channel *ichan) case IDMAC_SDC_0: case IDMAC_SDC_1: n_desc = 4; + break; default: break; } From d4e81342ea2399cf92e98ea5c0d025bcf8a3d065 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:43:09 -0500 Subject: [PATCH 0326/1469] s390: Fix fall-through warnings for Clang Fix the following fallthrough warnings: drivers/s390/net/ctcm_fsms.c:1457:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/s390/net/qeth_l3_main.c:437:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/s390/char/tape_char.c:374:4: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] arch/s390/kernel/uprobes.c:129:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- arch/s390/kernel/uprobes.c | 1 + drivers/s390/char/tape_char.c | 2 -- drivers/s390/net/ctcm_fsms.c | 1 + drivers/s390/net/qeth_l3_main.c | 1 + 4 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index bbf8622bbf5d..bd3ef121c379 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -126,6 +126,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, case DIE_SSTEP: if (uprobe_post_sstep_notifier(regs)) return NOTIFY_STOP; + break; default: break; } diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index 8abb42923307..cc8237afeffa 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -371,8 +371,6 @@ __tapechar_ioctl(struct tape_device *device, case MTSEEK: if (device->required_tapemarks) tape_std_terminate_write(device); - default: - ; } rc = tape_mtop(device, op.mt_op, op.mt_count); diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index b341075397d9..377e3689d1d4 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -1454,6 +1454,7 @@ again: get_ccwdev_lock(ch->cdev), saveflags); if (rc != 0) ctcm_ccw_check_rc(ch, rc, "normal RX"); + break; default: break; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d308ff744a29..f0d6f205c53c 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -434,6 +434,7 @@ static int qeth_l3_correct_routing_type(struct qeth_card *card, if (qeth_is_ipafunc_supported(card, prot, IPA_OSA_MC_ROUTER)) return 0; + goto out_inval; default: goto out_inval; } From d6a48a476a5de8bdfbdd6040aa5a48955fc49e44 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:48:28 -0500 Subject: [PATCH 0327/1469] dmaengine: ti: k3-udma: Fix fall-through warning for Clang Fix the following fallthrough warning: drivers/dma/ti/k3-udma.c:4951:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/dma/ti/k3-udma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 96ad21869ba7..a35858610780 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4948,6 +4948,7 @@ static int setup_resources(struct udma_dev *ud) ud->tchan_cnt), ud->rchan_cnt - bitmap_weight(ud->rchan_map, ud->rchan_cnt)); + break; default: break; } From b51883d47d37c3f3fa80d6bcd8cc3a57d5b95130 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:50:47 -0500 Subject: [PATCH 0328/1469] power: supply: Fix fall-through warnings for Clang Fix the following fallthrough warnings: drivers/power/supply/ab8500_fg.c:1730:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/power/supply/abx500_chargalg.c:1155:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/power/supply/ab8500_fg.c | 2 ++ drivers/power/supply/abx500_chargalg.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 3d45ed0157c6..a6ebdb269fdd 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -1728,6 +1728,7 @@ static void ab8500_fg_algorithm_calibrate(struct ab8500_fg *di) break; case AB8500_FG_CALIB_WAIT: dev_dbg(di->dev, "Calibration WFI\n"); + break; default: break; } @@ -2224,6 +2225,7 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) queue_work(di->fg_wq, &di->fg_work); break; } + break; default: break; } diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c index a17849bfacbf..b72826cf6794 100644 --- a/drivers/power/supply/abx500_chargalg.c +++ b/drivers/power/supply/abx500_chargalg.c @@ -1150,6 +1150,7 @@ static int abx500_chargalg_get_ext_psy_data(struct device *dev, void *data) default: break; } + break; default: break; } From 2feeb52859fc1ab94cd35b61ada3a6ac4ff24243 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 30 Jun 2021 19:44:13 +0300 Subject: [PATCH 0329/1469] drm/i915/gt: Fix -EDEADLK handling regression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The conversion to ww mutexes failed to address the fence code which already returns -EDEADLK when we run out of fences. Ww mutexes on the other hand treat -EDEADLK as an internal errno value indicating a need to restart the operation due to a deadlock. So now when the fence code returns -EDEADLK the higher level code erroneously restarts everything instead of returning the error to userspace as is expected. To remedy this let's switch the fence code to use a different errno value for this. -ENOBUFS seems like a semi-reasonable unique choice. Apart from igt the only user of this I could find is sna, and even there all we do is dump the current fence registers from debugfs into the X server log. So no user visible functionality is affected. If we really cared about preserving this we could of course convert back to -EDEADLK higher up, but doesn't seem like that's worth the hassle here. Not quite sure which commit specifically broke this, but I'll just attribute it to the general gem ww mutex work. Cc: stable@vger.kernel.org Cc: Maarten Lankhorst Cc: Thomas Hellström Testcase: igt/gem_pread/exhaustion Testcase: igt/gem_pwrite/basic-exhaustion Testcase: igt/gem_fenced_exec_thrash/too-many-fences Fixes: 80f0b679d6f0 ("drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210630164413.25481-1-ville.syrjala@linux.intel.com Reviewed-by: Maarten Lankhorst (cherry picked from commit 78d2ad7eb4e1f0e9cd5d79788446b6092c21d3e0) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index cac7f3f44642..f8948de72036 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -348,7 +348,7 @@ static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt) if (intel_has_pending_fb_unpin(ggtt->vm.i915)) return ERR_PTR(-EAGAIN); - return ERR_PTR(-EDEADLK); + return ERR_PTR(-ENOBUFS); } int __i915_vma_pin_fence(struct i915_vma *vma) From 4796372e7c117b84bfd929526f48e23c79030dcd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:58:18 -0500 Subject: [PATCH 0330/1469] ASoC: Mediatek: MT8183: Fix fall-through warning for Clang Fix the following fallthrough warning: sound/soc/mediatek/mt8183/mt8183-dai-adda.c:342:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- sound/soc/mediatek/mt8183/mt8183-dai-adda.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/mediatek/mt8183/mt8183-dai-adda.c b/sound/soc/mediatek/mt8183/mt8183-dai-adda.c index 2b758a18c2ea..5b8a274419ed 100644 --- a/sound/soc/mediatek/mt8183/mt8183-dai-adda.c +++ b/sound/soc/mediatek/mt8183/mt8183-dai-adda.c @@ -341,6 +341,7 @@ static int set_mtkaif_rx(struct mtk_base_afe *afe) case MT8183_MTKAIF_PROTOCOL_1: regmap_write(afe->regmap, AFE_AUD_PAD_TOP, 0x31); regmap_write(afe->regmap, AFE_ADDA_MTKAIF_CFG0, 0x0); + break; default: break; } From bc431d2153cc290573531601b5004babe7011568 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:38:58 -0500 Subject: [PATCH 0331/1469] MIPS: Fix fall-through warnings for Clang Fix the following fallthrough warnings: arch/mips/mm/tlbex.c:1386:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] arch/mips/mm/tlbex.c:2173:3: error: unannotated fall-through between switch labels [-Werror,-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/mips/mm/tlbex.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index cd4afcdf3725..9adad24c2e65 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1383,6 +1383,7 @@ static void build_r4000_tlb_refill_handler(void) switch (boot_cpu_type()) { default: if (sizeof(long) == 4) { + fallthrough; case CPU_LOONGSON2EF: /* Loongson2 ebase is different than r4k, we have more space */ if ((p - tlb_handler) > 64) @@ -2169,6 +2170,7 @@ static void build_r4000_tlb_load_handler(void) default: if (cpu_has_mips_r2_exec_hazard) { uasm_i_ehb(&p); + fallthrough; case CPU_CAVIUM_OCTEON: case CPU_CAVIUM_OCTEON_PLUS: From cf6678aec2530701f8e13b7551d131599c33e5ca Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:41:16 -0500 Subject: [PATCH 0332/1469] MIPS: Fix unreachable code issue Fix the following warning (mips-randconfig): arch/mips/include/asm/fpu.h:79:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] Originally, the /* fallthrough */ comment was introduced by commit: 597ce1723e0f ("MIPS: Support for 64-bit FP with O32 binaries") and it was wrongly replaced with fallthrough; by commit: c9b029903466 ("MIPS: Use fallthrough for arch/mips") As the original comment is actually useful, fix this issue by removing unreachable fallthrough; statement and place the original /* fallthrough */ comment back. Fixes: c9b029903466 ("MIPS: Use fallthrough for arch/mips") Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/mips/include/asm/fpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 08f9dd6903b7..86310d6e1035 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -76,7 +76,7 @@ static inline int __enable_fpu(enum fpu_mode mode) /* we only have a 32-bit FPU */ return SIGFPE; #endif - fallthrough; + /* fallthrough */ case FPU_32BIT: if (cpu_has_fre) { /* clear FRE */ From bcb9928a155444dbd212473e60241ca0a7f641e1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:40:21 +0300 Subject: [PATCH 0333/1469] net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave() This was not caught because there is no switch driver which implements the .port_bridge_join but not .port_bridge_leave method, but it should nonetheless be fixed, as in certain conditions (driver development) it might lead to NULL pointer dereference. Fixes: f66a6a69f97a ("net: dsa: permit cross-chip bridging between all trees in the system") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/dsa/switch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 248455145982..5ece05dfd8f2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,11 +113,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) + ds->ops->port_bridge_leave) ds->ops->port_bridge_leave(ds, info->port, info->br); if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) + ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, info->br); From 479857a9bcc86e808216daae8ca1c9213b9e117a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 19:19:03 -0500 Subject: [PATCH 0334/1469] powerpc/powernv: Fix fall-through warning for Clang Fix the following fallthrough warnings (powernv_defconfig and powerpc64): drivers/char/powernv-op-panel.c:78:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/char/powernv-op-panel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/char/powernv-op-panel.c b/drivers/char/powernv-op-panel.c index 027484ecfb0d..3c99696b145e 100644 --- a/drivers/char/powernv-op-panel.c +++ b/drivers/char/powernv-op-panel.c @@ -75,6 +75,7 @@ static int __op_panel_update_display(void) rc); break; } + break; case OPAL_SUCCESS: break; default: From 7e71b85473f863a29eb1c69265ef025389b4091d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 8 Jun 2021 14:26:58 +0300 Subject: [PATCH 0335/1469] arm64: dts: ls1028a: fix node name for the sysclk U-Boot attempts to fix up the "clock-frequency" property of the "/sysclk" node: https://elixir.bootlin.com/u-boot/v2021.04/source/arch/arm/cpu/armv8/fsl-layerscape/fdt.c#L512 but fails to do so: ## Booting kernel from Legacy Image at a1000000 ... Image Name: Created: 2021-06-08 10:31:38 UTC Image Type: AArch64 Linux Kernel Image (gzip compressed) Data Size: 15431370 Bytes = 14.7 MiB Load Address: 80080000 Entry Point: 80080000 Verifying Checksum ... OK ## Flattened Device Tree blob at a0000000 Booting using the fdt blob at 0xa0000000 Uncompressing Kernel Image Loading Device Tree to 00000000fbb19000, end 00000000fbb22717 ... OK Unable to update property /sysclk:clock-frequency, err=FDT_ERR_NOTFOUND Starting kernel ... All Layerscape SoCs except LS1028A use "sysclk" as the node name, and not "clock-sysclk". So change the node name of LS1028A accordingly. Fixes: 8897f3255c9c ("arm64: dts: Add support for NXP LS1028A SoC") Signed-off-by: Vladimir Oltean Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index b2e3e5d2a108..343ecf0e8973 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -66,7 +66,7 @@ }; }; - sysclk: clock-sysclk { + sysclk: sysclk { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <100000000>; From 7dd2dd4ff9f3abda601f22b9d01441a0869d20d7 Mon Sep 17 00:00:00 2001 From: Adrian Larumbe Date: Wed, 7 Jul 2021 00:43:38 +0100 Subject: [PATCH 0336/1469] dmaengine: xilinx_dma: Fix read-after-free bug when terminating transfers When user calls dmaengine_terminate_sync, the driver will clean up any remaining descriptors for all the pending or active transfers that had previously been submitted. However, this might happen whilst the tasklet is invoking the DMA callback for the last finished transfer, so by the time it returns and takes over the channel's spinlock, the list of completed descriptors it was traversing is no longer valid. This leads to a read-after-free situation. Fix it by signalling whether a user-triggered termination has happened by means of a boolean variable. Signed-off-by: Adrian Larumbe Link: https://lore.kernel.org/r/20210706234338.7696-3-adrian.martinezlarumbe@imgtec.com Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dma.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 75c0b8e904e5..4b9530a7bf65 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -394,6 +394,7 @@ struct xilinx_dma_tx_descriptor { * @genlock: Support genlock mode * @err: Channel has errors * @idle: Check for channel idle + * @terminating: Check for channel being synchronized by user * @tasklet: Cleanup work after irq * @config: Device configuration info * @flush_on_fsync: Flush on Frame sync @@ -431,6 +432,7 @@ struct xilinx_dma_chan { bool genlock; bool err; bool idle; + bool terminating; struct tasklet_struct tasklet; struct xilinx_vdma_config config; bool flush_on_fsync; @@ -1049,6 +1051,13 @@ static void xilinx_dma_chan_desc_cleanup(struct xilinx_dma_chan *chan) /* Run any dependencies, then free the descriptor */ dma_run_dependencies(&desc->async_tx); xilinx_dma_free_tx_descriptor(chan, desc); + + /* + * While we ran a callback the user called a terminate function, + * which takes care of cleaning up any remaining descriptors + */ + if (chan->terminating) + break; } spin_unlock_irqrestore(&chan->lock, flags); @@ -1965,6 +1974,8 @@ static dma_cookie_t xilinx_dma_tx_submit(struct dma_async_tx_descriptor *tx) if (desc->cyclic) chan->cyclic = true; + chan->terminating = false; + spin_unlock_irqrestore(&chan->lock, flags); return cookie; @@ -2436,6 +2447,7 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan) xilinx_dma_chan_reset(chan); /* Remove and free all of the descriptors in the lists */ + chan->terminating = true; xilinx_dma_free_descriptors(chan); chan->idle = true; From 1da569fa7ec8cb0591c74aa3050d4ea1397778b4 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 6 Jul 2021 20:45:21 +0800 Subject: [PATCH 0337/1469] dmaengine: usb-dmac: Fix PM reference leak in usb_dmac_probe() pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. Fix it by moving the error_pm label above the pm_runtime_put() in the error path. Reported-by: Hulk Robot Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20210706124521.1371901-1-yukuai3@huawei.com Signed-off-by: Vinod Koul --- drivers/dma/sh/usb-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c index 8f7ceb698226..1cc06900153e 100644 --- a/drivers/dma/sh/usb-dmac.c +++ b/drivers/dma/sh/usb-dmac.c @@ -855,8 +855,8 @@ static int usb_dmac_probe(struct platform_device *pdev) error: of_dma_controller_free(pdev->dev.of_node); - pm_runtime_put(&pdev->dev); error_pm: + pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); return ret; } From da435aedb00a4ef61019ff11ae0c08ffb9b1fb18 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 24 Jun 2021 12:09:29 -0700 Subject: [PATCH 0338/1469] dmaengine: idxd: fix array index when int_handles are being used The index to the irq vector should be local and has no relation to the assigned interrupt handle. Assign the MSIX interrupt index that is programmed for the descriptor. The interrupt handle only matters when it comes to hardware descriptor programming. Fixes: eb15e7154fbf ("dmaengine: idxd: add interrupt handle request and release support") Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162456176939.1121476.3366256009925001897.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/submit.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 19afb62abaff..e29887528077 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -128,19 +128,8 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) * Pending the descriptor to the lockless list for the irq_entry * that we designated the descriptor to. */ - if (desc->hw->flags & IDXD_OP_FLAG_RCI) { - int vec; - - /* - * If the driver is on host kernel, it would be the value - * assigned to interrupt handle, which is index for MSIX - * vector. If it's guest then can't use the int_handle since - * that is the index to IMS for the entire device. The guest - * device local index will be used. - */ - vec = !idxd->int_handles ? desc->hw->int_handle : desc->vector; - llist_add(&desc->llnode, &idxd->irq_entries[vec].pending_llist); - } + if (desc->hw->flags & IDXD_OP_FLAG_RCI) + llist_add(&desc->llnode, &idxd->irq_entries[desc->vector].pending_llist); return 0; } From d5c10e0fc8645342fe5c9796b00c84ab078cd713 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 24 Jun 2021 13:43:32 -0700 Subject: [PATCH 0339/1469] dmaengine: idxd: fix setup sequence for MSIXPERM table The MSIX permission table should be programmed BEFORE request_irq() happens. This prevents any possibility of an interrupt happening before the MSIX perm table is setup, however slight. Fixes: 6df0e6c57dfc ("dmaengine: idxd: clear MSIX permission entry on shutdown") Sign-off-by: Dave Jiang Link: https://lore.kernel.org/r/162456741222.1138073.1298447364671237896.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index c8ae41d36040..4e32a4dcc3ab 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -102,6 +102,8 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) spin_lock_init(&idxd->irq_entries[i].list_lock); } + idxd_msix_perm_setup(idxd); + irq_entry = &idxd->irq_entries[0]; rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread, 0, "idxd-misc", irq_entry); @@ -148,7 +150,6 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) } idxd_unmask_error_interrupts(idxd); - idxd_msix_perm_setup(idxd); return 0; err_wq_irqs: @@ -162,6 +163,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) err_misc_irq: /* Disable error interrupt generation */ idxd_mask_error_interrupts(idxd); + idxd_msix_perm_clear(idxd); err_irq_entries: pci_free_irq_vectors(pdev); dev_err(dev, "No usable interrupts\n"); From f9613aa07f16d6042e74208d1b40a6104d72964a Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 15 Jun 2021 20:52:38 +0800 Subject: [PATCH 0340/1469] ARM: imx: add missing iounmap() Commit e76bdfd7403a ("ARM: imx: Added perf functionality to mmdc driver") introduced imx_mmdc_remove(), the mmdc_base need be unmapped in it if config PERF_EVENTS is enabled. If imx_mmdc_perf_init() fails, the mmdc_base also need be unmapped. Fixes: e76bdfd7403a ("ARM: imx: Added perf functionality to mmdc driver") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Reviewed-by: Dong Aisheng Signed-off-by: Shawn Guo --- arch/arm/mach-imx/mmdc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 0dfd0ae7a63d..8e57691aafe2 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -462,6 +462,7 @@ static int imx_mmdc_remove(struct platform_device *pdev) cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); perf_pmu_unregister(&pmu_mmdc->pmu); + iounmap(pmu_mmdc->mmdc_base); kfree(pmu_mmdc); return 0; } @@ -567,7 +568,11 @@ static int imx_mmdc_probe(struct platform_device *pdev) val &= ~(1 << BP_MMDC_MAPSR_PSD); writel_relaxed(val, reg); - return imx_mmdc_perf_init(pdev, mmdc_base); + err = imx_mmdc_perf_init(pdev, mmdc_base); + if (err) + iounmap(mmdc_base); + + return err; } int imx_mmdc_get_ddr_type(void) From f07ec85365807b3939f32d0094a6dd5ce065d1b9 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 15 Jun 2021 20:52:39 +0800 Subject: [PATCH 0341/1469] ARM: imx: add missing clk_disable_unprepare() clock source is prepared and enabled by clk_prepare_enable() in probe function, but no disable or unprepare in remove and error path. Fixes: 9454a0caff6a ("ARM: imx: add mmdc ipg clock operation for mmdc") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Reviewed-by: Dong Aisheng Signed-off-by: Shawn Guo --- arch/arm/mach-imx/mmdc.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 8e57691aafe2..4a6f1359e1e9 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -103,6 +103,7 @@ struct mmdc_pmu { struct perf_event *mmdc_events[MMDC_NUM_COUNTERS]; struct hlist_node node; struct fsl_mmdc_devtype_data *devtype_data; + struct clk *mmdc_ipg_clk; }; /* @@ -463,11 +464,13 @@ static int imx_mmdc_remove(struct platform_device *pdev) cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); perf_pmu_unregister(&pmu_mmdc->pmu); iounmap(pmu_mmdc->mmdc_base); + clk_disable_unprepare(pmu_mmdc->mmdc_ipg_clk); kfree(pmu_mmdc); return 0; } -static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_base) +static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_base, + struct clk *mmdc_ipg_clk) { struct mmdc_pmu *pmu_mmdc; char *name; @@ -495,6 +498,7 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b } mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev); + pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; if (mmdc_num == 0) name = "mmdc"; else @@ -568,9 +572,11 @@ static int imx_mmdc_probe(struct platform_device *pdev) val &= ~(1 << BP_MMDC_MAPSR_PSD); writel_relaxed(val, reg); - err = imx_mmdc_perf_init(pdev, mmdc_base); - if (err) + err = imx_mmdc_perf_init(pdev, mmdc_base, mmdc_ipg_clk); + if (err) { iounmap(mmdc_base); + clk_disable_unprepare(mmdc_ipg_clk); + } return err; } From fb1425b436bcf936065edbbe8d092465a53185b6 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Thu, 17 Jun 2021 11:54:15 -0300 Subject: [PATCH 0342/1469] ARM: imx: common: Move prototype outside the SMP block Currently the imx_gpcv2_set_core1_pdn_pup_by_software() prototype is guarded by the CONFIG_SMP symbol. This causes W=1 build warnings when CONFIG_SMP is not selected: arch/arm/mach-imx/src.c:103:6: warning: no previous prototype for 'imx_gpcv2_set_core1_pdn_pup_by_software' [-Wmissing-prototypes] Fix it by moving the imx_gpcv2_set_core1_pdn_pup_by_software() prototype outside of the CONFIG_SMP block. Fixes: e34645f45805 ("ARM: imx: add smp support for imx7d") Reported-by: kernel test robot Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/mach-imx/common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index f0a073a71401..13f3068e9845 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -68,7 +68,6 @@ void imx_set_cpu_arg(int cpu, u32 arg); void v7_secondary_startup(void); void imx_scu_map_io(void); void imx_smp_prepare(void); -void imx_gpcv2_set_core1_pdn_pup_by_software(bool pdn); #else static inline void imx_scu_map_io(void) {} static inline void imx_smp_prepare(void) {} @@ -81,6 +80,7 @@ void imx_gpc_mask_all(void); void imx_gpc_restore_all(void); void imx_gpc_hwirq_mask(unsigned int hwirq); void imx_gpc_hwirq_unmask(unsigned int hwirq); +void imx_gpcv2_set_core1_pdn_pup_by_software(bool pdn); void imx_anatop_init(void); void imx_anatop_pre_suspend(void); void imx_anatop_post_resume(void); From fd8e83884fdd7b5fc411f201a58d8d01890198a2 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 25 Jun 2021 14:13:53 +0200 Subject: [PATCH 0343/1469] ARM: dts: imx6qdl-sr-som: Increase the PHY reset duration to 10ms MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The AR803x PHY used on this modules seems to require the reset line to be asserted for around 10ms in order to avoid rare cases where the PHY gets stuck in an incoherent state that prevents it to function correctly. The previous value of 2ms was found to be problematic on some setups, causing intermittent issues where the PHY would be unresponsive every once in a while on some sytems, with a low occurrence (it typically took around 30 consecutive reboots to encounter the issue). Bumping the delay to the 10ms makes the issue dissapear, with more than 2500 consecutive reboots performed without the issue showing-up. Fixes: 208d7baf8085 ("ARM: imx: initial SolidRun HummingBoard support") Signed-off-by: Maxime Chevallier Tested-by: Hervé Codina Reviewed-by: Russell King (Oracle) Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl-sr-som.dtsi | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi index 0ad8ccde0cf8..f86efd0ccc40 100644 --- a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi @@ -54,7 +54,13 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_microsom_enet_ar8035>; phy-mode = "rgmii-id"; - phy-reset-duration = <2>; + + /* + * The PHY seems to require a long-enough reset duration to avoid + * some rare issues where the PHY gets stuck in an inconsistent and + * non-functional state at boot-up. 10ms proved to be fine . + */ + phy-reset-duration = <10>; phy-reset-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; status = "okay"; From 80d9ac9bd7b9366c2a89d2716a397749299728e7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 13 Jul 2021 12:36:41 +0100 Subject: [PATCH 0344/1469] KVM: arm64: Fix detection of shared VMAs on guest fault When merging the KVM MTE support, the blob that was interposed between the chair and the keyboard experienced a neuronal accident (also known as a brain fart), turning a check for VM_SHARED into VM_PFNMAP as it was reshuffling some of the code. The blob having now come back to its senses, let's restore the initial check that the original author got right the first place. Fixes: ea7fc1bb1cd1 ("KVM: arm64: Introduce MTE VM feature") Reviewed-by: Steven Price Signed-off-by: Marc Zyngier Cc: Catalin Marinas Link: https://lore.kernel.org/r/20210713114804.594993-1-maz@kernel.org --- arch/arm64/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 3155c9e778f0..0625bf2353c2 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -947,7 +947,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_shift = get_vma_page_shift(vma, hva); } - shared = (vma->vm_flags & VM_PFNMAP); + shared = (vma->vm_flags & VM_SHARED); switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED From bac0b135907855e9f8c032877c3df3c60885a08f Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Tue, 13 Jul 2021 22:37:41 +0200 Subject: [PATCH 0345/1469] KVM: selftests: change pthread_yield to sched_yield MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With later GCC we get steal_time.c: In function ‘main’: steal_time.c:323:25: warning: ‘pthread_yield’ is deprecated: pthread_yield is deprecated, use sched_yield instead [-Wdeprecated-declarations] Let's follow the instructions and use sched_yield instead. Signed-off-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210713203742.29680-2-drjones@redhat.com --- tools/testing/selftests/kvm/steal_time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index b0031f2d38fd..ecec30865a74 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -320,7 +320,7 @@ int main(int ac, char **av) run_delay = get_run_delay(); pthread_create(&thread, &attr, do_steal_time, NULL); do - pthread_yield(); + sched_yield(); while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS); pthread_join(thread, NULL); run_delay = get_run_delay() - run_delay; From 5cf17746b302aa32a4f200cc6ce38865bfe4cf94 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Tue, 13 Jul 2021 22:37:42 +0200 Subject: [PATCH 0346/1469] KVM: arm64: selftests: get-reg-list: actually enable pmu regs in pmu sublist We reworked get-reg-list to make it easier to enable optional register sublists by parametrizing their vcpu feature flags as well as making other generalizations. That was all to make sure we enable the PMU registers when we want to test them. Somehow we forgot to actually include the PMU feature flag in the PMU sublist description though! Do that now. Fixes: 313673bad871 ("KVM: arm64: selftests: get-reg-list: Split base and pmu registers") Signed-off-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210713203742.29680-3-drjones@redhat.com --- tools/testing/selftests/kvm/aarch64/get-reg-list.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index a16c8f05366c..cc898181faab 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -1019,7 +1019,8 @@ static __u64 sve_rejects_set[] = { #define VREGS_SUBLIST \ { "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), } #define PMU_SUBLIST \ - { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } + { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \ + .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } #define SVE_SUBLIST \ { "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \ .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \ From ce36c94214f0d534aad4adb4219cc046270948fb Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 5 Jul 2021 08:56:57 +0200 Subject: [PATCH 0347/1469] iommu/qcom: Revert "iommu/arm: Cleanup resources in case of probe error path" QCOM IOMMU driver calls bus_set_iommu() for every IOMMU device controller, what fails for the second and latter IOMMU devices. This is intended and must be not fatal to the driver registration process. Also the cleanup path should take care of the runtime PM state, what is missing in the current patch. Revert relevant changes to the QCOM IOMMU driver until a proper fix is prepared. This partially reverts commit 249c9dc6aa0db74a0f7908efd04acf774e19b155. Fixes: 249c9dc6aa0d ("iommu/arm: Cleanup resources in case of probe error path") Suggested-by: Will Deacon Signed-off-by: Marek Szyprowski Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210705065657.30356-1-m.szyprowski@samsung.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 25ed444ff94d..021cf8f65ffc 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -849,12 +849,10 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev); if (ret) { dev_err(dev, "Failed to register iommu\n"); - goto err_sysfs_remove; + return ret; } - ret = bus_set_iommu(&platform_bus_type, &qcom_iommu_ops); - if (ret) - goto err_unregister_device; + bus_set_iommu(&platform_bus_type, &qcom_iommu_ops); if (qcom_iommu->local_base) { pm_runtime_get_sync(dev); @@ -863,13 +861,6 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) } return 0; - -err_unregister_device: - iommu_device_unregister(&qcom_iommu->iommu); - -err_sysfs_remove: - iommu_device_sysfs_remove(&qcom_iommu->iommu); - return ret; } static int qcom_iommu_device_remove(struct platform_device *pdev) From 37764b952e1b39053defc7ebe5dcd8c4e3e78de9 Mon Sep 17 00:00:00 2001 From: Sanjay Kumar Date: Mon, 12 Jul 2021 15:13:15 +0800 Subject: [PATCH 0348/1469] iommu/vt-d: Global devTLB flush when present context entry changed This fixes a bug in context cache clear operation. The code was not following the correct invalidation flow. A global device TLB invalidation should be added after the IOTLB invalidation. At the same time, it uses the domain ID from the context entry. But in scalable mode, the domain ID is in PASID table entry, not context entry. Fixes: 7373a8cc38197 ("iommu/vt-d: Setup context and enable RID2PASID support") Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Sanjay Kumar Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210712071315.3416543-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a6a07d985709..57270290d62b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2429,10 +2429,11 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return 0; } -static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn) +static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn) { - unsigned long flags; + struct intel_iommu *iommu = info->iommu; struct context_entry *context; + unsigned long flags; u16 did_old; if (!iommu) @@ -2444,7 +2445,16 @@ static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn spin_unlock_irqrestore(&iommu->lock, flags); return; } - did_old = context_domain_id(context); + + if (sm_supported(iommu)) { + if (hw_pass_through && domain_type_is_si(info->domain)) + did_old = FLPT_DEFAULT_DID; + else + did_old = info->domain->iommu_did[iommu->seq_id]; + } else { + did_old = context_domain_id(context); + } + context_clear_entry(context); __iommu_flush_cache(iommu, context, sizeof(*context)); spin_unlock_irqrestore(&iommu->lock, flags); @@ -2462,6 +2472,8 @@ static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn 0, 0, DMA_TLB_DSI_FLUSH); + + __iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH); } static inline void unlink_domain_info(struct device_domain_info *info) @@ -4425,9 +4437,9 @@ out_free_dmar: static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) { - struct intel_iommu *iommu = opaque; + struct device_domain_info *info = opaque; - domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); + domain_context_clear_one(info, PCI_BUS_NUM(alias), alias & 0xff); return 0; } @@ -4437,12 +4449,13 @@ static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *op * devices, unbinding the driver from any one of them will possibly leave * the others unable to operate. */ -static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) +static void domain_context_clear(struct device_domain_info *info) { - if (!iommu || !dev || !dev_is_pci(dev)) + if (!info->iommu || !info->dev || !dev_is_pci(info->dev)) return; - pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); + pci_for_each_dma_alias(to_pci_dev(info->dev), + &domain_context_clear_one_cb, info); } static void __dmar_remove_one_dev_info(struct device_domain_info *info) @@ -4466,7 +4479,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) iommu_disable_dev_iotlb(info); if (!dev_is_real_dma_subdevice(info->dev)) - domain_context_clear(iommu, info->dev); + domain_context_clear(info); intel_pasid_free_table(info->dev); } From 474dd1c6506411752a9b2f2233eec11f1733a099 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 12 Jul 2021 15:17:12 +0800 Subject: [PATCH 0349/1469] iommu/vt-d: Fix clearing real DMA device's scalable-mode context entries The commit 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") fixes an issue of "sub-device is removed where the context entry is cleared for all aliases". But this commit didn't consider the PASID entry and PASID table in VT-d scalable mode. This fix increases the coverage of scalable mode. Suggested-by: Sanjay Kumar Fixes: 8038bdb855331 ("iommu/vt-d: Only clear real DMA device's context entries") Fixes: 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") Cc: stable@vger.kernel.org # v5.6+ Cc: Jon Derrick Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210712071712.3416949-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 57270290d62b..dd22fc7d5176 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4472,14 +4472,13 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) iommu = info->iommu; domain = info->domain; - if (info->dev) { + if (info->dev && !dev_is_real_dma_subdevice(info->dev)) { if (dev_is_pci(info->dev) && sm_supported(iommu)) intel_pasid_tear_down_entry(iommu, info->dev, PASID_RID2PASID, false); iommu_disable_dev_iotlb(info); - if (!dev_is_real_dma_subdevice(info->dev)) - domain_context_clear(info); + domain_context_clear(info); intel_pasid_free_table(info->dev); } From c987b65a574fad8b598d6f58f010d8f630327428 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 12 Jul 2021 12:12:32 +0200 Subject: [PATCH 0350/1469] iommu/rockchip: Fix physical address decoding Restore bits 39 to 32 at correct position. It reverses the operation done in rk_dma_addr_dte_v2(). Fixes: c55356c534aa ("iommu: rockchip: Add support for iommu v2") Reported-by: Dan Carpenter Signed-off-by: Benjamin Gaignard Link: https://lore.kernel.org/r/20210712101232.318589-1-benjamin.gaignard@collabora.com Signed-off-by: Joerg Roedel --- drivers/iommu/rockchip-iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 94b9d8e5b9a4..9febfb7f3025 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -544,12 +544,14 @@ static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma) } #define DT_HI_MASK GENMASK_ULL(39, 32) +#define DTE_BASE_HI_MASK GENMASK(11, 4) #define DT_SHIFT 28 static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr) { - return (phys_addr_t)(addr & RK_DTE_PT_ADDRESS_MASK) | - ((addr & DT_HI_MASK) << DT_SHIFT); + u64 addr64 = addr; + return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) | + ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT); } static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma) From aa21548e34c19c12e924c736f3fd9e6a4d0f5419 Mon Sep 17 00:00:00 2001 From: Sathya Prakash M R Date: Mon, 12 Jul 2021 15:16:20 -0500 Subject: [PATCH 0351/1469] ASoC: SOF: Intel: Update ADL descriptor to use ACPI power states The ADL descriptor was missing an ACPI power setting, causing the DSP to enter D3 even with a D0i1-compatible wake-on-voice/hotwording capture stream. Fixes: 4ad03f894b3c ('ASoC: SOF: Intel: Update ADL P to use its own descriptor') Reviewed-by: Ranjani Sridharan Signed-off-by: Sathya Prakash M R Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210712201620.44311-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/intel/pci-tgl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c index a00262184efa..d04ce84fe7cc 100644 --- a/sound/soc/sof/intel/pci-tgl.c +++ b/sound/soc/sof/intel/pci-tgl.c @@ -89,6 +89,7 @@ static const struct sof_dev_desc adls_desc = { static const struct sof_dev_desc adl_desc = { .machines = snd_soc_acpi_intel_adl_machines, .alt_machines = snd_soc_acpi_intel_adl_sdw_machines, + .use_acpi_target_states = true, .resindex_lpe_base = 0, .resindex_pcicfg_base = -1, .resindex_imr_base = -1, From 9431f8df233f808baa5fcc62b520cc6503fdf022 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 13 Jul 2021 15:04:17 +0100 Subject: [PATCH 0352/1469] ASoC: codecs: wcd938x: make sdw dependency explicit in Kconfig currenlty wcd938x has only soundwire interface and depends on symbols from wcd938x soundwire module, so make this dependency explicit in Kconfig Without this one of the randconfig endup setting CONFIG_SND_SOC_WCD938X=y CONFIG_SND_SOC_WCD938X_SDW=m resulting in some undefined reference to wcd938x_sdw* symbols. Reported-by: kernel test robot Fixes: 045442228868 ("ASoC: codecs: wcd938x: add audio routing and Kconfig") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210713140417.23693-1-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 3a42c4611414..032c87637f63 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1557,6 +1557,7 @@ config SND_SOC_WCD934X Qualcomm SoCs like SDM845. config SND_SOC_WCD938X + depends on SND_SOC_WCD938X_SDW tristate config SND_SOC_WCD938X_SDW From c934fec1c32840224fd975544c347823962193b2 Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Tue, 13 Jul 2021 19:42:48 +0800 Subject: [PATCH 0353/1469] spi: mediatek: move devm_spi_register_master position This patch move devm_spi_register_master to the end of mtk_spi_probe. If slaves call spi_sync in there probe function, master should have probe done. Signed-off-by: Mason Zhang Link: https://lore.kernel.org/r/20210713114247.1536-1-mason.zhang@mediatek.com Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 8d5fa7f1e506..68dca8ceb3ad 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -803,12 +803,6 @@ static int mtk_spi_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); - ret = devm_spi_register_master(&pdev->dev, master); - if (ret) { - dev_err(&pdev->dev, "failed to register master (%d)\n", ret); - goto err_disable_runtime_pm; - } - if (mdata->dev_comp->need_pad_sel) { if (mdata->pad_num != master->num_chipselect) { dev_err(&pdev->dev, @@ -848,6 +842,12 @@ static int mtk_spi_probe(struct platform_device *pdev) dev_notice(&pdev->dev, "SPI dma_set_mask(%d) failed, ret:%d\n", addr_bits, ret); + ret = devm_spi_register_master(&pdev->dev, master); + if (ret) { + dev_err(&pdev->dev, "failed to register master (%d)\n", ret); + goto err_disable_runtime_pm; + } + return 0; err_disable_runtime_pm: From 0abb33bfca0fb74df76aac03e90ce685016ef7be Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 13 Jul 2021 14:04:31 +0100 Subject: [PATCH 0354/1469] drm/i915/gtt: drop the page table optimisation We skip filling out the pt with scratch entries if the va range covers the entire pt, since we later have to fill it with the PTEs for the object pages anyway. However this might leave open a small window where the PTEs don't point to anything valid for the HW to consume. When for example using 2M GTT pages this fill_px() showed up as being quite significant in perf measurements, and ends up being completely wasted since we ignore the pt and just use the pde directly. Anyway, currently we have our PTE construction split between alloc and insert, which is probably slightly iffy nowadays, since the alloc doesn't actually allocate anything anymore, instead it just sets up the page directories and points the PTEs at the scratch page. Later when we do the insert step we re-program the PTEs again. Better might be to squash the alloc and insert into a single step, then bringing back this optimisation(along with some others) should be possible. Fixes: 14826673247e ("drm/i915: Only initialize partially filled pagetables") Signed-off-by: Matthew Auld Cc: Jon Bloomfield Cc: Chris Wilson Cc: Daniel Vetter Cc: # v4.15+ Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210713130431.2392740-1-matthew.auld@intel.com (cherry picked from commit 8f88ca76b3942d82e2c1cea8735ec368d89ecc15) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 21c8b7350b7a..da4f5eb43ac2 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -303,10 +303,7 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm, __i915_gem_object_pin_pages(pt->base); i915_gem_object_make_unshrinkable(pt->base); - if (lvl || - gen8_pt_count(*start, end) < I915_PDES || - intel_vgpu_active(vm->i915)) - fill_px(pt, vm->scratch[lvl]->encode); + fill_px(pt, vm->scratch[lvl]->encode); spin_lock(&pd->lock); if (likely(!pd->entry[idx])) { From 49afa7f6c714ab3f5cb2a4c835f7f9dddc0bb2c1 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:36:58 +0800 Subject: [PATCH 0355/1469] perf pmu: Skip invalid hybrid pmu On hybrid platform, such as Alderlake, if atom CPUs are offlined, the kernel still exports the sysfs path '/sys/devices/cpu_atom/' for 'cpu_atom' pmu but the file '/sys/devices/cpu_atom/cpus' is empty, which indicates this is an invalid pmu. Need to check and skip the invalid hybrid pmu. Before: # perf list ... branch-instructions OR cpu_atom/branch-instructions/ [Kernel PMU event] branch-instructions OR cpu_core/branch-instructions/ [Kernel PMU event] branch-misses OR cpu_atom/branch-misses/ [Kernel PMU event] branch-misses OR cpu_core/branch-misses/ [Kernel PMU event] bus-cycles OR cpu_atom/bus-cycles/ [Kernel PMU event] bus-cycles OR cpu_core/bus-cycles/ [Kernel PMU event] ... The cpu_atom events are still displayed even if atom CPUs are offlined. After: # perf list ... branch-instructions OR cpu_core/branch-instructions/ [Kernel PMU event] branch-misses OR cpu_core/branch-misses/ [Kernel PMU event] bus-cycles OR cpu_core/bus-cycles/ [Kernel PMU event] ... Now only cpu_core events are displayed. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-2-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 44b90d638ad5..a1bd7007a8b4 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -950,6 +950,13 @@ static struct perf_pmu *pmu_lookup(const char *name) LIST_HEAD(format); LIST_HEAD(aliases); __u32 type; + bool is_hybrid = perf_pmu__hybrid_mounted(name); + + /* + * Check pmu name for hybrid and the pmu may be invalid in sysfs + */ + if (!strncmp(name, "cpu_", 4) && !is_hybrid) + return NULL; /* * The pmu data we store & need consists of the pmu @@ -978,7 +985,7 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->is_uncore = pmu_is_uncore(name); if (pmu->is_uncore) pmu->id = pmu_id(name); - pmu->is_hybrid = perf_pmu__hybrid_mounted(name); + pmu->is_hybrid = is_hybrid; pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); From 490e9a8fb4a3d74602668ef2e4cc29608e9b00a6 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:36:59 +0800 Subject: [PATCH 0356/1469] perf tests: Fix 'Parse event definition strings' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. We don't need the test case for 'cpu_atom'. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-3-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 56a7b6a14195..8d4866739255 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -6,6 +6,7 @@ #include "tests.h" #include "debug.h" #include "pmu.h" +#include "pmu-hybrid.h" #include #include #include @@ -1596,6 +1597,13 @@ static int test__hybrid_raw1(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + if (!perf_pmu__hybrid_mounted("cpu_atom")) { + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); + return 0; + } + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); @@ -1620,13 +1628,9 @@ static int test__hybrid_cache_event(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff)); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x10002 == (evsel->core.attr.config & 0xffffffff)); return 0; } @@ -2028,7 +2032,7 @@ static struct evlist_test test__hybrid_events[] = { .id = 7, }, { - .name = "cpu_core/LLC-loads/,cpu_atom/LLC-load-misses/", + .name = "cpu_core/LLC-loads/", .check = test__hybrid_cache_event, .id = 8, }, From 212f3d97abc8be09549de12cedb290f47b4dce5a Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:37:00 +0800 Subject: [PATCH 0357/1469] perf tests: Fix 'Roundtrip evsel->name' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. Perf will not create two events for one hw event, so the evsel->idx doesn't need to be divided by 2 before comparing. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-4-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/evsel-roundtrip-name.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 5ebf56331904..4e09f0a312af 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -5,6 +5,7 @@ #include "tests.h" #include "debug.h" #include "pmu.h" +#include "pmu-hybrid.h" #include #include @@ -102,7 +103,7 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int { int err = 0, ret = 0; - if (perf_pmu__has_hybrid()) + if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) return perf_evsel__name_array_test(evsel__hw_names, 2); err = perf_evsel__name_array_test(evsel__hw_names, 1); From de3d5fd83c9b1099b0d207b41a222dc451184a63 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:37:01 +0800 Subject: [PATCH 0358/1469] perf tests: Fix 'Convert perf time to TSC' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. We don't need the test case for 'cpu_atom'. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-time-to-tsc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 85d75b9b25a1..7c56bc1f4cff 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -21,6 +21,7 @@ #include "mmap.h" #include "tests.h" #include "pmu.h" +#include "pmu-hybrid.h" #define CHECK__(x) { \ while ((x) < 0) { \ @@ -93,7 +94,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe * For hybrid "cycles:u", it creates two events. * Init the second evsel here. */ - if (perf_pmu__has_hybrid()) { + if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) { evsel = evsel__next(evsel); evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; From e0a7ef2a62e4f61a751bccfc79b9e7acb51474de Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 7 Jul 2021 13:56:52 +0800 Subject: [PATCH 0359/1469] perf stat: Merge uncore events by default for hybrid platform On a hybrid platform, by default 'perf stat' aggregates and reports the event counts per PMU. For example, # perf stat -e cycles -a true Performance counter stats for 'system wide': 1,400,445 cpu_core/cycles/ 680,881 cpu_atom/cycles/ 0.001770773 seconds time elapsed But for uncore events that's not a suitable method. Uncore has nothing to do with hybrid. So for uncore events, we aggregate event counts from all PMUs and report the counts without PMUs. Before: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 2,058 uncore_arb_0/event=0x81,umask=0x1/ 2,028 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000614498 seconds time elapsed After: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 3,996 arb/event=0x81,umask=0x1/ 0 arb/event=0x84,umask=0x1/ 0.000630046 seconds time elapsed Of course, we also keep the '--no-merge' working for uncore events. # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ --no-merge true Performance counter stats for 'system wide': 1,952 uncore_arb_0/event=0x81,umask=0x1/ 1,921 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000575536 seconds time elapsed Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Kan Liang Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20210707055652.962-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 3 --- tools/perf/util/stat-display.c | 14 +++++++++++++- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d25cb8088e8c..634375937db9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2445,9 +2445,6 @@ int cmd_stat(int argc, const char **argv) evlist__check_cpu_maps(evsel_list); - if (perf_pmu__has_hybrid()) - stat_config.no_merge = true; - /* * Initialize thread_map with comm names, * so we could print it out on output. diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 83a2bc02df15..588601000f3f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -596,6 +596,18 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c } } +static bool is_uncore(struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + return pmu && pmu->is_uncore; +} + +static bool hybrid_uniquify(struct evsel *evsel) +{ + return perf_pmu__has_hybrid() && !is_uncore(evsel); +} + static bool collect_data(struct perf_stat_config *config, struct evsel *counter, void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), @@ -604,7 +616,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter, if (counter->merged_stat) return false; cb(config, counter, data, true); - if (config->no_merge) + if (config->no_merge || hybrid_uniquify(counter)) uniquify_event_name(counter); else if (counter->auto_merge_stats) collect_all_aliases(config, counter, cb, data); From 376a947653f6214f397ef1c5aa2b7b7fc7b68c49 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:55:30 -0300 Subject: [PATCH 0360/1469] tools headers UAPI: Sync files changed by the memfd_secret new syscall To pick the changes in this cset: 7bb7f2ac24a028b2 ("arch, mm: wire up memfd_secret system call where relevant") That silences these perf build warnings and add support for those new syscalls in tools such as 'perf trace'. For instance, this is now possible: # perf trace -v -e memfd_secret event qualifier tracepoint filter: (common_pid != 13375 && common_pid != 3713) && (id == 447) ^C# That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep memfd_secret tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 447 common memfd_secret sys_memfd_secret $ This addresses these perf build warnings: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h' diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Cc: Linus Torvalds Cc: Mike Rapoport Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/unistd.h | 1 + tools/include/uapi/asm-generic/unistd.h | 7 ++++++- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index f83a70e07df8..ce2ee8f1e361 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -20,5 +20,6 @@ #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #define __ARCH_WANT_SYS_CLONE3 +#define __ARCH_WANT_MEMFD_SECRET #include diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index f211961ce1da..a9d6fcd95f42 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -873,8 +873,13 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) #define __NR_landlock_restrict_self 446 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) +#ifdef __ARCH_WANT_MEMFD_SECRET +#define __NR_memfd_secret 447 +__SYSCALL(__NR_memfd_secret, sys_memfd_secret) +#endif + #undef __NR_syscalls -#define __NR_syscalls 447 +#define __NR_syscalls 448 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index af973e400053..f6b57799c1ea 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -368,6 +368,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +447 common memfd_secret sys_memfd_secret # # Due to a historical design error, certain syscalls are numbered differently From 50e98924d72dc730fe1f1646977205adf608dccd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 13 Jul 2021 11:19:07 +0200 Subject: [PATCH 0361/1469] libperf: Fix build error with LIBPFM4=1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix build error with LIBPFM4=1: CC util/pfm.o util/pfm.c: In function ‘parse_libpfm_events_option’: util/pfm.c:102:30: error: ‘struct evsel’ has no member named ‘leader’ 102 | evsel->leader = grp_leader; | ^~ Committer notes: There is this entry in 'make -C tools/perf build-test' to test the build with libpfm: $ grep libpfm tools/perf/tests/make make_with_libpfm4 := LIBPFM4=1 run += make_with_libpfm4 $ But the test machine lacked libpfm-devel, now its installed and further cases like this shouldn't happen. Committer testing: Before this patch this fails, after applying it: $ make -C tools/perf build-test make: Entering directory '/var/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . make_static: make LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 -j24 DESTDIR=/tmp/tmp.KzFSfvGRQa make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1 make_with_libpfm4_O: make LIBPFM4=1 make_install_prefix_O: make install prefix=/tmp/krava make_no_auxtrace_O: make NO_AUXTRACE=1 $ rpm -q libpfm-devel libpfm-devel-4.11.0-4.fc34.x86_64 $ FIXME: This shows a need for 'build-test' to bail out when a build option is specified that has no required library devel files installed. Fixes: fba7c86601e2e42d ("libperf: Move 'leader' from tools/perf to perf_evsel::leader") Signed-off-by: Heiko Carstens Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210713091907.1555560-1-hca@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pfm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index dd9ed56e0504..756295dedccc 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -99,7 +99,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_leader = evsel; if (grp_evt > -1) { - evsel->leader = grp_leader; + evsel__set_leader(evsel, grp_leader); grp_leader->core.nr_members++; grp_evt++; } From 95d429206c97cf109591009fa386004191c62c47 Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Mon, 28 Jun 2021 18:28:46 -0400 Subject: [PATCH 0362/1469] platform/x86: think-lmi: Add pending_reboot support The Think-lmi driver was missing pending_reboot support as it wasn't available from the BIOS. Turns out this is really useful to have from user space so implementing from a purely SW point of view. Thanks to Mario Limonciello for guidance on how fwupd would use this. Suggested-by: Mario Limonciello Signed-off-by: Mark Pearson Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210628222846.8830-1-markpearson@lenovo.com Signed-off-by: Hans de Goede --- drivers/platform/x86/think-lmi.c | 19 +++++++++++++++++++ drivers/platform/x86/think-lmi.h | 1 + 2 files changed, 20 insertions(+) diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 3671b5d20613..64dcec53a7a0 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -571,6 +571,11 @@ static ssize_t current_value_store(struct kobject *kobj, else ret = tlmi_save_bios_settings(""); + if (!ret && !tlmi_priv.pending_changes) { + tlmi_priv.pending_changes = true; + /* let userland know it may need to check reboot pending again */ + kobject_uevent(&tlmi_priv.class_dev->kobj, KOBJ_CHANGE); + } out: kfree(auth_str); kfree(set_str); @@ -647,6 +652,14 @@ static struct kobj_type tlmi_pwd_setting_ktype = { .sysfs_ops = &tlmi_kobj_sysfs_ops, }; +static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", tlmi_priv.pending_changes); +} + +static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot); + /* ---- Initialisation --------------------------------------------------------- */ static void tlmi_release_attr(void) { @@ -667,6 +680,7 @@ static void tlmi_release_attr(void) sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group); kobject_put(&tlmi_priv.pwd_power->kobj); kset_unregister(tlmi_priv.authentication_kset); + sysfs_remove_file(&tlmi_priv.class_dev->kobj, &pending_reboot.attr); } static int tlmi_sysfs_init(void) @@ -746,6 +760,11 @@ static int tlmi_sysfs_init(void) if (ret) goto fail_create_attr; + /* Create global sysfs files */ + ret = sysfs_create_file(&tlmi_priv.class_dev->kobj, &pending_reboot.attr); + if (ret) + goto fail_create_attr; + return ret; fail_create_attr: diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index 6fa8da7af6c7..eb598846628a 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -60,6 +60,7 @@ struct think_lmi { bool can_get_bios_selections; bool can_set_bios_password; bool can_get_password_settings; + bool pending_changes; struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT]; struct device *class_dev; From 95e1b60f8dc8f225b14619e9aca9bdd7d99167db Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:17:57 +0530 Subject: [PATCH 0363/1469] platform/x86: amd-pmc: Fix command completion code The protocol to submit a job request to SMU is to wait for AMD_PMC_REGISTER_RESPONSE to return 1,meaning SMU is ready to take requests. PMC driver has to make sure that the response code is always AMD_PMC_RESULT_OK before making any command submissions. When we submit a message to SMU, we have to wait until it processes the request. Adding a read_poll_timeout() check as this was missing in the existing code. Also, add a mutex to protect amd_pmc_send_cmd() calls to SMU. Fixes: 156ec4731cb2 ("platform/x86: amd-pmc: Add AMD platform support for S2Idle") Signed-off-by: Shyam Sundar S K Acked-by: Raul E Rangel Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-2-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 38 ++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index b9da58ee9b1e..1b5f149932c1 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -68,6 +68,7 @@ struct amd_pmc_dev { u32 base_addr; u32 cpu_id; struct device *dev; + struct mutex lock; /* generic mutex lock */ #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ @@ -138,9 +139,10 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) u8 msg; u32 val; + mutex_lock(&dev->lock); /* Wait until we get a valid response */ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE, - val, val > 0, PMC_MSG_DELAY_MIN_US, + val, val != 0, PMC_MSG_DELAY_MIN_US, PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "failed to talk to SMU\n"); @@ -156,7 +158,37 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) /* Write message ID to message ID register */ msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO; amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg); - return 0; + /* Wait until we get a valid response */ + rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE, + val, val != 0, PMC_MSG_DELAY_MIN_US, + PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); + if (rc) { + dev_err(dev->dev, "SMU response timed out\n"); + goto out_unlock; + } + + switch (val) { + case AMD_PMC_RESULT_OK: + break; + case AMD_PMC_RESULT_CMD_REJECT_BUSY: + dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val); + rc = -EBUSY; + goto out_unlock; + case AMD_PMC_RESULT_CMD_UNKNOWN: + dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val); + rc = -EINVAL; + goto out_unlock; + case AMD_PMC_RESULT_CMD_REJECT_PREREQ: + case AMD_PMC_RESULT_FAILED: + default: + dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val); + rc = -EIO; + goto out_unlock; + } + +out_unlock: + mutex_unlock(&dev->lock); + return rc; } static int __maybe_unused amd_pmc_suspend(struct device *dev) @@ -259,6 +291,7 @@ static int amd_pmc_probe(struct platform_device *pdev) amd_pmc_dump_registers(dev); + mutex_init(&dev->lock); platform_set_drvdata(pdev, dev); amd_pmc_dbgfs_register(dev); return 0; @@ -269,6 +302,7 @@ static int amd_pmc_remove(struct platform_device *pdev) struct amd_pmc_dev *dev = platform_get_drvdata(pdev); amd_pmc_dbgfs_unregister(dev); + mutex_destroy(&dev->lock); return 0; } From 4c06d35dfedf4c1fd03702e0f05292a69d020e21 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:17:58 +0530 Subject: [PATCH 0364/1469] platform/x86: amd-pmc: Fix SMU firmware reporting mechanism It was lately understood that the current mechanism available in the driver to get SMU firmware info works only on internal SMU builds and there is a separate way to get all the SMU logging counters (addressed in the next patch). Hence remove all the smu info shown via debugfs as it is no more useful. Fixes: 156ec4731cb2 ("platform/x86: amd-pmc: Add AMD platform support for S2Idle") Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-3-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 1b5f149932c1..b1d6175a13b2 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -52,7 +52,6 @@ #define AMD_CPU_ID_PCO AMD_CPU_ID_RV #define AMD_CPU_ID_CZN AMD_CPU_ID_RN -#define AMD_SMU_FW_VERSION 0x0 #define PMC_MSG_DELAY_MIN_US 100 #define RESPONSE_REGISTER_LOOP_MAX 200 @@ -89,11 +88,6 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3 #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) { - struct amd_pmc_dev *dev = s->private; - u32 value; - - value = ioread32(dev->smu_base + AMD_SMU_FW_VERSION); - seq_printf(s, "SMU FW Info: %x\n", value); return 0; } DEFINE_SHOW_ATTRIBUTE(smu_fw_info); @@ -280,10 +274,6 @@ static int amd_pmc_probe(struct platform_device *pdev) pci_dev_put(rdev); base_addr = ((u64)base_addr_hi << 32 | base_addr_lo); - dev->smu_base = devm_ioremap(dev->dev, base_addr, AMD_PMC_MAPPING_SIZE); - if (!dev->smu_base) - return -ENOMEM; - dev->regbase = devm_ioremap(dev->dev, base_addr + AMD_PMC_BASE_ADDR_OFFSET, AMD_PMC_MAPPING_SIZE); if (!dev->regbase) From 162b937a8064029ed22cd1039d4dcf7f1721f940 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:17:59 +0530 Subject: [PATCH 0365/1469] platform/x86: amd-pmc: call dump registers only once Currently amd_pmc_dump_registers() routine is being called at multiple places. The best to call it is after command submission to SMU. Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-4-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index b1d6175a13b2..e5107e3b1911 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -182,6 +182,7 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) out_unlock: mutex_unlock(&dev->lock); + amd_pmc_dump_registers(dev); return rc; } @@ -194,7 +195,6 @@ static int __maybe_unused amd_pmc_suspend(struct device *dev) if (rc) dev_err(pdev->dev, "suspend failed\n"); - amd_pmc_dump_registers(pdev); return 0; } @@ -207,7 +207,6 @@ static int __maybe_unused amd_pmc_resume(struct device *dev) if (rc) dev_err(pdev->dev, "resume failed\n"); - amd_pmc_dump_registers(pdev); return 0; } @@ -279,8 +278,6 @@ static int amd_pmc_probe(struct platform_device *pdev) if (!dev->regbase) return -ENOMEM; - amd_pmc_dump_registers(dev); - mutex_init(&dev->lock); platform_set_drvdata(pdev, dev); amd_pmc_dbgfs_register(dev); From 76620567496237f1f1f54683ec7da1755ee501d7 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:18:00 +0530 Subject: [PATCH 0366/1469] platform/x86: amd-pmc: Add support for logging SMU metrics SMU provides a way to dump the s0ix debug statistics in the form of a metrics table via a of set special mailbox commands. Add support to the driver which can send these commands to SMU and expose the information received via debugfs. The information contains the s0ix entry/exit, active time of each IP block etc. As a side note, SMU subsystem logging is not supported on Picasso based SoC's. Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-5-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 147 +++++++++++++++++++++++++++++++-- 1 file changed, 139 insertions(+), 8 deletions(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index e5107e3b1911..0ebb2732c46a 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -46,6 +46,14 @@ #define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE #define AMD_PMC_RESULT_FAILED 0xFF +/* SMU Message Definations */ +#define SMU_MSG_GETSMUVERSION 0x02 +#define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04 +#define SMU_MSG_LOG_GETDRAM_ADDR_LO 0x05 +#define SMU_MSG_LOG_START 0x06 +#define SMU_MSG_LOG_RESET 0x07 +#define SMU_MSG_LOG_DUMP_DATA 0x08 +#define SMU_MSG_GET_SUP_CONSTRAINTS 0x09 /* List of supported CPU ids */ #define AMD_CPU_ID_RV 0x15D0 #define AMD_CPU_ID_RN 0x1630 @@ -55,17 +63,42 @@ #define PMC_MSG_DELAY_MIN_US 100 #define RESPONSE_REGISTER_LOOP_MAX 200 +#define SOC_SUBSYSTEM_IP_MAX 12 +#define DELAY_MIN_US 2000 +#define DELAY_MAX_US 3000 enum amd_pmc_def { MSG_TEST = 0x01, MSG_OS_HINT_PCO, MSG_OS_HINT_RN, }; +struct amd_pmc_bit_map { + const char *name; + u32 bit_mask; +}; + +static const struct amd_pmc_bit_map soc15_ip_blk[] = { + {"DISPLAY", BIT(0)}, + {"CPU", BIT(1)}, + {"GFX", BIT(2)}, + {"VDD", BIT(3)}, + {"ACP", BIT(4)}, + {"VCN", BIT(5)}, + {"ISP", BIT(6)}, + {"NBIO", BIT(7)}, + {"DF", BIT(8)}, + {"USB0", BIT(9)}, + {"USB1", BIT(10)}, + {"LAPIC", BIT(11)}, + {} +}; + struct amd_pmc_dev { void __iomem *regbase; - void __iomem *smu_base; + void __iomem *smu_virt_addr; u32 base_addr; u32 cpu_id; + u32 active_ips; struct device *dev; struct mutex lock; /* generic mutex lock */ #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -74,6 +107,7 @@ struct amd_pmc_dev { }; static struct amd_pmc_dev pmc; +static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret); static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -85,9 +119,49 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3 iowrite32(val, dev->regbase + reg_offset); } +struct smu_metrics { + u32 table_version; + u32 hint_count; + u32 s0i3_cyclecount; + u32 timein_s0i2; + u64 timeentering_s0i3_lastcapture; + u64 timeentering_s0i3_totaltime; + u64 timeto_resume_to_os_lastcapture; + u64 timeto_resume_to_os_totaltime; + u64 timein_s0i3_lastcapture; + u64 timein_s0i3_totaltime; + u64 timein_swdrips_lastcapture; + u64 timein_swdrips_totaltime; + u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX]; + u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX]; +} __packed; + #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) { + struct amd_pmc_dev *dev = s->private; + struct smu_metrics table; + int idx; + + if (dev->cpu_id == AMD_CPU_ID_PCO) + return -EINVAL; + + memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics)); + + seq_puts(s, "\n=== SMU Statistics ===\n"); + seq_printf(s, "Table Version: %d\n", table.table_version); + seq_printf(s, "Hint Count: %d\n", table.hint_count); + seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount); + seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture); + seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture); + + seq_puts(s, "\n=== Active time (in us) ===\n"); + for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) { + if (soc15_ip_blk[idx].bit_mask & dev->active_ips) + seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name, + table.timecondition_notmet_lastcapture[idx]); + } + return 0; } DEFINE_SHOW_ATTRIBUTE(smu_fw_info); @@ -113,6 +187,32 @@ static inline void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) } #endif /* CONFIG_DEBUG_FS */ +static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev) +{ + u32 phys_addr_low, phys_addr_hi; + u64 smu_phys_addr; + + if (dev->cpu_id == AMD_CPU_ID_PCO) + return -EINVAL; + + /* Get Active devices list from SMU */ + amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1); + + /* Get dram address */ + amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1); + amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1); + smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); + + dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics)); + if (!dev->smu_virt_addr) + return -ENOMEM; + + /* Start the logging */ + amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0); + + return 0; +} + static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) { u32 value; @@ -127,10 +227,9 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev) dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value); } -static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) +static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret) { int rc; - u8 msg; u32 val; mutex_lock(&dev->lock); @@ -150,8 +249,8 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set); /* Write message ID to message ID register */ - msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO; amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg); + /* Wait until we get a valid response */ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE, val, val != 0, PMC_MSG_DELAY_MIN_US, @@ -163,6 +262,11 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set) switch (val) { case AMD_PMC_RESULT_OK: + if (ret) { + /* PMFW may take longer time to return back the data */ + usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US); + *data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT); + } break; case AMD_PMC_RESULT_CMD_REJECT_BUSY: dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val); @@ -186,12 +290,29 @@ out_unlock: return rc; } +static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) +{ + switch (dev->cpu_id) { + case AMD_CPU_ID_PCO: + return MSG_OS_HINT_PCO; + case AMD_CPU_ID_RN: + return MSG_OS_HINT_RN; + } + return -EINVAL; +} + static int __maybe_unused amd_pmc_suspend(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); int rc; + u8 msg; - rc = amd_pmc_send_cmd(pdev, 1); + /* Reset and Start SMU logging - to monitor the s0i3 stats */ + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0); + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0); + + msg = amd_pmc_get_os_hint(pdev); + rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0); if (rc) dev_err(pdev->dev, "suspend failed\n"); @@ -202,8 +323,13 @@ static int __maybe_unused amd_pmc_resume(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); int rc; + u8 msg; - rc = amd_pmc_send_cmd(pdev, 0); + /* Let SMU know that we are looking for stats */ + amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0); + + msg = amd_pmc_get_os_hint(pdev); + rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0); if (rc) dev_err(pdev->dev, "resume failed\n"); @@ -226,8 +352,7 @@ static int amd_pmc_probe(struct platform_device *pdev) { struct amd_pmc_dev *dev = &pmc; struct pci_dev *rdev; - u32 base_addr_lo; - u32 base_addr_hi; + u32 base_addr_lo, base_addr_hi; u64 base_addr; int err; u32 val; @@ -279,6 +404,12 @@ static int amd_pmc_probe(struct platform_device *pdev) return -ENOMEM; mutex_init(&dev->lock); + + /* Use SMU to get the s0i3 debug stats */ + err = amd_pmc_setup_smu_logging(dev); + if (err) + dev_err(dev->dev, "SMU debugging info not supported on this platform\n"); + platform_set_drvdata(pdev, dev); amd_pmc_dbgfs_register(dev); return 0; From b9a4fa6978bef902409858737fa180fa7b9346ac Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:18:01 +0530 Subject: [PATCH 0367/1469] platform/x86: amd-pmc: Add support for logging s0ix counters Even the FCH SSC registers provides certain level of information about the s0ix entry and exit times which comes handy when the SMU fails to report the statistics via the mailbox communication. This information is captured via a new debugfs file "s0ix_stats". A non-zero entry in this counters would mean that the system entered the s0ix state. If s0ix entry time and exit time don't change during suspend to idle, the silicon has not entered the deepest state. Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-6-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 45 +++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 0ebb2732c46a..7f011c3f60f2 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -46,6 +46,15 @@ #define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE #define AMD_PMC_RESULT_FAILED 0xFF +/* FCH SSC Registers */ +#define FCH_S0I3_ENTRY_TIME_L_OFFSET 0x30 +#define FCH_S0I3_ENTRY_TIME_H_OFFSET 0x34 +#define FCH_S0I3_EXIT_TIME_L_OFFSET 0x38 +#define FCH_S0I3_EXIT_TIME_H_OFFSET 0x3C +#define FCH_SSC_MAPPING_SIZE 0x800 +#define FCH_BASE_PHY_ADDR_LOW 0xFED81100 +#define FCH_BASE_PHY_ADDR_HIGH 0x00000000 + /* SMU Message Definations */ #define SMU_MSG_GETSMUVERSION 0x02 #define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04 @@ -96,6 +105,7 @@ static const struct amd_pmc_bit_map soc15_ip_blk[] = { struct amd_pmc_dev { void __iomem *regbase; void __iomem *smu_virt_addr; + void __iomem *fch_virt_addr; u32 base_addr; u32 cpu_id; u32 active_ips; @@ -166,6 +176,29 @@ static int smu_fw_info_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(smu_fw_info); +static int s0ix_stats_show(struct seq_file *s, void *unused) +{ + struct amd_pmc_dev *dev = s->private; + u64 entry_time, exit_time, residency; + + entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET); + entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET); + + exit_time = ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_H_OFFSET); + exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET); + + /* It's in 48MHz. We need to convert it */ + residency = (exit_time - entry_time) / 48; + + seq_puts(s, "=== S0ix statistics ===\n"); + seq_printf(s, "S0ix Entry Time: %lld\n", entry_time); + seq_printf(s, "S0ix Exit Time: %lld\n", exit_time); + seq_printf(s, "Residency Time: %lld\n", residency); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(s0ix_stats); + static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev) { debugfs_remove_recursive(dev->dbgfs_dir); @@ -176,6 +209,8 @@ static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL); debugfs_create_file("smu_fw_info", 0644, dev->dbgfs_dir, dev, &smu_fw_info_fops); + debugfs_create_file("s0ix_stats", 0644, dev->dbgfs_dir, dev, + &s0ix_stats_fops); } #else static inline void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev) @@ -353,7 +388,7 @@ static int amd_pmc_probe(struct platform_device *pdev) struct amd_pmc_dev *dev = &pmc; struct pci_dev *rdev; u32 base_addr_lo, base_addr_hi; - u64 base_addr; + u64 base_addr, fch_phys_addr; int err; u32 val; @@ -405,6 +440,14 @@ static int amd_pmc_probe(struct platform_device *pdev) mutex_init(&dev->lock); + /* Use FCH registers to get the S0ix stats */ + base_addr_lo = FCH_BASE_PHY_ADDR_LOW; + base_addr_hi = FCH_BASE_PHY_ADDR_HIGH; + fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo); + dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE); + if (!dev->fch_virt_addr) + return -ENOMEM; + /* Use SMU to get the s0i3 debug stats */ err = amd_pmc_setup_smu_logging(dev); if (err) From 9422584a601ae8e4af51e890a14a936b2b689628 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:18:02 +0530 Subject: [PATCH 0368/1469] platform/x86: amd-pmc: Add support for ACPI ID AMDI0006 Some newer BIOSes have added another ACPI ID for the uPEP device. SMU statistics behave identically on this device. Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-7-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 7f011c3f60f2..c5054fa2aed9 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -469,6 +469,7 @@ static int amd_pmc_remove(struct platform_device *pdev) static const struct acpi_device_id amd_pmc_acpi_ids[] = { {"AMDI0005", 0}, + {"AMDI0006", 0}, {"AMD0004", 0}, { } }; From 83cbaf14275a30f14cf558b09389a1664b173858 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Tue, 29 Jun 2021 14:18:03 +0530 Subject: [PATCH 0369/1469] platform/x86: amd-pmc: Add new acpi id for future PMC controllers The upcoming PMC controller would have a newer acpi id, add that to the supported acpid device list. Signed-off-by: Shyam Sundar S K Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210629084803.248498-8-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index c5054fa2aed9..d2f9a62e1166 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -68,6 +68,7 @@ #define AMD_CPU_ID_RN 0x1630 #define AMD_CPU_ID_PCO AMD_CPU_ID_RV #define AMD_CPU_ID_CZN AMD_CPU_ID_RN +#define AMD_CPU_ID_YC 0x14B5 #define PMC_MSG_DELAY_MIN_US 100 #define RESPONSE_REGISTER_LOOP_MAX 200 @@ -331,6 +332,7 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) case AMD_CPU_ID_PCO: return MSG_OS_HINT_PCO; case AMD_CPU_ID_RN: + case AMD_CPU_ID_YC: return MSG_OS_HINT_RN; } return -EINVAL; @@ -376,6 +378,7 @@ static const struct dev_pm_ops amd_pmc_pm_ops = { }; static const struct pci_device_id pmc_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PCO) }, @@ -470,6 +473,7 @@ static int amd_pmc_remove(struct platform_device *pdev) static const struct acpi_device_id amd_pmc_acpi_ids[] = { {"AMDI0005", 0}, {"AMDI0006", 0}, + {"AMDI0007", 0}, {"AMD0004", 0}, { } }; From a973c983375c37301645d4fea056b1f4bff77bf7 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 7 Jul 2021 09:16:47 -0500 Subject: [PATCH 0370/1469] platform/x86: amd-pmc: Use return code on suspend Right now the driver will still return success even if the OS_HINT command failed to send to the SMU. In the rare event of a failure, the suspend should really be aborted here so that relevant logs can may be captured. Signed-off-by: Mario Limonciello Acked-by: Shyam Sundar S K Link: https://lore.kernel.org/r/20210707141647.8871-1-mario.limonciello@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index d2f9a62e1166..680f94c7e075 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -353,7 +353,7 @@ static int __maybe_unused amd_pmc_suspend(struct device *dev) if (rc) dev_err(pdev->dev, "suspend failed\n"); - return 0; + return rc; } static int __maybe_unused amd_pmc_resume(struct device *dev) From 506c1da44fee32ba1d3a70413289ad58c772bba6 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 18 May 2021 15:05:50 +0000 Subject: [PATCH 0371/1469] cifs: use the expiry output of dns_query to schedule next resolution We recently fixed DNS resolution of the server hostname during reconnect. However, server IP address may change, even when the old one continues to server (although sub-optimally). We should schedule the next DNS resolution based on the TTL of the DNS record used for the last resolution. This way, we resolve the server hostname again when a DNS record expires. Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Cc: # v5.11+ Signed-off-by: Steve French --- fs/cifs/cifs_dfs_ref.c | 2 +- fs/cifs/cifsglob.h | 4 +++ fs/cifs/connect.c | 55 +++++++++++++++++++++++++++++++++++++++--- fs/cifs/dns_resolve.c | 10 +++++--- fs/cifs/dns_resolve.h | 2 +- fs/cifs/misc.c | 2 +- 6 files changed, 65 insertions(+), 10 deletions(-) diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 57f91311fdaa..fa131da01a5f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -176,7 +176,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, } } - rc = dns_resolve_server_name_to_ip(name, &srvIP); + rc = dns_resolve_server_name_to_ip(name, &srvIP, NULL); if (rc < 0) { cifs_dbg(FYI, "%s: Failed to resolve server part of %s to IP: %d\n", __func__, name, rc); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 3c2e117bb926..ade7080f7eaa 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -75,6 +75,9 @@ #define SMB_ECHO_INTERVAL_MAX 600 #define SMB_ECHO_INTERVAL_DEFAULT 60 +/* dns resolution interval in seconds */ +#define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600 + /* maximum number of PDUs in one compound */ #define MAX_COMPOUND 5 @@ -646,6 +649,7 @@ struct TCP_Server_Info { /* point to the SMBD connection if RDMA is used instead of socket */ struct smbd_connection *smbd_conn; struct delayed_work echo; /* echo ping workqueue job */ + struct delayed_work resolve; /* dns resolution workqueue job */ char *smallbuf; /* pointer to current "small" buffer */ char *bigbuf; /* pointer to current "big" buffer */ /* Total size of this PDU. Only valid from cifs_demultiplex_thread */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 01dc45178f66..f1a7e63ab58f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -78,6 +78,8 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) int rc; int len; char *unc, *ipaddr = NULL; + time64_t expiry, now; + unsigned long ttl = SMB_DNS_RESOLVE_INTERVAL_DEFAULT; if (!server->hostname) return -EINVAL; @@ -91,13 +93,13 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) } scnprintf(unc, len, "\\\\%s", server->hostname); - rc = dns_resolve_server_name_to_ip(unc, &ipaddr); + rc = dns_resolve_server_name_to_ip(unc, &ipaddr, &expiry); kfree(unc); if (rc < 0) { cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", __func__, server->hostname, rc); - return rc; + goto requeue_resolve; } spin_lock(&cifs_tcp_ses_lock); @@ -106,7 +108,45 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); kfree(ipaddr); - return !rc ? -1 : 0; + /* rc == 1 means success here */ + if (rc) { + now = ktime_get_real_seconds(); + if (expiry && expiry > now) + /* + * To make sure we don't use the cached entry, retry 1s + * after expiry. + */ + ttl = (expiry - now + 1); + } + rc = !rc ? -1 : 0; + +requeue_resolve: + cifs_dbg(FYI, "%s: next dns resolution scheduled for %lu seconds in the future\n", + __func__, ttl); + mod_delayed_work(cifsiod_wq, &server->resolve, (ttl * HZ)); + + return rc; +} + + +static void cifs_resolve_server(struct work_struct *work) +{ + int rc; + struct TCP_Server_Info *server = container_of(work, + struct TCP_Server_Info, resolve.work); + + mutex_lock(&server->srv_mutex); + + /* + * Resolve the hostname again to make sure that IP address is up-to-date. + */ + rc = reconn_set_ipaddr_from_hostname(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } + + mutex_unlock(&server->srv_mutex); } #ifdef CONFIG_CIFS_DFS_UPCALL @@ -680,6 +720,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); cancel_delayed_work_sync(&server->echo); + cancel_delayed_work_sync(&server->resolve); spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; @@ -1260,6 +1301,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) spin_unlock(&cifs_tcp_ses_lock); cancel_delayed_work_sync(&server->echo); + cancel_delayed_work_sync(&server->resolve); if (from_reconnect) /* @@ -1342,6 +1384,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); + INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); memcpy(&tcp_ses->srcaddr, &ctx->srcaddr, @@ -1427,6 +1470,12 @@ smbd_connected: /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); + /* queue dns resolution delayed work */ + cifs_dbg(FYI, "%s: next dns resolution scheduled for %d seconds in the future\n", + __func__, SMB_DNS_RESOLVE_INTERVAL_DEFAULT); + + queue_delayed_work(cifsiod_wq, &tcp_ses->resolve, (SMB_DNS_RESOLVE_INTERVAL_DEFAULT * HZ)); + return tcp_ses; out_err_crypto_release: diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index d15b82d569ef..8c616aaeb7c4 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -24,6 +24,7 @@ * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. * @unc: UNC path specifying the server (with '/' as delimiter) * @ip_addr: Where to return the IP address. + * @expiry: Where to return the expiry time for the dns record. * * The IP address will be returned in string form, and the caller is * responsible for freeing it. @@ -31,7 +32,7 @@ * Returns length of result on success, -ve on error. */ int -dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) +dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry) { struct sockaddr_storage ss; const char *hostname, *sep; @@ -66,13 +67,14 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) /* Perform the upcall */ rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len, - NULL, ip_addr, NULL, false); + NULL, ip_addr, expiry, false); if (rc < 0) cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", __func__, len, len, hostname); else - cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n", - __func__, len, len, hostname, *ip_addr); + cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n", + __func__, len, len, hostname, *ip_addr, + expiry ? (*expiry) : 0); return rc; name_is_IP_address: diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 5be060b82b13..9fa2807ef79e 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -12,7 +12,7 @@ #define _DNS_RESOLVE_H #ifdef __KERNEL__ -extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr); +extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry); #endif /* KERNEL */ #endif /* _DNS_RESOLVE_H */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 184138b4eb8c..844abeb2b48f 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1187,7 +1187,7 @@ int match_target_ip(struct TCP_Server_Info *server, cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2); - rc = dns_resolve_server_name_to_ip(target, &tip); + rc = dns_resolve_server_name_to_ip(target, &tip, NULL); if (rc < 0) goto out; From 50630b3f1ada0bf412d3f28e73bac310448d9d6f Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 13 Jul 2021 12:22:59 +1000 Subject: [PATCH 0372/1469] cifs: Do not use the original cruid when following DFS links for multiuser mounts Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=213565 cruid should only be used for the initial mount and after this we should use the current users credentials. Ignore the original cruid mount argument when creating a new context for a multiuser mount following a DFS link. Fixes: 24e0a1eff9e2 ("cifs: switch to new mount api") Cc: stable@vger.kernel.org # 5.11+ Reported-by: Xiaoli Feng Signed-off-by: Ronnie Sahlberg Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifs_dfs_ref.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index fa131da01a5f..007427ba75e5 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -211,6 +211,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, else noff = tkn_e - (sb_mountdata + off) + 1; + if (strncasecmp(sb_mountdata + off, "cruid=", 6) == 0) { + off += noff; + continue; + } if (strncasecmp(sb_mountdata + off, "unc=", 4) == 0) { off += noff; continue; From c9c9c6815f9004ee1ec87401ed0796853bd70f1b Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Mon, 12 Jul 2021 19:34:02 +0900 Subject: [PATCH 0373/1469] cifs: fix the out of range assignment to bit fields in parse_server_interfaces Because the out of range assignment to bit fields are compiler-dependant, the fields could have wrong value. Signed-off-by: Hyunchul Lee Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e4c8f603dd58..232d528df230 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -557,8 +557,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, p = buf; while (bytes_left >= sizeof(*p)) { info->speed = le64_to_cpu(p->LinkSpeed); - info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE); - info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE); + info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; + info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0; cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count); cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed); From 9e5c772954406829e928dbe59891d08938ead04b Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Wed, 14 Jul 2021 14:54:19 +0000 Subject: [PATCH 0374/1469] drm/ttm: add a check against null pointer dereference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When calling ttm_range_man_fini(), 'man' may be uninitialized, which may cause a null pointer dereference bug. Fix this by checking if it is a null pointer. This log reveals it: [ 7.902580 ] BUG: kernel NULL pointer dereference, address: 0000000000000058 [ 7.905721 ] RIP: 0010:ttm_range_man_fini+0x40/0x160 [ 7.911826 ] Call Trace: [ 7.911826 ] radeon_ttm_fini+0x167/0x210 [ 7.911826 ] radeon_bo_fini+0x15/0x40 [ 7.913767 ] rs400_fini+0x55/0x80 [ 7.914358 ] radeon_device_fini+0x3c/0x140 [ 7.914358 ] radeon_driver_unload_kms+0x5c/0xe0 [ 7.914358 ] radeon_driver_load_kms+0x13a/0x200 [ 7.914358 ] ? radeon_driver_unload_kms+0xe0/0xe0 [ 7.914358 ] drm_dev_register+0x1db/0x290 [ 7.914358 ] radeon_pci_probe+0x16a/0x230 [ 7.914358 ] local_pci_probe+0x4a/0xb0 Signed-off-by: Zheyu Ma Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/1626274459-8148-1-git-send-email-zheyuma97@gmail.com Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_range_manager.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index 03395386e8a7..f4b08a8705b3 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -181,6 +181,9 @@ int ttm_range_man_fini(struct ttm_device *bdev, struct drm_mm *mm = &rman->mm; int ret; + if (!man) + return 0; + ttm_resource_manager_set_used(man, false); ret = ttm_resource_manager_evict_all(bdev, man); From 14158aa4510439c611759d57b74ac01ebcca0081 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:02:37 -0500 Subject: [PATCH 0375/1469] usb: gadget: fsl_qe_udc: Fix fall-through warning for Clang Fix the following fallthrough warning (powerpc-randconfig): drivers/usb/gadget/udc/fsl_qe_udc.c:589:4: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/usb/gadget/udc/fsl_qe_udc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 8e8588933628..15db7a3868fe 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -586,6 +586,7 @@ static int qe_ep_init(struct qe_udc *udc, case USB_SPEED_FULL: if (max <= 1023) break; + fallthrough; default: goto en_done; } From afbd0d299289a0faaa605af74982f87ad75468fc Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:05:55 -0500 Subject: [PATCH 0376/1469] dmaengine: mpc512x: Fix fall-through warning for Clang Fix the following fallthrough warning (powerpc-randconfig): drivers/dma/mpc512x_dma.c:816:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/dma/mpc512x_dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index c1a69149c8bf..4a51fdbf5aa9 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -813,6 +813,7 @@ inline bool is_buswidth_valid(u8 buswidth, bool is_mpc8308) case 16: if (is_mpc8308) return false; + break; case 1: case 2: case 4: From d08c84e01afa7a7eee6badab25d5420fa847f783 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 14 Jul 2021 13:06:38 -0300 Subject: [PATCH 0377/1469] perf sched: Cast PTHREAD_STACK_MIN to int as it may turn into sysconf(__SC_THREAD_STACK_MIN_VALUE) In fedora rawhide the PTHREAD_STACK_MIN define may end up expanded to a sysconf() call, and that will return 'long int', breaking the build: 45 fedora:rawhide : FAIL gcc version 11.1.1 20210623 (Red Hat 11.1.1-6) (GCC) builtin-sched.c: In function 'create_tasks': /git/perf-5.14.0-rc1/tools/include/linux/kernel.h:43:24: error: comparison of distinct pointer types lacks a cast [-Werror] 43 | (void) (&_max1 == &_max2); \ | ^~ builtin-sched.c:673:34: note: in expansion of macro 'max' 673 | (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); | ^~~ cc1: all warnings being treated as errors $ grep __sysconf /usr/include/*/*.h /usr/include/bits/pthread_stack_min-dynamic.h:extern long int __sysconf (int __name) __THROW; /usr/include/bits/pthread_stack_min-dynamic.h:# define PTHREAD_STACK_MIN __sysconf (__SC_THREAD_STACK_MIN_VALUE) /usr/include/bits/time.h:extern long int __sysconf (int); /usr/include/bits/time.h:# define CLK_TCK ((__clock_t) __sysconf (2)) /* 2 is _SC_CLK_TCK */ $ So cast it to int to cope with that. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 954ce2f594e9..aaf1cde476c9 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched) err = pthread_attr_init(&attr); BUG_ON(err); err = pthread_attr_setstacksize(&attr, - (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); + (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN)); BUG_ON(err); err = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(err); From 64752a95b702817602d72f109ceaf5ec0780e283 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 14 Jul 2021 10:48:36 +0200 Subject: [PATCH 0378/1469] ALSA: usb-audio: Add missing proc text entry for BESPOKEN type Recently we've added a new usb_mixer element type, USB_MIXER_BESPOKEN, but it wasn't added in the table in snd_usb_mixer_dump_cval(). This is no big problem since each bespoken type should have its own dump method, but it still isn't disallowed to use the standard one, so we should cover it as well. Along with it, define the table with the explicit array initializer for avoiding other pitfalls. Fixes: 785b6f29a795 ("ALSA: usb-audio: scarlett2: Fix wrong resume call") Reported-by: Pavel Machek Cc: Link: https://lore.kernel.org/r/20210714084836.1977-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/mixer.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 30b3e128e28d..f4cdaf1ba44a 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -3295,7 +3295,15 @@ static void snd_usb_mixer_dump_cval(struct snd_info_buffer *buffer, { struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list); static const char * const val_types[] = { - "BOOLEAN", "INV_BOOLEAN", "S8", "U8", "S16", "U16", "S32", "U32", + [USB_MIXER_BOOLEAN] = "BOOLEAN", + [USB_MIXER_INV_BOOLEAN] = "INV_BOOLEAN", + [USB_MIXER_S8] = "S8", + [USB_MIXER_U8] = "U8", + [USB_MIXER_S16] = "S16", + [USB_MIXER_U16] = "U16", + [USB_MIXER_S32] = "S32", + [USB_MIXER_U32] = "U32", + [USB_MIXER_BESPOKEN] = "BESPOKEN", }; snd_iprintf(buffer, " Info: id=%i, control=%i, cmask=0x%x, " "channels=%i, type=\"%s\"\n", cval->head.id, From 104aba8dd7dca85d82e94aba07e71994ccdaf4cf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:10:40 -0500 Subject: [PATCH 0379/1469] powerpc/smp: Fix fall-through warning for Clang Fix the following fallthrough warning: arch/powerpc/platforms/powermac/smp.c:149:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/powerpc/platforms/powermac/smp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index bdfea6d6ab69..3256a316e884 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -146,6 +146,7 @@ static inline void psurge_clr_ipi(int cpu) switch(psurge_type) { case PSURGE_DUAL: out_8(psurge_sec_intr, ~0); + break; case PSURGE_NONE: break; default: From b7eb335e26a9c7f258c96b3962c283c379d3ede0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:57:54 -0500 Subject: [PATCH 0380/1469] Makefile: Enable -Wimplicit-fallthrough for Clang With the recent fixes for fallthrough warnings, it is now possible to enable -Wimplicit-fallthrough for Clang. It's important to mention that since we have adopted the use of the pseudo-keyword macro fallthrough; we also want to avoid having more /* fall through */ comments being introduced. Notice that contrary to GCC, Clang doesn't recognize any comments as implicit fall-through markings when the -Wimplicit-fallthrough option is enabled. So, in order to avoid having more comments being introduced, we have to use the option -Wimplicit-fallthrough=5 for GCC, which similar to Clang, will cause a warning in case a code comment is intended to be used as a fall-through marking. Co-developed-by: Kees Cook Signed-off-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- Makefile | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/Makefile b/Makefile index c3f9bd191b89..eaa692976851 100644 --- a/Makefile +++ b/Makefile @@ -797,12 +797,6 @@ KBUILD_CFLAGS += -Wno-gnu # source of a reference will be _MergedGlobals and not on of the whitelisted names. # See modpost pattern 2 KBUILD_CFLAGS += -mno-global-merge -else - -# Warn about unmarked fall-throughs in switch statement. -# Disabled for clang while comment to attribute conversion happens and -# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed. -KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,) endif # These warnings generated too much noise in a regular build. @@ -983,6 +977,9 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement +# Warn about unmarked fall-throughs in switch statement. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,$(call cc-option,-Wimplicit-fallthrough,)) + # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla From f8f0edabcc09fafd695ed2adc0eb825104e35d5c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 1 Jul 2021 08:19:28 +0100 Subject: [PATCH 0381/1469] KVM: selftests: x86: Address missing vm_install_exception_handler conversions Commit b78f4a59669 ("KVM: selftests: Rename vm_handle_exception") raced with a couple of new x86 tests, missing two vm_handle_exception to vm_install_exception_handler conversions. Help the two broken tests to catch up with the new world. Cc: Andrew Jones CC: Ricardo Koller Cc: Paolo Bonzini Signed-off-by: Marc Zyngier Message-Id: <20210701071928.2971053-1-maz@kernel.org> Reviewed-by: Andrew Jones Reviewed-by: Ricardo Koller Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/hyperv_features.c | 2 +- tools/testing/selftests/kvm/x86_64/mmu_role_test.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 42bd658f52a8..af27c7e829c1 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -615,7 +615,7 @@ int main(void) vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); pr_info("Testing access to Hyper-V specific MSRs\n"); guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c index 523371cf8e8f..da2325fcad87 100644 --- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c @@ -71,7 +71,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val) /* Set up a #PF handler to eat the RSVD #PF and signal all done! */ vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_handle_exception(vm, PF_VECTOR, guest_pf_handler); + vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler); r = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); From f0414b078dd11641a7a64027c2741396f47718fd Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Jun 2021 17:18:53 -0700 Subject: [PATCH 0382/1469] Revert "KVM: x86: WARN and reject loading KVM if NX is supported but not enabled" Let KVM load if EFER.NX=0 even if NX is supported, the analysis and testing (or lack thereof) for the non-PAE host case was garbage. If the kernel won't be using PAE paging, .Ldefault_entry in head_32.S skips over the entire EFER sequence. Hopefully that can be changed in the future to allow KVM to require EFER.NX, but the motivation behind KVM's requirement isn't yet merged. Reverting and revisiting the mess at a later date is by far the safest approach. This reverts commit 8bbed95d2cb6e5de8a342d761a89b0a04faed7be. Fixes: 8bbed95d2cb6 ("KVM: x86: WARN and reject loading KVM if NX is supported but not enabled") Signed-off-by: Sean Christopherson Message-Id: <20210625001853.318148-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 17468d983fbd..cf10d196ca65 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10981,9 +10981,6 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); - if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && - !(host_efer & EFER_NX))) - return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); From 4bf48e3c0aafd32b960d341c4925b48f416f14a5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:46 -0700 Subject: [PATCH 0383/1469] KVM: x86: Use guest MAXPHYADDR from CPUID.0x8000_0008 iff TDP is enabled Ignore the guest MAXPHYADDR reported by CPUID.0x8000_0008 if TDP, i.e. NPT, is disabled, and instead use the host's MAXPHYADDR. Per AMD'S APM: Maximum guest physical address size in bits. This number applies only to guests using nested paging. When this field is zero, refer to the PhysAddrSize field for the maximum guest physical address size. Fixes: 24c82e576b78 ("KVM: Sanitize cpuid") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c42613cfb5ba..1a4217b3e185 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -940,8 +940,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned phys_as = entry->eax & 0xff; - if (!g_phys_as) + /* + * Use bare metal's MAXPHADDR if the CPU doesn't report guest + * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the + * guest version "applies only to guests using nested paging". + */ + if (!g_phys_as || !tdp_enabled) g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); From e39f00f60ebd2e7b295c37a05e6349df656d3eb8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:47 -0700 Subject: [PATCH 0384/1469] KVM: x86: Use kernel's x86_phys_bits to handle reduced MAXPHYADDR Use boot_cpu_data.x86_phys_bits instead of the raw CPUID information to enumerate the MAXPHYADDR for KVM guests when TDP is disabled (the guest version is only relevant to NPT/TDP). When using shadow paging, any reductions to the host's MAXPHYADDR apply to KVM and its guests as well, i.e. using the raw CPUID info will cause KVM to misreport the number of PA bits available to the guest. Unconditionally zero out the "Physical Address bit reduction" entry. For !TDP, the adjustment is already done, and for TDP enumerating the host's reduction is wrong as the reduction does not apply to GPAs. Fixes: 9af9b94068fb ("x86/cpu/AMD: Handle SME reduction in physical address size") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1a4217b3e185..ca7866d63e98 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -941,11 +941,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) unsigned phys_as = entry->eax & 0xff; /* - * Use bare metal's MAXPHADDR if the CPU doesn't report guest - * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the - * guest version "applies only to guests using nested paging". + * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as + * the guest operates in the same PA space as the host, i.e. + * reductions in MAXPHYADDR for memory encryption affect shadow + * paging, too. + * + * If TDP is enabled but an explicit guest MAXPHYADDR is not + * provided, use the raw bare metal MAXPHYADDR as reductions to + * the HPAs do not affect GPAs. */ - if (!g_phys_as || !tdp_enabled) + if (!tdp_enabled) + g_phys_as = boot_cpu_data.x86_phys_bits; + else if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); @@ -970,12 +977,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x8000001a: case 0x8000001e: break; - /* Support memory encryption cpuid if host supports it */ case 0x8000001F: - if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) + if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; - else + } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); + + /* + * Enumerate '0' for "PA bits reduction", the adjusted + * MAXPHYADDR is enumerated directly (see 0x80000008). + */ + entry->ebx &= ~GENMASK(11, 6); + } break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: From fc9bf2e087efcd81bda2e52d09616d2a1bf982a8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:49 -0700 Subject: [PATCH 0385/1469] KVM: x86/mmu: Do not apply HPA (memory encryption) mask to GPAs Ignore "dynamic" host adjustments to the physical address mask when generating the masks for guest PTEs, i.e. the guest PA masks. The host physical address space and guest physical address space are two different beasts, e.g. even though SEV's C-bit is the same bit location for both host and guest, disabling SME in the host (which clears shadow_me_mask) does not affect the guest PTE->GPA "translation". For non-SEV guests, not dropping bits is the correct behavior. Assuming KVM and userspace correctly enumerate/configure guest MAXPHYADDR, bits that are lost as collateral damage from memory encryption are treated as reserved bits, i.e. KVM will never get to the point where it attempts to generate a gfn using the affected bits. And if userspace wants to create a bogus vCPU, then userspace gets to deal with the fallout of hardware doing odd things with bad GPAs. For SEV guests, not dropping the C-bit is technically wrong, but it's a moot point because KVM can't read SEV guest's page tables in any case since they're always encrypted. Not to mention that the current KVM code is also broken since sme_me_mask does not have to be non-zero for SEV to be supported by KVM. The proper fix would be to teach all of KVM to correctly handle guest private memory, but that's a task for the future. Fixes: d0ec49d4de90 ("kvm/x86/svm: Support Secure Memory Encryption within KVM") Cc: stable@vger.kernel.org Cc: Brijesh Singh Cc: Tom Lendacky Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-5-seanjc@google.com> [Use a new header instead of adding header guards to paging_tmpl.h. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 ++ arch/x86/kvm/mmu/paging.h | 14 ++++++++++++++ arch/x86/kvm/mmu/paging_tmpl.h | 4 ++-- arch/x86/kvm/mmu/spte.h | 6 ------ 4 files changed, 18 insertions(+), 8 deletions(-) create mode 100644 arch/x86/kvm/mmu/paging.h diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 00732757cc60..b888385d1933 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -53,6 +53,8 @@ #include #include "trace.h" +#include "paging.h" + extern bool itlb_multihit_kvm_mitigation; int __read_mostly nx_huge_pages = -1; diff --git a/arch/x86/kvm/mmu/paging.h b/arch/x86/kvm/mmu/paging.h new file mode 100644 index 000000000000..de8ab323bb70 --- /dev/null +++ b/arch/x86/kvm/mmu/paging.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Shadow paging constants/helpers that don't need to be #undef'd. */ +#ifndef __KVM_X86_PAGING_H +#define __KVM_X86_PAGING_H + +#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_LVL_ADDR_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#define PT64_LVL_OFFSET_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#endif /* __KVM_X86_PAGING_H */ + diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 490a028ddabe..ee044d357b5f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -24,7 +24,7 @@ #define pt_element_t u64 #define guest_walker guest_walker64 #define FNAME(name) paging##64_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -57,7 +57,7 @@ #define pt_element_t u64 #define guest_walker guest_walkerEPT #define FNAME(name) ept_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 7a5ce9314107..eb7b227fc6cf 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -38,12 +38,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); #else #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) #endif -#define PT64_LVL_ADDR_MASK(level) \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) -#define PT64_LVL_OFFSET_MASK(level) \ - (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ | shadow_x_mask | shadow_nx_mask | shadow_me_mask) From 76ff371b67cb12fb635396234468abcf6a466f16 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Jun 2021 19:03:54 -0700 Subject: [PATCH 0386/1469] KVM: SVM: Revert clearing of C-bit on GPA in #NPF handler Don't clear the C-bit in the #NPF handler, as it is a legal GPA bit for non-SEV guests, and for SEV guests the C-bit is dropped before the GPA hits the NPT in hardware. Clearing the bit for non-SEV guests causes KVM to mishandle #NPFs with that collide with the host's C-bit. Although the APM doesn't explicitly state that the C-bit is not reserved for non-SEV, Tom Lendacky confirmed that the following snippet about the effective reduction due to the C-bit does indeed apply only to SEV guests. Note that because guest physical addresses are always translated through the nested page tables, the size of the guest physical address space is not impacted by any physical address space reduction indicated in CPUID 8000_001F[EBX]. If the C-bit is a physical address bit however, the guest physical address space is effectively reduced by 1 bit. And for SEV guests, the APM clearly states that the bit is dropped before walking the nested page tables. If the C-bit is an address bit, this bit is masked from the guest physical address when it is translated through the nested page tables. Consequently, the hypervisor does not need to be aware of which pages the guest has chosen to mark private. Note, the bogus C-bit clearing was removed from legacy #PF handler in commit 6d1b867d0456 ("KVM: SVM: Don't strip the C-bit from CR2 on #PF interception"). Fixes: 0ede79e13224 ("KVM: SVM: Clear C-bit from the page fault address") Cc: Peter Gonda Cc: Brijesh Singh Cc: Tom Lendacky Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210625020354.431829-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8834822c00cd..ca5614a48b21 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1923,7 +1923,7 @@ static int npf_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); + u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; trace_kvm_page_fault(fault_address, error_code); From 23fa2e46a5556f787ce2ea1a315d3ab93cced204 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Sat, 26 Jun 2021 15:03:04 +0800 Subject: [PATCH 0387/1469] KVM: mmio: Fix use-after-free Read in kvm_vm_ioctl_unregister_coalesced_mmio BUG: KASAN: use-after-free in kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 Read of size 8 at addr ffff0000c03a2500 by task syz-executor083/4269 CPU: 5 PID: 4269 Comm: syz-executor083 Not tainted 5.10.0 #7 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2d0 arch/arm64/kernel/stacktrace.c:132 show_stack+0x28/0x34 arch/arm64/kernel/stacktrace.c:196 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x110/0x164 lib/dump_stack.c:118 print_address_description+0x78/0x5c8 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report+0x148/0x1e4 mm/kasan/report.c:562 check_memory_region_inline mm/kasan/generic.c:183 [inline] __asan_load8+0xb4/0xbc mm/kasan/generic.c:252 kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Allocated by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0xdc/0x120 mm/kasan/common.c:461 kasan_kmalloc+0xc/0x14 mm/kasan/common.c:475 kmem_cache_alloc_trace include/linux/slab.h:450 [inline] kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:664 [inline] kvm_vm_ioctl_register_coalesced_mmio+0x78/0x1cc arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:146 kvm_vm_ioctl+0x7e8/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3746 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Freed by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x38/0x6c mm/kasan/common.c:56 kasan_set_free_info+0x20/0x40 mm/kasan/generic.c:355 __kasan_slab_free+0x124/0x150 mm/kasan/common.c:422 kasan_slab_free+0x10/0x1c mm/kasan/common.c:431 slab_free_hook mm/slub.c:1544 [inline] slab_free_freelist_hook mm/slub.c:1577 [inline] slab_free mm/slub.c:3142 [inline] kfree+0x104/0x38c mm/slub.c:4124 coalesced_mmio_destructor+0x94/0xa4 arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:102 kvm_iodevice_destructor include/kvm/iodev.h:61 [inline] kvm_io_bus_unregister_dev+0x248/0x280 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:4374 kvm_vm_ioctl_unregister_coalesced_mmio+0x158/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:186 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 If kvm_io_bus_unregister_dev() return -ENOMEM, we already call kvm_iodevice_destructor() inside this function to delete 'struct kvm_coalesced_mmio_dev *dev' from list and free the dev, but kvm_iodevice_destructor() is called again, it will lead the above issue. Let's check the the return value of kvm_io_bus_unregister_dev(), only call kvm_iodevice_destructor() if the return value is 0. Cc: Paolo Bonzini Cc: kvm@vger.kernel.org Reported-by: Hulk Robot Signed-off-by: Kefeng Wang Message-Id: <20210626070304.143456-1-wangkefeng.wang@huawei.com> Cc: stable@vger.kernel.org Fixes: 5d3c4c79384a ("KVM: Stop looking for coalesced MMIO zones if the bus is destroyed", 2021-04-20) Signed-off-by: Paolo Bonzini --- virt/kvm/coalesced_mmio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index f08f5e82460b..0be80c213f7f 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -186,7 +186,6 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, coalesced_mmio_in_range(dev, zone->addr, zone->size)) { r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); - kvm_iodevice_destructor(&dev->dev); /* * On failure, unregister destroys all devices on the @@ -196,6 +195,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, */ if (r) break; + kvm_iodevice_destructor(&dev->dev); } } From 7234c362ccb3c2228f06f19f93b132de9cfa7ae4 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 28 Jun 2021 15:43:54 +0800 Subject: [PATCH 0388/1469] KVM: x86/pmu: Clear anythread deprecated bit when 0xa leaf is unsupported on the SVM The AMD platform does not support the functions Ah CPUID leaf. The returned results for this entry should all remain zero just like the native does: AMD host: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00000000 (uncanny) AMD guest: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00008000 Fixes: cadbaa039b99 ("perf/x86/intel: Make anythread filter support conditional") Signed-off-by: Like Xu Message-Id: <20210628074354.33848-1-likexu@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ca7866d63e98..739be5da3bca 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -765,7 +765,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.anythread_deprecated = 1; + if (cap.version) + edx.split.anythread_deprecated = 1; edx.split.reserved1 = 0; edx.split.reserved2 = 0; From 3b0462726e7ef281c35a7a4ae33e93ee2bc9975b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 14 Jul 2021 15:47:49 +0200 Subject: [PATCH 0389/1469] cgroup: verify that source is a string The following sequence can be used to trigger a UAF: int fscontext_fd = fsopen("cgroup"); int fd_null = open("/dev/null, O_RDONLY); int fsconfig(fscontext_fd, FSCONFIG_SET_FD, "source", fd_null); close_range(3, ~0U, 0); The cgroup v1 specific fs parser expects a string for the "source" parameter. However, it is perfectly legitimate to e.g. specify a file descriptor for the "source" parameter. The fs parser doesn't know what a filesystem allows there. So it's a bug to assume that "source" is always of type fs_value_is_string when it can reasonably also be fs_value_is_file. This assumption in the cgroup code causes a UAF because struct fs_parameter uses a union for the actual value. Access to that union is guarded by the param->type member. Since the cgroup paramter parser didn't check param->type but unconditionally moved param->string into fc->source a close on the fscontext_fd would trigger a UAF during put_fs_context() which frees fc->source thereby freeing the file stashed in param->file causing a UAF during a close of the fd_null. Fix this by verifying that param->type is actually a string and report an error if not. In follow up patches I'll add a new generic helper that can be used here and by other filesystems instead of this error-prone copy-pasta fix. But fixing it in here first makes backporting a it to stable a lot easier. Fixes: 8d2451f4994f ("cgroup1: switch to option-by-option parsing") Reported-by: syzbot+283ce5a46486d6acdbaf@syzkaller.appspotmail.com Cc: Christoph Hellwig Cc: Alexander Viro Cc: Dmitry Vyukov Cc: Cc: syzkaller-bugs Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- kernel/cgroup/cgroup-v1.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index ee93b6e89587..527917c0b30b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -912,6 +912,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { + if (param->type != fs_value_is_string) + return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources not supported"); fc->source = param->string; From d1d488d813703618f0dd93f0e4c4a05928114aa8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 14 Jul 2021 15:47:50 +0200 Subject: [PATCH 0390/1469] fs: add vfs_parse_fs_param_source() helper Add a simple helper that filesystems can use in their parameter parser to parse the "source" parameter. A few places open-coded this function and that already caused a bug in the cgroup v1 parser that we fixed. Let's make it harder to get this wrong by introducing a helper which performs all necessary checks. Link: https://syzkaller.appspot.com/bug?id=6312526aba5beae046fdae8f00399f87aab48b12 Cc: Christoph Hellwig Cc: Alexander Viro Cc: Dmitry Vyukov Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- fs/fs_context.c | 54 +++++++++++++++++++++++++------------- include/linux/fs_context.h | 2 ++ kernel/cgroup/cgroup-v1.c | 14 ++++------ 3 files changed, 43 insertions(+), 27 deletions(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 2834d1afa6e8..de1985eae535 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -79,6 +79,35 @@ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key) return -ENOPARAM; } +/** + * vfs_parse_fs_param_source - Handle setting "source" via parameter + * @fc: The filesystem context to modify + * @param: The parameter + * + * This is a simple helper for filesystems to verify that the "source" they + * accept is sane. + * + * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and + * -EINVAL otherwise. In the event of failure, supplementary error information + * is logged. + */ +int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param) +{ + if (strcmp(param->key, "source") != 0) + return -ENOPARAM; + + if (param->type != fs_value_is_string) + return invalf(fc, "Non-string source"); + + if (fc->source) + return invalf(fc, "Multiple sources"); + + fc->source = param->string; + param->string = NULL; + return 0; +} +EXPORT_SYMBOL(vfs_parse_fs_param_source); + /** * vfs_parse_fs_param - Add a single parameter to a superblock config * @fc: The filesystem context to modify @@ -122,15 +151,9 @@ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param) /* If the filesystem doesn't take any arguments, give it the * default handling of source. */ - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "VFS: Non-string source"); - if (fc->source) - return invalf(fc, "VFS: Multiple sources"); - fc->source = param->string; - param->string = NULL; - return 0; - } + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; return invalf(fc, "%s: Unknown parameter '%s'", fc->fs_type->name, param->key); @@ -504,16 +527,11 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) struct legacy_fs_context *ctx = fc->fs_private; unsigned int size = ctx->data_size; size_t len = 0; + int ret; - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "VFS: Legacy: Non-string source"); - if (fc->source) - return invalf(fc, "VFS: Legacy: Multiple sources"); - fc->source = param->string; - param->string = NULL; - return 0; - } + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS) return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options"); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 37e1e8f7f08d..e2bc16300c82 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -139,6 +139,8 @@ extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); +extern int vfs_parse_fs_param_source(struct fs_context *fc, + struct fs_parameter *param); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 527917c0b30b..8d6bf56ed77a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -911,15 +911,11 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "Non-string source"); - if (fc->source) - return invalf(fc, "Multiple sources not supported"); - fc->source = param->string; - param->string = NULL; - return 0; - } + int ret; + + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; From edb25572fc7058db5a98223e11d2d50497178553 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 23 Jun 2021 00:50:01 -0700 Subject: [PATCH 0391/1469] mmc: core: Use kref in place of struct mmc_blk_data::usage Ulf reported the following KASAN splat after adding some manual hacks into mmc-utils[1]. DEBUG: mmc_blk_open: Let's sleep for 10s.. mmc1: card 0007 removed BUG: KASAN: use-after-free in mmc_blk_get+0x58/0xb8 Read of size 4 at addr ffff00000a394a28 by task mmc/180 CPU: 2 PID: 180 Comm: mmc Not tainted 5.10.0-rc4-00069-gcc758c8c7127-dirty #5 Hardware name: Qualcomm Technologies, Inc. APQ 8016 SBC (DT) Call trace: dump_backtrace+0x0/0x2b4 show_stack+0x18/0x6c dump_stack+0xfc/0x168 print_address_description.constprop.0+0x6c/0x488 kasan_report+0x118/0x210 __asan_load4+0x94/0xd0 mmc_blk_get+0x58/0xb8 mmc_blk_open+0x7c/0xdc __blkdev_get+0x3b4/0x964 blkdev_get+0x64/0x100 blkdev_open+0xe8/0x104 do_dentry_open+0x234/0x61c vfs_open+0x54/0x64 path_openat+0xe04/0x1584 do_filp_open+0xe8/0x1e4 do_sys_openat2+0x120/0x230 __arm64_sys_openat+0xf0/0x15c el0_svc_common.constprop.0+0xac/0x234 do_el0_svc+0x84/0xa0 el0_sync_handler+0x264/0x270 el0_sync+0x174/0x180 Allocated by task 33: stack_trace_save+0x9c/0xdc kasan_save_stack+0x28/0x60 __kasan_kmalloc.constprop.0+0xc8/0xf0 kasan_kmalloc+0x10/0x20 mmc_blk_alloc_req+0x94/0x4b0 mmc_blk_probe+0x2d4/0xaa4 mmc_bus_probe+0x34/0x4c really_probe+0x148/0x6e0 driver_probe_device+0x78/0xec __device_attach_driver+0x108/0x16c bus_for_each_drv+0xf4/0x15c __device_attach+0x168/0x240 device_initial_probe+0x14/0x20 bus_probe_device+0xec/0x100 device_add+0x55c/0xaf0 mmc_add_card+0x288/0x380 mmc_attach_sd+0x18c/0x22c mmc_rescan+0x444/0x4f0 process_one_work+0x3b8/0x650 worker_thread+0xa0/0x724 kthread+0x218/0x220 ret_from_fork+0x10/0x38 Freed by task 33: stack_trace_save+0x9c/0xdc kasan_save_stack+0x28/0x60 kasan_set_track+0x28/0x40 kasan_set_free_info+0x24/0x4c __kasan_slab_free+0x100/0x180 kasan_slab_free+0x14/0x20 kfree+0xb8/0x46c mmc_blk_put+0xe4/0x11c mmc_blk_remove_req.part.0+0x6c/0xe4 mmc_blk_remove+0x368/0x370 mmc_bus_remove+0x34/0x50 __device_release_driver+0x228/0x31c device_release_driver+0x2c/0x44 bus_remove_device+0x1e4/0x200 device_del+0x2b0/0x770 mmc_remove_card+0xf0/0x150 mmc_sd_detect+0x9c/0x150 mmc_rescan+0x110/0x4f0 process_one_work+0x3b8/0x650 worker_thread+0xa0/0x724 kthread+0x218/0x220 ret_from_fork+0x10/0x38 The buggy address belongs to the object at ffff00000a394800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 552 bytes inside of 1024-byte region [ffff00000a394800, ffff00000a394c00) The buggy address belongs to the page: page:00000000ff84ed53 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8a390 head:00000000ff84ed53 order:3 compound_mapcount:0 compound_pincount:0 flags: 0x3fffc0000010200(slab|head) raw: 03fffc0000010200 dead000000000100 dead000000000122 ffff000009f03800 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff00000a394900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff00000a394980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff00000a394a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff00000a394a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff00000a394b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Looking closer at the problem, it looks like a classic dangling pointer bug. The 'struct mmc_blk_data' that is used after being freed in mmc_blk_put() is stashed away in 'md->disk->private_data' via mmc_blk_alloc_req() but used in mmc_blk_get() because the 'usage' count isn't properly aligned with the lifetime of the pointer. You'd expect the 'usage' member to be in sync with the kfree(), and it mostly is, except that mmc_blk_get() needs to dereference the potentially freed memory storage for the 'struct mmc_blk_data' stashed away in the private_data member to look at 'usage' before it actually figures out if it wants to consider it a valid pointer or not. That's not going to work if the freed memory has been overwritten by something else after the free, and KASAN rightly complains here. To fix the immediate problem, let's set the private_data member to NULL in mmc_blk_put() so that mmc_blk_get() can consider the object "on the way out" if the pointer is NULL and not even try to look at 'usage' if the object isn't going to be around much longer. With that set to NULL on the last mmc_blk_put(), optimize the get path further and use a kref underneath the 'open_lock' mutex to only up the reference count if it's non-zero, i.e. alive, and otherwise make mmc_blk_get() return NULL, without actually testing the reference count if we're in the process of removing the object from the system. Finally, tighten the locking region on the put side to only be around the parts that are removing the 'mmc_blk_data' from the system and publishing that fact to the gendisk and then drop the lock as soon as we can to avoid holding the lock around code that doesn't need it. This fixes the KASAN issue. Cc: Matthias Schiffer Cc: Sujit Kautkar Cc: Zubin Mithra Reported-by: Ulf Hansson Link: https://lore.kernel.org/linux-mmc/CAPDyKFryT63Jc7+DXWSpAC19qpZRqFr1orxwYGMuSqx247O8cQ@mail.gmail.com/ [1] Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20210623075002.1746924-2-swboyd@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 37 ++++++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 15 deletions(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 9890a1532cb0..ce8aed562929 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -111,7 +112,7 @@ struct mmc_blk_data { #define MMC_BLK_CMD23 (1 << 0) /* Can do SET_BLOCK_COUNT for multiblock */ #define MMC_BLK_REL_WR (1 << 1) /* MMC Reliable write support */ - unsigned int usage; + struct kref kref; unsigned int read_only; unsigned int part_type; unsigned int reset_done; @@ -181,10 +182,8 @@ static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk) mutex_lock(&open_lock); md = disk->private_data; - if (md && md->usage == 0) + if (md && !kref_get_unless_zero(&md->kref)) md = NULL; - if (md) - md->usage++; mutex_unlock(&open_lock); return md; @@ -196,18 +195,25 @@ static inline int mmc_get_devidx(struct gendisk *disk) return devidx; } +static void mmc_blk_kref_release(struct kref *ref) +{ + struct mmc_blk_data *md = container_of(ref, struct mmc_blk_data, kref); + int devidx; + + devidx = mmc_get_devidx(md->disk); + ida_simple_remove(&mmc_blk_ida, devidx); + + mutex_lock(&open_lock); + md->disk->private_data = NULL; + mutex_unlock(&open_lock); + + put_disk(md->disk); + kfree(md); +} + static void mmc_blk_put(struct mmc_blk_data *md) { - mutex_lock(&open_lock); - md->usage--; - if (md->usage == 0) { - int devidx = mmc_get_devidx(md->disk); - - ida_simple_remove(&mmc_blk_ida, devidx); - put_disk(md->disk); - kfree(md); - } - mutex_unlock(&open_lock); + kref_put(&md->kref, mmc_blk_kref_release); } static ssize_t power_ro_lock_show(struct device *dev, @@ -2327,7 +2333,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, INIT_LIST_HEAD(&md->part); INIT_LIST_HEAD(&md->rpmbs); - md->usage = 1; + kref_init(&md->kref); + md->queue.blkdata = md; md->disk->major = MMC_BLOCK_MAJOR; From 10252bae863d09b9648bed2e035572d207200ca1 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 23 Jun 2021 00:50:02 -0700 Subject: [PATCH 0392/1469] mmc: core: Don't allocate IDA for OF aliases There's a chance that the IDA allocated in mmc_alloc_host() is not freed for some time because it's freed as part of a class' release function (see mmc_host_classdev_release() where the IDA is freed). If another thread is holding a reference to the class, then only once all balancing device_put() calls (in turn calling kobject_put()) have been made will the IDA be released and usable again. Normally this isn't a problem because the kobject is released before anything else that may want to use the same number tries to again, but with CONFIG_DEBUG_KOBJECT_RELEASE=y and OF aliases it becomes pretty easy to try to allocate an alias from the IDA twice while the first time it was allocated is still pending a call to ida_simple_remove(). It's also possible to trigger it by using CONFIG_DEBUG_KOBJECT_RELEASE and probe defering a driver at boot that calls mmc_alloc_host() before trying to get resources that may defer likes clks or regulators. Instead of allocating from the IDA in this scenario, let's just skip it if we know this is an OF alias. The number is already "claimed" and devices that aren't using OF aliases won't try to use the claimed numbers anyway (see mmc_first_nonreserved_index()). This should avoid any issues with mmc_alloc_host() returning failures from the ida_simple_get() in the case that we're using an OF alias. Cc: Matthias Schiffer Cc: Sujit Kautkar Reported-by: Zubin Mithra Fixes: fa2d0aa96941 ("mmc: core: Allow setting slot index via device tree alias") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20210623075002.1746924-3-swboyd@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/host.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index eda4a1892c33..0475d96047c4 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -75,7 +75,8 @@ static void mmc_host_classdev_release(struct device *dev) { struct mmc_host *host = cls_dev_to_mmc_host(dev); wakeup_source_unregister(host->ws); - ida_simple_remove(&mmc_host_ida, host->index); + if (of_alias_get_id(host->parent->of_node, "mmc") < 0) + ida_simple_remove(&mmc_host_ida, host->index); kfree(host); } @@ -502,7 +503,7 @@ static int mmc_first_nonreserved_index(void) */ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) { - int err; + int index; struct mmc_host *host; int alias_id, min_idx, max_idx; @@ -515,20 +516,19 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) alias_id = of_alias_get_id(dev->of_node, "mmc"); if (alias_id >= 0) { - min_idx = alias_id; - max_idx = alias_id + 1; + index = alias_id; } else { min_idx = mmc_first_nonreserved_index(); max_idx = 0; + + index = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL); + if (index < 0) { + kfree(host); + return NULL; + } } - err = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL); - if (err < 0) { - kfree(host); - return NULL; - } - - host->index = err; + host->index = index; dev_set_name(&host->class_dev, "mmc%d", host->index); host->ws = wakeup_source_register(NULL, dev_name(&host->class_dev)); From fa2c02e5798c17c89cbb3135940086ebe07e5c9f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 14 Jul 2021 14:28:02 -0300 Subject: [PATCH 0393/1469] tools headers: Remove broken definition of __LITTLE_ENDIAN The linux/kconfig.h file was copied from the kernel but the line where with the generated/autoconf.h include from where the CONFIG_ entries would come from was deleted, as tools/ build system don't create that file, so we ended up always defining just __LITTLE_ENDIAN as CONFIG_CPU_BIG_ENDIAN was nowhere to be found. This in turn ended up breaking the build in some systems where __LITTLE_ENDIAN was already defined, such as the androind NDK. So just ditch that block that depends on the CONFIG_CPU_BIG_ENDIAN define. The kconfig.h file was copied just to get IS_ENABLED() and a 'make -C tools/all' doesn't breaks with this removal. Fixes: 93281c4a96572a34 ("x86/insn: Add an insn_decode() API") Cc: Adrian Hunter Cc: Borislav Petkov Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/YO8hK7lqJcIWuBzx@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/kconfig.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h index 1555a0c4f345..13b86bd3b746 100644 --- a/tools/include/linux/kconfig.h +++ b/tools/include/linux/kconfig.h @@ -4,12 +4,6 @@ /* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ -#ifdef CONFIG_CPU_BIG_ENDIAN -#define __BIG_ENDIAN 4321 -#else -#define __LITTLE_ENDIAN 1234 -#endif - #define __ARG_PLACEHOLDER_1 0, #define __take_second_arg(__ignored, val, ...) val From 83d1fc92d4cdd1ea2d229347ddf11ea2aa751059 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 24 Jun 2021 17:43:02 +0100 Subject: [PATCH 0394/1469] perf cs-etm: Split Coresight decode by aux records Populate the auxtrace queues using AUX records rather than whole auxtrace buffers so that the decoder is reset between each aux record. This is similar to the auxtrace_queues__process_index() -> auxtrace_queues__add_indexed_event() flow where perf_session__peek_event() is used to read AUXTRACE events out of random positions in the file based on the auxtrace index. But now we loop over all PERF_RECORD_AUX events instead of AUXTRACE buffers. For each PERF_RECORD_AUX event, we find the corresponding AUXTRACE buffer using the index, and add a fragment of that buffer to the auxtrace queues. No other changes to decoding were made, apart from populating the auxtrace queues. The result of decoding is identical to before, except in cases where decoding failed completely, due to not resetting the decoder. The reason for this change is because AUX records are emitted any time tracing is disabled, for example when the process is scheduled out. Because ETM was disabled and enabled again, the decoder also needs to be reset to force the search for a sync packet. Otherwise there would be fatal decoding errors. Testing ======= Testing was done with the following script, to diff the decoding results between the patched and un-patched versions of perf: #!/bin/bash set -ex $1 script -i $3 $4 > split.script $2 script -i $3 $4 > default.script diff split.script default.script | head -n 20 And it was run like this, with various itrace options depending on the quantity of synthesised events: compare.sh ./perf-patched ./perf-default perf-per-cpu-2-threads.data --itrace=i100000ns No changes in output were observed in the following scenarios: * Simple per-cpu perf record -e cs_etm/@tmc_etr0/u top * Per-thread, single thread perf record -e cs_etm/@tmc_etr0/u --per-thread ./threads_C * Per-thread multiple threads (but only one thread collected data): perf record -e cs_etm/@tmc_etr0/u --per-thread --pid 4596,4597 * Per-thread multiple threads (both threads collected data): perf record -e cs_etm/@tmc_etr0/u --per-thread --pid 4596,4597 * Per-cpu explicit threads: perf record -e cs_etm/@tmc_etr0/u --pid 853,854 * System-wide (per-cpu): perf record -e cs_etm/@tmc_etr0/u -a * No data collected (no aux buffers) Can happen with any command when run for a short period * Containing truncated records Can happen with any command * Containing aux records with 0 size Can happen with any command * Snapshot mode (various files with and without buffer wrap) perf record -e cs_etm/@tmc_etr0/u -a --snapshot Some differences were observed in the following scenario: * Snapshot mode (with duplicate buffers) perf record -e cs_etm/@tmc_etr0/u -a --snapshot Fewer samples are generated in snapshot mode if duplicate buffers were gathered because buffers with the same offset are now only added once. This gives different, but more correct results and no duplicate data is decoded any more. Signed-off-by: James Clark Reviewed-by: Mathieu Poirier Tested-by: Leo Yan Cc: Al Grant Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Branislav Rankov Cc: Denis Nikitin Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20210624164303.28632-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 168 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 167 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 32ad92d3e454..22f8326547eb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2683,6 +2683,172 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset, return metadata; } +/** + * Puts a fragment of an auxtrace buffer into the auxtrace queues based + * on the bounds of aux_event, if it matches with the buffer that's at + * file_offset. + * + * Normally, whole auxtrace buffers would be added to the queue. But we + * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder + * is reset across each buffer, so splitting the buffers up in advance has + * the same effect. + */ +static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz, + struct perf_record_aux *aux_event, struct perf_sample *sample) +{ + int err; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *auxtrace_event_union; + struct perf_record_auxtrace *auxtrace_event; + union perf_event auxtrace_fragment; + __u64 aux_offset, aux_size; + + struct cs_etm_auxtrace *etm = container_of(session->auxtrace, + struct cs_etm_auxtrace, + auxtrace); + + /* + * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got + * from looping through the auxtrace index. + */ + err = perf_session__peek_event(session, file_offset, buf, + PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL); + if (err) + return err; + auxtrace_event = &auxtrace_event_union->auxtrace; + if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE) + return -EINVAL; + + if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) || + auxtrace_event->header.size != sz) { + return -EINVAL; + } + + /* + * In per-thread mode, CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + */ + if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || + auxtrace_event->cpu != sample->cpu) + return 1; + + if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { + /* + * Clamp size in snapshot mode. The buffer size is clamped in + * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect + * the buffer size. + */ + aux_size = min(aux_event->aux_size, auxtrace_event->size); + + /* + * In this mode, the head also points to the end of the buffer so aux_offset + * needs to have the size subtracted so it points to the beginning as in normal mode + */ + aux_offset = aux_event->aux_offset - aux_size; + } else { + aux_size = aux_event->aux_size; + aux_offset = aux_event->aux_offset; + } + + if (aux_offset >= auxtrace_event->offset && + aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) { + /* + * If this AUX event was inside this buffer somewhere, create a new auxtrace event + * based on the sizes of the aux event, and queue that fragment. + */ + auxtrace_fragment.auxtrace = *auxtrace_event; + auxtrace_fragment.auxtrace.size = aux_size; + auxtrace_fragment.auxtrace.offset = aux_offset; + file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size; + + pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu); + return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment, + file_offset, NULL); + } + + /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */ + return 1; +} + +static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + struct perf_sample sample; + int ret; + struct auxtrace_index_entry *ent; + struct auxtrace_index *auxtrace_index; + struct evsel *evsel; + size_t i; + + /* Don't care about any other events, we're only queuing buffers for AUX events */ + if (event->header.type != PERF_RECORD_AUX) + return 0; + + if (event->header.size < sizeof(struct perf_record_aux)) + return -EINVAL; + + /* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */ + if (!event->aux.aux_size) + return 0; + + /* + * Parse the sample, we need the sample_id_all data that comes after the event so that the + * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID. + */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + ret = evsel__parse_sample(evsel, event, &sample); + if (ret) + return ret; + + /* + * Loop through the auxtrace index to find the buffer that matches up with this aux event. + */ + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { + for (i = 0; i < auxtrace_index->nr; i++) { + ent = &auxtrace_index->entries[i]; + ret = cs_etm__queue_aux_fragment(session, ent->file_offset, + ent->sz, &event->aux, &sample); + /* + * Stop search on error or successful values. Continue search on + * 1 ('not found') + */ + if (ret != 1) + return ret; + } + } + + /* + * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but + * don't exit with an error because it will still be possible to decode other aux records. + */ + pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); + return 0; +} + +static int cs_etm__queue_aux_records(struct perf_session *session) +{ + struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index, + struct auxtrace_index, list); + if (index && index->nr > 0) + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__queue_aux_records_cb, NULL); + + /* + * We would get here if there are no entries in the index (either no auxtrace + * buffers or no index at all). Fail silently as there is the possibility of + * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still + * false. + * + * In that scenario, buffers will not be split by AUX records. + */ + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2883,7 +3049,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - err = auxtrace_queues__process_index(&etm->queues, session); + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; From 775da83005cb61d4c213c636df9337da05714ff1 Mon Sep 17 00:00:00 2001 From: Jinzhou Su Date: Tue, 13 Jul 2021 09:26:11 +0800 Subject: [PATCH 0395/1469] drm/amdgpu: add another Renoir DID Add new PCI device id. Signed-off-by: Jinzhou Su Reviewed-by: Huang Rui Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.11.x --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 71beb0db0125..abb928894eac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1168,6 +1168,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ + {0x1002, 0x15E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, From 23e9592b06b43cea4d6799843795beca13437907 Mon Sep 17 00:00:00 2001 From: Alex Hung Date: Sat, 10 Jul 2021 13:08:10 -0600 Subject: [PATCH 0396/1469] platform/x86: wireless-hotkey: remove hardcoded "hp" from the error message This driver is no longer specific to HP laptops so "hp" in the error message is no longer applicable. Signed-off-by: Alex Hung Link: https://lore.kernel.org/r/20210710190810.313104-1-alex.hung@canonical.com Signed-off-by: Hans de Goede --- drivers/platform/x86/wireless-hotkey.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/wireless-hotkey.c b/drivers/platform/x86/wireless-hotkey.c index b010e4ca3383..11c60a273446 100644 --- a/drivers/platform/x86/wireless-hotkey.c +++ b/drivers/platform/x86/wireless-hotkey.c @@ -78,7 +78,7 @@ static int wl_add(struct acpi_device *device) err = wireless_input_setup(); if (err) - pr_err("Failed to setup hp wireless hotkeys\n"); + pr_err("Failed to setup wireless hotkeys\n"); return err; } From 9c23aa51477a37f8b56c3c40192248db0663c196 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 14 Jul 2021 19:00:21 +0200 Subject: [PATCH 0397/1469] r8152: Fix potential PM refcount imbalance rtl8152_close() takes the refcount via usb_autopm_get_interface() but it doesn't release when RTL8152_UNPLUG test hits. This may lead to the imbalance of PM refcount. This patch addresses it. Link: https://bugzilla.suse.com/show_bug.cgi?id=1186194 Signed-off-by: Takashi Iwai Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 1692d3b1b6e1..4096e20e9725 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -6763,10 +6763,11 @@ static int rtl8152_close(struct net_device *netdev) tp->rtl_ops.down(tp); mutex_unlock(&tp->control); - - usb_autopm_put_interface(tp->intf); } + if (!res) + usb_autopm_put_interface(tp->intf); + free_all_mem(tp); return res; From 776ac63a986d211286230c4fd70f85390eabedcd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 14 Jul 2021 19:00:22 +0200 Subject: [PATCH 0398/1469] r8152: Fix a deadlock by doubly PM resume r8152 driver sets up the MAC address at reset-resume, while rtl8152_set_mac_address() has the temporary autopm get/put. This may lead to a deadlock as the PM lock has been already taken for the execution of the runtime PM callback. This patch adds the workaround to avoid the superfluous autpm when called from rtl8152_reset_resume(). Link: https://bugzilla.suse.com/show_bug.cgi?id=1186194 Signed-off-by: Takashi Iwai Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4096e20e9725..e09b107b5c99 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1552,7 +1552,8 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex, u32 advertising); -static int rtl8152_set_mac_address(struct net_device *netdev, void *p) +static int __rtl8152_set_mac_address(struct net_device *netdev, void *p, + bool in_resume) { struct r8152 *tp = netdev_priv(netdev); struct sockaddr *addr = p; @@ -1561,9 +1562,11 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p) if (!is_valid_ether_addr(addr->sa_data)) goto out1; - ret = usb_autopm_get_interface(tp->intf); - if (ret < 0) - goto out1; + if (!in_resume) { + ret = usb_autopm_get_interface(tp->intf); + if (ret < 0) + goto out1; + } mutex_lock(&tp->control); @@ -1575,11 +1578,17 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p) mutex_unlock(&tp->control); - usb_autopm_put_interface(tp->intf); + if (!in_resume) + usb_autopm_put_interface(tp->intf); out1: return ret; } +static int rtl8152_set_mac_address(struct net_device *netdev, void *p) +{ + return __rtl8152_set_mac_address(netdev, p, false); +} + /* Devices containing proper chips can support a persistent * host system provided MAC address. * Examples of this are Dell TB15 and Dell WD15 docks @@ -1698,7 +1707,7 @@ static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa) return ret; } -static int set_ethernet_addr(struct r8152 *tp) +static int set_ethernet_addr(struct r8152 *tp, bool in_resume) { struct net_device *dev = tp->netdev; struct sockaddr sa; @@ -1711,7 +1720,7 @@ static int set_ethernet_addr(struct r8152 *tp) if (tp->version == RTL_VER_01) ether_addr_copy(dev->dev_addr, sa.sa_data); else - ret = rtl8152_set_mac_address(dev, &sa); + ret = __rtl8152_set_mac_address(dev, &sa, in_resume); return ret; } @@ -8444,7 +8453,7 @@ static int rtl8152_reset_resume(struct usb_interface *intf) clear_bit(SELECTIVE_SUSPEND, &tp->flags); tp->rtl_ops.init(tp); queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - set_ethernet_addr(tp); + set_ethernet_addr(tp, true); return rtl8152_resume(intf); } @@ -9645,7 +9654,7 @@ static int rtl8152_probe(struct usb_interface *intf, tp->rtl_fw.retry = true; #endif queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - set_ethernet_addr(tp); + set_ethernet_addr(tp, false); usb_set_intfdata(intf, tp); From 1a3402d93c73bf6bb4df6d7c2aac35abfc3c50e2 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 3 Jun 2021 01:15:59 +0200 Subject: [PATCH 0399/1469] posix-cpu-timers: Fix rearm racing against process tick Since the process wide cputime counter is started locklessly from posix_cpu_timer_rearm(), it can be concurrently stopped by operations on other timers from the same thread group, such as in the following unlucky scenario: CPU 0 CPU 1 ----- ----- timer_settime(TIMER B) posix_cpu_timer_rearm(TIMER A) cpu_clock_sample_group() (pct->timers_active already true) handle_posix_cpu_timers() check_process_timers() stop_process_timers() pct->timers_active = false arm_timer(TIMER A) tick -> run_posix_cpu_timers() // sees !pct->timers_active, ignore // our TIMER A Fix this with simply locking process wide cputime counting start and timer arm in the same block. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Fixes: 60f2ceaa8111 ("posix-cpu-timers: Remove unnecessary locking around cpu_clock_sample_group") Cc: stable@vger.kernel.org Cc: Oleg Nesterov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Eric W. Biederman --- kernel/time/posix-cpu-timers.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 29a5e54e6e10..517be7fd175e 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -991,6 +991,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) if (!p) goto out; + /* Protect timer list r/w in arm_timer() */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) + goto out; + /* * Fetch the current sample and update the timer's expiry time. */ @@ -1001,11 +1006,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) bump_cpu_timer(timer, now); - /* Protect timer list r/w in arm_timer() */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) - goto out; - /* * Now re-arm for the new expiry time. */ From aebacb7f6ca1926918734faae14d1f0b6fae5cb7 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Fri, 9 Jul 2021 16:13:25 +0200 Subject: [PATCH 0400/1469] timers: Fix get_next_timer_interrupt() with no timers pending 31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") subtly altered get_next_timer_interrupt()'s behaviour. The function no longer consistently returns KTIME_MAX with no timers pending. In order to decide if there are any timers pending we check whether the next expiry will happen NEXT_TIMER_MAX_DELTA jiffies from now. Unfortunately, the next expiry time and the timer base clock are no longer updated in unison. The former changes upon certain timer operations (enqueue, expire, detach), whereas the latter keeps track of jiffies as they move forward. Ultimately breaking the logic above. A simplified example: - Upon entering get_next_timer_interrupt() with: jiffies = 1 base->clk = 0; base->next_expiry = NEXT_TIMER_MAX_DELTA; 'base->next_expiry == base->clk + NEXT_TIMER_MAX_DELTA', the function returns KTIME_MAX. - 'base->clk' is updated to the jiffies value. - The next time we enter get_next_timer_interrupt(), taking into account no timer operations happened: base->clk = 1; base->next_expiry = NEXT_TIMER_MAX_DELTA; 'base->next_expiry != base->clk + NEXT_TIMER_MAX_DELTA', the function returns a valid expire time, which is incorrect. This ultimately might unnecessarily rearm sched's timer on nohz_full setups, and add latency to the system[1]. So, introduce 'base->timers_pending'[2], update it every time 'base->next_expiry' changes, and use it in get_next_timer_interrupt(). [1] See tick_nohz_stop_tick(). [2] A quick pahole check on x86_64 and arm64 shows it doesn't make 'struct timer_base' any bigger. Fixes: 31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Frederic Weisbecker --- kernel/time/timer.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 3fadb58fc9d7..9eb11c2209e5 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -207,6 +207,7 @@ struct timer_base { unsigned int cpu; bool next_expiry_recalc; bool is_idle; + bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; + base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } @@ -1582,6 +1584,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) } base->next_expiry_recalc = false; + base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); return next; } @@ -1633,7 +1636,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; - bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1646,7 +1648,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; - is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); /* * We have a fresh next event. Check whether we can forward the @@ -1664,7 +1665,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - if (!is_max_delta) + if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. @@ -1947,6 +1948,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->timers_pending = false; base->is_idle = false; } return 0; From 4a5c155a5ab372516a1a5ddd29473f8f696feb79 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 15 Jul 2021 04:02:22 +0700 Subject: [PATCH 0401/1469] MAINTAINERS: Add Suravee Suthikulpanit as Reviewer for AMD IOMMU (AMD-Vi) To help review changes related to AMD IOMMU. Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/1626296542-30454-1-git-send-email-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..f2b60e955593 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -933,6 +933,7 @@ F: drivers/video/fbdev/geode/ AMD IOMMU (AMD-VI) M: Joerg Roedel +R: Suravee Suthikulpanit L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git From 95edbbf78c3bdbd1daa921dd4a2e61c751e469ba Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 15 Jul 2021 15:43:27 +0800 Subject: [PATCH 0402/1469] platform/x86: amd-pmc: Fix missing unlock on error in amd_pmc_send_cmd() Add the missing unlock before return from function amd_pmc_send_cmd() in the error handling case. Fixes: 95e1b60f8dc8 ("platform/x86: amd-pmc: Fix command completion code") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20210715074327.1966083-1-yangyingliang@huawei.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 680f94c7e075..663a4ca0580d 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -275,7 +275,7 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX); if (rc) { dev_err(dev->dev, "failed to talk to SMU\n"); - return rc; + goto out_unlock; } /* Write zero to response register */ From 32a19de21ae40f0601f48575b610dde4f518ccc6 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 7 Jul 2021 11:51:10 +0200 Subject: [PATCH 0403/1469] drm/vc4: hdmi: Drop devm interrupt handler for CEC interrupts The CEC interrupt handlers are registered through the devm_request_threaded_irq function. However, while free_irq is indeed called properly when the device is unbound or bind fails, it's called after unbind or bind is done. In our particular case, it means that on failure it creates a window where our interrupt handler can be called, but we're freeing every resource (CEC adapter, DRM objects, etc.) it might need. In order to address this, let's switch to the non-devm variant to control better when the handler will be unregistered and allow us to make it safe. Fixes: 15b4511a4af6 ("drm/vc4: add HDMI CEC support") Signed-off-by: Maxime Ripard Reviewed-by: Dave Stevenson Link: https://patchwork.freedesktop.org/patch/msgid/20210707095112.1469670-2-maxime@cerno.tech --- drivers/gpu/drm/vc4/vc4_hdmi.c | 49 +++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index aab1b36ceb3c..c2876731ee2d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1857,38 +1857,46 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi) vc4_hdmi_cec_update_clk_div(vc4_hdmi); if (vc4_hdmi->variant->external_irq_controller) { - ret = devm_request_threaded_irq(&pdev->dev, - platform_get_irq_byname(pdev, "cec-rx"), - vc4_cec_irq_handler_rx_bare, - vc4_cec_irq_handler_rx_thread, 0, - "vc4 hdmi cec rx", vc4_hdmi); + ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-rx"), + vc4_cec_irq_handler_rx_bare, + vc4_cec_irq_handler_rx_thread, 0, + "vc4 hdmi cec rx", vc4_hdmi); if (ret) goto err_delete_cec_adap; - ret = devm_request_threaded_irq(&pdev->dev, - platform_get_irq_byname(pdev, "cec-tx"), - vc4_cec_irq_handler_tx_bare, - vc4_cec_irq_handler_tx_thread, 0, - "vc4 hdmi cec tx", vc4_hdmi); + ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-tx"), + vc4_cec_irq_handler_tx_bare, + vc4_cec_irq_handler_tx_thread, 0, + "vc4 hdmi cec tx", vc4_hdmi); if (ret) - goto err_delete_cec_adap; + goto err_remove_cec_rx_handler; } else { HDMI_WRITE(HDMI_CEC_CPU_MASK_SET, 0xffffffff); - ret = devm_request_threaded_irq(&pdev->dev, platform_get_irq(pdev, 0), - vc4_cec_irq_handler, - vc4_cec_irq_handler_thread, 0, - "vc4 hdmi cec", vc4_hdmi); + ret = request_threaded_irq(platform_get_irq(pdev, 0), + vc4_cec_irq_handler, + vc4_cec_irq_handler_thread, 0, + "vc4 hdmi cec", vc4_hdmi); if (ret) goto err_delete_cec_adap; } ret = cec_register_adapter(vc4_hdmi->cec_adap, &pdev->dev); if (ret < 0) - goto err_delete_cec_adap; + goto err_remove_handlers; return 0; +err_remove_handlers: + if (vc4_hdmi->variant->external_irq_controller) + free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi); + else + free_irq(platform_get_irq(pdev, 0), vc4_hdmi); + +err_remove_cec_rx_handler: + if (vc4_hdmi->variant->external_irq_controller) + free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi); + err_delete_cec_adap: cec_delete_adapter(vc4_hdmi->cec_adap); @@ -1897,6 +1905,15 @@ err_delete_cec_adap: static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi) { + struct platform_device *pdev = vc4_hdmi->pdev; + + if (vc4_hdmi->variant->external_irq_controller) { + free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi); + free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi); + } else { + free_irq(platform_get_irq(pdev, 0), vc4_hdmi); + } + cec_unregister_adapter(vc4_hdmi->cec_adap); } #else From f8c2602733c953ed7a16e060640b8e96f9d94b9b Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 25 Jun 2021 23:50:07 +0200 Subject: [PATCH 0404/1469] s390/ftrace: fix ftrace_update_ftrace_func implementation s390 enforces DYNAMIC_FTRACE if FUNCTION_TRACER is selected. At the same time implementation of ftrace_caller is not compliant with HAVE_DYNAMIC_FTRACE since it doesn't provide implementation of ftrace_update_ftrace_func() and calls ftrace_trace_function() directly. The subtle difference is that during ftrace code patching ftrace replaces function tracer via ftrace_update_ftrace_func() and activates it back afterwards. Unexpected direct calls to ftrace_trace_function() during ftrace code patching leads to nullptr-dereferences when tracing is activated for one of functions which are used during code patching. Those function currently are: copy_from_kernel_nofault() copy_from_kernel_nofault_allowed() preempt_count_sub() [with debug_defconfig] preempt_count_add() [with debug_defconfig] Corresponding KASAN report: BUG: KASAN: nullptr-dereference in function_trace_call+0x316/0x3b0 Read of size 4 at addr 0000000000001e08 by task migration/0/15 CPU: 0 PID: 15 Comm: migration/0 Tainted: G B 5.13.0-41423-g08316af3644d Hardware name: IBM 3906 M04 704 (LPAR) Stopper: multi_cpu_stop+0x0/0x3e0 <- stop_machine_cpuslocked+0x1e4/0x218 Call Trace: [<0000000001f77caa>] show_stack+0x16a/0x1d0 [<0000000001f8de42>] dump_stack+0x15a/0x1b0 [<0000000001f81d56>] print_address_description.constprop.0+0x66/0x2e0 [<000000000082b0ca>] kasan_report+0x152/0x1c0 [<00000000004cfd8e>] function_trace_call+0x316/0x3b0 [<0000000001fb7082>] ftrace_caller+0x7a/0x7e [<00000000006bb3e6>] copy_from_kernel_nofault_allowed+0x6/0x10 [<00000000006bb42e>] copy_from_kernel_nofault+0x3e/0xd0 [<000000000014605c>] ftrace_make_call+0xb4/0x1f8 [<000000000047a1b4>] ftrace_replace_code+0x134/0x1d8 [<000000000047a6e0>] ftrace_modify_all_code+0x120/0x1d0 [<000000000047a7ec>] __ftrace_modify_code+0x5c/0x78 [<000000000042395c>] multi_cpu_stop+0x224/0x3e0 [<0000000000423212>] cpu_stopper_thread+0x33a/0x5a0 [<0000000000243ff2>] smpboot_thread_fn+0x302/0x708 [<00000000002329ea>] kthread+0x342/0x408 [<00000000001066b2>] __ret_from_fork+0x92/0xf0 [<0000000001fb57fa>] ret_from_fork+0xa/0x30 The buggy address belongs to the page: page:(____ptrval____) refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1 flags: 0x1ffff00000001000(reserved|node=0|zone=0|lastcpupid=0x1ffff) raw: 1ffff00000001000 0000040000000048 0000040000000048 0000000000000000 raw: 0000000000000000 0000000000000000 ffffffff00000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: 0000000000001d00: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 0000000000001d80: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 >0000000000001e00: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 ^ 0000000000001e80: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 0000000000001f00: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 ================================================================== To fix that introduce ftrace_func callback to be called from ftrace_caller and update it in ftrace_update_ftrace_func(). Fixes: 4cc9bed034d1 ("[S390] cleanup ftrace backend functions") Cc: stable@vger.kernel.org Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ftrace.h | 1 + arch/s390/kernel/ftrace.c | 2 ++ arch/s390/kernel/mcount.S | 4 ++-- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 695c61989f97..345cbe982a8b 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -19,6 +19,7 @@ void ftrace_caller(void); extern char ftrace_graph_caller_end; extern unsigned long ftrace_plt; +extern void *ftrace_func; struct dyn_arch_ftrace { }; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index c6ddeb5029b4..2d8f595d9196 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -40,6 +40,7 @@ * trampoline (ftrace_plt), which clobbers also r1. */ +void *ftrace_func __read_mostly = ftrace_stub; unsigned long ftrace_plt; int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, @@ -85,6 +86,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) int ftrace_update_ftrace_func(ftrace_func_t func) { + ftrace_func = func; return 0; } diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index faf64c2f90f5..6b13797143a7 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -59,13 +59,13 @@ ENTRY(ftrace_caller) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES aghik %r2,%r0,-MCOUNT_INSN_SIZE lgrl %r4,function_trace_op - lgrl %r1,ftrace_trace_function + lgrl %r1,ftrace_func #else lgr %r2,%r0 aghi %r2,-MCOUNT_INSN_SIZE larl %r4,function_trace_op lg %r4,0(%r4) - larl %r1,ftrace_trace_function + larl %r1,ftrace_func lg %r1,0(%r1) #endif lgr %r3,%r14 From ac34de14ac30ba4484d68f8845a54b6b6c23db42 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 28 Jun 2021 23:09:55 +0200 Subject: [PATCH 0405/1469] Revert "soc: imx8m: change to use platform driver" With the SoC matching changed to a platform driver the match data is available only after other drivers, which may rely on it are already probed. This breaks at least the CAAM driver on i.MX8M. Revert the change until all those drivers have been audited and changed to be able to eal with match data being available later in the boot process. Fixes: 7d981405d0fd ("soc: imx8m: change to use platform driver") Signed-off-by: Lucas Stach Tested-by: Frieder Schrempf Acked-by: Peng Fan Signed-off-by: Shawn Guo --- drivers/soc/imx/soc-imx8m.c | 84 ++++++------------------------------- 1 file changed, 12 insertions(+), 72 deletions(-) diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c index 071e14496e4b..cc57a384d74d 100644 --- a/drivers/soc/imx/soc-imx8m.c +++ b/drivers/soc/imx/soc-imx8m.c @@ -5,8 +5,6 @@ #include #include -#include -#include #include #include #include @@ -31,7 +29,7 @@ struct imx8_soc_data { char *name; - u32 (*soc_revision)(struct device *dev); + u32 (*soc_revision)(void); }; static u64 soc_uid; @@ -52,7 +50,7 @@ static u32 imx8mq_soc_revision_from_atf(void) static inline u32 imx8mq_soc_revision_from_atf(void) { return 0; }; #endif -static u32 __init imx8mq_soc_revision(struct device *dev) +static u32 __init imx8mq_soc_revision(void) { struct device_node *np; void __iomem *ocotp_base; @@ -77,20 +75,9 @@ static u32 __init imx8mq_soc_revision(struct device *dev) rev = REV_B1; } - if (dev) { - int ret; - - ret = nvmem_cell_read_u64(dev, "soc_unique_id", &soc_uid); - if (ret) { - iounmap(ocotp_base); - of_node_put(np); - return ret; - } - } else { - soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH); - soc_uid <<= 32; - soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW); - } + soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH); + soc_uid <<= 32; + soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW); iounmap(ocotp_base); of_node_put(np); @@ -120,7 +107,7 @@ static void __init imx8mm_soc_uid(void) of_node_put(np); } -static u32 __init imx8mm_soc_revision(struct device *dev) +static u32 __init imx8mm_soc_revision(void) { struct device_node *np; void __iomem *anatop_base; @@ -138,15 +125,7 @@ static u32 __init imx8mm_soc_revision(struct device *dev) iounmap(anatop_base); of_node_put(np); - if (dev) { - int ret; - - ret = nvmem_cell_read_u64(dev, "soc_unique_id", &soc_uid); - if (ret) - return ret; - } else { - imx8mm_soc_uid(); - } + imx8mm_soc_uid(); return rev; } @@ -171,7 +150,7 @@ static const struct imx8_soc_data imx8mp_soc_data = { .soc_revision = imx8mm_soc_revision, }; -static __maybe_unused const struct of_device_id imx8_machine_match[] = { +static __maybe_unused const struct of_device_id imx8_soc_match[] = { { .compatible = "fsl,imx8mq", .data = &imx8mq_soc_data, }, { .compatible = "fsl,imx8mm", .data = &imx8mm_soc_data, }, { .compatible = "fsl,imx8mn", .data = &imx8mn_soc_data, }, @@ -179,20 +158,12 @@ static __maybe_unused const struct of_device_id imx8_machine_match[] = { { } }; -static __maybe_unused const struct of_device_id imx8_soc_match[] = { - { .compatible = "fsl,imx8mq-soc", .data = &imx8mq_soc_data, }, - { .compatible = "fsl,imx8mm-soc", .data = &imx8mm_soc_data, }, - { .compatible = "fsl,imx8mn-soc", .data = &imx8mn_soc_data, }, - { .compatible = "fsl,imx8mp-soc", .data = &imx8mp_soc_data, }, - { } -}; - #define imx8_revision(soc_rev) \ soc_rev ? \ kasprintf(GFP_KERNEL, "%d.%d", (soc_rev >> 4) & 0xf, soc_rev & 0xf) : \ "unknown" -static int imx8_soc_info(struct platform_device *pdev) +static int __init imx8_soc_init(void) { struct soc_device_attribute *soc_dev_attr; struct soc_device *soc_dev; @@ -211,10 +182,7 @@ static int imx8_soc_info(struct platform_device *pdev) if (ret) goto free_soc; - if (pdev) - id = of_match_node(imx8_soc_match, pdev->dev.of_node); - else - id = of_match_node(imx8_machine_match, of_root); + id = of_match_node(imx8_soc_match, of_root); if (!id) { ret = -ENODEV; goto free_soc; @@ -223,16 +191,8 @@ static int imx8_soc_info(struct platform_device *pdev) data = id->data; if (data) { soc_dev_attr->soc_id = data->name; - if (data->soc_revision) { - if (pdev) { - soc_rev = data->soc_revision(&pdev->dev); - ret = soc_rev; - if (ret < 0) - goto free_soc; - } else { - soc_rev = data->soc_revision(NULL); - } - } + if (data->soc_revision) + soc_rev = data->soc_revision(); } soc_dev_attr->revision = imx8_revision(soc_rev); @@ -270,24 +230,4 @@ free_soc: kfree(soc_dev_attr); return ret; } - -/* Retain device_initcall is for backward compatibility with DTS. */ -static int __init imx8_soc_init(void) -{ - if (of_find_matching_node_and_match(NULL, imx8_soc_match, NULL)) - return 0; - - return imx8_soc_info(NULL); -} device_initcall(imx8_soc_init); - -static struct platform_driver imx8_soc_info_driver = { - .probe = imx8_soc_info, - .driver = { - .name = "imx8_soc_info", - .of_match_table = imx8_soc_match, - }, -}; - -module_platform_driver(imx8_soc_info_driver); -MODULE_LICENSE("GPL v2"); From e44fbdb68049539de9923ce4bad2d277aef54892 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 12 Jul 2021 11:36:50 +1000 Subject: [PATCH 0406/1469] KVM: PPC: Book3S HV P9: Fix guest TM support The conversion to C introduced several bugs in TM handling that can cause host crashes with TM bad thing interrupts. Mostly just simple typos or missed logic in the conversion that got through due to my not testing TM in the guest sufficiently. - Early TM emulation for the softpatch interrupt should be done if fake suspend mode is _not_ active. - Early TM emulation wants to return immediately to the guest so as to not doom transactions unnecessarily. - And if exiting from the guest, the host MSR should include the TM[S] bit if the guest was T/S, before it is treclaimed. After this fix, all the TM selftests pass when running on a P9 processor that implements TM with softpatch interrupt. Fixes: 89d35b2391015 ("KVM: PPC: Book3S HV P9: Implement the rest of the P9 path in C") Reported-by: Alexey Kardashevskiy Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210712013650.376325-1-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv_p9_entry.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 83f592eadcd2..961b3d70483c 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -317,6 +317,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc */ mtspr(SPRN_HDEC, hdec); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +tm_return_to_guest: +#endif mtspr(SPRN_DAR, vcpu->arch.shregs.dar); mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); @@ -415,11 +418,23 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc * is in real suspend mode and is trying to transition to * transactional mode. */ - if (local_paca->kvm_hstate.fake_suspend && + if (!local_paca->kvm_hstate.fake_suspend && (vcpu->arch.shregs.msr & MSR_TS_S)) { if (kvmhv_p9_tm_emulation_early(vcpu)) { - /* Prevent it being handled again. */ - trap = 0; + /* + * Go straight back into the guest with the + * new NIP/MSR as set by TM emulation. + */ + mtspr(SPRN_HSRR0, vcpu->arch.regs.nip); + mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr); + + /* + * tm_return_to_guest re-loads SRR0/1, DAR, + * DSISR after RI is cleared, in case they had + * been clobbered by a MCE. + */ + __mtmsrd(0, 1); /* clear RI */ + goto tm_return_to_guest; } } #endif @@ -499,6 +514,10 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc * If we are in real mode, only switch MMU on after the MMU is * switched to host, to avoid the P9_RADIX_PREFETCH_BUG. */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + vcpu->arch.shregs.msr & MSR_TS_MASK) + msr |= MSR_TS_S; + __mtmsrd(msr, 0); end_timing(vcpu); From 21de80b53b3727c33d0771c5a28114be5803d157 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 2 Jul 2021 20:29:31 -0500 Subject: [PATCH 0407/1469] LICENSES/dual/CC-BY-4.0: Git rid of "smart quotes" A couple of exotic quote characters came in with this license text; they can confuse software that is not expecting non-ASCII text. Switch to normal quotes here, with no changes to the actual license text. Reported-by: Rahul T R Signed-off-by: Nishanth Menon CC: Greg Kroah-Hartman Acked-by: Thomas Gleixner Acked-by: Thorsten Leemhuis Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20210703012931.30604-1-nm@ti.com Signed-off-by: Jonathan Corbet --- LICENSES/dual/CC-BY-4.0 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/LICENSES/dual/CC-BY-4.0 b/LICENSES/dual/CC-BY-4.0 index 45a81b8e4669..869cad3d1643 100644 --- a/LICENSES/dual/CC-BY-4.0 +++ b/LICENSES/dual/CC-BY-4.0 @@ -392,7 +392,7 @@ Section 8 -- Interpretation. Creative Commons is not a party to its public licenses. Notwithstanding, Creative Commons may elect to apply one of its public licenses to material it publishes and in those instances -will be considered the “Licensor.” The text of the Creative Commons +will be considered the "Licensor." The text of the Creative Commons public licenses is dedicated to the public domain under the CC0 Public Domain Dedication. Except for the limited purpose of indicating that material is shared under a Creative Commons public license or as From 842f697776926b06ada93b16658cdd77cc0ef710 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 1 Jul 2021 13:31:52 +0200 Subject: [PATCH 0408/1469] Documentation/features: Update the ARCH_HAS_TICK_BROADCAST entry Risc-V gained support recently. Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/YN2nqOVHgGDt4Iid@gmail.com Signed-off-by: Jonathan Corbet --- .../features/time/arch-tick-broadcast/arch-support.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt index 8639fe8315f5..8dcaab070c7b 100644 --- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt +++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt @@ -22,7 +22,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | TODO | | sh: | ok | | sparc: | TODO | From d3fb38266afefc6424d7179c14936c5908d5e2f2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 1 Jul 2021 13:31:17 +0200 Subject: [PATCH 0409/1469] Documentation/features: Add THREAD_INFO_IN_TASK feature matrix Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/YN2nhV5F0hBVNPuX@gmail.com Signed-off-by: Jonathan Corbet --- .../core/thread-info-in-task/arch-support.txt | 32 +++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 Documentation/features/core/thread-info-in-task/arch-support.txt diff --git a/Documentation/features/core/thread-info-in-task/arch-support.txt b/Documentation/features/core/thread-info-in-task/arch-support.txt new file mode 100644 index 000000000000..9f0259bbd7df --- /dev/null +++ b/Documentation/features/core/thread-info-in-task/arch-support.txt @@ -0,0 +1,32 @@ +# +# Feature name: thread-info-in-task +# Kconfig: THREAD_INFO_IN_TASK +# description: arch makes use of the core kernel facility to embedd thread_info in task_struct +# + ----------------------- + | arch |status| + ----------------------- + | alpha: | TODO | + | arc: | TODO | + | arm: | TODO | + | arm64: | ok | + | csky: | TODO | + | h8300: | TODO | + | hexagon: | TODO | + | ia64: | TODO | + | m68k: | TODO | + | microblaze: | TODO | + | mips: | TODO | + | nds32: | ok | + | nios2: | TODO | + | openrisc: | TODO | + | parisc: | TODO | + | powerpc: | ok | + | riscv: | ok | + | s390: | ok | + | sh: | TODO | + | sparc: | TODO | + | um: | TODO | + | x86: | ok | + | xtensa: | TODO | + ----------------------- From 530c4374e21ae750c5fa5aa67b36a97635ddb379 Mon Sep 17 00:00:00 2001 From: Hu Haowen Date: Sun, 20 Jun 2021 09:04:44 +0800 Subject: [PATCH 0410/1469] docs/zh_CN: add a missing space character "LinusTorvalds" is not pretty. Replace it with "Linus Torvalds". Signed-off-by: Hu Haowen Link: https://lore.kernel.org/r/20210620010444.24813-1-src.res@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/process/2.Process.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/translations/zh_CN/process/2.Process.rst b/Documentation/translations/zh_CN/process/2.Process.rst index 229629e305ca..4a6ed0219494 100644 --- a/Documentation/translations/zh_CN/process/2.Process.rst +++ b/Documentation/translations/zh_CN/process/2.Process.rst @@ -47,7 +47,7 @@ （顺便说一句，值得注意的是，合并窗口期间集成的更改并不是凭空产生的；它们是经 提前收集、测试和分级的。稍后将详细描述该过程的工作方式。） -合并窗口持续大约两周。在这段时间结束时，LinusTorvalds将声明窗口已关闭，并 +合并窗口持续大约两周。在这段时间结束时，Linus Torvalds将声明窗口已关闭，并 释放第一个“rc”内核。例如，对于目标为5.6的内核，在合并窗口结束时发生的释放 将被称为5.6-rc1。-rc1 版本是一个信号，表示合并新特性的时间已经过去，稳定下一 个内核的时间已经到来。 @@ -168,7 +168,7 @@ Greg Kroah-Hartman领导。稳定团队将使用5.x.y编号方案不定期地发 补丁如何进入内核 ---------------- -只有一个人可以将补丁合并到主线内核存储库中：LinusTorvalds。但是，在进入 +只有一个人可以将补丁合并到主线内核存储库中：Linus Torvalds。但是，在进入 2.6.38内核的9500多个补丁中，只有112个（大约1.3%）是由Linus自己直接选择的。 内核项目已经发展到一个没有一个开发人员可以在没有支持的情况下检查和选择每个 补丁的规模。内核开发人员处理这种增长的方式是使用围绕信任链构建的助理系统。 From d549c66766ee42175e2f4a47219b4103ddab4ffa Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 22 Jun 2021 13:33:27 +0200 Subject: [PATCH 0411/1469] dt-bindings: net: dsa: sja1105: Fix indentation warnings Some of the lines aren't properly indented, causing yamllint to warn about them: .../nxp,sja1105.yaml:70:17: [warning] wrong indentation: expected 18 but found 16 (indentation) Use the proper indentation to fix those warnings. Signed-off-by: Thierry Reding Fixes: 070f5b701d559ae1 ("dt-bindings: net: dsa: sja1105: add SJA1110 bindings") Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210622113327.3613595-1-thierry.reding@gmail.com Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index 0b8a05dd52e6..f978f8719d8e 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -67,8 +67,8 @@ properties: reg: oneOf: - enum: - - 0 - - 1 + - 0 + - 1 required: - compatible From 004d62eb4e57db3c391ed0df007cc11c93b6fbeb Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 1 Jul 2021 22:55:00 +0300 Subject: [PATCH 0412/1469] kvm: debugfs: fix memory leak in kvm_create_vm_debugfs In commit bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") loop for filling debugfs_stat_data was copy-pasted 2 times, but in the second loop pointers are saved over pointers allocated in the first loop. All this causes is a memory leak, fix it. Fixes: bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") Signed-off-by: Pavel Skripkin Reviewed-by: Jing Zhang Message-Id: <20210701195500.27097-1-paskripkin@gmail.com> Reviewed-by: Jing Zhang Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f7445c3bcd90..6980dabe9df5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -935,7 +935,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VCPU; - kvm->debugfs_stat_data[i] = stat_data; + kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); From 6f2f86ec28fb68cf6a342767a35f7b13703aa96f Mon Sep 17 00:00:00 2001 From: Ricardo Koller Date: Fri, 2 Jul 2021 13:10:42 -0700 Subject: [PATCH 0413/1469] KVM: selftests: Address extra memslot parameters in vm_vaddr_alloc Commit a75a895e6457 ("KVM: selftests: Unconditionally use memslot 0 for vaddr allocations") removed the memslot parameters from vm_vaddr_alloc. It addressed all callers except one under lib/aarch64/, due to a race with commit e3db7579ef35 ("KVM: selftests: Add exception handling support for aarch64") Fix the vm_vaddr_alloc call in lib/aarch64/processor.c. Reported-by: Zenghui Yu Signed-off-by: Ricardo Koller Message-Id: <20210702201042.4036162-1-ricarkol@google.com> Reviewed-by: Eric Auger Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/lib/aarch64/processor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 9f49f6caafe5..632b74d6b3ca 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -401,7 +401,7 @@ unexpected_exception: void vm_init_descriptor_tables(struct kvm_vm *vm) { vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers), - vm->page_size, 0, 0); + vm->page_size); *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; } From f85d40160691881a17a397c448d799dfc90987ba Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 29 Jun 2021 01:26:32 +0800 Subject: [PATCH 0414/1469] KVM: X86: Disable hardware breakpoints unconditionally before kvm_x86->run() When the host is using debug registers but the guest is not using them nor is the guest in guest-debug state, the kvm code does not reset the host debug registers before kvm_x86->run(). Rather, it relies on the hardware vmentry instruction to automatically reset the dr7 registers which ensures that the host breakpoints do not affect the guest. This however violates the non-instrumentable nature around VM entry and exit; for example, when a host breakpoint is set on vcpu->arch.cr2, Another issue is consistency. When the guest debug registers are active, the host breakpoints are reset before kvm_x86->run(). But when the guest debug registers are inactive, the host breakpoints are delayed to be disabled. The host tracing tools may see different results depending on what the guest is doing. To fix the problems, we clear %db7 unconditionally before kvm_x86->run() if the host has set any breakpoints, no matter if the guest is using them or not. Signed-off-by: Lai Jiangshan Message-Id: <20210628172632.81029-1-jiangshanlai@gmail.com> Cc: stable@vger.kernel.org [Only clear %db7 instead of reloading all debug registers. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf10d196ca65..c471b1375f36 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9597,6 +9597,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; + } else if (unlikely(hw_breakpoint_active())) { + set_debugreg(0, 7); } for (;;) { From c0e1303ed4cc9e7ce39f106b471ad92ca559e3d3 Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 8 Jul 2021 07:57:02 +0800 Subject: [PATCH 0415/1469] KVM: VMX: Remove vmx_msr_index from vmx.h vmx_msr_index was used to record the list of MSRs which can be lazily restored when kvm returns to userspace. It is now reimplemented as kvm_uret_msrs_list, a common x86 list which is only used inside x86.c. So just remove the obsolete declaration in vmx.h. Signed-off-by: Yu Zhang Message-Id: <20210707235702.31595-1-yu.c.zhang@linux.intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 3979a947933a..db88ed4f2121 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -14,8 +14,6 @@ #include "vmx_ops.h" #include "cpuid.h" -extern const u32 vmx_msr_index[]; - #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 #define MSR_TYPE_RW 3 From 991afbbee8ac93b055a27477278a5fb556af1ff4 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:50:58 +0300 Subject: [PATCH 0416/1469] KVM: SVM: #SMI interception must not skip the instruction Commit 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code"), unfortunately made a mistake of treating nop_on_interception and nop_interception in the same way. Former does truly nothing while the latter skips the instruction. SMI VM exit handler should do nothing. (SMI itself is handled by the host when we do STGI) Fixes: 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code") Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-2-mlevitsk@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ca5614a48b21..80790faf6370 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2106,6 +2106,11 @@ static int nmi_interception(struct kvm_vcpu *vcpu) return 1; } +static int smi_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int intr_interception(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; @@ -3080,7 +3085,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, - [SVM_EXIT_SMI] = kvm_emulate_as_nop, + [SVM_EXIT_SMI] = smi_interception, [SVM_EXIT_INIT] = kvm_emulate_as_nop, [SVM_EXIT_VINTR] = interrupt_window_interception, [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, From 896707c212d440a6863ce0a3930c8a609e24497d Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:50:59 +0300 Subject: [PATCH 0417/1469] KVM: SVM: remove INIT intercept handler Kernel never sends real INIT even to CPUs, other than on boot. Thus INIT interception is an error which should be caught by a check for an unknown VMexit reason. On top of that, the current INIT VM exit handler skips the current instruction which is wrong. That was added in commit 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code"). Fixes: 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code") Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-3-mlevitsk@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 80790faf6370..18aa4d45cc64 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3086,7 +3086,6 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = smi_interception, - [SVM_EXIT_INIT] = kvm_emulate_as_nop, [SVM_EXIT_VINTR] = interrupt_window_interception, [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, [SVM_EXIT_CPUID] = kvm_emulate_cpuid, From 4b639a9f82fcf15497d1613a29aa1df798a24029 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:51:00 +0300 Subject: [PATCH 0418/1469] KVM: SVM: add module param to control the #SMI interception In theory there are no side effects of not intercepting #SMI, because then #SMI becomes transparent to the OS and the KVM. Plus an observation on recent Zen2 CPUs reveals that these CPUs ignore #SMI interception and never deliver #SMI VMexits. This is also useful to test nested KVM to see that L1 handles #SMIs correctly in case when L1 doesn't intercept #SMI. Finally the default remains the same, the SMI are intercepted by default thus this patch doesn't have any effect unless non default module param value is used. Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 4 ++++ arch/x86/kvm/svm/svm.c | 10 +++++++++- arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 21d03e3a5dfd..2884c54a72bb 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -154,6 +154,10 @@ void recalc_intercepts(struct vcpu_svm *svm) for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; + + /* If SMI is not intercepted, ignore guest SMI intercept as well */ + if (!intercept_smi) + vmcb_clr_intercept(c, INTERCEPT_SMI); } static void copy_vmcb_control_area(struct vmcb_control_area *dst, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 18aa4d45cc64..63488d3beb5b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -198,6 +198,11 @@ module_param(avic, bool, 0444); bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); + +bool intercept_smi = true; +module_param(intercept_smi, bool, 0444); + + static bool svm_gp_erratum_intercept = true; static u8 rsm_ins_bytes[] = "\x0f\xaa"; @@ -1185,7 +1190,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_set_intercept(svm, INTERCEPT_INTR); svm_set_intercept(svm, INTERCEPT_NMI); - svm_set_intercept(svm, INTERCEPT_SMI); + + if (intercept_smi) + svm_set_intercept(svm, INTERCEPT_SMI); + svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0); svm_set_intercept(svm, INTERCEPT_RDPMC); svm_set_intercept(svm, INTERCEPT_CPUID); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f89b623bb591..8cb3bd59c5ea 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -31,6 +31,7 @@ #define MSRPM_OFFSETS 16 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +extern bool intercept_smi; /* * Clean bits in VMCB. From b4a693924aab93f3747465b2261add46c82c3220 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 May 2021 10:58:25 -0700 Subject: [PATCH 0419/1469] KVM: SVM: Return -EFAULT if copy_to_user() for SEV mig packet header fails Return -EFAULT if copy_to_user() fails; if accessing user memory faults, copy_to_user() returns the number of bytes remaining, not an error code. Reported-by: Dan Carpenter Cc: Steve Rutherford Cc: Brijesh Singh Cc: Ashish Kalra Fixes: d3d1af85e2c7 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") Signed-off-by: Sean Christopherson Message-Id: <20210506175826.2166383-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 8d36f0c73071..3dc3e2897804 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1309,8 +1309,9 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) } /* Copy packet header to userspace. */ - ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, - params.hdr_len); + if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + params.hdr_len)) + ret = -EFAULT; e_free_trans_data: kfree(trans_data); From c7a1b2b678c54ac19320daf525038d0e2e43ca7c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 May 2021 10:58:26 -0700 Subject: [PATCH 0420/1469] KVM: SVM: Fix sev_pin_memory() error checks in SEV migration utilities Use IS_ERR() instead of checking for a NULL pointer when querying for sev_pin_memory() failures. sev_pin_memory() always returns an error code cast to a pointer, or a valid pointer; it never returns NULL. Reported-by: Dan Carpenter Cc: Steve Rutherford Cc: Brijesh Singh Cc: Ashish Kalra Fixes: d3d1af85e2c7 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") Fixes: 15fb7de1a7f5 ("KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command") Signed-off-by: Sean Christopherson Message-Id: <20210506175826.2166383-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 3dc3e2897804..02d60d7f903d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1271,8 +1271,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) - return -EFAULT; + if (IS_ERR(guest_page)) + return PTR_ERR(guest_page); /* allocate memory for header and transport buffer */ ret = -ENOMEM; @@ -1463,11 +1463,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.trans_len = params.trans_len; /* Pin guest memory */ - ret = -EFAULT; guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) + if (IS_ERR(guest_page)) { + ret = PTR_ERR(guest_page); goto e_free_trans; + } /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; From fce7e152ffc8f89d02a80617b16c7aa1527847c8 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:20 +0200 Subject: [PATCH 0421/1469] KVM: nSVM: Check the value written to MSR_VM_HSAVE_PA APM states that #GP is raised upon write to MSR_VM_HSAVE_PA when the supplied address is not page-aligned or is outside of "maximum supported physical address for this implementation". page_address_valid() check seems suitable. Also, forcefully page-align the address when it's written from VMM. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-2-vkuznets@redhat.com> Cc: stable@vger.kernel.org Reviewed-by: Maxim Levitsky [Add comment about behavior for host-provided values. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 63488d3beb5b..b6e91de891cb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2954,7 +2954,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm_disable_lbrv(vcpu); break; case MSR_VM_HSAVE_PA: - svm->nested.hsave_msr = data; + /* + * Old kernels did not validate the value written to + * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid + * value to allow live migrating buggy or malicious guests + * originating from those kernels. + */ + if (!msr->host_initiated && !page_address_valid(vcpu, data)) + return 1; + + svm->nested.hsave_msr = data & PAGE_MASK; break; case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); From fb79f566e4c99db8647cf0435e3732f12e856ab0 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:21 +0200 Subject: [PATCH 0422/1469] KVM: nSVM: Check that VM_HSAVE_PA MSR was set before VMRUN APM states that "The address written to the VM_HSAVE_PA MSR, which holds the address of the page used to save the host state on a VMRUN, must point to a hypervisor-owned page. If this check fails, the WRMSR will fail with a #GP(0) exception. Note that a value of 0 is not considered valid for the VM_HSAVE_PA MSR and a VMRUN that is attempted while the HSAVE_PA is 0 will fail with a #GP(0) exception." svm_set_msr() already checks that the supplied address is valid, so only check for '0' is missing. Add it to nested_svm_vmrun(). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-3-vkuznets@redhat.com> Reviewed-by: Maxim Levitsky Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2884c54a72bb..ec16a06f9aa8 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -622,6 +622,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) struct kvm_host_map map; u64 vmcb12_gpa; + if (!svm->nested.hsave_msr) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (is_smm(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; From 0a758290762cf6fb69ad09712ac834cd4f07504f Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:22 +0200 Subject: [PATCH 0423/1469] KVM: nSVM: Introduce svm_copy_vmrun_state() Separate the code setting non-VMLOAD-VMSAVE state from svm_set_nested_state() into its own function. This is going to be re-used from svm_enter_smm()/svm_leave_smm(). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 40 +++++++++++++++++++++------------------ arch/x86/kvm/svm/svm.h | 2 ++ 2 files changed, 24 insertions(+), 18 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index ec16a06f9aa8..c4296fb4b8be 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -701,6 +701,27 @@ out: return ret; } +/* Copy state save area fields which are handled by VMRUN */ +void svm_copy_vmrun_state(struct vmcb_save_area *from_save, + struct vmcb_save_area *to_save) +{ + to_save->es = from_save->es; + to_save->cs = from_save->cs; + to_save->ss = from_save->ss; + to_save->ds = from_save->ds; + to_save->gdtr = from_save->gdtr; + to_save->idtr = from_save->idtr; + to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED; + to_save->efer = from_save->efer; + to_save->cr0 = from_save->cr0; + to_save->cr3 = from_save->cr3; + to_save->cr4 = from_save->cr4; + to_save->rax = from_save->rax; + to_save->rsp = from_save->rsp; + to_save->rip = from_save->rip; + to_save->cpl = 0; +} + void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; @@ -1364,28 +1385,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - svm->vmcb01.ptr->save.es = save->es; - svm->vmcb01.ptr->save.cs = save->cs; - svm->vmcb01.ptr->save.ss = save->ss; - svm->vmcb01.ptr->save.ds = save->ds; - svm->vmcb01.ptr->save.gdtr = save->gdtr; - svm->vmcb01.ptr->save.idtr = save->idtr; - svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED; - svm->vmcb01.ptr->save.efer = save->efer; - svm->vmcb01.ptr->save.cr0 = save->cr0; - svm->vmcb01.ptr->save.cr3 = save->cr3; - svm->vmcb01.ptr->save.cr4 = save->cr4; - svm->vmcb01.ptr->save.rax = save->rax; - svm->vmcb01.ptr->save.rsp = save->rsp; - svm->vmcb01.ptr->save.rip = save->rip; - svm->vmcb01.ptr->save.cpl = 0; - + svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save); nested_load_control_from_vmcb12(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); - nested_vmcb02_prepare_control(svm); - kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8cb3bd59c5ea..fe87fd68b73b 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -464,6 +464,8 @@ void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); +void svm_copy_vmrun_state(struct vmcb_save_area *from_save, + struct vmcb_save_area *to_save); void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); From 37be407b2ce807179108eeac788805848fe048f1 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:23 +0200 Subject: [PATCH 0424/1469] KVM: nSVM: Fix L1 state corruption upon return from SMM VMCB split commit 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") broke return from SMM when we entered there from guest (L2) mode. Gen2 WS2016/Hyper-V is known to do this on boot. The problem manifests itself like this: kvm_exit: reason EXIT_RSM rip 0x7ffbb280 info 0 0 kvm_emulate_insn: 0:7ffbb280: 0f aa kvm_smm_transition: vcpu 0: leaving SMM, smbase 0x7ffb3000 kvm_nested_vmrun: rip: 0x000000007ffbb280 vmcb: 0x0000000008224000 nrip: 0xffffffffffbbe119 int_ctl: 0x01020000 event_inj: 0x00000000 npt: on kvm_nested_intercepts: cr_read: 0000 cr_write: 0010 excp: 40060002 intercepts: fd44bfeb 0000217f 00000000 kvm_entry: vcpu 0, rip 0xffffffffffbbe119 kvm_exit: reason EXIT_NPF rip 0xffffffffffbbe119 info 200000006 1ab000 kvm_nested_vmexit: vcpu 0 reason npf rip 0xffffffffffbbe119 info1 0x0000000200000006 info2 0x00000000001ab000 intr_info 0x00000000 error_code 0x00000000 kvm_page_fault: address 1ab000 error_code 6 kvm_nested_vmexit_inject: reason EXIT_NPF info1 200000006 info2 1ab000 int_info 0 int_info_err 0 kvm_entry: vcpu 0, rip 0x7ffbb280 kvm_exit: reason EXIT_EXCP_GP rip 0x7ffbb280 info 0 0 kvm_emulate_insn: 0:7ffbb280: 0f aa kvm_inj_exception: #GP (0x0) Note: return to L2 succeeded but upon first exit to L1 its RIP points to 'RSM' instruction but we're not in SMM. The problem appears to be that VMCB01 gets irreversibly destroyed during SMM execution. Previously, we used to have 'hsave' VMCB where regular (pre-SMM) L1's state was saved upon nested_svm_vmexit() but now we just switch to VMCB01 from VMCB02. Pre-split (working) flow looked like: - SMM is triggered during L2's execution - L2's state is pushed to SMRAM - nested_svm_vmexit() restores L1's state from 'hsave' - SMM -> RSM - enter_svm_guest_mode() switches to L2 but keeps 'hsave' intact so we have pre-SMM (and pre L2 VMRUN) L1's state there - L2's state is restored from SMRAM - upon first exit L1's state is restored from L1. This was always broken with regards to svm_get_nested_state()/ svm_set_nested_state(): 'hsave' was never a part of what's being save and restored so migration happening during SMM triggered from L2 would never restore L1's state correctly. Post-split flow (broken) looks like: - SMM is triggered during L2's execution - L2's state is pushed to SMRAM - nested_svm_vmexit() switches to VMCB01 from VMCB02 - SMM -> RSM - enter_svm_guest_mode() switches from VMCB01 to VMCB02 but pre-SMM VMCB01 is already lost. - L2's state is restored from SMRAM - upon first exit L1's state is restored from VMCB01 but it is corrupted (reflects the state during 'RSM' execution). VMX doesn't have this problem because unlike VMCB, VMCS keeps both guest and host state so when we switch back to VMCS02 L1's state is intact there. To resolve the issue we need to save L1's state somewhere. We could've created a third VMCB for SMM but that would require us to modify saved state format. L1's architectural HSAVE area (pointed by MSR_VM_HSAVE_PA) seems appropriate: L0 is free to save any (or none) of L1's state there. Currently, KVM does 'none'. Note, for nested state migration to succeed, both source and destination hypervisors must have the fix. We, however, don't need to create a new flag indicating the fact that HSAVE area is now populated as migration during SMM triggered from L2 was always broken. Fixes: 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b6e91de891cb..cf8471890266 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4309,6 +4309,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map_save; int ret; if (is_guest_mode(vcpu)) { @@ -4324,6 +4325,29 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) ret = nested_svm_vmexit(svm); if (ret) return ret; + + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, + map_save.hva + 0x400); + + kvm_vcpu_unmap(vcpu, &map_save, true); } return 0; } @@ -4331,7 +4355,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_host_map map; + struct kvm_host_map map, map_save; int ret = 0; if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { @@ -4355,6 +4379,19 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva); kvm_vcpu_unmap(vcpu, &map, true); + + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); } } From bb00bd9c0862558c6528e3ac97470aee222436ef Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:24 +0200 Subject: [PATCH 0425/1469] KVM: nSVM: Restore nested control upon leaving SMM If the VM was migrated while in SMM, no nested state was saved/restored, and therefore svm_leave_smm has to load both save and control area of the vmcb12. Save area is already loaded from HSAVE area, so now load the control area as well from the vmcb12. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-6-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 4 ++-- arch/x86/kvm/svm/svm.c | 7 ++++++- arch/x86/kvm/svm/svm.h | 2 ++ 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index c4296fb4b8be..3bd09c50c98b 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -308,8 +308,8 @@ static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, return true; } -static void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control) { copy_vmcb_control_area(&svm->nested.ctl, control); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cf8471890266..664d20f0689c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4362,6 +4362,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + struct vmcb *vmcb12; if (guest) { if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) @@ -4377,7 +4378,11 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (svm_allocate_nested(svm)) return 1; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva); + vmcb12 = map.hva; + + nested_load_control_from_vmcb12(svm, &vmcb12->control); + + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); kvm_vcpu_unmap(vcpu, &map, true); /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index fe87fd68b73b..7e2090752d8f 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -482,6 +482,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); From d951b2210c1ad2dc08345bb8d97e5a172a15261e Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:25 +0200 Subject: [PATCH 0426/1469] KVM: selftests: smm_test: Test SMM enter from L2 Two additional tests are added: - SMM triggered from L2 does not currupt L1 host state. - Save/restore during SMM triggered from L2 does not corrupt guest/host state. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-7-vkuznets@redhat.com> Reviewed-by: Maxim Levitsky Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/smm_test.c | 70 +++++++++++++++++-- 1 file changed, 64 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index c1f831803ad2..d0fe2fdce58c 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -53,15 +53,28 @@ static inline void sync_with_host(uint64_t phase) : "+a" (phase)); } -void self_smi(void) +static void self_smi(void) { x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); } -void guest_code(void *arg) +static void l2_guest_code(void) { + sync_with_host(8); + + sync_with_host(10); + + vmcall(); +} + +static void guest_code(void *arg) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + struct svm_test_data *svm = arg; + struct vmx_pages *vmx_pages = arg; sync_with_host(1); @@ -74,21 +87,50 @@ void guest_code(void *arg) sync_with_host(4); if (arg) { - if (cpu_has_svm()) - generic_svm_setup(arg, NULL, NULL); - else - GUEST_ASSERT(prepare_for_vmx_operation(arg)); + if (cpu_has_svm()) { + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + } else { + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + } sync_with_host(5); self_smi(); sync_with_host(7); + + if (cpu_has_svm()) { + run_guest(svm->vmcb, svm->vmcb_gpa); + svm->vmcb->save.rip += 3; + run_guest(svm->vmcb, svm->vmcb_gpa); + } else { + vmlaunch(); + vmresume(); + } + + /* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */ + sync_with_host(12); } sync_with_host(DONE); } +void inject_smi(struct kvm_vm *vm) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vm, VCPU_ID, &events); + + events.smi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_SMM; + + vcpu_events_set(vm, VCPU_ID, &events); +} + int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; @@ -147,6 +189,22 @@ int main(int argc, char *argv[]) "Unexpected stage: #%x, got %x", stage, stage_reported); + /* + * Enter SMM during L2 execution and check that we correctly + * return from it. Do not perform save/restore while in SMM yet. + */ + if (stage == 8) { + inject_smi(vm); + continue; + } + + /* + * Perform save/restore while the guest is in SMM triggered + * during L2 execution. + */ + if (stage == 10) + inject_smi(vm); + state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); kvm_vm_restart(vm, O_RDWR); From e8917266ae0944385d50da5e691c89f64c5975a3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 13 Jul 2021 13:34:53 -0600 Subject: [PATCH 0427/1469] dt-bindings: More dropping redundant minItems/maxItems Another round of removing redundant minItems/maxItems from new schema in the recent merge window. If a property has an 'items' list, then a 'minItems' or 'maxItems' with the same size as the list is redundant and can be dropped. Note that is DT schema specific behavior and not standard json-schema behavior. The tooling will fixup the final schema adding any unspecified minItems/maxItems. This condition is partially checked with the meta-schema already, but only if both 'minItems' and 'maxItems' are equal to the 'items' length. An improved meta-schema is pending. Cc: Stephen Boyd Cc: Joerg Roedel Cc: Will Deacon Cc: Krzysztof Kozlowski Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Cc: Alessandro Zummo Cc: Alexandre Belloni Cc: Greg Kroah-Hartman Cc: Sureshkumar Relli Cc: Brian Norris Cc: Kamal Dasu Cc: Linus Walleij Cc: Sebastian Siewior Cc: Laurent Pinchart Cc: linux-clk@vger.kernel.org Cc: iommu@lists.linux-foundation.org Cc: linux-mtd@lists.infradead.org Cc: linux-rtc@vger.kernel.org Cc: linux-usb@vger.kernel.org Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Acked-by: Alexandre Belloni Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20210713193453.690290-1-robh@kernel.org --- .../devicetree/bindings/clock/brcm,iproc-clocks.yaml | 1 - .../devicetree/bindings/iommu/rockchip,iommu.yaml | 2 -- .../bindings/memory-controllers/arm,pl353-smc.yaml | 1 - Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml | 8 -------- .../devicetree/bindings/rtc/faraday,ftrtc010.yaml | 1 - Documentation/devicetree/bindings/usb/nxp,isp1760.yaml | 2 -- 6 files changed, 15 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml index 8dc7b404ee12..1174c9aa9934 100644 --- a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml +++ b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml @@ -50,7 +50,6 @@ properties: reg: minItems: 1 - maxItems: 3 items: - description: base register - description: power register diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml index d2e28a9e3545..ba9124f721f1 100644 --- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml @@ -28,14 +28,12 @@ properties: - description: configuration registers for MMU instance 0 - description: configuration registers for MMU instance 1 minItems: 1 - maxItems: 2 interrupts: items: - description: interruption for MMU instance 0 - description: interruption for MMU instance 1 minItems: 1 - maxItems: 2 clocks: items: diff --git a/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml b/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml index 7a63c85ef8c5..01c9acf9275d 100644 --- a/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml @@ -57,7 +57,6 @@ properties: ranges: minItems: 1 - maxItems: 3 description: | Memory bus areas for interacting with the devices. Reflects the memory layout with four integer values following: diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml index e5f1a33332a5..dd5a64969e37 100644 --- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml +++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml @@ -84,7 +84,6 @@ properties: interrupts: minItems: 1 - maxItems: 3 items: - description: NAND CTLRDY interrupt - description: FLASH_DMA_DONE if flash DMA is available @@ -92,7 +91,6 @@ properties: interrupt-names: minItems: 1 - maxItems: 3 items: - const: nand_ctlrdy - const: flash_dma_done @@ -148,8 +146,6 @@ allOf: then: properties: reg-names: - minItems: 2 - maxItems: 2 items: - const: nand - const: nand-int-base @@ -161,8 +157,6 @@ allOf: then: properties: reg-names: - minItems: 3 - maxItems: 3 items: - const: nand - const: nand-int-base @@ -175,8 +169,6 @@ allOf: then: properties: reg-names: - minItems: 3 - maxItems: 3 items: - const: nand - const: iproc-idm diff --git a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml index 657c13b62b67..056d42daae06 100644 --- a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml +++ b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml @@ -30,7 +30,6 @@ properties: maxItems: 1 clocks: - minItems: 2 items: - description: PCLK clocks - description: EXTCLK clocks. Faraday calls it CLK1HZ and says the clock diff --git a/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml b/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml index a88f99adfe8e..f238848ad094 100644 --- a/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml +++ b/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml @@ -25,14 +25,12 @@ properties: interrupts: minItems: 1 - maxItems: 2 items: - description: Host controller interrupt - description: Device controller interrupt in isp1761 interrupt-names: minItems: 1 - maxItems: 2 items: - const: host - const: peripheral From f88321a3bf775649c685379a25fb9f3f79836bfd Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 13 Jul 2021 13:35:14 -0600 Subject: [PATCH 0428/1469] dt-bindings: Move fixed string 'patternProperties' to 'properties' There's no need for fixed strings to be under 'patternProperties', so move them under 'properties' instead. Cc: Jean Delvare Cc: Guenter Roeck Cc: Kishon Vijay Abraham I Cc: Vinod Koul Cc: Saravanan Sekar Cc: Mark Brown Cc: Jagan Teki Cc: Troy Kisky Cc: linux-hwmon@vger.kernel.org Cc: linux-phy@lists.infradead.org Cc: linux-spi@vger.kernel.org Signed-off-by: Rob Herring Acked-by: Mark Brown Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20210713193514.690894-1-robh@kernel.org --- .../devicetree/bindings/hwmon/adt7475.yaml | 22 ++++---- .../bindings/phy/ti,phy-j721e-wiz.yaml | 56 +++++++++---------- .../bindings/regulator/mps,mpq7920.yaml | 6 +- .../regulator/nxp,pf8x00-regulator.yaml | 3 +- .../bindings/spi/spi-controller.yaml | 32 +++++------ 5 files changed, 60 insertions(+), 59 deletions(-) diff --git a/Documentation/devicetree/bindings/hwmon/adt7475.yaml b/Documentation/devicetree/bindings/hwmon/adt7475.yaml index ad0ec9f35bd8..7d9c083632b9 100644 --- a/Documentation/devicetree/bindings/hwmon/adt7475.yaml +++ b/Documentation/devicetree/bindings/hwmon/adt7475.yaml @@ -39,17 +39,7 @@ properties: reg: maxItems: 1 -patternProperties: - "^adi,bypass-attenuator-in[0-4]$": - description: | - Configures bypassing the individual voltage input attenuator. If - set to 1 the attenuator is bypassed if set to 0 the attenuator is - not bypassed. If the property is absent then the attenuator - retains it's configuration from the bios/bootloader. - $ref: /schemas/types.yaml#/definitions/uint32 - enum: [0, 1] - - "^adi,pwm-active-state$": + adi,pwm-active-state: description: | Integer array, represents the active state of the pwm outputs If set to 0 the pwm uses a logic low output for 100% duty cycle. If set to 1 the pwm @@ -61,6 +51,16 @@ patternProperties: enum: [0, 1] default: 1 +patternProperties: + "^adi,bypass-attenuator-in[0-4]$": + description: | + Configures bypassing the individual voltage input attenuator. If + set to 1 the attenuator is bypassed if set to 0 the attenuator is + not bypassed. If the property is absent then the attenuator + retains it's configuration from the bios/bootloader. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1] + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index 5272b6f284ba..dcd63908aeae 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -77,6 +77,34 @@ properties: Type-C spec states minimum CC pin debounce of 100 ms and maximum of 200 ms. However, some solutions might need more than 200 ms. + refclk-dig: + type: object + description: | + WIZ node should have subnode for refclk_dig to select the reference + clock source for the reference clock used in the PHY and PMA digital + logic. + properties: + clocks: + minItems: 2 + maxItems: 4 + description: Phandle to two (Torrent) or four (Sierra) clock nodes representing + the inputs to refclk_dig + + "#clock-cells": + const: 0 + + assigned-clocks: + maxItems: 1 + + assigned-clock-parents: + maxItems: 1 + + required: + - clocks + - "#clock-cells" + - assigned-clocks + - assigned-clock-parents + patternProperties: "^pll[0|1]-refclk$": type: object @@ -121,34 +149,6 @@ patternProperties: - clocks - "#clock-cells" - "^refclk-dig$": - type: object - description: | - WIZ node should have subnode for refclk_dig to select the reference - clock source for the reference clock used in the PHY and PMA digital - logic. - properties: - clocks: - minItems: 2 - maxItems: 4 - description: Phandle to two (Torrent) or four (Sierra) clock nodes representing - the inputs to refclk_dig - - "#clock-cells": - const: 0 - - assigned-clocks: - maxItems: 1 - - assigned-clock-parents: - maxItems: 1 - - required: - - clocks - - "#clock-cells" - - assigned-clocks - - assigned-clock-parents - "^serdes@[0-9a-f]+$": type: object description: | diff --git a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml index 12b8963615c3..c2e8c54e5311 100644 --- a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml +++ b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml @@ -36,12 +36,12 @@ properties: switching frequency must be one of following corresponding value 1.1MHz, 1.65MHz, 2.2MHz, 2.75MHz - patternProperties: - "^ldo[1-4]$": + ldortc: type: object $ref: regulator.yaml# - "^ldortc$": + patternProperties: + "^ldo[1-4]$": type: object $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml index 8761437ed8ad..aabf50f5b39e 100644 --- a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml @@ -83,7 +83,8 @@ properties: unevaluatedProperties: false - "^vsnvs$": + properties: + vsnvs: type: object $ref: regulator.yaml# description: diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml index faef4f6f55b8..8246891602e7 100644 --- a/Documentation/devicetree/bindings/spi/spi-controller.yaml +++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml @@ -79,22 +79,7 @@ properties: description: The SPI controller acts as a slave, instead of a master. -allOf: - - if: - not: - required: - - spi-slave - then: - properties: - "#address-cells": - const: 1 - else: - properties: - "#address-cells": - const: 0 - -patternProperties: - "^slave$": + slave: type: object properties: @@ -105,6 +90,7 @@ patternProperties: required: - compatible +patternProperties: "^.*@[0-9a-f]+$": type: object @@ -180,6 +166,20 @@ patternProperties: - compatible - reg +allOf: + - if: + not: + required: + - spi-slave + then: + properties: + "#address-cells": + const: 1 + else: + properties: + "#address-cells": + const: 0 + additionalProperties: true examples: From 58b63e0f556c2debb8c942abcc9e6beadc4a07f0 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Tue, 6 Jul 2021 09:07:34 +0800 Subject: [PATCH 0429/1469] pd: fix order of cleaning up the queue and freeing the tagset We must release the queue before freeing the tagset. Fixes: 262d431f9000 ("pd: use blk_mq_alloc_disk and blk_cleanup_disk") Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210706010734.1356066-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/paride/pd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 3b2b8e872beb..9b3298926356 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -1014,8 +1014,8 @@ static void __exit pd_exit(void) if (p) { disk->gd = NULL; del_gendisk(p); - blk_mq_free_tag_set(&disk->tag_set); blk_cleanup_disk(p); + blk_mq_free_tag_set(&disk->tag_set); pi_release(disk->pi); } } From 16ad3db3b24cd9f70aa24e93cef0d4a83dece7ac Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Tue, 6 Jul 2021 12:00:16 +0800 Subject: [PATCH 0430/1469] nbd: fix order of cleaning up the queue and freeing the tagset We must release the queue before freeing the tagset. Fixes: 4af5f2e03013 ("nbd: use blk_mq_alloc_disk and blk_cleanup_disk") Reported-and-tested-by: syzbot+9ca43ff47167c0ee3466@syzkaller.appspotmail.com Signed-off-by: Wang Qing Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210706040016.1360412-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b7d663736d35..c38317979f74 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -239,8 +239,8 @@ static void nbd_dev_remove(struct nbd_device *nbd) if (disk) { del_gendisk(disk); - blk_mq_free_tag_set(&nbd->tag_set); blk_cleanup_disk(disk); + blk_mq_free_tag_set(&nbd->tag_set); } /* From 05d69d950d9d84218fc9beafd02dea1f6a70e09e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 16:17:11 +0200 Subject: [PATCH 0431/1469] xen-blkfront: sanitize the removal state machine xen-blkfront has a weird protocol where close message from the remote side can be delayed, and where hot removals are treated somewhat differently from regular removals, all leading to potential NULL pointer removals, and a del_gendisk from the block device release method, which will deadlock. Fix this by just performing normal hot removals even when the device is opened like all other Linux block drivers. Fixes: c76f48eb5c08 ("block: take bd_mutex around delete_partitions in del_gendisk") Reported-by: Vitaly Kuznetsov Signed-off-by: Christoph Hellwig Tested-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/20210715141711.1257293-1-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/xen-blkfront.c | 230 +++++------------------------------ 1 file changed, 29 insertions(+), 201 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8d49f8fa98bb..d83fee21f6c5 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -502,34 +502,21 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) static int blkif_ioctl(struct block_device *bdev, fmode_t mode, unsigned command, unsigned long argument) { - struct blkfront_info *info = bdev->bd_disk->private_data; int i; - dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n", - command, (long)argument); - switch (command) { case CDROMMULTISESSION: - dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n"); for (i = 0; i < sizeof(struct cdrom_multisession); i++) if (put_user(0, (char __user *)(argument + i))) return -EFAULT; return 0; - - case CDROM_GET_CAPABILITY: { - struct gendisk *gd = info->gd; - if (gd->flags & GENHD_FL_CD) + case CDROM_GET_CAPABILITY: + if (bdev->bd_disk->flags & GENHD_FL_CD) return 0; return -EINVAL; - } - default: - /*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n", - command);*/ - return -EINVAL; /* same return as native Linux */ + return -EINVAL; } - - return 0; } static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo, @@ -1177,36 +1164,6 @@ out_release_minors: return err; } -static void xlvbd_release_gendisk(struct blkfront_info *info) -{ - unsigned int minor, nr_minors, i; - struct blkfront_ring_info *rinfo; - - if (info->rq == NULL) - return; - - /* No more blkif_request(). */ - blk_mq_stop_hw_queues(info->rq); - - for_each_rinfo(info, rinfo, i) { - /* No more gnttab callback work. */ - gnttab_cancel_free_callback(&rinfo->callback); - - /* Flush gnttab callback work. Must be done with no locks held. */ - flush_work(&rinfo->work); - } - - del_gendisk(info->gd); - - minor = info->gd->first_minor; - nr_minors = info->gd->minors; - xlbd_release_minors(minor, nr_minors); - - blk_cleanup_disk(info->gd); - info->gd = NULL; - blk_mq_free_tag_set(&info->tag_set); -} - /* Already hold rinfo->ring_lock. */ static inline void kick_pending_request_queues_locked(struct blkfront_ring_info *rinfo) { @@ -1756,12 +1713,6 @@ abort_transaction: return err; } -static void free_info(struct blkfront_info *info) -{ - list_del(&info->info_list); - kfree(info); -} - /* Common code used when first setting up, and when resuming. */ static int talk_to_blkback(struct xenbus_device *dev, struct blkfront_info *info) @@ -1880,13 +1831,6 @@ again: xenbus_dev_fatal(dev, err, "%s", message); destroy_blkring: blkif_free(info, 0); - - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - - dev_set_drvdata(&dev->dev, NULL); - return err; } @@ -2126,38 +2070,26 @@ static int blkfront_resume(struct xenbus_device *dev) static void blkfront_closing(struct blkfront_info *info) { struct xenbus_device *xbdev = info->xbdev; - struct block_device *bdev = NULL; + struct blkfront_ring_info *rinfo; + unsigned int i; - mutex_lock(&info->mutex); - - if (xbdev->state == XenbusStateClosing) { - mutex_unlock(&info->mutex); + if (xbdev->state == XenbusStateClosing) return; + + /* No more blkif_request(). */ + blk_mq_stop_hw_queues(info->rq); + blk_set_queue_dying(info->rq); + set_capacity(info->gd, 0); + + for_each_rinfo(info, rinfo, i) { + /* No more gnttab callback work. */ + gnttab_cancel_free_callback(&rinfo->callback); + + /* Flush gnttab callback work. Must be done with no locks held. */ + flush_work(&rinfo->work); } - if (info->gd) - bdev = bdgrab(info->gd->part0); - - mutex_unlock(&info->mutex); - - if (!bdev) { - xenbus_frontend_closed(xbdev); - return; - } - - mutex_lock(&bdev->bd_disk->open_mutex); - - if (bdev->bd_openers) { - xenbus_dev_error(xbdev, -EBUSY, - "Device in use; refusing to close"); - xenbus_switch_state(xbdev, XenbusStateClosing); - } else { - xlvbd_release_gendisk(info); - xenbus_frontend_closed(xbdev); - } - - mutex_unlock(&bdev->bd_disk->open_mutex); - bdput(bdev); + xenbus_frontend_closed(xbdev); } static void blkfront_setup_discard(struct blkfront_info *info) @@ -2472,8 +2404,7 @@ static void blkback_changed(struct xenbus_device *dev, break; fallthrough; case XenbusStateClosing: - if (info) - blkfront_closing(info); + blkfront_closing(info); break; } } @@ -2481,56 +2412,21 @@ static void blkback_changed(struct xenbus_device *dev, static int blkfront_remove(struct xenbus_device *xbdev) { struct blkfront_info *info = dev_get_drvdata(&xbdev->dev); - struct block_device *bdev = NULL; - struct gendisk *disk; dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename); - if (!info) - return 0; + del_gendisk(info->gd); + + mutex_lock(&blkfront_mutex); + list_del(&info->info_list); + mutex_unlock(&blkfront_mutex); blkif_free(info, 0); + xlbd_release_minors(info->gd->first_minor, info->gd->minors); + blk_cleanup_disk(info->gd); + blk_mq_free_tag_set(&info->tag_set); - mutex_lock(&info->mutex); - - disk = info->gd; - if (disk) - bdev = bdgrab(disk->part0); - - info->xbdev = NULL; - mutex_unlock(&info->mutex); - - if (!bdev) { - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - return 0; - } - - /* - * The xbdev was removed before we reached the Closed - * state. See if it's safe to remove the disk. If the bdev - * isn't closed yet, we let release take care of it. - */ - - mutex_lock(&disk->open_mutex); - info = disk->private_data; - - dev_warn(disk_to_dev(disk), - "%s was hot-unplugged, %d stale handles\n", - xbdev->nodename, bdev->bd_openers); - - if (info && !bdev->bd_openers) { - xlvbd_release_gendisk(info); - disk->private_data = NULL; - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - } - - mutex_unlock(&disk->open_mutex); - bdput(bdev); - + kfree(info); return 0; } @@ -2541,77 +2437,9 @@ static int blkfront_is_ready(struct xenbus_device *dev) return info->is_ready && info->xbdev; } -static int blkif_open(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - struct blkfront_info *info; - int err = 0; - - mutex_lock(&blkfront_mutex); - - info = disk->private_data; - if (!info) { - /* xbdev gone */ - err = -ERESTARTSYS; - goto out; - } - - mutex_lock(&info->mutex); - - if (!info->gd) - /* xbdev is closed */ - err = -ERESTARTSYS; - - mutex_unlock(&info->mutex); - -out: - mutex_unlock(&blkfront_mutex); - return err; -} - -static void blkif_release(struct gendisk *disk, fmode_t mode) -{ - struct blkfront_info *info = disk->private_data; - struct xenbus_device *xbdev; - - mutex_lock(&blkfront_mutex); - if (disk->part0->bd_openers) - goto out_mutex; - - /* - * Check if we have been instructed to close. We will have - * deferred this request, because the bdev was still open. - */ - - mutex_lock(&info->mutex); - xbdev = info->xbdev; - - if (xbdev && xbdev->state == XenbusStateClosing) { - /* pending switch to state closed */ - dev_info(disk_to_dev(disk), "releasing disk\n"); - xlvbd_release_gendisk(info); - xenbus_frontend_closed(info->xbdev); - } - - mutex_unlock(&info->mutex); - - if (!xbdev) { - /* sudden device removal */ - dev_info(disk_to_dev(disk), "releasing disk\n"); - xlvbd_release_gendisk(info); - disk->private_data = NULL; - free_info(info); - } - -out_mutex: - mutex_unlock(&blkfront_mutex); -} - static const struct block_device_operations xlvbd_block_fops = { .owner = THIS_MODULE, - .open = blkif_open, - .release = blkif_release, .getgeo = blkif_getgeo, .ioctl = blkif_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, From 295cf156231ca3f9e3a66bde7fab5e09c41835e0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 12 Jul 2021 15:27:46 +0100 Subject: [PATCH 0432/1469] arm64: Avoid premature usercopy failure Al reminds us that the usercopy API must only return complete failure if absolutely nothing could be copied. Currently, if userspace does something silly like giving us an unaligned pointer to Device memory, or a size which overruns MTE tag bounds, we may fail to honour that requirement when faulting on a multi-byte access even though a smaller access could have succeeded. Add a mitigation to the fixup routines to fall back to a single-byte copy if we faulted on a larger access before anything has been written to the destination, to guarantee making *some* forward progress. We needn't be too concerned about the overall performance since this should only occur when callers are doing something a bit dodgy in the first place. Particularly broken userspace might still be able to trick generic_perform_write() into an infinite loop by targeting write() at an mmap() of some read-only device register where the fault-in load succeeds but any store synchronously aborts such that copy_to_user() is genuinely unable to make progress, but, well, don't do that... CC: stable@vger.kernel.org Reported-by: Chen Huang Suggested-by: Al Viro Reviewed-by: Catalin Marinas Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/dc03d5c675731a1f24a62417dba5429ad744234e.1626098433.git.robin.murphy@arm.com Signed-off-by: Will Deacon --- arch/arm64/lib/copy_from_user.S | 13 ++++++++++--- arch/arm64/lib/copy_in_user.S | 21 ++++++++++++++------- arch/arm64/lib/copy_to_user.S | 14 +++++++++++--- 3 files changed, 35 insertions(+), 13 deletions(-) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 95cd62d67371..2cf999e41d30 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -29,7 +29,7 @@ .endm .macro ldrh1 reg, ptr, val - user_ldst 9998f, ldtrh, \reg, \ptr, \val + user_ldst 9997f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val @@ -37,7 +37,7 @@ .endm .macro ldr1 reg, ptr, val - user_ldst 9998f, ldtr, \reg, \ptr, \val + user_ldst 9997f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val @@ -45,7 +45,7 @@ .endm .macro ldp1 reg1, reg2, ptr, val - user_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9997f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val @@ -53,8 +53,10 @@ .endm end .req x5 +srcin .req x15 SYM_FUNC_START(__arch_copy_from_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 // Nothing to copy ret @@ -63,6 +65,11 @@ EXPORT_SYMBOL(__arch_copy_from_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder +USER(9998f, ldtrb tmp1w, [srcin]) + strb tmp1w, [dst], #1 9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 1f61cd0df062..dbea3799c3ef 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -30,33 +30,34 @@ .endm .macro ldrh1 reg, ptr, val - user_ldst 9998f, ldtrh, \reg, \ptr, \val + user_ldst 9997f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val - user_ldst 9998f, sttrh, \reg, \ptr, \val + user_ldst 9997f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val - user_ldst 9998f, ldtr, \reg, \ptr, \val + user_ldst 9997f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val - user_ldst 9998f, sttr, \reg, \ptr, \val + user_ldst 9997f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val - user_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9997f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val - user_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9997f, \reg1, \reg2, \ptr, \val .endm end .req x5 - +srcin .req x15 SYM_FUNC_START(__arch_copy_in_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 ret @@ -65,6 +66,12 @@ EXPORT_SYMBOL(__arch_copy_in_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder +USER(9998f, ldtrb tmp1w, [srcin]) +USER(9998f, sttrb tmp1w, [dst]) + add dst, dst, #1 9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 043da90f5dd7..9f380eecf653 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -32,7 +32,7 @@ .endm .macro strh1 reg, ptr, val - user_ldst 9998f, sttrh, \reg, \ptr, \val + user_ldst 9997f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val @@ -40,7 +40,7 @@ .endm .macro str1 reg, ptr, val - user_ldst 9998f, sttr, \reg, \ptr, \val + user_ldst 9997f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val @@ -48,12 +48,14 @@ .endm .macro stp1 reg1, reg2, ptr, val - user_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9997f, \reg1, \reg2, \ptr, \val .endm end .req x5 +srcin .req x15 SYM_FUNC_START(__arch_copy_to_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 ret @@ -62,6 +64,12 @@ EXPORT_SYMBOL(__arch_copy_to_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder + ldrb tmp1w, [srcin] +USER(9998f, sttrb tmp1w, [dst]) + add dst, dst, #1 9998: sub x0, end, dst // bytes not copied ret .previous From 59f44069e0527523f27948da7b77599a73dab157 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Jul 2021 15:38:41 +0100 Subject: [PATCH 0433/1469] arm64: mte: fix restoration of GCR_EL1 from suspend Since commit: bad1e1c663e0a72f ("arm64: mte: switch GCR_EL1 in kernel entry and exit") we saved/restored the user GCR_EL1 value at exception boundaries, and update_gcr_el1_excl() is no longer used for this. However it is used to restore the kernel's GCR_EL1 value when returning from a suspend state. Thus, the comment is misleading (and an ISB is necessary). When restoring the kernel's GCR value, we need an ISB to ensure this is used by subsequent instructions. We don't necessarily get an ISB by other means (e.g. if the kernel is built without support for pointer authentication). As __cpu_setup() initialised GCR_EL1.Exclude to 0xffff, until a context synchronization event, allocation tag 0 may be used rather than the desired set of tags. This patch drops the misleading comment, adds the missing ISB, and for clarity folds update_gcr_el1_excl() into its only user. Fixes: bad1e1c663e0 ("arm64: mte: switch GCR_EL1 in kernel entry and exit") Signed-off-by: Mark Rutland Cc: Andrey Konovalov Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Will Deacon Link: https://lore.kernel.org/r/20210714143843.56537-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/mte.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 69b3fde8759e..36f51b0e438a 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -193,18 +193,6 @@ void mte_check_tfsr_el1(void) } #endif -static void update_gcr_el1_excl(u64 excl) -{ - - /* - * Note that the mask controlled by the user via prctl() is an - * include while GCR_EL1 accepts an exclude mask. - * No need for ISB since this only affects EL0 currently, implicit - * with ERET. - */ - sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl); -} - static void set_gcr_el1_excl(u64 excl) { current->thread.gcr_user_excl = excl; @@ -265,7 +253,8 @@ void mte_suspend_exit(void) if (!system_supports_mte()) return; - update_gcr_el1_excl(gcr_kernel_excl); + sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, gcr_kernel_excl); + isb(); } long set_mte_ctrl(struct task_struct *task, unsigned long arg) From 31a7f0f6c8f392f002c937f34f372943cf8be5a9 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Jul 2021 18:28:01 +0100 Subject: [PATCH 0434/1469] arm64: entry: add missing noinstr We intend that all the early exception handling code is marked as `noinstr`, but we forgot this for __el0_error_handler_common(), which is called before we have completed entry from user mode. If it were instrumented, we could run into problems with RCU, lockdep, etc. Mark it as `noinstr` to prevent this. The few other functions in entry-common.c which do not have `noinstr` are called once we've completed entry, and are safe to instrument. Fixes: bb8e93a287a5 ("arm64: entry: convert SError handlers to C") Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Marc Zyngier Cc: Joey Gouly Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20210714172801.16475-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 12ce14a98b7c..db8b2e2d02c2 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -604,7 +604,7 @@ asmlinkage void noinstr el0t_64_fiq_handler(struct pt_regs *regs) __el0_fiq_handler_common(regs); } -static void __el0_error_handler_common(struct pt_regs *regs) +static void noinstr __el0_error_handler_common(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); From e6f85cbeb23bd74b8966cf1f15bf7d01399ff625 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 15 Jul 2021 13:30:49 +0100 Subject: [PATCH 0435/1469] arm64: entry: fix KCOV suppression We suppress KCOV for entry.o rather than entry-common.o. As entry.o is built from entry.S, this is pointless, and permits instrumentation of entry-common.o, which is built from entry-common.c. Fix the Makefile to suppress KCOV for entry-common.o, as we had intended to begin with. I've verified with objdump that this is working as expected. Fixes: bf6fa2c0dda7 ("arm64: entry: don't instrument entry code with KCOV") Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Marc Zyngier Cc: Will Deacon Link: https://lore.kernel.org/r/20210715123049.9990-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index cce308586fcc..3f1490bfb938 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -17,7 +17,7 @@ CFLAGS_syscall.o += -fno-stack-protector # It's not safe to invoke KCOV when portions of the kernel environment aren't # available or are out-of-sync with HW state. Since `noinstr` doesn't always # inhibit KCOV instrumentation, disable it for the entire compilation unit. -KCOV_INSTRUMENT_entry.o := n +KCOV_INSTRUMENT_entry-common.o := n KCOV_INSTRUMENT_idle.o := n # Object file lists. From 3ac1d426510f97ace05093ae9f2f710d9cbe6215 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 09:58:04 -0700 Subject: [PATCH 0436/1469] iomap: remove the length variable in iomap_seek_data The length variable is rather pointless given that it can be trivially deduced from offset and size. Also the initial calculation can lead to KASAN warnings. Signed-off-by: Christoph Hellwig Reported-by: Leizhen (ThunderTown) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) --- fs/iomap/seek.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index dab1b02eba5b..50b8f1418f26 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -83,27 +83,23 @@ loff_t iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) { loff_t size = i_size_read(inode); - loff_t length = size - offset; loff_t ret; /* Nothing to be found before or beyond the end of the file. */ if (offset < 0 || offset >= size) return -ENXIO; - while (length > 0) { - ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, - &offset, iomap_seek_data_actor); + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_data_actor); if (ret < 0) return ret; if (ret == 0) - break; - + return offset; offset += ret; - length -= ret; } - if (length <= 0) - return -ENXIO; - return offset; + /* We've reached the end of the file without finding data */ + return -ENXIO; } EXPORT_SYMBOL_GPL(iomap_seek_data); From 49694d14ff68fa4b5f86019dbcfb44a8bd213e58 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 09:58:04 -0700 Subject: [PATCH 0437/1469] iomap: remove the length variable in iomap_seek_hole The length variable is rather pointless given that it can be trivially deduced from offset and size. Also the initial calculation can lead to KASAN warnings. Signed-off-by: Christoph Hellwig Reported-by: Leizhen (ThunderTown) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) --- fs/iomap/seek.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 50b8f1418f26..ce6fb810854f 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -35,23 +35,20 @@ loff_t iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) { loff_t size = i_size_read(inode); - loff_t length = size - offset; loff_t ret; /* Nothing to be found before or beyond the end of the file. */ if (offset < 0 || offset >= size) return -ENXIO; - while (length > 0) { - ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, - &offset, iomap_seek_hole_actor); + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_hole_actor); if (ret < 0) return ret; if (ret == 0) break; - offset += ret; - length -= ret; } return offset; From 8e1bcef8e18d0fec4afe527c074bb1fd6c2b140c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:05 -0700 Subject: [PATCH 0438/1469] iomap: Permit pages without an iop to enter writeback Create an iop in the writeback path if one doesn't exist. This allows us to avoid creating the iop in some cases. We'll initially do that for pages with inline data, but it can be extended to pages which are entirely within an extent. It also allows for an iop to be removed from pages in the future (eg page split). Co-developed-by: Matthew Wilcox (Oracle) Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41da4f14c00b..ad976634d56b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1304,14 +1304,13 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct inode *inode, struct page *page, u64 end_offset) { - struct iomap_page *iop = to_iomap_page(page); + struct iomap_page *iop = iomap_page_create(inode, page); struct iomap_ioend *ioend, *next; unsigned len = i_blocksize(inode); u64 file_offset; /* file offset of page */ int error = 0, count = 0, i; LIST_HEAD(submit_list); - WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop); WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0); /* From 637d3375953e052a62c0db409557e3b3354be88a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:05 -0700 Subject: [PATCH 0439/1469] iomap: Don't create iomap_page objects for inline files In iomap_readpage_actor, don't create iop objects for inline inodes. Otherwise, iomap_read_inline_data will set PageUptodate without setting iop->uptodate, and iomap_page_release will eventually complain. To prevent this kind of bug from occurring in the future, make sure the page doesn't have private data attached in iomap_read_inline_data. Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index ad976634d56b..41076bab18cb 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -215,6 +215,7 @@ iomap_read_inline_data(struct inode *inode, struct page *page, if (PageUptodate(page)) return; + BUG_ON(page_has_private(page)); BUG_ON(page->index); BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); @@ -239,7 +240,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; - struct iomap_page *iop = iomap_page_create(inode, page); + struct iomap_page *iop; bool same_page = false, is_contig = false; loff_t orig_pos = pos; unsigned poff, plen; @@ -252,6 +253,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } /* zero post-eof blocks as the page may be mapped */ + iop = iomap_page_create(inode, page); iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen); if (plen == 0) goto done; From 229adf3c64dbeae4e2f45fb561907ada9fcc0d0c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:06 -0700 Subject: [PATCH 0440/1469] iomap: Don't create iomap_page objects in iomap_page_mkwrite_actor Now that we create those objects in iomap_writepage_map when needed, there's no need to pre-create them in iomap_page_mkwrite_actor anymore. Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41076bab18cb..87ccb3438bec 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -969,7 +969,6 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, block_commit_write(page, 0, length); } else { WARN_ON_ONCE(!PageUptodate(page)); - iomap_page_create(inode, page); set_page_dirty(page); } From da062d16a897c0759ae907e786bc0bea950c0c9d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:47 -0700 Subject: [PATCH 0441/1469] xfs: check for sparse inode clusters that cross new EOAG when shrinking While running xfs/168, I noticed occasional write verifier shutdowns involving inodes at the very end of the filesystem. Existing inode btree validation code checks that all inode clusters are fully contained within the filesystem. However, due to inadequate checking in the fs shrink code, it's possible that there could be a sparse inode cluster at the end of the filesystem where the upper inodes of the cluster are marked as holes and the corresponding blocks are free. In this case, the last blocks in the AG are listed in the bnobt. This enables the shrink to proceed but results in a filesystem that trips the inode verifiers. Fix this by disallowing the shrink. Signed-off-by: Darrick J. Wong Reviewed-by: Gao Xiang --- fs/xfs/libxfs/xfs_ag.c | 8 ++++++ fs/xfs/libxfs/xfs_ialloc.c | 55 ++++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_ialloc.h | 3 +++ 3 files changed, 66 insertions(+) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 778ec52cce70..ee9ec0c50bec 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -803,6 +803,14 @@ xfs_ag_shrink_space( args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta); + /* + * Make sure that the last inode cluster cannot overlap with the new + * end of the AG, even if it's sparse. + */ + error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta); + if (error) + return error; + /* * Disable perag reservations so it doesn't cause the allocation request * to fail. We'll reestablish reservation before we return. diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 57d9cb632983..aaf8805a82df 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2928,3 +2928,58 @@ xfs_ialloc_calc_rootino( return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno)); } + +/* + * Ensure there are not sparse inode clusters that cross the new EOAG. + * + * This is a no-op for non-spinode filesystems since clusters are always fully + * allocated and checking the bnobt suffices. However, a spinode filesystem + * could have a record where the upper inodes are free blocks. If those blocks + * were removed from the filesystem, the inode record would extend beyond EOAG, + * which will be flagged as corruption. + */ +int +xfs_ialloc_check_shrink( + struct xfs_trans *tp, + xfs_agnumber_t agno, + struct xfs_buf *agibp, + xfs_agblock_t new_length) +{ + struct xfs_inobt_rec_incore rec; + struct xfs_btree_cur *cur; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_perag *pag; + xfs_agino_t agino = XFS_AGB_TO_AGINO(mp, new_length); + int has; + int error; + + if (!xfs_sb_version_hassparseinodes(&mp->m_sb)) + return 0; + + pag = xfs_perag_get(mp, agno); + cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO); + + /* Look up the inobt record that would correspond to the new EOFS. */ + error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has); + if (error || !has) + goto out; + + error = xfs_inobt_get_rec(cur, &rec, &has); + if (error) + goto out; + + if (!has) { + error = -EFSCORRUPTED; + goto out; + } + + /* If the record covers inodes that would be beyond EOFS, bail out. */ + if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) { + error = -ENOSPC; + goto out; + } +out: + xfs_btree_del_cursor(cur, error); + xfs_perag_put(pag); + return error; +} diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 9df7c80408ff..9a2112b4ad5e 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -122,4 +122,7 @@ int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); void xfs_ialloc_setup_geometry(struct xfs_mount *mp); xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit); +int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno, + struct xfs_buf *agibp, xfs_agblock_t new_length); + #endif /* __XFS_IALLOC_H__ */ From 5838d0356bb3c320867c393f12b169c01a870bda Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:48 -0700 Subject: [PATCH 0442/1469] xfs: reset child dir '..' entry when unlinking child While running xfs/168, I noticed a second source of post-shrink corruption errors causing shutdowns. Let's say that directory B has a low inode number and is a child of directory A, which has a high number. If B is empty but open, and unlinked from A, B's dotdot link continues to point to A. If A is then unlinked and the filesystem shrunk so that A is no longer a valid inode, a subsequent AIL push of B will trip the inode verifiers because the dotdot entry points outside of the filesystem. To avoid this problem, reset B's dotdot entry to the root directory when unlinking directories, since the root directory cannot be removed. Signed-off-by: Darrick J. Wong Reviewed-by: Gao Xiang --- fs/xfs/xfs_inode.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a835ceb79ba5..990b72ae3635 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2763,6 +2763,19 @@ xfs_remove( error = xfs_droplink(tp, ip); if (error) goto out_trans_cancel; + + /* + * Point the unlinked child directory's ".." entry to the root + * directory to eliminate back-references to inodes that may + * get freed before the child directory is closed. If the fs + * gets shrunk, this can lead to dirent inode validation errors. + */ + if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) { + error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, + tp->t_mountp->m_sb.sb_rootino, 0); + if (error) + return error; + } } else { /* * When removing a non-directory we need to log the parent From 83193e5ebb0164d612aa620ceab7d3746e80e2a4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:50 -0700 Subject: [PATCH 0443/1469] xfs: correct the narrative around misaligned rtinherit/extszinherit dirs While auditing the realtime growfs code, I realized that the GROWFSRT ioctl (and by extension xfs_growfs) has always allowed sysadmins to change the realtime extent size when adding a realtime section to the filesystem. Since we also have always allowed sysadmins to set RTINHERIT and EXTSZINHERIT on directories even if there is no realtime device, this invalidates the premise laid out in the comments added in commit 603f000b15f2. In other words, this is not a case of inadequate metadata validation. This is a case of nearly forgotten (and apparently untested) but supported functionality. Update the comments to reflect what we've learned, and remove the log message about correcting the misalignment. Fixes: 603f000b15f2 ("xfs: validate extsz hints against rt extent size when rtinherit is set") Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_inode_buf.c | 28 ++++++++++++++++------------ fs/xfs/libxfs/xfs_trans_inode.c | 10 ++++------ fs/xfs/xfs_ioctl.c | 8 ++++---- 3 files changed, 24 insertions(+), 22 deletions(-) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 04ce361688f7..84ea2e0af9f0 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -592,23 +592,27 @@ xfs_inode_validate_extsize( /* * This comment describes a historic gap in this verifier function. * - * On older kernels, the extent size hint verifier doesn't check that - * the extent size hint is an integer multiple of the realtime extent - * size on a directory with both RTINHERIT and EXTSZINHERIT flags set. - * The verifier has always enforced the alignment rule for regular - * files with the REALTIME flag set. + * For a directory with both RTINHERIT and EXTSZINHERIT flags set, this + * function has never checked that the extent size hint is an integer + * multiple of the realtime extent size. Since we allow users to set + * this combination on non-rt filesystems /and/ to change the rt + * extent size when adding a rt device to a filesystem, the net effect + * is that users can configure a filesystem anticipating one rt + * geometry and change their minds later. Directories do not use the + * extent size hint, so this is harmless for them. * * If a directory with a misaligned extent size hint is allowed to * propagate that hint into a new regular realtime file, the result * is that the inode cluster buffer verifier will trigger a corruption - * shutdown the next time it is run. + * shutdown the next time it is run, because the verifier has always + * enforced the alignment rule for regular files. * - * Unfortunately, there could be filesystems with these misconfigured - * directories in the wild, so we cannot add a check to this verifier - * at this time because that will result a new source of directory - * corruption errors when reading an existing filesystem. Instead, we - * permit the misconfiguration to pass through the verifiers so that - * callers of this function can correct and mitigate externally. + * Because we allow administrators to set a new rt extent size when + * adding a rt section, we cannot add a check to this verifier because + * that will result a new source of directory corruption errors when + * reading an existing filesystem. Instead, we rely on callers to + * decide when alignment checks are appropriate, and fix things up as + * needed. */ if (rt_flag) diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 8d595a5c4abd..16f723ebe8dd 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -143,16 +143,14 @@ xfs_trans_log_inode( } /* - * Inode verifiers on older kernels don't check that the extent size - * hint is an integer multiple of the rt extent size on a directory - * with both rtinherit and extszinherit flags set. If we're logging a - * directory that is misconfigured in this way, clear the hint. + * Inode verifiers do not check that the extent size hint is an integer + * multiple of the rt extent size on a directory with both rtinherit + * and extszinherit flags set. If we're logging a directory that is + * misconfigured in this way, clear the hint. */ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { - xfs_info_once(ip->i_mount, - "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino); ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT); ip->i_extsize = 0; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 65270e63c032..275d1c3123bd 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1292,10 +1292,10 @@ xfs_ioctl_setattr_check_extsize( new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); /* - * Inode verifiers on older kernels don't check that the extent size - * hint is an integer multiple of the rt extent size on a directory - * with both rtinherit and extszinherit flags set. Don't let sysadmins - * misconfigure directories. + * Inode verifiers do not check that the extent size hint is an integer + * multiple of the rt extent size on a directory with both rtinherit + * and extszinherit flags set. Don't let sysadmins misconfigure + * directories. */ if ((new_diflags & XFS_DIFLAG_RTINHERIT) && (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) { From 5aa5b278237f356f86205c4b03d4cc64a293850a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:51 -0700 Subject: [PATCH 0444/1469] xfs: don't expose misaligned extszinherit hints to userspace Commit 603f000b15f2 changed xfs_ioctl_setattr_check_extsize to reject an attempt to set an EXTSZINHERIT extent size hint on a directory with RTINHERIT set if the hint isn't a multiple of the realtime extent size. However, I have recently discovered that it is possible to change the realtime extent size when adding a rt device to a filesystem, which means that the existence of directories with misaligned inherited hints is not an accident. As a result, it's possible that someone could have set a valid hint and added an rt volume with a different rt extent size, which invalidates the ondisk hints. After such a sequence, FSGETXATTR will report a misaligned hint, which FSSETXATTR will trip over, causing confusion if the user was doing the usual GET/SET sequence to change some other attribute. Change xfs_fill_fsxattr to omit the hint if it isn't aligned properly. Fixes: 603f000b15f2 ("xfs: validate extsz hints against rt extent size when rtinherit is set") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_ioctl.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 275d1c3123bd..16039ea10ac9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1065,7 +1065,24 @@ xfs_fill_fsxattr( fileattr_fill_xflags(fa, xfs_ip2xflags(ip)); - fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) { + fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + } else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) { + /* + * Don't let a misaligned extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_extsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | + FS_XFLAG_EXTSZINHERIT); + fa->fsx_extsize = 0; + } else { + fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + } + } + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); fa->fsx_projid = ip->i_projid; From 0e2af9296f4f9c4c815ced2beb21093af7c38644 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:48 -0700 Subject: [PATCH 0445/1469] xfs: improve FSGROWFSRT precondition checking Improve the checking at the start of a realtime grow operation so that we avoid accidentally set a new extent size that is too large and avoid adding an rt volume to a filesystem with rmap or reflink because we don't support rt rmap or reflink yet. While we're at it, separate the checks so that we're only testing one aspect at a time. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_rtalloc.c | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 4e7be6b4ca8e..8f6a05db4468 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -923,16 +923,41 @@ xfs_growfs_rt( uint8_t *rsum_cache; /* old summary cache */ sbp = &mp->m_sb; - /* - * Initial error checking. - */ + if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (mp->m_rtdev_targp == NULL || mp->m_rbmip == NULL || - (nrblocks = in->newblocks) <= sbp->sb_rblocks || - (sbp->sb_rblocks && (in->extsize != sbp->sb_rextsize))) + + /* Needs to have been mounted with an rt device. */ + if (!XFS_IS_REALTIME_MOUNT(mp)) return -EINVAL; - if ((error = xfs_sb_validate_fsb_count(sbp, nrblocks))) + /* + * Mount should fail if the rt bitmap/summary files don't load, but + * we'll check anyway. + */ + if (!mp->m_rbmip || !mp->m_rsumip) + return -EINVAL; + + /* Shrink not supported. */ + if (in->newblocks <= sbp->sb_rblocks) + return -EINVAL; + + /* Can only change rt extent size when adding rt volume. */ + if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize) + return -EINVAL; + + /* Range check the extent size. */ + if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE || + XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) + return -EINVAL; + + /* Unsupported realtime features. */ + if (xfs_sb_version_hasrmapbt(&mp->m_sb) || + xfs_sb_version_hasreflink(&mp->m_sb)) + return -EOPNOTSUPP; + + nrblocks = in->newblocks; + error = xfs_sb_validate_fsb_count(sbp, nrblocks); + if (error) return error; /* * Read in the last block of the device, make sure it exists. From 0925fecc557471b6f6a488c3590a275151210572 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:49 -0700 Subject: [PATCH 0446/1469] xfs: fix an integer overflow error in xfs_growfs_rt During a realtime grow operation, we run a single transaction for each rt bitmap block added to the filesystem. This means that each step has to be careful to increase sb_rblocks appropriately. Fix the integer overflow error in this calculation that can happen when the extent size is very large. Found by running growfs to add a rt volume to a filesystem formatted with a 1g rt extent size. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_rtalloc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 8f6a05db4468..699066fb9052 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1021,7 +1021,8 @@ xfs_growfs_rt( ((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0); bmbno < nrbmblocks; bmbno++) { - xfs_trans_t *tp; + struct xfs_trans *tp; + xfs_rfsblock_t nrblocks_step; *nmp = *mp; nsbp = &nmp->m_sb; @@ -1030,10 +1031,9 @@ xfs_growfs_rt( */ nsbp->sb_rextsize = in->extsize; nsbp->sb_rbmblocks = bmbno + 1; - nsbp->sb_rblocks = - XFS_RTMIN(nrblocks, - nsbp->sb_rbmblocks * NBBY * - nsbp->sb_blocksize * nsbp->sb_rextsize); + nrblocks_step = (bmbno + 1) * NBBY * nsbp->sb_blocksize * + nsbp->sb_rextsize; + nsbp->sb_rblocks = min(nrblocks, nrblocks_step); nsbp->sb_rextents = nsbp->sb_rblocks; do_div(nsbp->sb_rextents, nsbp->sb_rextsize); ASSERT(nsbp->sb_rextents != 0); From b102a46ce16fd5550aed882c3c5b95f50da7992c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 14 Jul 2021 09:03:41 -0700 Subject: [PATCH 0447/1469] xfs: detect misaligned rtinherit directory extent size hints If we encounter a directory that has been configured to pass on an extent size hint to a new realtime file and the hint isn't an integer multiple of the rt extent size, we should flag the hint for administrative review because that is a misconfiguration (that other parts of the kernel will fix automatically). Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/scrub/inode.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 61f90b2c9430..76fbc7ca4cec 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -73,11 +73,25 @@ xchk_inode_extsize( uint16_t flags) { xfs_failaddr_t fa; + uint32_t value = be32_to_cpu(dip->di_extsize); - fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize), - mode, flags); + fa = xfs_inode_validate_extsize(sc->mp, value, mode, flags); if (fa) xchk_ino_set_corrupt(sc, ino); + + /* + * XFS allows a sysadmin to change the rt extent size when adding a rt + * section to a filesystem after formatting. If there are any + * directories with extszinherit and rtinherit set, the hint could + * become misaligned with the new rextsize. The verifier doesn't check + * this, because we allow rtinherit directories even without an rt + * device. Flag this as an administrative warning since we will clean + * this up eventually. + */ + if ((flags & XFS_DIFLAG_RTINHERIT) && + (flags & XFS_DIFLAG_EXTSZINHERIT) && + value % sc->mp->m_sb.sb_rextsize > 0) + xchk_ino_set_warning(sc, ino); } /* From 99bb2ebab953435852340cdb198c5abbf0bb5dd3 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 11:58:12 +0200 Subject: [PATCH 0448/1469] net: dsa: mv88e6xxx: NET_DSA_MV88E6XXX_PTP should depend on NET_DSA_MV88E6XXX Making global2 support mandatory removed the Kconfig symbol NET_DSA_MV88E6XXX_GLOBAL2. This symbol also served as an intermediate symbol to make NET_DSA_MV88E6XXX_PTP depend on NET_DSA_MV88E6XXX. With the symbol removed, the user is always asked about PTP support for Marvell 88E6xxx switches, even if the latter support is not enabled. Fix this by reinstating the dependency. Fixes: 63368a7416df144b ("net: dsa: mv88e6xxx: Make global2 support mandatory") Signed-off-by: Geert Uytterhoeven Reviewed-by: Andrew Lunn Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 05af632b0f59..634a48e6616b 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -12,7 +12,7 @@ config NET_DSA_MV88E6XXX config NET_DSA_MV88E6XXX_PTP bool "PTP support for Marvell 88E6xxx" default n - depends on PTP_1588_CLOCK + depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK help Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch chips that support it. From 0d4a062af2cea33c2000b28420e8e2eb58b4fd0b Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 21:26:34 -0700 Subject: [PATCH 0449/1469] mm: move helper to check slub_debug_enabled Move the helper to check slub_debug_enabled, so that we can confine the use of #ifdef outside slub.c as well. Link: https://lkml.kernel.org/r/20210705103229.8505-2-yee.lee@mediatek.com Signed-off-by: Marco Elver Signed-off-by: Yee Lee Suggested-by: Matthew Wilcox Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Chinwen Chang Cc: Dmitry Vyukov Cc: Kuan-Ying Lee Cc: Nicholas Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.h | 15 +++++++++++---- mm/slub.c | 14 -------------- 2 files changed, 11 insertions(+), 18 deletions(-) diff --git a/mm/slab.h b/mm/slab.h index 67e06637ff2e..f997fd5e42c8 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -216,10 +216,18 @@ DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); long validate_slab_cache(struct kmem_cache *s); +static inline bool __slub_debug_enabled(void) +{ + return static_branch_unlikely(&slub_debug_enabled); +} #else static inline void print_tracking(struct kmem_cache *s, void *object) { } +static inline bool __slub_debug_enabled(void) +{ + return false; +} #endif /* @@ -229,11 +237,10 @@ static inline void print_tracking(struct kmem_cache *s, void *object) */ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); - if (static_branch_unlikely(&slub_debug_enabled)) + if (IS_ENABLED(CONFIG_SLUB_DEBUG)) + VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); + if (__slub_debug_enabled()) return s->flags & flags; -#endif return false; } diff --git a/mm/slub.c b/mm/slub.c index dc863c1ea324..e1644ac6ee7b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -120,25 +120,11 @@ */ #ifdef CONFIG_SLUB_DEBUG - #ifdef CONFIG_SLUB_DEBUG_ON DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); #else DEFINE_STATIC_KEY_FALSE(slub_debug_enabled); #endif - -static inline bool __slub_debug_enabled(void) -{ - return static_branch_unlikely(&slub_debug_enabled); -} - -#else /* CONFIG_SLUB_DEBUG */ - -static inline bool __slub_debug_enabled(void) -{ - return false; -} - #endif /* CONFIG_SLUB_DEBUG */ static inline bool kmem_cache_debug(struct kmem_cache *s) From 77a63c69ec43f4dc28f4b2d1c933c39e55de6ad8 Mon Sep 17 00:00:00 2001 From: Yee Lee Date: Wed, 14 Jul 2021 21:26:37 -0700 Subject: [PATCH 0450/1469] kasan: add memzero init for unaligned size at DEBUG Issue: when SLUB debug is on, hwtag kasan_unpoison() would overwrite the redzone of object with unaligned size. An additional memzero_explicit() path is added to replacing init by hwtag instruction for those unaligned size at SLUB debug mode. The penalty is acceptable since they are only enabled in debug mode, not production builds. A block of comment is added for explanation. Link: https://lkml.kernel.org/r/20210705103229.8505-3-yee.lee@mediatek.com Signed-off-by: Yee Lee Suggested-by: Andrey Konovalov Suggested-by: Marco Elver Reviewed-by: Marco Elver Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Nicholas Tang Cc: Kuan-Ying Lee Cc: Chinwen Chang Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 98e3059bfea4..d739cdd1621a 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -9,6 +9,7 @@ #ifdef CONFIG_KASAN_HW_TAGS #include +#include "../slab.h" DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace); extern bool kasan_flag_async __ro_after_init; @@ -387,6 +388,17 @@ static inline void kasan_unpoison(const void *addr, size_t size, bool init) if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) return; + /* + * Explicitly initialize the memory with the precise object size to + * avoid overwriting the SLAB redzone. This disables initialization in + * the arch code and may thus lead to performance penalty. The penalty + * is accepted since SLAB redzones aren't enabled in production builds. + */ + if (__slub_debug_enabled() && + init && ((unsigned long)size & KASAN_GRANULE_MASK)) { + init = false; + memzero_explicit((void *)addr, size); + } size = round_up(size, KASAN_GRANULE_SIZE); hw_set_mem_tag_range((void *)addr, size, tag, init); From 2db710cc846d3321a4dc0977fa13769bddba2351 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 21:26:40 -0700 Subject: [PATCH 0451/1469] kasan: fix build by including kernel.h The header relies on _RET_IP_ being defined, and had been receiving that definition via inclusion of bug.h which includes kernel.h. However, since f39650de687e ("kernel.h: split out panic and oops helpers") that is no longer the case and get the following build error when building CONFIG_KASAN_HW_TAGS on arm64: In file included from arch/arm64/mm/kasan_init.c:10: include/linux/kasan.h: In function 'kasan_slab_free': include/linux/kasan.h:230:39: error: '_RET_IP_' undeclared (first use in this function) 230 | return __kasan_slab_free(s, object, _RET_IP_, init); Fix it by including kernel.h from kasan.h. Link: https://lkml.kernel.org/r/20210705072716.2125074-1-elver@google.com Fixes: f39650de687e ("kernel.h: split out panic and oops helpers") Signed-off-by: Marco Elver Reviewed-by: Andy Shevchenko Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Peter Collingbourne Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5310e217bd74..dd874a1ee862 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include +#include #include #include From 54aa386661fef92b5f092d7068bc6d4952b91a71 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Wed, 14 Jul 2021 21:26:43 -0700 Subject: [PATCH 0452/1469] Revert "mm/page_alloc: make should_fail_alloc_page() static" This reverts commit f7173090033c70886d925995e9dfdfb76dbb2441. Fix an unresolved symbol error when CONFIG_DEBUG_INFO_BTF=y: LD vmlinux BTFIDS vmlinux FAILED unresolved symbol should_fail_alloc_page make: *** [Makefile:1199: vmlinux] Error 255 make: *** Deleting file 'vmlinux' Link: https://lkml.kernel.org/r/20210708191128.153796-1-mcroce@linux.microsoft.com Fixes: f7173090033c ("mm/page_alloc: make should_fail_alloc_page() static") Signed-off-by: Matteo Croce Acked-by: Mel Gorman Tested-by: John Hubbard Cc: Michal Hocko Cc: David Hildenbrand Cc: Vlastimil Babka Cc: Dan Streetman Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3b97e17806be..bf3117bb1e16 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3820,7 +3820,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } From 187ad460b8413e863c951998cb321a117a717868 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 14 Jul 2021 21:26:46 -0700 Subject: [PATCH 0453/1469] mm/page_alloc: avoid page allocator recursion with pagesets.lock held Syzbot is reporting potential deadlocks due to pagesets.lock when PAGE_OWNER is enabled. One example from Desmond Cheong Zhi Xi is as follows __alloc_pages_bulk() local_lock_irqsave(&pagesets.lock, flags) <---- outer lock here prep_new_page(): post_alloc_hook(): set_page_owner(): __set_page_owner(): save_stack(): stack_depot_save(): alloc_pages(): alloc_page_interleave(): __alloc_pages(): get_page_from_freelist(): rm_queue(): rm_queue_pcplist(): local_lock_irqsave(&pagesets.lock, flags); *** DEADLOCK *** Zhang, Qiang also reported BUG: sleeping function called from invalid context at mm/page_alloc.c:5179 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0 ..... __dump_stack lib/dump_stack.c:79 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:96 ___might_sleep.cold+0x1f1/0x237 kernel/sched/core.c:9153 prepare_alloc_pages+0x3da/0x580 mm/page_alloc.c:5179 __alloc_pages+0x12f/0x500 mm/page_alloc.c:5375 alloc_page_interleave+0x1e/0x200 mm/mempolicy.c:2147 alloc_pages+0x238/0x2a0 mm/mempolicy.c:2270 stack_depot_save+0x39d/0x4e0 lib/stackdepot.c:303 save_stack+0x15e/0x1e0 mm/page_owner.c:120 __set_page_owner+0x50/0x290 mm/page_owner.c:181 prep_new_page mm/page_alloc.c:2445 [inline] __alloc_pages_bulk+0x8b9/0x1870 mm/page_alloc.c:5313 alloc_pages_bulk_array_node include/linux/gfp.h:557 [inline] vm_area_alloc_pages mm/vmalloc.c:2775 [inline] __vmalloc_area_node mm/vmalloc.c:2845 [inline] __vmalloc_node_range+0x39d/0x960 mm/vmalloc.c:2947 __vmalloc_node mm/vmalloc.c:2996 [inline] vzalloc+0x67/0x80 mm/vmalloc.c:3066 There are a number of ways it could be fixed. The page owner code could be audited to strip GFP flags that allow sleeping but it'll impair the functionality of PAGE_OWNER if allocations fail. The bulk allocator could add a special case to release/reacquire the lock for prep_new_page and lookup PCP after the lock is reacquired at the cost of performance. The pages requiring prep could be tracked using the least significant bit and looping through the array although it is more complicated for the list interface. The options are relatively complex and the second one still incurs a performance penalty when PAGE_OWNER is active so this patch takes the simple approach -- disable bulk allocation of PAGE_OWNER is active. The caller will be forced to allocate one page at a time incurring a performance penalty but PAGE_OWNER is already a performance penalty. Link: https://lkml.kernel.org/r/20210708081434.GV3840@techsingularity.net Fixes: dbbee9d5cd83 ("mm/page_alloc: convert per-cpu list protection to local_lock") Signed-off-by: Mel Gorman Reported-by: Desmond Cheong Zhi Xi Reported-by: "Zhang, Qiang" Reported-by: syzbot+127fd7828d6eeb611703@syzkaller.appspotmail.com Tested-by: syzbot+127fd7828d6eeb611703@syzkaller.appspotmail.com Acked-by: Rafael Aquini Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bf3117bb1e16..84609716bab5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5239,6 +5239,18 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (nr_pages - nr_populated == 1) goto failed; +#ifdef CONFIG_PAGE_OWNER + /* + * PAGE_OWNER may recurse into the allocator to allocate space to + * save the stack with pagesets.lock held. Releasing/reacquiring + * removes much of the performance benefit of bulk allocation so + * force the caller to allocate one page at a time as it'll have + * similar performance to added complexity to the bulk allocator. + */ + if (static_branch_unlikely(&page_owner_inited)) + goto failed; +#endif + /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */ gfp &= gfp_allowed_mask; alloc_gfp = gfp; From e5c15cea339115edf99dc92282865f173cf84510 Mon Sep 17 00:00:00 2001 From: Yanfei Xu Date: Wed, 14 Jul 2021 21:26:49 -0700 Subject: [PATCH 0454/1469] mm/page_alloc: correct return value when failing at preparing If the array passed in is already partially populated, we should return "nr_populated" even failing at preparing arguments stage. Link: https://lkml.kernel.org/r/20210713152100.10381-3-mgorman@techsingularity.net Signed-off-by: Yanfei Xu Signed-off-by: Mel Gorman Link: https://lore.kernel.org/r/20210709102855.55058-1-yanfei.xu@windriver.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 84609716bab5..4d79e357a4ba 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5255,7 +5255,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp &= gfp_allowed_mask; alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) - return 0; + return nr_populated; gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ From 061478438d04779181c2ce4d7ffeeca343a70a98 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 14 Jul 2021 21:26:52 -0700 Subject: [PATCH 0455/1469] mm/page_alloc: further fix __alloc_pages_bulk() return value The author of commit b3b64ebd3822 ("mm/page_alloc: do bulk array bounds check after checking populated elements") was possibly confused by the mixture of return values throughout the function. The API contract is clear that the function "Returns the number of pages on the list or array." It does not list zero as a unique return value with a special meaning. Therefore zero is a plausible return value only if @nr_pages is zero or less. Clean up the return logic to make it clear that the returned value is always the total number of pages in the array/list, not the number of pages that were allocated during this call. The only change in behavior with this patch is the value returned if prepare_alloc_pages() fails. To match the API contract, the number of pages currently in the array/list is returned in this case. The call site in __page_pool_alloc_pages_slow() also seems to be confused on this matter. It should be attended to by someone who is familiar with that code. [mel@techsingularity.net: Return nr_populated if 0 pages are requested] Link: https://lkml.kernel.org/r/20210713152100.10381-4-mgorman@techsingularity.net Signed-off-by: Chuck Lever Signed-off-by: Mel Gorman Acked-by: Jesper Dangaard Brouer Cc: Desmond Cheong Zhi Xi Cc: Zhang Qiang Cc: Yanfei Xu Cc: Matteo Croce Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4d79e357a4ba..3e97e68aef7a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5221,9 +5221,6 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, unsigned int alloc_flags = ALLOC_WMARK_LOW; int nr_populated = 0, nr_account = 0; - if (unlikely(nr_pages <= 0)) - return 0; - /* * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs. @@ -5231,9 +5228,13 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, while (page_array && nr_populated < nr_pages && page_array[nr_populated]) nr_populated++; + /* No pages requested? */ + if (unlikely(nr_pages <= 0)) + goto out; + /* Already populated array? */ if (unlikely(page_array && nr_pages - nr_populated == 0)) - return nr_populated; + goto out; /* Use the single page allocator for one page. */ if (nr_pages - nr_populated == 1) @@ -5255,7 +5256,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp &= gfp_allowed_mask; alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) - return nr_populated; + goto out; gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ @@ -5323,6 +5324,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); +out: return nr_populated; failed_irq: @@ -5338,7 +5340,7 @@ failed: nr_populated++; } - return nr_populated; + goto out; } EXPORT_SYMBOL_GPL(__alloc_pages_bulk); From ab7965de1725cd8514f0edbced5c2fb793846078 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jul 2021 21:26:55 -0700 Subject: [PATCH 0456/1469] mm: fix the try_to_unmap prototype for !CONFIG_MMU Adjust the nommu stub of try_to_unmap to match the changed protype for the full version. Turn it into an inline instead of a macro to generally improve the type checking. Link: https://lkml.kernel.org/r/20210705053944.885828-1-hch@lst.de Fixes: 1fb08ac63bee ("mm: rmap: make try_to_unmap() void function") Signed-off-by: Christoph Hellwig Reviewed-by: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 83fb86133fe1..c976cc6de257 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -291,7 +291,9 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -#define try_to_unmap(page, refs) false +static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +{ +} static inline int page_mkclean(struct page *page) { From c52114d9df6a193fba5317933c75bc9bb5f6cf8a Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 14 Jul 2021 21:26:58 -0700 Subject: [PATCH 0457/1469] lib/test_hmm: remove set but unused page variable The HMM selftests use atomic_check_access() to check atomic access to a page has been revoked. It doesn't matter if the page mapping has been removed from the mirrored page tables as that also implies atomic access has been revoked. Therefore remove the unused page variable to fix this compiler warning: lib/test_hmm.c:631:16: warning: variable `page' set but not used [-Wunused-but-set-variable] Link: https://lkml.kernel.org/r/20210706025603.4059-1-apopple@nvidia.com Fixes: b659baea7546 ("mm: selftests for exclusive device memory") Signed-off-by: Alistair Popple Reported-by: Hulk Robot Reported-by: kernel test robot Reported-by: Yang Yingliang Acked-by: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hmm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 8c55c4723692..c259842f6d44 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -628,10 +628,8 @@ static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start, for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) { void *entry; - struct page *page; entry = xa_load(&dmirror->pt, pfn); - page = xa_untag_pointer(entry); if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC) return -EPERM; } From 16ee572eaf0d09daa4c8a755fdb71e40dbf8562d Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:01 -0700 Subject: [PATCH 0458/1469] hfs: add missing clean-up in hfs_fill_super Patch series "hfs: fix various errors", v2. This series ultimately aims to address a lockdep warning in hfs_find_init reported by Syzbot [1]. The work done for this led to the discovery of another bug, and the Syzkaller repro test also reveals an invalid memory access error after clearing the lockdep warning. Hence, this series is broken up into three patches: 1. Add a missing call to hfs_find_exit for an error path in hfs_fill_super 2. Fix memory mapping in hfs_bnode_read by fixing calls to kmap 3. Add lock nesting notation to tell lockdep that the observed locking hierarchy is safe This patch (of 3): Before exiting hfs_fill_super, the struct hfs_find_data used in hfs_find_init should be passed to hfs_find_exit to be cleaned up, and to release the lock held on the btree. The call to hfs_find_exit is missing from an error path. We add it back in by consolidating calls to hfs_find_exit for error paths. Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585db [1] Link: https://lkml.kernel.org/r/20210701030756.58760-1-desmondcheongzx@gmail.com Link: https://lkml.kernel.org/r/20210701030756.58760-2-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reviewed-by: Viacheslav Dubeyko Cc: Gustavo A. R. Silva Cc: Al Viro Cc: Shuah Khan Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 44d07c9e3a7f..12d9bae39363 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -420,14 +420,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; - goto bail; + goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } - if (res) { - hfs_find_exit(&fd); - goto bail_no_root; - } + if (res) + goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); @@ -443,6 +441,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) /* everything's okay */ return 0; +bail_hfs_find: + hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail: From 54a5ead6f5e2b47131a7385d0c0af18e7b89cb02 Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:05 -0700 Subject: [PATCH 0459/1469] hfs: fix high memory mapping in hfs_bnode_read Pages that we read in hfs_bnode_read need to be kmapped into kernel address space. However, currently only the 0th page is kmapped. If the given offset + length exceeds this 0th page, then we have an invalid memory access. To fix this, we kmap relevant pages one by one and copy their relevant portions of data. An example of invalid memory access occurring without this fix can be seen in the following crash report: ================================================================== BUG: KASAN: use-after-free in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: use-after-free in hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 Read of size 2 at addr ffff888125fdcffe by task syz-executor5/4634 CPU: 0 PID: 4634 Comm: syz-executor5 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x195/0x1f8 lib/dump_stack.c:120 print_address_description.constprop.0+0x1d/0x110 mm/kasan/report.c:233 __kasan_report mm/kasan/report.c:419 [inline] kasan_report.cold+0x7b/0xd4 mm/kasan/report.c:436 check_region_inline mm/kasan/generic.c:180 [inline] kasan_check_range+0x154/0x1b0 mm/kasan/generic.c:186 memcpy+0x24/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 hfs_bnode_read_u16 fs/hfs/bnode.c:34 [inline] hfs_bnode_find+0x880/0xcc0 fs/hfs/bnode.c:365 hfs_brec_find+0x2d8/0x540 fs/hfs/bfind.c:126 hfs_brec_read+0x27/0x120 fs/hfs/bfind.c:165 hfs_cat_find_brec+0x19a/0x3b0 fs/hfs/catalog.c:194 hfs_fill_super+0xc13/0x1460 fs/hfs/super.c:419 mount_bdev+0x331/0x3f0 fs/super.c:1368 hfs_mount+0x35/0x40 fs/hfs/super.c:457 legacy_get_tree+0x10c/0x220 fs/fs_context.c:592 vfs_get_tree+0x93/0x300 fs/super.c:1498 do_new_mount fs/namespace.c:2905 [inline] path_mount+0x13f5/0x20e0 fs/namespace.c:3235 do_mount fs/namespace.c:3248 [inline] __do_sys_mount fs/namespace.c:3456 [inline] __se_sys_mount fs/namespace.c:3433 [inline] __x64_sys_mount+0x2b8/0x340 fs/namespace.c:3433 do_syscall_64+0x37/0xc0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x45e63a Code: 48 c7 c2 bc ff ff ff f7 d8 64 89 02 b8 ff ff ff ff eb d2 e8 88 04 00 00 0f 1f 84 00 00 00 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9404d410d8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000248 RCX: 000000000045e63a RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f9404d41120 RBP: 00007f9404d41120 R08: 00000000200002c0 R09: 0000000020000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000003 R14: 00000000004ad5d8 R15: 0000000000000000 The buggy address belongs to the page: page:00000000dadbcf3e refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 pfn:0x125fdc flags: 0x2fffc0000000000(node=0|zone=2|lastcpupid=0x3fff) raw: 02fffc0000000000 ffffea000497f748 ffffea000497f6c8 0000000000000000 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888125fdce80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdcf00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888125fdcf80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888125fdd000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdd080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Link: https://lkml.kernel.org/r/20210701030756.58760-3-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reviewed-by: Viacheslav Dubeyko Cc: Al Viro Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/bnode.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index b63a4df7327b..c0a73a6ffb28 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -15,16 +15,31 @@ #include "btree.h" -void hfs_bnode_read(struct hfs_bnode *node, void *buf, - int off, int len) +void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; + int pagenum; + int bytes_read; + int bytes_to_read; + void *vaddr; off += node->page_offset; - page = node->page[0]; + pagenum = off >> PAGE_SHIFT; + off &= ~PAGE_MASK; /* compute page offset for the first page */ - memcpy(buf, kmap(page) + off, len); - kunmap(page); + for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { + if (pagenum >= node->tree->pages_per_bnode) + break; + page = node->page[pagenum]; + bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); + + vaddr = kmap_atomic(page); + memcpy(buf + bytes_read, vaddr + off, bytes_to_read); + kunmap_atomic(vaddr); + + pagenum++; + off = 0; /* page offset only applies to the first page */ + } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) From b3b2177a2d795e35dc11597b2609eb1e7e57e570 Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:08 -0700 Subject: [PATCH 0460/1469] hfs: add lock nesting notation to hfs_find_init Syzbot reports a possible recursive lock in [1]. This happens due to missing lock nesting information. From the logs, we see that a call to hfs_fill_super is made to mount the hfs filesystem. While searching for the root inode, the lock on the catalog btree is grabbed. Then, when the parent of the root isn't found, a call to __hfs_bnode_create is made to create the parent of the root. This eventually leads to a call to hfs_ext_read_extent which grabs a lock on the extents btree. Since the order of locking is catalog btree -> extents btree, this lock hierarchy does not lead to a deadlock. To tell lockdep that this locking is safe, we add nesting notation to distinguish between catalog btrees, extents btrees, and attributes btrees (for HFS+). This has already been done in hfsplus. Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585db [1] Link: https://lkml.kernel.org/r/20210701030756.58760-4-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reported-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.com Tested-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.com Reviewed-by: Viacheslav Dubeyko Cc: Al Viro Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/bfind.c | 14 +++++++++++++- fs/hfs/btree.h | 7 +++++++ 2 files changed, 20 insertions(+), 1 deletion(-) diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index 4af318fbda77..ef9498a6e88a 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -25,7 +25,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + return -EINVAL; + } return 0; } diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index 4ba45caf5939..0e6baee93245 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -13,6 +13,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *); #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfs_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* A HFS BTree held in memory */ struct hfs_btree { struct super_block *sb; From d08af0a59684e18a51aa4bfd24c658994ea3fc5b Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 14 Jul 2021 21:27:11 -0700 Subject: [PATCH 0461/1469] mm/hugetlb: fix refs calculation from unaligned @vaddr Commit 82e5d378b0e47 ("mm/hugetlb: refactor subpage recording") refactored the count of subpages but missed an edge case when @vaddr is not aligned to PAGE_SIZE e.g. when close to vma->vm_end. It would then errousnly set @refs to 0 and record_subpages_vmas() wouldn't set the @pages array element to its value, consequently causing the reported null-deref by syzbot. Fix it by aligning down @vaddr by PAGE_SIZE in @refs calculation. Link: https://lkml.kernel.org/r/20210713152440.28650-1-joao.m.martins@oracle.com Fixes: 82e5d378b0e47 ("mm/hugetlb: refactor subpage recording") Reported-by: syzbot+a3fcd59df1b372066f5a@syzkaller.appspotmail.com Signed-off-by: Joao Martins Reviewed-by: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 924553aa8f78..dfc940d5221d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5440,8 +5440,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, continue; } - refs = min3(pages_per_huge_page(h) - pfn_offset, - (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder); + /* vaddr may not be aligned to PAGE_SIZE */ + refs = min3(pages_per_huge_page(h) - pfn_offset, remainder, + (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT); if (pages || vmas) record_subpages_vmas(mem_map_offset(page, pfn_offset), From e7efc2ce3d0789cd7c21b70ff00cd7838d382639 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 14 Jul 2021 16:23:43 +0100 Subject: [PATCH 0462/1469] liquidio: Fix unintentional sign extension issue on left shift of u16 Shifting the u16 integer oct->pcie_port by CN23XX_PKT_INPUT_CTL_MAC_NUM_POS (29) bits will be promoted to a 32 bit signed int and then sign-extended to a u64. In the cases where oct->pcie_port where bit 2 is set (e.g. 3..7) the shifted value will be sign extended and the top 32 bits of the result will be set. Fix this by casting the u16 values to a u64 before the 29 bit left shift. Addresses-Coverity: ("Unintended sign extension") Fixes: 3451b97cce2d ("liquidio: CN23XX register setup") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 4cddd628d41b..9ed3d1ab2ca5 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -420,7 +420,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct) * bits 32:47 indicate the PVF num. */ for (q_no = 0; q_no < ern; q_no++) { - reg_val = oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS; + reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS; /* for VF assigned queues. */ if (q_no < oct->sriov_info.pf_srn) { From 65875073eddd24d7b3968c1501ef29277398dc7b Mon Sep 17 00:00:00 2001 From: Qitao Xu Date: Wed, 14 Jul 2021 22:59:23 -0700 Subject: [PATCH 0463/1469] net: use %px to print skb address in trace_netif_receive_skb The print format of skb adress in tracepoint class net_dev_template is changed to %px from %p, because we want to use skb address as a quick way to identify a packet. Note, trace ring buffer is only accessible to privileged users, it is safe to use a real kernel address here. Reviewed-by: Cong Wang Signed-off-by: Qitao Xu Signed-off-by: David S. Miller --- include/trace/events/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 2399073c3afc..78c448c6ab4c 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(net_dev_template, __assign_str(name, skb->dev->name); ), - TP_printk("dev=%s skbaddr=%p len=%u", + TP_printk("dev=%s skbaddr=%px len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) From 851f36e40962408309ad2665bf0056c19a97881c Mon Sep 17 00:00:00 2001 From: Qitao Xu Date: Wed, 14 Jul 2021 23:00:21 -0700 Subject: [PATCH 0464/1469] net_sched: use %px to print skb address in trace_qdisc_dequeue() Print format of skbaddr is changed to %px from %p, because we want to use skb address as a quick way to identify a packet. Note, trace ring buffer is only accessible to privileged users, it is safe to use a real kernel address here. Reviewed-by: Cong Wang Signed-off-by: Qitao Xu Signed-off-by: David S. Miller --- include/trace/events/qdisc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 330d32d84485..58209557cb3a 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -41,7 +41,7 @@ TRACE_EVENT(qdisc_dequeue, __entry->txq_state = txq->state; ), - TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", + TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); From 70713dddf3d25a02d1952f8c5d2688c986d2f2fb Mon Sep 17 00:00:00 2001 From: Qitao Xu Date: Wed, 14 Jul 2021 23:03:24 -0700 Subject: [PATCH 0465/1469] net_sched: introduce tracepoint trace_qdisc_enqueue() Tracepoint trace_qdisc_enqueue() is introduced to trace skb at the entrance of TC layer on TX side. This is similar to trace_qdisc_dequeue(): 1. For both we only trace successful cases. The failure cases can be traced via trace_kfree_skb(). 2. They are called at entrance or exit of TC layer, not for each ->enqueue() or ->dequeue(). This is intentional, because we want to make trace_qdisc_enqueue() symmetric to trace_qdisc_dequeue(), which is easier to use. The return value of qdisc_enqueue() is not interesting here, we have Qdisc's drop packets in ->dequeue(), it is impossible to trace them even if we have the return value, the only way to trace them is tracing kfree_skb(). We only add information we need to trace ring buffer. If any other information is needed, it is easy to extend it without breaking ABI, see commit 3dd344ea84e1 ("net: tracepoint: exposing sk_family in all tcp:tracepoints"). Reviewed-by: Cong Wang Signed-off-by: Qitao Xu Signed-off-by: David S. Miller --- include/trace/events/qdisc.h | 26 ++++++++++++++++++++++++++ net/core/dev.c | 20 ++++++++++++++++---- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 58209557cb3a..c3006c6b4a87 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -46,6 +46,32 @@ TRACE_EVENT(qdisc_dequeue, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); +TRACE_EVENT(qdisc_enqueue, + + TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb), + + TP_ARGS(qdisc, txq, skb), + + TP_STRUCT__entry( + __field(struct Qdisc *, qdisc) + __field(void *, skbaddr) + __field(int, ifindex) + __field(u32, handle) + __field(u32, parent) + ), + + TP_fast_assign( + __entry->qdisc = qdisc; + __entry->skbaddr = skb; + __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; + __entry->handle = qdisc->handle; + __entry->parent = qdisc->parent; + ), + + TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px", + __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr) +); + TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), diff --git a/net/core/dev.c b/net/core/dev.c index 64b21f0a2048..7aeefc467ddc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -131,6 +131,7 @@ #include #include #include +#include #include #include #include @@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) } } +static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, + struct sk_buff **to_free, + struct netdev_queue *txq) +{ + int rc; + + rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; + if (rc == NET_XMIT_SUCCESS) + trace_qdisc_enqueue(q, txq, skb); + return rc; +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { - rc = q->enqueue(skb, q, &to_free) & - NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); @@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return NET_XMIT_SUCCESS; } - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: @@ -3923,7 +3935,7 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); From b18c7da63fcb46e2f9a093cc18d7c219e13a887c Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Mon, 5 Jul 2021 11:41:54 -0500 Subject: [PATCH 0466/1469] RDMA/rxe: Fix memory leak in error path code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In rxe_mr_init_user() at the third error the driver fails to free the memory at mr->map. This patch adds code to do that. This error only occurs if page_address() fails to return a non zero address which should never happen for 64 bit architectures. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/20210705164153.17652-1-rpearsonhpe@gmail.com Reported by: Haakon Bugge Signed-off-by: Bob Pearson Reviewed-by: Zhu Yanjun Reviewed-by: Håkon Bugge Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_mr.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 6aabcb4de235..be4bcb420fab 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -113,13 +113,14 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, int num_buf; void *vaddr; int err; + int i; umem = ib_umem_get(pd->ibpd.device, start, length, access); if (IS_ERR(umem)) { - pr_warn("err %d from rxe_umem_get\n", - (int)PTR_ERR(umem)); + pr_warn("%s: Unable to pin memory region err = %d\n", + __func__, (int)PTR_ERR(umem)); err = PTR_ERR(umem); - goto err1; + goto err_out; } mr->umem = umem; @@ -129,9 +130,9 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, err = rxe_mr_alloc(mr, num_buf); if (err) { - pr_warn("err %d from rxe_mr_alloc\n", err); - ib_umem_release(umem); - goto err1; + pr_warn("%s: Unable to allocate memory for map\n", + __func__); + goto err_release_umem; } mr->page_shift = PAGE_SHIFT; @@ -151,10 +152,10 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, vaddr = page_address(sg_page_iter_page(&sg_iter)); if (!vaddr) { - pr_warn("null vaddr\n"); - ib_umem_release(umem); + pr_warn("%s: Unable to get virtual address\n", + __func__); err = -ENOMEM; - goto err1; + goto err_cleanup_map; } buf->addr = (uintptr_t)vaddr; @@ -177,7 +178,13 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, return 0; -err1: +err_cleanup_map: + for (i = 0; i < mr->num_map; i++) + kfree(mr->map[i]); + kfree(mr->map); +err_release_umem: + ib_umem_release(umem); +err_out: return err; } From 91091656252f5d6d8c476e0c92776ce9fae7b445 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 15 Jul 2021 13:57:12 +0100 Subject: [PATCH 0467/1469] s390/bpf: Perform r1 range checking before accessing jit->seen_reg[r1] Currently array jit->seen_reg[r1] is being accessed before the range checking of index r1. The range changing on r1 should be performed first since it will avoid any potential out-of-range accesses on the array seen_reg[] and also it is more optimal to perform checks on r1 before fetching data from the array. Fix this by swapping the order of the checks before the array access. Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Signed-off-by: Colin Ian King Signed-off-by: Daniel Borkmann Tested-by: Ilya Leoshkevich Acked-by: Ilya Leoshkevich Link: https://lore.kernel.org/bpf/20210715125712.24690-1-colin.king@canonical.com --- arch/s390/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 63cae0476bb4..2ae419f5115a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -112,7 +112,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) { u32 r1 = reg2hex[b1]; - if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15) + if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1]) jit->seen_reg[r1] = 1; } From 7e6b27a69167f97c56b5437871d29e9722c3e470 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 12 Jul 2021 12:55:45 -0700 Subject: [PATCH 0468/1469] bpf, sockmap: Fix potential memory leak on unlikely error case If skb_linearize is needed and fails we could leak a msg on the error handling. To fix ensure we kfree the msg block before returning error. Found during code review. Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com --- net/core/skmsg.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9b6160a191f8..15d71288e741 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, if (skb_linearize(skb)) return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); - if (unlikely(num_sge < 0)) { - kfree(msg); + if (unlikely(num_sge < 0)) return num_sge; - } copied = skb->len; msg->sg.start = 0; @@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) { struct sock *sk = psock->sk; struct sk_msg *msg; + int err; /* If we are receiving on the same sock skb->sk is already assigned, * skip memory accounting and owner transition seeing it already set @@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } /* Puts an skb on the ingress queue of the socket already assigned to the @@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; + int err; if (unlikely(!msg)) return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, From 228a4a7ba8e99bb9ef980b62f71e3be33f4aae69 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 12 Jul 2021 12:55:46 -0700 Subject: [PATCH 0469/1469] bpf, sockmap, tcp: sk_prot needs inuse_idx set for proc stats The proc socket stats use sk_prot->inuse_idx value to record inuse sock stats. We currently do not set this correctly from sockmap side. The result is reading sock stats '/proc/net/sockstat' gives incorrect values. The socket counter is incremented correctly, but because we don't set the counter correctly when we replace sk_prot we may omit the decrement. To get the correct inuse_idx value move the core_initcall that initializes the TCP proto handlers to late_initcall. This way it is initialized after TCP has the chance to assign the inuse_idx value from the register protocol handler. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Suggested-by: Jakub Sitnicki Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Link: https://lore.kernel.org/bpf/20210712195546.423990-3-john.fastabend@gmail.com --- net/ipv4/tcp_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f26916a62f25..d3e9386b493e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void) tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } -core_initcall(tcp_bpf_v4_build_proto); +late_initcall(tcp_bpf_v4_build_proto); static int tcp_bpf_assert_proto_ops(struct proto *ops) { From 54ea2f49fd9400dd698c25450be3352b5613b3b4 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 14 Jul 2021 17:47:50 +0200 Subject: [PATCH 0470/1469] bpf, sockmap, udp: sk_prot needs inuse_idx set for proc stats The proc socket stats use sk_prot->inuse_idx value to record inuse sock stats. We currently do not set this correctly from sockmap side. The result is reading sock stats '/proc/net/sockstat' gives incorrect values. The socket counter is incremented correctly, but because we don't set the counter correctly when we replace sk_prot we may omit the decrement. To get the correct inuse_idx value move the core_initcall that initializes the UDP proto handlers to late_initcall. This way it is initialized after UDP has the chance to assign the inuse_idx value from the register protocol handler. Fixes: edc6741cc660 ("bpf: Add sockmap hooks for UDP sockets") Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210714154750.528206-1-jakub@cloudflare.com --- net/ipv4/udp_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 45b8782aec0c..9f5a5cdc38e6 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void) udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot); return 0; } -core_initcall(udp_bpf_v4_build_proto); +late_initcall(udp_bpf_v4_build_proto); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { From d444b06e40855219ef38b5e9286db16d435f06dc Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Thu, 15 Jul 2021 13:06:09 +0200 Subject: [PATCH 0471/1469] bpftool: Check malloc return value in mount_bpffs_for_pin Fix and add a missing NULL check for the prior malloc() call. Fixes: 49a086c201a9 ("bpftool: implement prog load command") Signed-off-by: Tobias Klauser Signed-off-by: Daniel Borkmann Reviewed-by: Quentin Monnet Acked-by: Roman Gushchin Link: https://lore.kernel.org/bpf/20210715110609.29364-1-tklauser@distanz.ch --- tools/bpf/bpftool/common.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1828bba19020..dc6daa193557 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name) int err = 0; file = malloc(strlen(name) + 1); + if (!file) { + p_err("mem alloc failed"); + return -1; + } + strcpy(file, name); dir = dirname(file); From 0dc2d6ff40364a00cd66cae3ed327894dcd11c82 Mon Sep 17 00:00:00 2001 From: Tatyana Nikolova Date: Thu, 8 Jul 2021 14:35:21 -0700 Subject: [PATCH 0472/1469] RDMA/irdma: Check vsi pointer before using it Fix a coverity warning about NULL pointer dereference: Dereferencing "vsi", which is known to be "NULL". Link: https://lore.kernel.org/r/20210708213521.438-1-tatyana.e.nikolova@intel.com Reported-by: coverity-bot Addresses-Coverity-ID: 1505164 ("Null pointer dereferences") Fixes: 8498a30e1b94 ("RDMA/irdma: Register auxiliary driver and implement private channel OPs") Signed-off-by: Mustafa Ismail Signed-off-by: Tatyana Nikolova Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/main.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c index ea59432351fb..51a41359e0b4 100644 --- a/drivers/infiniband/hw/irdma/main.c +++ b/drivers/infiniband/hw/irdma/main.c @@ -215,10 +215,10 @@ static void irdma_remove(struct auxiliary_device *aux_dev) pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn)); } -static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf) +static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf, + struct ice_vsi *vsi) { struct irdma_pci_f *rf = iwdev->rf; - struct ice_vsi *vsi = ice_get_main_vsi(pf); rf->cdev = pf; rf->gen_ops.register_qset = irdma_lan_register_qset; @@ -253,12 +253,15 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_ struct iidc_auxiliary_dev, adev); struct ice_pf *pf = iidc_adev->pf; + struct ice_vsi *vsi = ice_get_main_vsi(pf); struct iidc_qos_params qos_info = {}; struct irdma_device *iwdev; struct irdma_pci_f *rf; struct irdma_l2params l2params = {}; int err; + if (!vsi) + return -EIO; iwdev = ib_alloc_device(irdma_device, ibdev); if (!iwdev) return -ENOMEM; @@ -268,7 +271,7 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_ return -ENOMEM; } - irdma_fill_device_info(iwdev, pf); + irdma_fill_device_info(iwdev, pf, vsi); rf = iwdev->rf; if (irdma_ctrl_init_hw(rf)) { From 991e634360f2622a683b48dfe44fe6d9cb765a09 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Thu, 15 Jul 2021 20:22:04 +0800 Subject: [PATCH 0473/1469] net: fix uninit-value in caif_seqpkt_sendmsg When nr_segs equal to zero in iovec_from_user, the object msg->msg_iter.iov is uninit stack memory in caif_seqpkt_sendmsg which is defined in ___sys_sendmsg. So we cann't just judge msg->msg_iter.iov->base directlly. We can use nr_segs to judge msg in caif_seqpkt_sendmsg whether has data buffers. ===================================================== BUG: KMSAN: uninit-value in caif_seqpkt_sendmsg+0x693/0xf60 net/caif/caif_socket.c:542 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 caif_seqpkt_sendmsg+0x693/0xf60 net/caif/caif_socket.c:542 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2343 ___sys_sendmsg net/socket.c:2397 [inline] __sys_sendmmsg+0x808/0xc90 net/socket.c:2480 __compat_sys_sendmmsg net/compat.c:656 [inline] Reported-by: syzbot+09a5d591c1f98cf5efcb@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=1ace85e8fc9b0d5a45c08c2656c3e91762daa9b8 Fixes: bece7b2398d0 ("caif: Rewritten socket implementation") Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller --- net/caif/caif_socket.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 647554c9813b..e12fd3cad619 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, goto err; ret = -EINVAL; - if (unlikely(msg->msg_iter.iov->iov_base == NULL)) + if (unlikely(msg->msg_iter.nr_segs == 0) || + unlikely(msg->msg_iter.iov->iov_base == NULL)) goto err; noblock = msg->msg_flags & MSG_DONTWAIT; From a323da0b73b89b3ecabd661c56978a271e1911b6 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Tue, 13 Jul 2021 23:11:28 -0400 Subject: [PATCH 0474/1469] RDMA/irdma: change the returned type of irdma_sc_repost_aeq_entries to void The function irdma_sc_repost_aeq_entries always returns zero. So the returned type is changed to void. Link: https://lore.kernel.org/r/20210714031130.1511109-2-yanjun.zhu@linux.dev Signed-off-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/ctrl.c | 4 +--- drivers/infiniband/hw/irdma/type.h | 3 +-- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index c3880a85e255..f1e5515256e0 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -4186,11 +4186,9 @@ enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq, * @dev: sc device struct * @count: allocate count */ -enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count) +void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count) { writel(count, dev->hw_regs[IRDMA_AEQALLOC]); - - return 0; } /** diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h index 7387b83e826d..874bc25a938b 100644 --- a/drivers/infiniband/hw/irdma/type.h +++ b/drivers/infiniband/hw/irdma/type.h @@ -1222,8 +1222,7 @@ enum irdma_status_code irdma_sc_aeq_init(struct irdma_sc_aeq *aeq, struct irdma_aeq_init_info *info); enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq, struct irdma_aeqe_info *info); -enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, - u32 count); +void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count); void irdma_sc_pd_init(struct irdma_sc_dev *dev, struct irdma_sc_pd *pd, u32 pd_id, int abi_ver); From 41f5fa9fa75cebd48b5ce9ec244ee25390ac3b89 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Tue, 13 Jul 2021 23:11:29 -0400 Subject: [PATCH 0475/1469] RDMA/irdma: Change the returned type of irdma_set_hw_rsrc to void Since the function irdma_set_hw_rsrc always returns zero, change the returned type to void and remove all the related source code. Link: https://lore.kernel.org/r/20210714031130.1511109-3-yanjun.zhu@linux.dev Signed-off-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/hw.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 7afb8a6a0526..00de5ee9a260 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -1920,7 +1920,7 @@ enum irdma_status_code irdma_ctrl_init_hw(struct irdma_pci_f *rf) * irdma_set_hw_rsrc - set hw memory resources. * @rf: RDMA PCI function */ -static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf) +static void irdma_set_hw_rsrc(struct irdma_pci_f *rf) { rf->allocated_qps = (void *)(rf->mem_rsrc + (sizeof(struct irdma_arp_entry) * rf->arp_table_size)); @@ -1937,8 +1937,6 @@ static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf) spin_lock_init(&rf->arp_lock); spin_lock_init(&rf->qptable_lock); spin_lock_init(&rf->qh_list_lock); - - return 0; } /** @@ -2000,9 +1998,7 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf) rf->arp_table = (struct irdma_arp_entry *)rf->mem_rsrc; - ret = irdma_set_hw_rsrc(rf); - if (ret) - goto set_hw_rsrc_fail; + irdma_set_hw_rsrc(rf); set_bit(0, rf->allocated_mrs); set_bit(0, rf->allocated_qps); @@ -2025,9 +2021,6 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf) return 0; -set_hw_rsrc_fail: - kfree(rf->mem_rsrc); - rf->mem_rsrc = NULL; mem_rsrc_kzalloc_fail: kfree(rf->allocated_ws_nodes); rf->allocated_ws_nodes = NULL; From dc6afef7e14252c5ca5b8a8444946cb4b75b0aa0 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Tue, 13 Jul 2021 23:11:30 -0400 Subject: [PATCH 0476/1469] RDMA/irdma: Change returned type of irdma_setup_virt_qp to void Since the returned value of the function irdma_setup_virt_qp is always 0, remove the returned value check and change the returned type to void. Link: https://lore.kernel.org/r/20210714031130.1511109-4-yanjun.zhu@linux.dev Signed-off-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/verbs.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 9712f6902ba8..717147ed0519 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -557,7 +557,7 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) * @iwqp: qp ptr * @init_info: initialize info to return */ -static int irdma_setup_virt_qp(struct irdma_device *iwdev, +static void irdma_setup_virt_qp(struct irdma_device *iwdev, struct irdma_qp *iwqp, struct irdma_qp_init_info *init_info) { @@ -574,8 +574,6 @@ static int irdma_setup_virt_qp(struct irdma_device *iwdev, init_info->sq_pa = qpmr->sq_pbl.addr; init_info->rq_pa = qpmr->rq_pbl.addr; } - - return 0; } /** @@ -914,7 +912,7 @@ static struct ib_qp *irdma_create_qp(struct ib_pd *ibpd, } } init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver; - err_code = irdma_setup_virt_qp(iwdev, iwqp, &init_info); + irdma_setup_virt_qp(iwdev, iwqp, &init_info); } else { init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER; err_code = irdma_setup_kmode_qp(iwdev, iwqp, &init_info, init_attr); From e48bf29cf9d6d60d810e2af71e54b71a324094e0 Mon Sep 17 00:00:00 2001 From: Ye Xiang Date: Sun, 13 Jun 2021 11:25:07 +0800 Subject: [PATCH 0477/1469] HID: intel-ish-hid: use async resume function ISH IPC driver uses asynchronous workqueue to do resume now, but there is a potential timing issue: when child devices resume before bus driver, it will cause child devices resume failed and cannot be recovered until reboot. The current implementation in this case do wait for IPC to resume but fail to accommodate for a case when there is no ISH reboot and soft resume is taking time. This issue is apparent on Tiger Lake platform with 5.11.13 kernel when doing suspend to idle then resume(s0ix) test. To resolve this issue, we change ISHTP HID client to use asynchronous resume callback too. In the asynchronous resume callback, it waits for the ISHTP resume done event, and then notify ISHTP HID client link ready. Signed-off-by: Ye Xiang Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-hid-client.c | 15 +++++++++- drivers/hid/intel-ish-hid/ishtp-hid.h | 1 + drivers/hid/intel-ish-hid/ishtp/bus.c | 29 +++++++++++++++----- include/linux/intel-ish-client-if.h | 2 ++ 4 files changed, 39 insertions(+), 8 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 6b1fa971b33e..91bf4d01e91a 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -784,6 +784,17 @@ static void hid_ishtp_cl_reset_handler(struct work_struct *work) } } +static void hid_ishtp_cl_resume_handler(struct work_struct *work) +{ + struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, resume_work); + struct ishtp_cl *hid_ishtp_cl = client_data->hid_ishtp_cl; + + if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) { + client_data->suspended = false; + wake_up_interruptible(&client_data->ishtp_resume_wait); + } +} + ishtp_print_log ishtp_hid_print_trace; /** @@ -822,6 +833,8 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) init_waitqueue_head(&client_data->ishtp_resume_wait); INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler); + INIT_WORK(&client_data->resume_work, hid_ishtp_cl_resume_handler); + ishtp_hid_print_trace = ishtp_trace_callback(cl_device); @@ -921,7 +934,7 @@ static int hid_ishtp_cl_resume(struct device *device) hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, hid_ishtp_cl); - client_data->suspended = false; + schedule_work(&client_data->resume_work); return 0; } diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h index f88443a7d935..6a5cc11aefd8 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.h +++ b/drivers/hid/intel-ish-hid/ishtp-hid.h @@ -135,6 +135,7 @@ struct ishtp_cl_data { int multi_packet_cnt; struct work_struct work; + struct work_struct resume_work; struct ishtp_cl_device *cl_device; }; diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f0802b047ed8..aa2c51624012 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -314,13 +314,6 @@ static int ishtp_cl_device_resume(struct device *dev) if (!device) return 0; - /* - * When ISH needs hard reset, it is done asynchrnously, hence bus - * resume will be called before full ISH resume - */ - if (device->ishtp_dev->resume_flag) - return 0; - driver = to_ishtp_cl_driver(dev->driver); if (driver && driver->driver.pm) { if (driver->driver.pm->resume) @@ -849,6 +842,28 @@ struct device *ishtp_device(struct ishtp_cl_device *device) } EXPORT_SYMBOL(ishtp_device); +/** + * ishtp_wait_resume() - Wait for IPC resume + * + * Wait for IPC resume + * + * Return: resume complete or not + */ +bool ishtp_wait_resume(struct ishtp_device *dev) +{ + /* 50ms to get resume response */ + #define WAIT_FOR_RESUME_ACK_MS 50 + + /* Waiting to get resume response */ + if (dev->resume_flag) + wait_event_interruptible_timeout(dev->resume_wait, + !dev->resume_flag, + msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS)); + + return (!dev->resume_flag); +} +EXPORT_SYMBOL_GPL(ishtp_wait_resume); + /** * ishtp_get_pci_device() - Return PCI device dev pointer * This interface is used to return PCI device pointer diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 25e2b4e80502..aee8ff4739b1 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); +/* wait for IPC resume */ +bool ishtp_wait_resume(struct ishtp_device *dev); /* Trace interface for clients */ ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ From 55cef88bbf12f3bfbe5c2379a8868a034707e755 Mon Sep 17 00:00:00 2001 From: Yoshitaka Ikeda Date: Thu, 15 Jul 2021 16:21:32 +0000 Subject: [PATCH 0478/1469] spi: spi-cadence-quadspi: Fix division by zero warning Fix below division by zero warning: - Added an if statement because buswidth can be zero, resulting in division by zero. - The modified code was based on another driver (atmel-quadspi). [ 0.795337] Division by zero in kernel. : [ 0.834051] [<807fd40c>] (__div0) from [<804e1acc>] (Ldiv0+0x8/0x10) [ 0.839097] [<805f0710>] (cqspi_exec_mem_op) from [<805edb4c>] (spi_mem_exec_op+0x3b0/0x3f8) Fixes: 7512eaf54190 ("spi: cadence-quadspi: Fix dummy cycle calculation when buswidth > 1") Signed-off-by: Yoshitaka Ikeda Link: https://lore.kernel.org/r/ed989af6-da88-4e0b-9ed8-126db6cad2e4@nskint.co.jp Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 7a00346ff9b9..13d1f0ce618e 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -307,11 +307,13 @@ static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata) static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) { - unsigned int dummy_clk; + unsigned int dummy_clk = 0; - dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); - if (dtr) - dummy_clk /= 2; + if (op->dummy.buswidth && op->dummy.nbytes) { + dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); + if (dtr) + dummy_clk /= 2; + } return dummy_clk; } From a1c9ca5f65c9acfd7c02474b9d5cacbd7ea288df Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 15 Jul 2021 11:55:31 -0700 Subject: [PATCH 0479/1469] EDAC/igen6: fix core dependency AGAIN My previous patch had a typo/thinko which prevents this driver from being enabled: change X64_64 to X86_64. Fixes: 0a9ece9ba154 ("EDAC/igen6: fix core dependency") Signed-off-by: Randy Dunlap Cc: Qiuxu Zhuo Cc: Borislav Petkov Cc: Mauro Carvalho Chehab Cc: linux-edac@vger.kernel.org Cc: bowsingbetee Cc: stable@vger.kernel.org Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- drivers/edac/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 91164c5f0757..2fc4c3f91fd5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -271,7 +271,7 @@ config EDAC_PND2 config EDAC_IGEN6 tristate "Intel client SoC Integrated MC" depends on PCI && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG - depends on X64_64 && X86_MCE_INTEL + depends on X86_64 && X86_MCE_INTEL help Support for error detection and correction on the Intel client SoC Integrated Memory Controller using In-Band ECC IP. From 3fdcf7cdfc229346d028242e73562704ad644dd0 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Mon, 5 Jul 2021 10:26:59 +1200 Subject: [PATCH 0480/1469] HID: asus: Remove check for same LED brightness on set Remove the early return on LED brightness set so that any controller application, daemon, or desktop may set the same brightness at any stage. This is required because many ASUS ROG keyboards will default to max brightness on laptop resume if the LEDs were set to off before sleep. Signed-off-by: Luke D Jones Signed-off-by: Jiri Kosina --- drivers/hid/hid-asus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index fca8fc78a78a..fb807c8e989b 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -485,9 +485,6 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); - if (led->brightness == brightness) - return; - led->brightness = brightness; schedule_work(&led->work); } From 6206b7981a36476f4695d661ae139f7db36a802d Mon Sep 17 00:00:00 2001 From: Jia He Date: Thu, 15 Jul 2021 16:08:21 +0800 Subject: [PATCH 0481/1469] qed: fix possible unpaired spin_{un}lock_bh in _qed_mcp_cmd_and_union() Liajian reported a bug_on hit on a ThunderX2 arm64 server with FastLinQ QL41000 ethernet controller: BUG: scheduling while atomic: kworker/0:4/531/0x00000200 [qed_probe:488()]hw prepare failed kernel BUG at mm/vmalloc.c:2355! Internal error: Oops - BUG: 0 [#1] SMP CPU: 0 PID: 531 Comm: kworker/0:4 Tainted: G W 5.4.0-77-generic #86-Ubuntu pstate: 00400009 (nzcv daif +PAN -UAO) Call trace: vunmap+0x4c/0x50 iounmap+0x48/0x58 qed_free_pci+0x60/0x80 [qed] qed_probe+0x35c/0x688 [qed] __qede_probe+0x88/0x5c8 [qede] qede_probe+0x60/0xe0 [qede] local_pci_probe+0x48/0xa0 work_for_cpu_fn+0x24/0x38 process_one_work+0x1d0/0x468 worker_thread+0x238/0x4e0 kthread+0xf0/0x118 ret_from_fork+0x10/0x18 In this case, qed_hw_prepare() returns error due to hw/fw error, but in theory work queue should be in process context instead of interrupt. The root cause might be the unpaired spin_{un}lock_bh() in _qed_mcp_cmd_and_union(), which causes botton half is disabled incorrectly. Reported-by: Lijian Zhang Signed-off-by: Jia He Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 4387292c37e2..79d879a5d663 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -474,14 +474,18 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); - if (!qed_mcp_has_pending_cmd(p_hwfn)) + if (!qed_mcp_has_pending_cmd(p_hwfn)) { + spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); break; + } rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt); - if (!rc) + if (!rc) { + spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); break; - else if (rc != -EAGAIN) + } else if (rc != -EAGAIN) { goto err; + } spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); @@ -498,6 +502,8 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EAGAIN; } + spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); + /* Send the mailbox command */ qed_mcp_reread_offsets(p_hwfn, p_ptt); seq_num = ++p_hwfn->mcp_info->drv_mb_seq; @@ -524,14 +530,18 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); - if (p_cmd_elem->b_is_completed) + if (p_cmd_elem->b_is_completed) { + spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); break; + } rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt); - if (!rc) + if (!rc) { + spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); break; - else if (rc != -EAGAIN) + } else if (rc != -EAGAIN) { goto err; + } spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); } while (++cnt < max_retries); @@ -554,6 +564,7 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EAGAIN; } + spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem); spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); From a6ecfb39ba9d7316057cea823b196b734f6b18ca Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Wed, 14 Jul 2021 17:13:22 +0800 Subject: [PATCH 0482/1469] usb: hso: fix error handling code of hso_create_net_device The current error handling code of hso_create_net_device is hso_free_net_device, no matter which errors lead to. For example, WARNING in hso_free_net_device [1]. Fix this by refactoring the error handling code of hso_create_net_device by handling different errors by different code. [1] https://syzkaller.appspot.com/bug?id=66eff8d49af1b28370ad342787413e35bbe76efe Reported-by: syzbot+44d53c7255bb1aea22d2@syzkaller.appspotmail.com Fixes: 5fcfb6d0bfcd ("hso: fix bailout in error case of probe") Signed-off-by: Dongliang Mu Signed-off-by: David S. Miller --- drivers/net/usb/hso.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 63006838bdcc..dec96e8ab567 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2495,7 +2495,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, hso_net_init); if (!net) { dev_err(&interface->dev, "Unable to create ethernet device\n"); - goto exit; + goto err_hso_dev; } hso_net = netdev_priv(net); @@ -2508,13 +2508,13 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, USB_DIR_IN); if (!hso_net->in_endp) { dev_err(&interface->dev, "Can't find BULK IN endpoint\n"); - goto exit; + goto err_net; } hso_net->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK, USB_DIR_OUT); if (!hso_net->out_endp) { dev_err(&interface->dev, "Can't find BULK OUT endpoint\n"); - goto exit; + goto err_net; } SET_NETDEV_DEV(net, &interface->dev); SET_NETDEV_DEVTYPE(net, &hso_type); @@ -2523,18 +2523,18 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) { hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL); if (!hso_net->mux_bulk_rx_urb_pool[i]) - goto exit; + goto err_mux_bulk_rx; hso_net->mux_bulk_rx_buf_pool[i] = kzalloc(MUX_BULK_RX_BUF_SIZE, GFP_KERNEL); if (!hso_net->mux_bulk_rx_buf_pool[i]) - goto exit; + goto err_mux_bulk_rx; } hso_net->mux_bulk_tx_urb = usb_alloc_urb(0, GFP_KERNEL); if (!hso_net->mux_bulk_tx_urb) - goto exit; + goto err_mux_bulk_rx; hso_net->mux_bulk_tx_buf = kzalloc(MUX_BULK_TX_BUF_SIZE, GFP_KERNEL); if (!hso_net->mux_bulk_tx_buf) - goto exit; + goto err_free_tx_urb; add_net_device(hso_dev); @@ -2542,7 +2542,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, result = register_netdev(net); if (result) { dev_err(&interface->dev, "Failed to register device\n"); - goto exit; + goto err_free_tx_buf; } hso_log_port(hso_dev); @@ -2550,8 +2550,21 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, hso_create_rfkill(hso_dev, interface); return hso_dev; -exit: - hso_free_net_device(hso_dev, true); + +err_free_tx_buf: + remove_net_device(hso_dev); + kfree(hso_net->mux_bulk_tx_buf); +err_free_tx_urb: + usb_free_urb(hso_net->mux_bulk_tx_urb); +err_mux_bulk_rx: + for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) { + usb_free_urb(hso_net->mux_bulk_rx_urb_pool[i]); + kfree(hso_net->mux_bulk_rx_buf_pool[i]); + } +err_net: + free_netdev(net); +err_hso_dev: + kfree(hso_dev); return NULL; } From 8aa6348634d1bc81801329e6ea98cd88ec07fb10 Mon Sep 17 00:00:00 2001 From: Dylan MacKenzie Date: Tue, 13 Jul 2021 16:31:07 -0700 Subject: [PATCH 0483/1469] HID: amd_sfh: Use correct MMIO register for DMA address amd_stop_sensor_v2 accidentally used a different MMIO register than amd_start_sensor_v2 for the DMA address. Fixes: f264481ad614dfd9 ("HID: amd_sfh: Extend driver capabilities for multi-generation support") Signed-off-by: Dylan MacKenzie Acked-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 96e2577fa37e..8d68796aa905 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -58,7 +58,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx) cmd_base.cmd_v2.sensor_id = sensor_idx; cmd_base.cmd_v2.length = 16; - writeq(0x0, privdata->mmio + AMD_C2P_MSG2); + writeq(0x0, privdata->mmio + AMD_C2P_MSG1); writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); } From 9a3223b0713369e6258fd8656e0c0a5ed794d186 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 15 Jul 2021 12:59:52 -0600 Subject: [PATCH 0484/1469] ASoC: dt-bindings: renesas: rsnd: Fix incorrect 'port' regex schema A property regex goes under 'patternProperties', not 'properties' schema. Otherwise, the regex is interpretted as a fixed string. Fixes: 17c2d247ddd2 ("ASoC: dt-bindings: renesas: rsnd: tidyup properties") Cc: Mark Brown Cc: Kuninori Morimoto Cc: alsa-devel@alsa-project.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210715185952.1470138-1-robh@kernel.org Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/sound/renesas,rsnd.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml index ee936d1aa724..c2930d65728e 100644 --- a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml +++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml @@ -114,7 +114,7 @@ properties: ports: $ref: /schemas/graph.yaml#/properties/ports - properties: + patternProperties: port(@[0-9a-f]+)?: $ref: audio-graph-port.yaml# unevaluatedProperties: false From 0967ebffe098157180a0bbd180ac90348c6e07d7 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 0485/1469] perf inject: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of: # perf test "31: Lookup mmap thread" The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased when a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: 27c9c3424fc217da ("perf inject: Add --buildid-all option") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 5d6f583e2cd3..ffd2b25039e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -361,9 +361,10 @@ static struct dso *findnew_dso(int pid, int tid, const char *filename, dso = machine__findnew_dso_id(machine, filename, id); } - if (dso) + if (dso) { + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; - else + } else nsinfo__put(nsi); thread__put(thread); From 2d6b74baa7147251c30a46c4996e8cc224aa2dc5 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 0486/1469] perf map: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of # perf test "31: Lookup mmap thread" The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased whenever a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: bf2e710b3cb8445c ("perf maps: Lookup maps in both intitial mountns and inner mountns.") Cc: Ian Rogers Cc: Jiri Olsa Cc: Krister Johansen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8af693d9678c..72e7f3616157 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -192,6 +192,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (!(prot & PROT_EXEC)) dso__set_loaded(dso); } + + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; if (build_id__is_defined(bid)) From dedeb4be203b382ba7245d13079bc3b0f6d40c65 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 0487/1469] perf probe: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of: # perf test "31: Lookup mmap thread". The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased whenever a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: 544abd44c7064c8a ("perf probe: Allow placing uprobes in alternate namespaces.") Cc: Ian Rogers Cc: Jiri Olsa Cc: Krister Johansen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c14e1d228e56..e05750cea34c 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -179,8 +179,10 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) struct map *map; map = dso__new_map(target); - if (map && map->dso) + if (map && map->dso) { + nsinfo__put(map->dso->nsinfo); map->dso->nsinfo = nsinfo__get(nsi); + } return map; } else { return kernel_get_module_map(target); From 42db3d9ded555f7148b5695109a7dc8d66f0dde4 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:07 +0200 Subject: [PATCH 0488/1469] perf env: Fix sibling_dies memory leak ASan reports a memory leak in perf_env while running: # perf test "41: Session topology" Caused by sibling_dies not being freed. This patch adds the required free. Fixes: acae8b36cded0ee6 ("perf header: Add die information in CPU topology") Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/2140d0b57656e4eb9021ca9772250c24c032924b.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index ebc5e9ad35db..6c765946ef6f 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -186,6 +186,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cpuid); zfree(&env->cmdline); zfree(&env->cmdline_argv); + zfree(&env->sibling_dies); zfree(&env->sibling_cores); zfree(&env->sibling_threads); zfree(&env->pmu_mappings); From 233f2dc1c284337286f9a64c0152236779a42f6c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:08 +0200 Subject: [PATCH 0489/1469] perf test session_topology: Delete session->evlist ASan reports a memory leak related to session->evlist while running: # perf test "41: Session topology". When perf_data is in write mode, session->evlist is owned by the caller, which should also take care of deleting it. This patch adds the missing evlist__delete(). Signed-off-by: Riccardo Mancini Fixes: c84974ed9fb67293 ("perf test: Add entry to test cpu topology") Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/822f741f06eb25250fb60686cf30a35f447e9e91.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/topology.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index ec4e3b21b831..b5efe675b321 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -61,6 +61,7 @@ static int session_write_header(char *path) TEST_ASSERT_VAL("failed to write header", !perf_session__write_header(session, session->evlist, data.file.fd, true)); + evlist__delete(session->evlist); perf_session__delete(session); return 0; From fc56f54f6fcd5337634f4545af6459613129b432 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:09 +0200 Subject: [PATCH 0490/1469] perf test event_update: Fix memory leak of evlist ASan reports a memory leak when running: # perf test "49: Synthesize attr update" Caused by evlist not being deleted. This patch adds the missing evlist__delete and removes the perf_cpu_map__put since it's already being deleted by evlist__delete. Signed-off-by: Riccardo Mancini Fixes: a6e5281780d1da65 ("perf tools: Add event_update event unit type") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/f7994ad63d248f7645f901132d208fadf9f2b7e4.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/event_update.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 656218179222..932ab0740d11 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -118,6 +118,6 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - perf_cpu_map__put(evsel->core.own_cpus); + evlist__delete(evlist); return 0; } From dccfca926c351ba0893af4c8b481477bdb2881a4 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:10 +0200 Subject: [PATCH 0491/1469] perf test event_update: Fix memory leak of unit ASan reports a memory leak while running: # perf test "49: Synthesize attr update" Caused by a string being duplicated but never freed. This patch adds the missing free(). Note that evsel->unit is not deallocated together with evsel since it is supposed to be a constant string. Signed-off-by: Riccardo Mancini Fixes: a6e5281780d1da65 ("perf tools: Add event_update event unit type") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/1fbc8158663fb0d4d5392e36bae564f6ad60be3c.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/event_update.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 932ab0740d11..44a50527f9d9 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -88,6 +88,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); + char *unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to get evlist", evlist); @@ -98,7 +99,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); - evsel->unit = strdup("KRAVA"); + evsel->unit = unit; TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -118,6 +119,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); + free(unit); evlist__delete(evlist); return 0; } From 581e295a0f6b5c2931d280259fbbfff56959faa9 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:11 +0200 Subject: [PATCH 0492/1469] perf dso: Fix memory leak in dso__new_map() ASan reports a memory leak when running: # perf test "65: maps__merge_in". The causes of the leaks are two, this patch addresses only the first one, which is related to dso__new_map(). The bug is that dso__new_map() creates a new dso but never decreases the refcount it gets from creating it. This patch adds the missing dso__put(). Signed-off-by: Riccardo Mancini Fixes: d3a7c489c7fd2463 ("perf tools: Reference count struct dso") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/60bfe0cd06e89e2ca33646eb8468d7f5de2ee597.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d786cf6b0cfa..ee15db2be2f4 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1154,8 +1154,10 @@ struct map *dso__new_map(const char *name) struct map *map = NULL; struct dso *dso = dso__new(name); - if (dso) + if (dso) { map = map__new2(0, dso); + dso__put(dso); + } return map; } From 244d1797c8c8e850b8de7992af713aa5c70d5650 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:12 +0200 Subject: [PATCH 0493/1469] perf test maps__merge_in: Fix memory leak of maps ASan reports a memory leak when running: # perf test "65: maps__merge_in" This is the second and final patch addressing these memory leaks. This time, the problem is simply that the maps object is never destructed. This patch adds the missing maps__exit call. Signed-off-by: Riccardo Mancini Fixes: 79b6bb73f888933c ("perf maps: Merge 'struct maps' with 'struct map_groups'") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/a1a29b97a58738987d150e94d4ebfad0282fb038.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/maps.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index edcbc70ff9d6..1ac72919fa35 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -116,5 +116,7 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps); TEST_ASSERT_VAL("merge check failed", !ret); + + maps__exit(&maps); return TEST_OK; } From da6b7c6c0626901428245f65712385805e42eba6 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:13 +0200 Subject: [PATCH 0494/1469] perf env: Fix memory leak of cpu_pmu_caps ASan reports memory leaks while running: # perf test "83: Zstd perf.data compression/decompression" The first of the leaks is caused by env->cpu_pmu_caps not being freed. This patch adds the missing (z)free inside perf_env__exit. Signed-off-by: Riccardo Mancini Fixes: 6f91ea283a1ed23e ("perf header: Support CPU PMU capabilities") Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/6ba036a8220156ec1f3d6be3e5d25920f6145028.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6c765946ef6f..cec2e6cad8aa 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -191,6 +191,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->cpu_pmu_caps); zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) From a37338aad8c4d8676173ead14e881d2ec308155c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:14 +0200 Subject: [PATCH 0495/1469] perf report: Free generated help strings for sort option ASan reports the memory leak of the strings allocated by sort_help() when running perf report. This patch changes the returned pointer to char* (instead of const char*), saves it in a temporary variable, and finally deallocates it at function exit. Signed-off-by: Riccardo Mancini Fixes: 702fb9b415e7c99b ("perf report: Show all sort keys in help output") Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/a38b13f02812a8a6759200b9063c6191337f44d4.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 33 ++++++++++++++++++++++----------- tools/perf/util/sort.c | 2 +- tools/perf/util/sort.h | 2 +- 3 files changed, 24 insertions(+), 13 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6386af6a2612..dc0364f671b9 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1175,6 +1175,8 @@ int cmd_report(int argc, const char **argv) .annotation_opts = annotation__default_options, .skip_empty = true, }; + char *sort_order_help = sort_help("sort by key(s):"); + char *field_order_help = sort_help("output field(s): overhead period sample "); const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1209,9 +1211,9 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - sort_help("sort by key(s):")), + sort_order_help), OPT_STRING('F', "fields", &field_order, "key[,keys...]", - sort_help("output field(s): overhead period sample ")), + field_order_help), OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, @@ -1344,11 +1346,11 @@ int cmd_report(int argc, const char **argv) char sort_tmp[128]; if (ret < 0) - return ret; + goto exit; ret = perf_config(report__config, &report); if (ret) - return ret; + goto exit; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -1362,8 +1364,10 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } - if (annotate_check_args(&report.annotation_opts) < 0) - return -EINVAL; + if (annotate_check_args(&report.annotation_opts) < 0) { + ret = -EINVAL; + goto exit; + } if (report.mmaps_mode) report.tasks_mode = true; @@ -1377,12 +1381,14 @@ int cmd_report(int argc, const char **argv) if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); - return -EINVAL; + ret = -EINVAL; + goto exit; } if (symbol_conf.kallsyms_name && access(symbol_conf.kallsyms_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); - return -EINVAL; + ret = -EINVAL; + goto exit; } if (report.inverted_callchain) @@ -1406,12 +1412,14 @@ int cmd_report(int argc, const char **argv) repeat: session = perf_session__new(&data, false, &report.tool); - if (IS_ERR(session)) - return PTR_ERR(session); + if (IS_ERR(session)) { + ret = PTR_ERR(session); + goto exit; + } ret = evswitch__init(&report.evswitch, session->evlist, stderr); if (ret) - return ret; + goto exit; if (zstd_init(&(session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); @@ -1646,5 +1654,8 @@ error: zstd_fini(&(session->zstd_data)); perf_session__delete(session); +exit: + free(sort_order_help); + free(field_order_help); return ret; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 88ce47f2547e..568a88c001c6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3370,7 +3370,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int add_key(sb, s[i].name, llen); } -const char *sort_help(const char *prefix) +char *sort_help(const char *prefix) { struct strbuf sb; char *s; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 87a092645aa7..b67c469aba79 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -302,7 +302,7 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); -const char *sort_help(const char *prefix); +char *sort_help(const char *prefix); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); From 02e6246f5364d5260a6ea6f92ab6f409058b162f Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:15 +0200 Subject: [PATCH 0496/1469] perf inject: Close inject.output on exit ASan reports a memory leak when running: # perf test "83: Zstd perf.data compression/decompression" which happens inside 'perf inject'. The bug is caused by inject.output never being closed. This patch adds the missing perf_data__close(). Signed-off-by: Riccardo Mancini Fixes: 6ef81c55a2b6584c ("perf session: Return error code for perf_session__new() function on failure") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mamatha Inamdar Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/c06f682afa964687367cf6e92a64ceb49aec76a5.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index ffd2b25039e3..c88c61e7f8cc 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -993,8 +993,10 @@ int cmd_inject(int argc, const char **argv) data.path = inject.input_name; inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool); - if (IS_ERR(inject.session)) - return PTR_ERR(inject.session); + if (IS_ERR(inject.session)) { + ret = PTR_ERR(inject.session); + goto out_close_output; + } if (zstd_init(&(inject.session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed.\n"); @@ -1036,6 +1038,8 @@ int cmd_inject(int argc, const char **argv) out_delete: zstd_fini(&(inject.session->zstd_data)); perf_session__delete(inject.session); +out_close_output: + perf_data__close(&inject.output); free(inject.itrace_synth_opts.vm_tm_corr_args); return ret; } From 423b9174f5f71fd3d245f4da0feaf958976f66e7 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:16 +0200 Subject: [PATCH 0497/1469] perf session: Cleanup trace_event ASan reports several memory leaks when running: # perf test "82: Use vfs_getname probe to get syscall args filenames" many of which are related to session->tevent. This patch will solve this problem, then next patch will fix the remaining memory leaks in 'perf script'. This bug is due to a missing deallocation of the trace_event data strutures. This patch adds the missing trace_event__cleanup() in perf_session__delete(). Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/fa2a3f221d90e47ce4e5b7e2d6e64c3509ddc96a.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e9c929a39973..51f727402912 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -306,6 +306,7 @@ void perf_session__delete(struct perf_session *session) evlist__delete(session->evlist); perf_data__close(session->data); } + trace_event__cleanup(&session->tevent); free(session); } From 1b1f57cf9e4c8eb16c8f6b2ce12cc5dd3517fc61 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:17 +0200 Subject: [PATCH 0498/1469] perf script: Release zstd data ASan reports several memory leak while running: # perf test "82: Use vfs_getname probe to get syscall args filenames" One of the leaks is caused by zstd data not being released on exit in perf-script. This patch adds the missing zstd_fini(). Signed-off-by: Riccardo Mancini Fixes: b13b04d9382113f7 ("perf script: Initialize zstd_data") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/39388e8cc2f85ca219ea18697a17b7bd8f74b693.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8c03a9862872..bae0e5b72c0e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -4143,6 +4143,7 @@ out_delete: zfree(&script.ptime_range); } + zstd_fini(&(session->zstd_data)); evlist__free_stats(session->evlist); perf_session__delete(session); From faf3ac305d61341c74e5cdd9e41daecce7f67bfe Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:18 +0200 Subject: [PATCH 0499/1469] perf script: Fix memory 'threads' and 'cpus' leaks on exit ASan reports several memory leaks while running: # perf test "82: Use vfs_getname probe to get syscall args filenames" Two of these are caused by some refcounts not being decreased on perf-script exit, namely script.threads and script.cpus. This patch adds the missing __put calls in a new perf_script__exit function, which is called at the end of cmd_script. This patch concludes the fixes of all remaining memory leaks in perf test "82: Use vfs_getname probe to get syscall args filenames". Signed-off-by: Riccardo Mancini Fixes: cfc8874a48599249 ("perf script: Process cpu/threads maps") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/5ee73b19791c6fa9d24c4d57f4ac1a23609400d7.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index bae0e5b72c0e..064da7f3618d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2601,6 +2601,12 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script) } } +static void perf_script__exit(struct perf_script *script) +{ + perf_thread_map__put(script->threads); + perf_cpu_map__put(script->cpus); +} + static int __cmd_script(struct perf_script *script) { int ret; @@ -4146,6 +4152,7 @@ out_delete: zstd_fini(&(session->zstd_data)); evlist__free_stats(session->evlist); perf_session__delete(session); + perf_script__exit(&script); if (script_started) cleanup_scripting(); From f8cbb0f926ae1e1fb5f9e51614e5437560ed4039 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:19 +0200 Subject: [PATCH 0500/1469] perf lzma: Close lzma stream on exit ASan reports memory leaks when running: # perf test "88: Check open filename arg using perf trace + vfs_getname" One of these is caused by the lzma stream never being closed inside lzma_decompress_to_file(). This patch adds the missing lzma_end(). Signed-off-by: Riccardo Mancini Fixes: 80a32e5b498a7547 ("perf tools: Add lzma decompression support for kernel module") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/aaf50bdce7afe996cfc06e1bbb36e4a2a9b9db93.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/lzma.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 39062df02629..51424cdc3b68 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -69,7 +69,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ferror(infile)) { pr_err("lzma: read error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } if (feof(infile)) @@ -83,7 +83,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (writen(output_fd, buf_out, write_size) != write_size) { pr_err("lzma: write error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } strm.next_out = buf_out; @@ -95,11 +95,13 @@ int lzma_decompress_to_file(const char *input, int output_fd) break; pr_err("lzma: failed %s\n", lzma_strerror(ret)); - goto err_fclose; + goto err_lzma_end; } } err = 0; +err_lzma_end: + lzma_end(&strm); err_fclose: fclose(infile); return err; From 6c7f0ab04707c2882f08d5abb9dc41b54493b61c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:20 +0200 Subject: [PATCH 0501/1469] perf trace: Free malloc'd trace fields on exit ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The first of these leaks is related to struct trace fields never being deallocated. This patch adds the function trace__exit, which is called at the end of cmd_trace, replacing the existing deallocation, which is now moved inside the new function. This function deallocates: - ev_qualifier - ev_qualifier_ids.entries - syscalls.table - sctbl - perfconfig_events Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/de5945ed5c0cb882cbfa3268567d0bff460ff016.1626343282.git.rickyman7@gmail.com [ Removed needless initialization to zero, missing named initializers are zeroed by the compiler ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7ec18ff57fc4..e239e322e030 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4701,6 +4701,15 @@ out: return err; } +static void trace__exit(struct trace *trace) +{ + strlist__delete(trace->ev_qualifier); + free(trace->ev_qualifier_ids.entries); + free(trace->syscalls.table); + syscalltbl__delete(trace->sctbl); + zfree(&trace->perfconfig_events); +} + int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { @@ -5135,6 +5144,6 @@ out_close: if (output_name != NULL) fclose(trace.output); out: - zfree(&trace.perfconfig_events); + trace__exit(&trace); return err; } From f2ebf8ffe7af10bff02d34addbebd9199de65ed2 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:21 +0200 Subject: [PATCH 0502/1469] perf trace: Free syscall->arg_fmt ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The second of these leaks is caused by the arg_fmt field of syscall not being deallocated. This patch adds a new function syscall__exit which is called on all syscalls.table entries in trace__exit, which will free the arg_fmt field. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/d68f25c043d30464ac9fa79c3399e18f429bca82.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e239e322e030..4039ff4c0788 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2266,6 +2266,14 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam return augmented_args; } +static void syscall__exit(struct syscall *sc) +{ + if (!sc) + return; + + free(sc->arg_fmt); +} + static int trace__sys_enter(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -4703,9 +4711,15 @@ out: static void trace__exit(struct trace *trace) { + int i; + strlist__delete(trace->ev_qualifier); free(trace->ev_qualifier_ids.entries); - free(trace->syscalls.table); + if (trace->syscalls.table) { + for (i = 0; i <= trace->sctbl->syscalls.max_id; i++) + syscall__exit(&trace->syscalls.table[i]); + free(trace->syscalls.table); + } syscalltbl__delete(trace->sctbl); zfree(&trace->perfconfig_events); } From 3cb4d5e00e037c70f239173bdd399a7e6040830f Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:22 +0200 Subject: [PATCH 0503/1469] perf trace: Free syscall tp fields in evsel->priv ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The third of these leaks is related to evsel->priv fields of sycalls never being deallocated. This patch adds the function evlist__free_syscall_tp_fields which iterates over all evsels in evlist, matching syscalls, and calling the missing frees. This new function is called at the end of trace__run, right before calling evlist__delete. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/46526611904ec5ff2768b59014e3afce8e0197d1.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4039ff4c0788..0d9e58190f15 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3103,6 +3103,21 @@ static struct evsel *evsel__new_pgfault(u64 config) return evsel; } +static void evlist__free_syscall_tp_fields(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + struct evsel_trace *et = evsel->priv; + + if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) + continue; + + free(et->fmt); + free(et); + } +} + static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) { const u32 type = event->header.type; @@ -4138,7 +4153,7 @@ out_disable: out_delete_evlist: trace__symbols__exit(trace); - + evlist__free_syscall_tp_fields(evlist); evlist__delete(evlist); cgroup__put(trace->cgroup); trace->evlist = NULL; From 659ede7d13f1cc37882088deecbc085da285b8f8 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:23 +0200 Subject: [PATCH 0504/1469] perf trace: Free strings in trace__parse_events_option() ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The fourth of these leaks is related to some strings never being freed in trace__parse_events_option. This patch adds the missing frees. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/34d08535b11124106b859790549991abff5a7de8.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 0d9e58190f15..9c265fa96011 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4659,6 +4659,9 @@ do_concat: err = parse_events_option(&o, lists[0], 0); } out: + free(strace_groups_dir); + free(lists[0]); + free(lists[1]); if (sep) *sep = ','; From 704adfb5a9978462cd861f170201ae2b5e3d3a80 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 15 Jul 2021 00:02:06 -0400 Subject: [PATCH 0505/1469] tracing: Do not reference char * as a string in histograms The histogram logic was allowing events with char * pointers to be used as normal strings. But it was easy to crash the kernel with: # echo 'hist:keys=filename' > events/syscalls/sys_enter_openat/trigger And open some files, and boom! BUG: unable to handle page fault for address: 00007f2ced0c3280 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 1173fa067 P4D 1173fa067 PUD 1171b6067 PMD 1171dd067 PTE 0 Oops: 0000 [#1] PREEMPT SMP CPU: 6 PID: 1810 Comm: cat Not tainted 5.13.0-rc5-test+ #61 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 RIP: 0010:strlen+0x0/0x20 Code: f6 82 80 2a 0b a9 20 74 11 0f b6 50 01 48 83 c0 01 f6 82 80 2a 0b a9 20 75 ef c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 RSP: 0018:ffffbdbf81567b50 EFLAGS: 00010246 RAX: 0000000000000003 RBX: ffff93815cdb3800 RCX: ffff9382401a22d0 RDX: 0000000000000100 RSI: 0000000000000000 RDI: 00007f2ced0c3280 RBP: 0000000000000100 R08: ffff9382409ff074 R09: ffffbdbf81567c98 R10: ffff9382409ff074 R11: 0000000000000000 R12: ffff9382409ff074 R13: 0000000000000001 R14: ffff93815a744f00 R15: 00007f2ced0c3280 FS: 00007f2ced0f8580(0000) GS:ffff93825a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2ced0c3280 CR3: 0000000107069005 CR4: 00000000001706e0 Call Trace: event_hist_trigger+0x463/0x5f0 ? find_held_lock+0x32/0x90 ? sched_clock_cpu+0xe/0xd0 ? lock_release+0x155/0x440 ? kernel_init_free_pages+0x6d/0x90 ? preempt_count_sub+0x9b/0xd0 ? kernel_init_free_pages+0x6d/0x90 ? get_page_from_freelist+0x12c4/0x1680 ? __rb_reserve_next+0xe5/0x460 ? ring_buffer_lock_reserve+0x12a/0x3f0 event_triggers_call+0x52/0xe0 ftrace_syscall_enter+0x264/0x2c0 syscall_trace_enter.constprop.0+0x1ee/0x210 do_syscall_64+0x1c/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Where it triggered a fault on strlen(key) where key was the filename. The reason is that filename is a char * to user space, and the histogram code just blindly dereferenced it, with obvious bad results. I originally tried to use strncpy_from_user/kernel_nofault() but found that there's other places that its dereferenced and not worth the effort. Just do not allow "char *" to act like strings. Link: https://lkml.kernel.org/r/20210715000206.025df9d2@rorschach.local.home Cc: Ingo Molnar Cc: Andrew Morton Cc: Masami Hiramatsu Cc: Tzvetomir Stoyanov Cc: stable@vger.kernel.org Acked-by: Namhyung Kim Acked-by: Tom Zanussi Fixes: 79e577cbce4c4 ("tracing: Support string type key properly") Fixes: 5967bd5c4239 ("tracing: Let filter_assign_type() detect FILTER_PTR_STRING") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0207aeed31e6..16a9dfc9fffc 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1689,7 +1689,9 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (WARN_ON_ONCE(!field)) goto out; - if (is_string_field(field)) { + /* Pointers to strings are just pointers and dangerous to dereference */ + if (is_string_field(field) && + (field->filter_type != FILTER_PTR_STRING)) { flags |= HIST_FIELD_FL_STRING; hist_field->size = MAX_FILTER_STR_VAL; @@ -4495,8 +4497,6 @@ static inline void add_to_key(char *compound_key, void *key, field = key_field->field; if (field->filter_type == FILTER_DYN_STRING) size = *(u32 *)(rec + field->offset) >> 16; - else if (field->filter_type == FILTER_PTR_STRING) - size = strlen(key); else if (field->filter_type == FILTER_STATIC_STRING) size = field->size; From 507345b5ae6a57b7ecd7550ff39282ed20de7b8d Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 12 Jul 2021 12:38:24 -0300 Subject: [PATCH 0506/1469] cifs: handle reconnect of tcon when there is no cached dfs referral When there is no cached DFS referral of tcon->dfs_path, then reconnect to same share. Signed-off-by: Paulo Alcantara (SUSE) Cc: Signed-off-by: Steve French --- fs/cifs/connect.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f1a7e63ab58f..d49c9e5c33fa 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4144,7 +4144,8 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru if (!tree) return -ENOMEM; - if (!tcon->dfs_path) { + /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ + if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) { if (tcon->ipc) { scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); @@ -4154,9 +4155,6 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru goto out; } - rc = dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl); - if (rc) - goto out; isroot = ref.server_type == DFS_TYPE_ROOT; free_dfs_info_param(&ref); From 63f94e946fafcfc5080b4a4aec9770158268e4ee Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 13 Jul 2021 19:40:33 -0500 Subject: [PATCH 0507/1469] cifs: fix missing null session check in mount Although it is unlikely to be have ended up with a null session pointer calling cifs_try_adding_channels in cifs_mount. Coverity correctly notes that we are already checking for it earlier (when we return from do_dfs_failover), so at a minimum to clarify the code we should make sure we also check for it when we exit the loop so we don't end up calling cifs_try_adding_channels or mount_setup_tlink with a null ses pointer. Addresses-Coverity: 1505608 ("Derefernce after null check") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/connect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d49c9e5c33fa..a1e870232114 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3508,7 +3508,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) rc = -ELOOP; } while (rc == -EREMOTE); - if (rc || !tcon) + if (rc || !tcon || !ses) goto error; kfree(ref_path); From 16dd9b8c31aee7ae074fa3ee36a797e9ba9f7e4f Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Wed, 14 Jul 2021 23:00:00 -0500 Subject: [PATCH 0508/1469] cifs: added WARN_ON for all the count decrements We have a few ref counters srv_count, ses_count and tc_count which we use for ref counting. Added a WARN_ON during the decrement of each of these counters to make sure that they don't go below their minimum values. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/connect.c | 9 +++++++++ fs/cifs/smb2ops.c | 2 ++ 2 files changed, 11 insertions(+) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a1e870232114..6b6c3e341b42 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1295,6 +1295,9 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) return; } + /* srv_count can never go negative */ + WARN_ON(server->srv_count < 0); + put_net(cifs_net_ns(server)); list_del_init(&server->tcp_ses_list); @@ -1654,6 +1657,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses) } spin_unlock(&cifs_tcp_ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); + spin_lock(&GlobalMid_Lock); if (ses->status == CifsGood) ses->status = CifsExiting; @@ -2021,6 +2027,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) return; } + /* tc_count can never go negative */ + WARN_ON(tcon->tc_count < 0); + if (tcon->use_witness) { int rc; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 232d528df230..ba3c58e1f725 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2910,6 +2910,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, /* ipc tcons are not refcounted */ spin_lock(&cifs_tcp_ses_lock); tcon->tc_count--; + /* tc_count can never go negative */ + WARN_ON(tcon->tc_count < 0); spin_unlock(&cifs_tcp_ses_lock); } kfree(utf16_path); From 4511d7c8f440ab13520601141d67d13cb074620a Mon Sep 17 00:00:00 2001 From: Steve French Date: Wed, 14 Jul 2021 23:32:09 -0500 Subject: [PATCH 0509/1469] SMB3.1.1: fix mount failure to some servers when compression enabled When sending the compression context to some servers, they rejected the SMB3.1.1 negotiate protocol because they expect the compression context to have a data length of a multiple of 8. Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/smb2pdu.h | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 4b27cb9105fd..e9cac7970b66 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -394,6 +394,7 @@ struct smb2_compression_capabilities_context { __u16 Padding; __u32 Flags; __le16 CompressionAlgorithms[3]; + __u16 Pad; /* Some servers require pad to DataLen multiple of 8 */ /* Check if pad needed */ } __packed; From d936eb23874433caa3e3d841cfa16f5434b85dcf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 15 Jul 2021 18:05:31 -0700 Subject: [PATCH 0510/1469] Revert "Makefile: Enable -Wimplicit-fallthrough for Clang" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit b7eb335e26a9c7f258c96b3962c283c379d3ede0. It turns out that the problem with the clang -Wimplicit-fallthrough warning is not about the kernel source code, but about clang itself, and that the warning is unusable until clang fixes its broken ways. In particular, when you enable this warning for clang, you not only get warnings about implicit fallthroughs. You also get this: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] which is completely broken becasue it (a) doesn't even tell you where the problem is (seriously: no line numbers, no filename, no nothing). (b) is fundamentally broken anyway, because there are perfectly valid reasons to have a fallthrough statement even if it turns out that it can perhaps not be reached. In the kernel, an example of that second case is code in the scheduler: switch (state) { case cpuset: if (IS_ENABLED(CONFIG_CPUSETS)) { cpuset_cpus_allowed_fallback(p); state = possible; break; } fallthrough; case possible: where if CONFIG_CPUSETS is enabled you actually never hit the fallthrough case at all. But that in no way makes the fallthrough wrong. So the warning is completely broken, and enabling it for clang is a very bad idea. In the meantime, we can keep the gcc option enabled, and make the gcc build use -Wimplicit-fallthrough=5 which means that we will at least continue to require a proper fallthrough statement, and that gcc won't silently accept the magic comment versions. Because gcc does this all correctly, and while the odd "=5" part is kind of obscure, it's documented in [1]: "-Wimplicit-fallthrough=5 doesn’t recognize any comments as fallthrough comments, only attributes disable the warning" so if clang ever fixes its bad behavior we can try enabling it there again. Link: https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html [1] Cc: Kees Cook Cc: Gustavo A. R. Silva Cc: Nathan Chancellor Cc: Nick Desaulniers Signed-off-by: Linus Torvalds --- Makefile | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index eaa692976851..e97e7548315c 100644 --- a/Makefile +++ b/Makefile @@ -797,6 +797,12 @@ KBUILD_CFLAGS += -Wno-gnu # source of a reference will be _MergedGlobals and not on of the whitelisted names. # See modpost pattern 2 KBUILD_CFLAGS += -mno-global-merge +else + +# Warn about unmarked fall-throughs in switch statement. +# Disabled for clang while comment to attribute conversion happens and +# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,) endif # These warnings generated too much noise in a regular build. @@ -977,9 +983,6 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement -# Warn about unmarked fall-throughs in switch statement. -KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,$(call cc-option,-Wimplicit-fallthrough,)) - # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla From 2f53d15cf95824ed320abed3c33759b8b21aca15 Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Wed, 30 Jun 2021 10:33:36 -0400 Subject: [PATCH 0511/1469] zonefs: remove redundant null bio check bio_alloc() with __GFP_DIRECT_RECLAIM, which is included in GFP_NOFS, never fails, see comments in bio_alloc_bioset(). Signed-off-by: Xianting Tian Signed-off-by: Damien Le Moal --- fs/zonefs/super.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index dbf03635869c..70055d486bf7 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -705,9 +705,6 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) return 0; bio = bio_alloc(GFP_NOFS, nr_pages); - if (!bio) - return -ENOMEM; - bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = zi->i_zsector; bio->bi_write_hint = iocb->ki_hint; From cdc3363065aba2711e51019b3d5787f044f8a133 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 15 Jul 2021 21:53:53 -0300 Subject: [PATCH 0512/1469] cifs: do not share tcp sessions of dfs connections Make sure that we do not share tcp sessions of dfs mounts when mounting regular shares that connect to same server. DFS connections rely on a single instance of tcp in order to do failover properly in cifs_reconnect(). Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 3 +++ fs/cifs/connect.c | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index ade7080f7eaa..c0bfc2f01030 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -693,6 +693,9 @@ struct TCP_Server_Info { bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif +#ifdef CONFIG_CIFS_DFS_UPCALL + bool is_dfs_conn; /* if a dfs connection */ +#endif }; struct cifs_credits { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6b6c3e341b42..1b04d6ec14dd 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1268,6 +1268,16 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { +#ifdef CONFIG_CIFS_DFS_UPCALL + /* + * DFS failover implementation in cifs_reconnect() requires unique tcp sessions for + * DFS connections to do failover properly, so avoid sharing them with regular + * shares or even links that may connect to same server but having completely + * different failover targets. + */ + if (server->is_dfs_conn) + continue; +#endif /* * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). @@ -2968,6 +2978,23 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, } #ifdef CONFIG_CIFS_DFS_UPCALL +static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, + unsigned int *xid, struct TCP_Server_Info **nserver, + struct cifs_ses **nses, struct cifs_tcon **ntcon) +{ + int rc; + + ctx->nosharesock = true; + rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon); + if (*nserver) { + cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__); + spin_lock(&cifs_tcp_ses_lock); + (*nserver)->is_dfs_conn = true; + spin_unlock(&cifs_tcp_ses_lock); + } + return rc; +} + /* * cifs_build_path_to_root returns full path to root when we do not have an * existing connection (tcon) @@ -3163,7 +3190,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ tmp_ctx.prepath); mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon); - rc = mount_get_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); + rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); if (!rc || (*server && *ses)) { /* * We were able to connect to new target server. Update current context with @@ -3462,7 +3489,12 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; } - ctx->nosharesock = true; + mount_put_conns(cifs_sb, xid, server, ses, tcon); + /* + * Ignore error check here because we may failover to other targets from cached a + * referral. + */ + (void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); /* Get path of DFS root */ ref_path = build_unc_path_to_root(ctx, cifs_sb, false); @@ -3491,7 +3523,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) /* Connect to new DFS target only if we were redirected */ if (oldmnt != cifs_sb->ctx->mount_options) { mount_put_conns(cifs_sb, xid, server, ses, tcon); - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); } if (rc && !server && !ses) { /* Failed to connect. Try to connect to other targets in the referral. */ From fa5239f2af983ffdf08395a542a7d6356b6222c5 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Thu, 15 Jul 2021 15:05:37 -0400 Subject: [PATCH 0513/1469] drm/amdgpu: workaround failed COW checks for Thunk VMAs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KFD Thunk maps invisible VRAM BOs with PROT_NONE, MAP_PRIVATE. is_cow_mapping returns true for these mappings, which causes mmap to fail in ttm_bo_mmap_obj. As a workaround, clear VM_MAYWRITE for PROT_NONE-COW mappings. This should prevent the mapping from ever becoming writable and makes is_cow_mapping(vm_flags) false. Fixes: f91142c62161 ("drm/ttm: nuke VM_MIXEDMAP on BO mappings v3") Suggested-by: Daniel Vetter Tested-by: Felix Kuehling Signed-off-by: Felix Kuehling Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210715190537.585456-1-Felix.Kuehling@amd.com Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index b3404c43a911..9f952b7fc197 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -255,6 +255,15 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) return -EPERM; + /* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings + * for debugger access to invisible VRAM. Should have used MAP_SHARED + * instead. Clearing VM_MAYWRITE prevents the mapping from ever + * becoming writable and makes is_cow_mapping(vm_flags) false. + */ + if (is_cow_mapping(vma->vm_flags) && + !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))) + vma->vm_flags &= ~VM_MAYWRITE; + return drm_gem_ttm_mmap(obj, vma); } From 40ac971eab89330d6153e7721e88acd2d98833f9 Mon Sep 17 00:00:00 2001 From: Roman Skakun Date: Fri, 16 Jul 2021 11:39:34 +0300 Subject: [PATCH 0514/1469] dma-mapping: handle vmalloc addresses in dma_common_{mmap,get_sgtable} xen-swiotlb can use vmalloc backed addresses for dma coherent allocations and uses the common helpers. Properly handle them to unbreak Xen on ARM platforms. Fixes: 1b65c4e5a9af ("swiotlb-xen: use xen_alloc/free_coherent_pages") Signed-off-by: Roman Skakun Reviewed-by: Andrii Anisov [hch: split the patch, renamed the helpers] Signed-off-by: Christoph Hellwig --- kernel/dma/ops_helpers.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c index 910ae69cae77..af4a6ef48ce0 100644 --- a/kernel/dma/ops_helpers.c +++ b/kernel/dma/ops_helpers.c @@ -5,6 +5,13 @@ */ #include +static struct page *dma_common_vaddr_to_page(void *cpu_addr) +{ + if (is_vmalloc_addr(cpu_addr)) + return vmalloc_to_page(cpu_addr); + return virt_to_page(cpu_addr); +} + /* * Create scatter-list for the already allocated DMA buffer. */ @@ -12,7 +19,7 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct page *page = virt_to_page(cpu_addr); + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret; ret = sg_alloc_table(sgt, 1, GFP_KERNEL); @@ -32,6 +39,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret = -ENXIO; vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); @@ -43,7 +51,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return -ENXIO; return remap_pfn_range(vma, vma->vm_start, - page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff, + page_to_pfn(page) + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); #else return -ENXIO; From 2acf15b94d5b8ea8392c4b6753a6ffac3135cd78 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 2 Jul 2021 12:07:43 +0800 Subject: [PATCH 0515/1469] reiserfs: add check for root_inode in reiserfs_fill_super Our syzcaller report a NULL pointer dereference: BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 116e95067 P4D 116e95067 PUD 1080b5067 PMD 0 Oops: 0010 [#1] SMP KASAN CPU: 7 PID: 592 Comm: a.out Not tainted 5.13.0-next-20210629-dirty #67 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-p4 RIP: 0010:0x0 Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6. RSP: 0018:ffff888114e779b8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 1ffff110229cef39 RCX: ffffffffaa67e1aa RDX: 0000000000000000 RSI: ffff88810a58ee00 RDI: ffff8881233180b0 RBP: ffffffffac38e9c0 R08: ffffffffaa67e17e R09: 0000000000000001 R10: ffffffffb91c5557 R11: fffffbfff7238aaa R12: ffff88810a58ee00 R13: ffff888114e77aa0 R14: 0000000000000000 R15: ffff8881233180b0 FS: 00007f946163c480(0000) GS:ffff88839f1c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 00000001099c1000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __lookup_slow+0x116/0x2d0 ? page_put_link+0x120/0x120 ? __d_lookup+0xfc/0x320 ? d_lookup+0x49/0x90 lookup_one_len+0x13c/0x170 ? __lookup_slow+0x2d0/0x2d0 ? reiserfs_schedule_old_flush+0x31/0x130 reiserfs_lookup_privroot+0x64/0x150 reiserfs_fill_super+0x158c/0x1b90 ? finish_unfinished+0xb10/0xb10 ? bprintf+0xe0/0xe0 ? __mutex_lock_slowpath+0x30/0x30 ? __kasan_check_write+0x20/0x30 ? up_write+0x51/0xb0 ? set_blocksize+0x9f/0x1f0 mount_bdev+0x27c/0x2d0 ? finish_unfinished+0xb10/0xb10 ? reiserfs_kill_sb+0x120/0x120 get_super_block+0x19/0x30 legacy_get_tree+0x76/0xf0 vfs_get_tree+0x49/0x160 ? capable+0x1d/0x30 path_mount+0xacc/0x1380 ? putname+0x97/0xd0 ? finish_automount+0x450/0x450 ? kmem_cache_free+0xf8/0x5a0 ? putname+0x97/0xd0 do_mount+0xe2/0x110 ? path_mount+0x1380/0x1380 ? copy_mount_options+0x69/0x140 __x64_sys_mount+0xf0/0x190 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae This is because 'root_inode' is initialized with wrong mode, and it's i_op is set to 'reiserfs_special_inode_operations'. Thus add check for 'root_inode' to fix the problem. Link: https://lore.kernel.org/r/20210702040743.1918552-1-yukuai3@huawei.com Signed-off-by: Yu Kuai Signed-off-by: Jan Kara --- fs/reiserfs/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 3ffafc73acf0..58481f8d63d5 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2082,6 +2082,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) unlock_new_inode(root_inode); } + if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) || + !root_inode->i_size) { + SWARN(silent, s, "", "corrupt root inode, run fsck"); + iput(root_inode); + errval = -EUCLEAN; + goto error; + } + s->s_root = d_make_root(root_inode); if (!s->s_root) goto error; From 728d392f8a799f037812d0f2b254fb3b5e115fcf Mon Sep 17 00:00:00 2001 From: Javier Pello Date: Wed, 14 Jul 2021 18:54:48 +0200 Subject: [PATCH 0516/1469] fs/ext2: Avoid page_address on pages returned by ext2_get_page Commit 782b76d7abdf02b12c46ed6f1e9bf715569027f7 ("fs/ext2: Replace kmap() with kmap_local_page()") replaced the kmap/kunmap calls in ext2_get_page/ext2_put_page with kmap_local_page/kunmap_local for efficiency reasons. As a necessary side change, the commit also made ext2_get_page (and ext2_find_entry and ext2_dotdot) return the mapping address along with the page itself, as it is required for kunmap_local, and converted uses of page_address on such pages to use the newly returned address instead. However, uses of page_address on such pages were missed in ext2_check_page and ext2_delete_entry, which triggers oopses if kmap_local_page happens to return an address from high memory. Fix this now by converting the remaining uses of page_address to use the right address, as returned by kmap_local_page. Link: https://lore.kernel.org/r/20210714185448.8707ac239e9f12b3a7f5b9f9@urjc.es Reviewed-by: Ira Weiny Signed-off-by: Javier Pello Fixes: 782b76d7abdf ("fs/ext2: Replace kmap() with kmap_local_page()") Signed-off-by: Jan Kara --- fs/ext2/dir.c | 12 ++++++------ fs/ext2/ext2.h | 3 ++- fs/ext2/namei.c | 4 ++-- 3 files changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 14292dba3a12..2c2f179b6977 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -106,12 +106,11 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) return err; } -static bool ext2_check_page(struct page *page, int quiet) +static bool ext2_check_page(struct page *page, int quiet, char *kaddr) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; unsigned chunk_size = ext2_chunk_size(dir); - char *kaddr = page_address(page); u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count); unsigned offs, rec_len; unsigned limit = PAGE_SIZE; @@ -205,7 +204,8 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n, if (!IS_ERR(page)) { *page_addr = kmap_local_page(page); if (unlikely(!PageChecked(page))) { - if (PageError(page) || !ext2_check_page(page, quiet)) + if (PageError(page) || !ext2_check_page(page, quiet, + *page_addr)) goto fail; } } @@ -584,10 +584,10 @@ out_unlock: * ext2_delete_entry deletes a directory entry by merging it with the * previous entry. Page is up-to-date. */ -int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page ) +int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page, + char *kaddr) { struct inode *inode = page->mapping->host; - char *kaddr = page_address(page); unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1); unsigned to = ((char *)dir - kaddr) + ext2_rec_len_from_disk(dir->rec_len); @@ -607,7 +607,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page ) de = ext2_next_entry(de); } if (pde) - from = (char*)pde - (char*)page_address(page); + from = (char *)pde - kaddr; pos = page_offset(page) + from; lock_page(page); err = ext2_prepare_chunk(page, pos, to - from); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index b0a694820cb7..e512630cb63e 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -740,7 +740,8 @@ extern int ext2_inode_by_name(struct inode *dir, extern int ext2_make_empty(struct inode *, struct inode *); extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *, struct page **, void **res_page_addr); -extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *); +extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page, + char *kaddr); extern int ext2_empty_dir (struct inode *); extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa); extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *, diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 1f69b81655b6..5f6b7560eb3f 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -293,7 +293,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry) goto out; } - err = ext2_delete_entry (de, page); + err = ext2_delete_entry (de, page, page_addr); ext2_put_page(page, page_addr); if (err) goto out; @@ -397,7 +397,7 @@ static int ext2_rename (struct user_namespace * mnt_userns, old_inode->i_ctime = current_time(old_inode); mark_inode_dirty(old_inode); - ext2_delete_entry(old_de, old_page); + ext2_delete_entry(old_de, old_page, old_page_addr); if (dir_de) { if (old_dir != new_dir) From 13d257503c0930010ef9eed78b689cec417ab741 Mon Sep 17 00:00:00 2001 From: Shreyansh Chouhan Date: Fri, 9 Jul 2021 20:59:29 +0530 Subject: [PATCH 0517/1469] reiserfs: check directory items on read from disk While verifying the leaf item that we read from the disk, reiserfs doesn't check the directory items, this could cause a crash when we read a directory item from the disk that has an invalid deh_location. This patch adds a check to the directory items read from the disk that does a bounds check on deh_location for the directory entries. Any directory entry header with a directory entry offset greater than the item length is considered invalid. Link: https://lore.kernel.org/r/20210709152929.766363-1-chouhan.shreyansh630@gmail.com Reported-by: syzbot+c31a48e6702ccb3d64c9@syzkaller.appspotmail.com Signed-off-by: Shreyansh Chouhan Signed-off-by: Jan Kara --- fs/reiserfs/stree.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 476a7ff49482..ef42729216d1 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -387,6 +387,24 @@ void pathrelse(struct treepath *search_path) search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET; } +static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih) +{ + struct reiserfs_de_head *deh; + int i; + + deh = B_I_DEH(bh, ih); + for (i = 0; i < ih_entry_count(ih); i++) { + if (deh_location(&deh[i]) > ih_item_len(ih)) { + reiserfs_warning(NULL, "reiserfs-5094", + "directory entry location seems wrong %h", + &deh[i]); + return 0; + } + } + + return 1; +} + static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) { struct block_head *blkh; @@ -454,11 +472,14 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) "(second one): %h", ih); return 0; } - if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) { - reiserfs_warning(NULL, "reiserfs-5093", - "item entry count seems wrong %h", - ih); - return 0; + if (is_direntry_le_ih(ih)) { + if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) { + reiserfs_warning(NULL, "reiserfs-5093", + "item entry count seems wrong %h", + ih); + return 0; + } + return has_valid_deh_location(bh, ih); } prev_location = ih_location(ih); } From f99986c0fcad8e1d7d842e9a636f55bcc6748da5 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 16 Jul 2021 11:57:35 +0100 Subject: [PATCH 0518/1469] ASoC: codecs: wcd938x: setup irq during component bind SoundWire registers are only accessable after sdw components are succesfully binded. Setup irqs at that point instead of doing at probe. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210716105735.6073-1-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/codecs/wcd938x.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index 78b76eceff8f..2fcc97370be2 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -3317,13 +3317,6 @@ static int wcd938x_soc_codec_probe(struct snd_soc_component *component) (WCD938X_DIGITAL_INTR_LEVEL_0 + i), 0); } - ret = wcd938x_irq_init(wcd938x, component->dev); - if (ret) { - dev_err(component->dev, "%s: IRQ init failed: %d\n", - __func__, ret); - return ret; - } - wcd938x->hphr_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip, WCD938X_IRQ_HPHR_PDM_WD_INT); wcd938x->hphl_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip, @@ -3553,7 +3546,6 @@ static int wcd938x_bind(struct device *dev) } wcd938x->sdw_priv[AIF1_PB] = dev_get_drvdata(wcd938x->rxdev); wcd938x->sdw_priv[AIF1_PB]->wcd938x = wcd938x; - wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq; wcd938x->txdev = wcd938x_sdw_device_get(wcd938x->txnode); if (!wcd938x->txdev) { @@ -3562,7 +3554,6 @@ static int wcd938x_bind(struct device *dev) } wcd938x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd938x->txdev); wcd938x->sdw_priv[AIF1_CAP]->wcd938x = wcd938x; - wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq; wcd938x->tx_sdw_dev = dev_to_sdw_dev(wcd938x->txdev); if (!wcd938x->tx_sdw_dev) { dev_err(dev, "could not get txslave with matching of dev\n"); @@ -3595,6 +3586,15 @@ static int wcd938x_bind(struct device *dev) return PTR_ERR(wcd938x->regmap); } + ret = wcd938x_irq_init(wcd938x, dev); + if (ret) { + dev_err(dev, "%s: IRQ init failed: %d\n", __func__, ret); + return ret; + } + + wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq; + wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq; + ret = wcd938x_set_micbias_data(wcd938x); if (ret < 0) { dev_err(dev, "%s: bad micbias pdata\n", __func__); From 59dd33f82dc0975c55d3d46801e7ca45532d7673 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Fri, 16 Jul 2021 18:00:12 +0530 Subject: [PATCH 0519/1469] ASoC: soc-pcm: add a flag to reverse the stop sequence On stream stop, currently CPU DAI stop sequence invoked first followed by DMA. For Few platforms, it is required to stop the DMA first before stopping CPU DAI. Introduced new flag in dai_link structure for reordering stop sequence. Based on flag check, ASoC core will re-order the stop sequence. Fixes: 4378f1fbe92405 ("ASoC: soc-pcm: Use different sequence for start/stop trigger") Signed-off-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20210716123015.15697-1-vijendar.mukunda@amd.com Signed-off-by: Mark Brown --- include/sound/soc.h | 6 ++++++ sound/soc/soc-pcm.c | 22 ++++++++++++++++------ 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/include/sound/soc.h b/include/sound/soc.h index 675849d07284..8e6dd8a257c5 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -712,6 +712,12 @@ struct snd_soc_dai_link { /* Do not create a PCM for this DAI link (Backend link) */ unsigned int ignore:1; + /* This flag will reorder stop sequence. By enabling this flag + * DMA controller stop sequence will be invoked first followed by + * CPU DAI driver stop sequence + */ + unsigned int stop_dma_first:1; + #ifdef CONFIG_SND_SOC_TOPOLOGY struct snd_soc_dobj dobj; /* For topology */ #endif diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 46513bb97904..d1c570ca21ea 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1015,6 +1015,7 @@ out: static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { + struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); int ret = -EINVAL, _ret = 0; int rollback = 0; @@ -1055,14 +1056,23 @@ start_err: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback); - if (ret < 0) - break; + if (rtd->dai_link->stop_dma_first) { + ret = snd_soc_pcm_component_trigger(substream, cmd, rollback); + if (ret < 0) + break; - ret = snd_soc_pcm_component_trigger(substream, cmd, rollback); - if (ret < 0) - break; + ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback); + if (ret < 0) + break; + } else { + ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback); + if (ret < 0) + break; + ret = snd_soc_pcm_component_trigger(substream, cmd, rollback); + if (ret < 0) + break; + } ret = snd_soc_link_trigger(substream, cmd, rollback); break; } From 7883490cba002121a5870e786a1dc0acce5e1caf Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Fri, 16 Jul 2021 18:00:13 +0530 Subject: [PATCH 0520/1469] ASoC: amd: reverse stop sequence for stoneyridge platform For Stoneyridge platform, it is required to invoke DMA driver stop first rather than invoking DWC I2S controller stop. Enable dai_link structure stop_dma_fist flag to reverse the stop sequence. Signed-off-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20210716123015.15697-2-vijendar.mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp-da7219-max98357a.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c index 84e3906abd4f..9449fb40a956 100644 --- a/sound/soc/amd/acp-da7219-max98357a.c +++ b/sound/soc/amd/acp-da7219-max98357a.c @@ -576,6 +576,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = { | SND_SOC_DAIFMT_CBM_CFM, .init = cz_rt5682_init, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_rt5682_play_ops, SND_SOC_DAILINK_REG(designware1, rt5682, platform), }, @@ -585,6 +586,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_rt5682_cap_ops, SND_SOC_DAILINK_REG(designware2, rt5682, platform), }, @@ -594,6 +596,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_rt5682_max_play_ops, SND_SOC_DAILINK_REG(designware3, mx, platform), }, @@ -604,6 +607,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_rt5682_dmic0_cap_ops, SND_SOC_DAILINK_REG(designware3, adau, platform), }, @@ -614,6 +618,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_rt5682_dmic1_cap_ops, SND_SOC_DAILINK_REG(designware2, adau, platform), }, From 6a503e1c455316fd0bfd8188c0a62cce7c5525ca Mon Sep 17 00:00:00 2001 From: Oder Chiou Date: Fri, 16 Jul 2021 16:58:53 +0800 Subject: [PATCH 0521/1469] ASoC: rt5682: Fix the issue of garbled recording after powerd_dbus_suspend While using the DMIC recording, the garbled data will be captured by the DMIC. It is caused by the critical power of PLL closed in the jack detect function. Signed-off-by: Oder Chiou Link: https://lore.kernel.org/r/20210716085853.20170-1-oder_chiou@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5682.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index e4c91571abae..abcd6f483788 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -973,10 +973,14 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) rt5682_enable_push_button_irq(component, false); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW); - if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS")) + if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS") && + !snd_soc_dapm_get_pin_status(dapm, "PLL1") && + !snd_soc_dapm_get_pin_status(dapm, "PLL2B")) snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, RT5682_PWR_MB, 0); - if (!snd_soc_dapm_get_pin_status(dapm, "Vref2")) + if (!snd_soc_dapm_get_pin_status(dapm, "Vref2") && + !snd_soc_dapm_get_pin_status(dapm, "PLL1") && + !snd_soc_dapm_get_pin_status(dapm, "PLL2B")) snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, RT5682_PWR_VREF2, 0); snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3, From 59089a189e3adde4cf85f2ce479738d1ae4c514d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 29 Jun 2021 09:39:15 +0000 Subject: [PATCH 0522/1469] bpf: Remove superfluous aux sanitation on subprog rejection Follow-up to fe9a5ca7e370 ("bpf: Do not mark insn as seen under speculative path verification"). The sanitize_insn_aux_data() helper does not serve a particular purpose in today's code. The original intention for the helper was that if function-by-function verification fails, a given program would be cleared from temporary insn_aux_data[], and then its verification would be re-attempted in the context of the main program a second time. However, a failure in do_check_subprogs() will skip do_check_main() and propagate the error to the user instead, thus such situation can never occur. Given its interaction is not compatible to the Spectre v1 mitigation (due to comparing aux->seen with env->pass_cnt), just remove sanitize_insn_aux_data() to avoid future bugs in this area. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9de3c9c3267c..8a7a28b4cfb9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12752,37 +12752,6 @@ static void free_states(struct bpf_verifier_env *env) } } -/* The verifier is using insn_aux_data[] to store temporary data during - * verification and to store information for passes that run after the - * verification like dead code sanitization. do_check_common() for subprogram N - * may analyze many other subprograms. sanitize_insn_aux_data() clears all - * temporary data after do_check_common() finds that subprogram N cannot be - * verified independently. pass_cnt counts the number of times - * do_check_common() was run and insn->aux->seen tells the pass number - * insn_aux_data was touched. These variables are compared to clear temporary - * data from failed pass. For testing and experiments do_check_common() can be - * run multiple times even when prior attempt to verify is unsuccessful. - * - * Note that special handling is needed on !env->bypass_spec_v1 if this is - * ever called outside of error path with subsequent program rejection. - */ -static void sanitize_insn_aux_data(struct bpf_verifier_env *env) -{ - struct bpf_insn *insn = env->prog->insnsi; - struct bpf_insn_aux_data *aux; - int i, class; - - for (i = 0; i < env->prog->len; i++) { - class = BPF_CLASS(insn[i].code); - if (class != BPF_LDX && class != BPF_STX) - continue; - aux = &env->insn_aux_data[i]; - if (aux->seen != env->pass_cnt) - continue; - memset(aux, 0, offsetof(typeof(*aux), orig_idx)); - } -} - static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); @@ -12859,9 +12828,6 @@ out: if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); - if (ret) - /* clean aux data in case subprog was rejected */ - sanitize_insn_aux_data(env); return ret; } From e042aa532c84d18ff13291d00620502ce7a38dda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 16 Jul 2021 09:18:21 +0000 Subject: [PATCH 0523/1469] bpf: Fix pointer arithmetic mask tightening under state pruning In 7fedb63a8307 ("bpf: Tighten speculative pointer arithmetic mask") we narrowed the offset mask for unprivileged pointer arithmetic in order to mitigate a corner case where in the speculative domain it is possible to advance, for example, the map value pointer by up to value_size-1 out-of- bounds in order to leak kernel memory via side-channel to user space. The verifier's state pruning for scalars leaves one corner case open where in the first verification path R_x holds an unknown scalar with an aux->alu_limit of e.g. 7, and in a second verification path that same register R_x, here denoted as R_x', holds an unknown scalar which has tighter bounds and would thus satisfy range_within(R_x, R_x') as well as tnum_in(R_x, R_x') for state pruning, yielding an aux->alu_limit of 3: Given the second path fits the register constraints for pruning, the final generated mask from aux->alu_limit will remain at 7. While technically not wrong for the non-speculative domain, it would however be possible to craft similar cases where the mask would be too wide as in 7fedb63a8307. One way to fix it is to detect the presence of unknown scalar map pointer arithmetic and force a deeper search on unknown scalars to ensure that we do not run into a masking mismatch. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 27 +++++++++++++++++---------- 2 files changed, 18 insertions(+), 10 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..7ba7e800d472 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -414,6 +414,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; bool allow_ptr_to_map_access; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8a7a28b4cfb9..657062cb4d85 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6561,6 +6561,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + /* Limit pruning on unknown scalars to enable deep search for + * potential masking differences from other program paths. + */ + if (!off_is_imm) + env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); @@ -9936,8 +9942,8 @@ next: } /* Returns true if (rold safe implies rcur safe) */ -static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct bpf_id_pair *idmap) +static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, + struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { bool equal; @@ -9963,6 +9969,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; switch (rold->type) { case SCALAR_VALUE: + if (env->explore_alu_limits) + return false; if (rcur->type == SCALAR_VALUE) { if (!rold->precise && !rcur->precise) return true; @@ -10053,9 +10061,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } -static bool stacksafe(struct bpf_func_state *old, - struct bpf_func_state *cur, - struct bpf_id_pair *idmap) +static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, + struct bpf_func_state *cur, struct bpf_id_pair *idmap) { int i, spi; @@ -10100,9 +10107,8 @@ static bool stacksafe(struct bpf_func_state *old, continue; if (old->stack[spi].slot_type[0] != STACK_SPILL) continue; - if (!regsafe(&old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, - idmap)) + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -10159,10 +10165,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + if (!regsafe(env, &old->regs[i], &cur->regs[i], + env->idmap_scratch)) return false; - if (!stacksafe(old, cur, env->idmap_scratch)) + if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; if (!refsafe(old, cur)) From a6c39de76d709f30982d4b80a9b9537e1d388858 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 16 Jul 2021 13:15:33 +0000 Subject: [PATCH 0524/1469] bpf, selftests: Add test cases for pointer alu from multiple paths Add several test cases for checking update_alu_sanitation_state() under multiple paths: # ./test_verifier [...] #1061/u map access: known scalar += value_ptr unknown vs const OK #1061/p map access: known scalar += value_ptr unknown vs const OK #1062/u map access: known scalar += value_ptr const vs unknown OK #1062/p map access: known scalar += value_ptr const vs unknown OK #1063/u map access: known scalar += value_ptr const vs const (ne) OK #1063/p map access: known scalar += value_ptr const vs const (ne) OK #1064/u map access: known scalar += value_ptr const vs const (eq) OK #1064/p map access: known scalar += value_ptr const vs const (eq) OK #1065/u map access: known scalar += value_ptr unknown vs unknown (eq) OK #1065/p map access: known scalar += value_ptr unknown vs unknown (eq) OK #1066/u map access: known scalar += value_ptr unknown vs unknown (lt) OK #1066/p map access: known scalar += value_ptr unknown vs unknown (lt) OK #1067/u map access: known scalar += value_ptr unknown vs unknown (gt) OK #1067/p map access: known scalar += value_ptr unknown vs unknown (gt) OK [...] Summary: 1762 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov --- .../selftests/bpf/verifier/value_ptr_arith.c | 229 ++++++++++++++++++ 1 file changed, 229 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index a3e593ddfafc..2debba4e8a3a 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1,3 +1,232 @@ +{ + "map access: known scalar += value_ptr unknown vs const", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs unknown", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (ne)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (lt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (gt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, { "map access: known scalar += value_ptr from different maps", .insns = { From 0ccfd1ba84a4503b509250941af149e9ebd605ca Mon Sep 17 00:00:00 2001 From: Yoshitaka Ikeda Date: Fri, 16 Jul 2021 14:33:12 +0000 Subject: [PATCH 0525/1469] spi: spi-cadence-quadspi: Revert "Fix division by zero warning" Revert to change to a better code. This reverts commit 55cef88bbf12f3bfbe5c2379a8868a034707e755. Signed-off-by: Yoshitaka Ikeda Link: https://lore.kernel.org/r/bd30bdb4-07c4-f713-5648-01c898d51f1b@nskint.co.jp Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 13d1f0ce618e..7a00346ff9b9 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -307,13 +307,11 @@ static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata) static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) { - unsigned int dummy_clk = 0; + unsigned int dummy_clk; - if (op->dummy.buswidth && op->dummy.nbytes) { - dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); - if (dtr) - dummy_clk /= 2; - } + dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); + if (dtr) + dummy_clk /= 2; return dummy_clk; } From 0e85ee897858b1c7a5de53f496d016899d9639c5 Mon Sep 17 00:00:00 2001 From: Yoshitaka Ikeda Date: Fri, 16 Jul 2021 14:35:13 +0000 Subject: [PATCH 0526/1469] spi: spi-cadence-quadspi: Fix division by zero warning Fix below division by zero warning: - The reason for dividing by zero is because the dummy bus width is zero, but if the dummy n bytes is zero, it indicates that there is no data transfer, so we can just return zero without doing any calculations. [ 0.795337] Division by zero in kernel. : [ 0.834051] [<807fd40c>] (__div0) from [<804e1acc>] (Ldiv0+0x8/0x10) [ 0.839097] [<805f0710>] (cqspi_exec_mem_op) from [<805edb4c>] (spi_mem_exec_op+0x3b0/0x3f8) Fixes: 7512eaf54190 ("spi: cadence-quadspi: Fix dummy cycle calculation when buswidth > 1") Signed-off-by: Yoshitaka Ikeda Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/92eea403-9b21-2488-9cc1-664bee760c5e@nskint.co.jp Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 7a00346ff9b9..d62d69dd72b9 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -309,6 +309,9 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) { unsigned int dummy_clk; + if (!op->dummy.nbytes) + return 0; + dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); if (dtr) dummy_clk /= 2; From 674a9f1f6815849bfb5bf385e7da8fc198aaaba9 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Thu, 8 Jul 2021 11:46:54 +0200 Subject: [PATCH 0527/1469] efi/tpm: Differentiate missing and invalid final event log table. Missing TPM final event log table is not a firmware bug. Clearly if providing event log in the old format makes the final event log invalid it should not be provided at least in that case. Fixes: b4f1874c6216 ("tpm: check event log version before reading final events") Signed-off-by: Michal Suchanek Reviewed-by: Jarkko Sakkinen Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/tpm.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index c1955d320fec..8f665678e9e3 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -62,9 +62,11 @@ int __init efi_tpm_eventlog_init(void) tbl_size = sizeof(*log_tbl) + log_tbl->size; memblock_reserve(efi.tpm_log, tbl_size); - if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR || - log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) { - pr_warn(FW_BUG "TPM Final Events table missing or invalid\n"); + if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR) { + pr_info("TPM Final Events table not present\n"); + goto out; + } else if (log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) { + pr_warn(FW_BUG "TPM Final Events table invalid\n"); goto out; } From 2bab693a608bdf614b9fcd44083c5100f34b9f77 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 13 Jul 2021 19:43:26 +0100 Subject: [PATCH 0528/1469] firmware/efi: Tell memblock about EFI iomem reservations kexec_load_file() relies on the memblock infrastructure to avoid stamping over regions of memory that are essential to the survival of the system. However, nobody seems to agree how to flag these regions as reserved, and (for example) EFI only publishes its reservations in /proc/iomem for the benefit of the traditional, userspace based kexec tool. On arm64 platforms with GICv3, this can result in the payload being placed at the location of the LPI tables. Shock, horror! Let's augment the EFI reservation code with a memblock_reserve() call, protecting our dear tables from the secondary kernel invasion. Reported-by: Moritz Fischer Tested-by: Moritz Fischer Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Cc: Ard Biesheuvel Cc: James Morse Cc: Catalin Marinas Cc: Will Deacon Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/efi.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4b7ee3fa9224..847f33ffc4ae 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -896,6 +896,7 @@ static int __init efi_memreserve_map_root(void) static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size) { struct resource *res, *parent; + int ret; res = kzalloc(sizeof(struct resource), GFP_ATOMIC); if (!res) @@ -908,7 +909,17 @@ static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size) /* we expect a conflict with a 'System RAM' region */ parent = request_resource_conflict(&iomem_resource, res); - return parent ? request_resource(parent, res) : 0; + ret = parent ? request_resource(parent, res) : 0; + + /* + * Given that efi_mem_reserve_iomem() can be called at any + * time, only call memblock_reserve() if the architecture + * keeps the infrastructure around. + */ + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK) && !ret) + memblock_reserve(addr, size); + + return ret; } int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) From 947228cb9f1a2c69a5da5279c48f02bb4f49ce32 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 2 Jul 2021 12:10:44 -0700 Subject: [PATCH 0529/1469] efi/libstub: Fix the efi_load_initrd function description The soft_limit and hard_limit in the function efi_load_initrd describes the preferred and max address of initrd loading location respectively. However, the description wrongly describes it as the size of the allocated memory. Fix the function description. Signed-off-by: Atish Patra Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/efi-stub-helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index aa8da0a49829..ae87dded989d 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -630,8 +630,8 @@ efi_status_t efi_load_initrd_cmdline(efi_loaded_image_t *image, * @image: EFI loaded image protocol * @load_addr: pointer to loaded initrd * @load_size: size of loaded initrd - * @soft_limit: preferred size of allocated memory for loading the initrd - * @hard_limit: minimum size of allocated memory + * @soft_limit: preferred address for loading the initrd + * @hard_limit: upper limit address for loading the initrd * * Return: status code */ From 9d7a6c95f62bc335b62aaf9d50590122bd03a796 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 5 Jul 2021 10:44:52 +0200 Subject: [PATCH 0530/1469] perf: Fix required permissions if sigtrap is requested If perf_event_open() is called with another task as target and perf_event_attr::sigtrap is set, and the target task's user does not match the calling user, also require the CAP_KILL capability or PTRACE_MODE_ATTACH permissions. Otherwise, with the CAP_PERFMON capability alone it would be possible for a user to send SIGTRAP signals via perf events to another user's tasks. This could potentially result in those tasks being terminated if they cannot handle SIGTRAP signals. Note: The check complements the existing capability check, but is not supposed to supersede the ptrace_may_access() check. At a high level we now have: capable of CAP_PERFMON and (CAP_KILL if sigtrap) OR ptrace_may_access(...) // also checks for same thread-group and uid Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Dmitry Vyukov Cc: # 5.13+ Link: https://lore.kernel.org/r/20210705084453.2151729-1-elver@google.com --- kernel/events/core.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 464917096e73..c13730b7ac01 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -12158,10 +12158,33 @@ SYSCALL_DEFINE5(perf_event_open, } if (task) { + unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS; + bool is_capable; + err = down_read_interruptible(&task->signal->exec_update_lock); if (err) goto err_file; + is_capable = perfmon_capable(); + if (attr.sigtrap) { + /* + * perf_event_attr::sigtrap sends signals to the other + * task. Require the current task to also have + * CAP_KILL. + */ + rcu_read_lock(); + is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL); + rcu_read_unlock(); + + /* + * If the required capabilities aren't available, checks + * for ptrace permissions: upgrade to ATTACH, since + * sending signals can effectively change the target + * task. + */ + ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS; + } + /* * Preserve ptrace permission check for backwards compatibility. * @@ -12171,7 +12194,7 @@ SYSCALL_DEFINE5(perf_event_open, * perf_event_exit_task() that could imply). */ err = -EACCES; - if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) + if (!is_capable && !ptrace_may_access(task, ptrace_mode)) goto err_cred; } From b068fc04de10fff8974f6ef32b861ad134d94ba4 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 5 Jul 2021 10:44:53 +0200 Subject: [PATCH 0531/1469] perf: Refactor permissions check into perf_check_permission() Refactor the permission check in perf_event_open() into a helper perf_check_permission(). This makes the permission check logic more readable (because we no longer have a negated disjunction). Add a comment mentioning the ptrace check also checks the uid. No functional change intended. Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20210705084453.2151729-2-elver@google.com --- kernel/events/core.c | 58 ++++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 26 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index c13730b7ac01..1cb1f9b8392e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11917,6 +11917,37 @@ again: return gctx; } +static bool +perf_check_permission(struct perf_event_attr *attr, struct task_struct *task) +{ + unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS; + bool is_capable = perfmon_capable(); + + if (attr->sigtrap) { + /* + * perf_event_attr::sigtrap sends signals to the other task. + * Require the current task to also have CAP_KILL. + */ + rcu_read_lock(); + is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL); + rcu_read_unlock(); + + /* + * If the required capabilities aren't available, checks for + * ptrace permissions: upgrade to ATTACH, since sending signals + * can effectively change the target task. + */ + ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS; + } + + /* + * Preserve ptrace permission check for backwards compatibility. The + * ptrace check also includes checks that the current task and other + * task have matching uids, and is therefore not done here explicitly. + */ + return is_capable || ptrace_may_access(task, ptrace_mode); +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -12158,43 +12189,18 @@ SYSCALL_DEFINE5(perf_event_open, } if (task) { - unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS; - bool is_capable; - err = down_read_interruptible(&task->signal->exec_update_lock); if (err) goto err_file; - is_capable = perfmon_capable(); - if (attr.sigtrap) { - /* - * perf_event_attr::sigtrap sends signals to the other - * task. Require the current task to also have - * CAP_KILL. - */ - rcu_read_lock(); - is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL); - rcu_read_unlock(); - - /* - * If the required capabilities aren't available, checks - * for ptrace permissions: upgrade to ATTACH, since - * sending signals can effectively change the target - * task. - */ - ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS; - } - /* - * Preserve ptrace permission check for backwards compatibility. - * * We must hold exec_update_lock across this and any potential * perf_install_in_context() call for this new event to * serialize against exec() altering our credentials (and the * perf_event_exit_task() that could imply). */ err = -EACCES; - if (!is_capable && !ptrace_may_access(task, ptrace_mode)) + if (!perf_check_permission(&attr, task)) goto err_cred; } From 937654ce497fb6e977a8c52baee5f7d9616302d9 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:24 +0200 Subject: [PATCH 0532/1469] perf test bpf: Free obj_buf ASan reports some memory leaks when running: # perf test "42: BPF filter" The first of these leaks is caused by obj_buf never being deallocated in __test__bpf. This patch adds the missing free. Signed-off-by: Riccardo Mancini Fixes: ba1fae431e74bb42 ("perf test: Add 'perf test BPF'") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lore.kernel.org/lkml/60f3ca935fe6672e7e866276ce6264c9e26e4c87.1626343282.git.rickyman7@gmail.com [ Added missing stdlib.h include ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 33bda9c26542..dbf5f5215abe 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -276,6 +277,7 @@ static int __test__bpf(int idx) } out: + free(obj_buf); bpf__clear(); return ret; } From 9cb2ff11171264d10be7ea9e31d9ee5d49ba84a5 Mon Sep 17 00:00:00 2001 From: Apurva Nandan Date: Tue, 13 Jul 2021 12:57:41 +0000 Subject: [PATCH 0533/1469] spi: cadence-quadspi: Disable Auto-HW polling cadence-quadspi has a builtin Auto-HW polling funtionality using which it keep tracks of completion of write operations. When Auto-HW polling is enabled, it automatically initiates status register read operation, until the flash clears its busy bit. cadence-quadspi controller doesn't allow an address phase when auto-polling the busy bit on the status register. Unlike SPI NOR flashes, SPI NAND flashes do require the address of status register when polling the busy bit using the read register operation. As Auto-HW polling is enabled by default, cadence-quadspi returns a timeout for every write operation after an indefinite amount of polling on SPI NAND flashes. Disable Auto-HW polling completely as the spi-nor core, spinand core, etc. take care of polling the busy bit on their own. Signed-off-by: Apurva Nandan Link: https://lore.kernel.org/r/20210713125743.1540-2-a-nandan@ti.com Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index d62d69dd72b9..a2de23516553 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -800,19 +800,20 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata, reg = cqspi_calc_rdreg(f_pdata); writel(reg, reg_base + CQSPI_REG_RD_INSTR); - if (f_pdata->dtr) { - /* - * Some flashes like the cypress Semper flash expect a 4-byte - * dummy address with the Read SR command in DTR mode, but this - * controller does not support sending address with the Read SR - * command. So, disable write completion polling on the - * controller's side. spi-nor will take care of polling the - * status register. - */ - reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL); - reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL; - writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL); - } + /* + * SPI NAND flashes require the address of the status register to be + * passed in the Read SR command. Also, some SPI NOR flashes like the + * cypress Semper flash expect a 4-byte dummy address in the Read SR + * command in DTR mode. + * + * But this controller does not support address phase in the Read SR + * command when doing auto-HW polling. So, disable write completion + * polling on the controller's side. spinand and spi-nor will take + * care of polling the status register. + */ + reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL); + reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL; + writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL); reg = readl(reg_base + CQSPI_REG_SIZE); reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK; From 50d8d7e19c4398da74d028f367754e73547b078b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 12:19:36 +0200 Subject: [PATCH 0534/1469] dt-bindings: display: renesas,du: Make resets optional on R-Car H1 The "resets" property is not present on R-Car Gen1 SoCs. Supporting it would require migrating from renesas,cpg-clocks to renesas,cpg-mssr. Reflect this in the DT bindings by removing the global "required: resets". All SoCs that do have "resets" properties already have SoC-specific rules making it required. Fixes: 99d66127fad25ebb ("dt-bindings: display: renesas,du: Convert binding to YAML") Signed-off-by: Geert Uytterhoeven Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/98575791b154d80347d5b78132c1d53f5315ee62.1626257936.git.geert+renesas@glider.be Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/display/renesas,du.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/display/renesas,du.yaml b/Documentation/devicetree/bindings/display/renesas,du.yaml index 5f4345d43020..e3ca5389c17d 100644 --- a/Documentation/devicetree/bindings/display/renesas,du.yaml +++ b/Documentation/devicetree/bindings/display/renesas,du.yaml @@ -92,7 +92,6 @@ required: - reg - clocks - interrupts - - resets - ports allOf: From ea272ce46f3c86d15d9b58bd4d8d44de6cee04b7 Mon Sep 17 00:00:00 2001 From: Veerabadhran Gopalakrishnan Date: Fri, 9 Jul 2021 13:00:11 +0530 Subject: [PATCH 0535/1469] amdgpu/nv.c - Added video codec support for Yellow Carp Added the supported codecs in the video capabilities query. Signed-off-by: Veerabadhran Gopalakrishnan Reviewed-by: James Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nv.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 94a2c0742ee5..04f6cf38c552 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -333,6 +333,19 @@ static const struct amdgpu_video_codecs bg_video_codecs_encode = { .codec_array = NULL, }; +/* Yellow Carp*/ +static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, +}; + +static const struct amdgpu_video_codecs yc_video_codecs_decode = { + .codec_count = ARRAY_SIZE(bg_video_codecs_decode_array), + .codec_array = bg_video_codecs_decode_array, +}; + static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, const struct amdgpu_video_codecs **codecs) { @@ -353,12 +366,17 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: case CHIP_VANGOGH: - case CHIP_YELLOW_CARP: if (encode) *codecs = &nv_video_codecs_encode; else *codecs = &sc_video_codecs_decode; return 0; + case CHIP_YELLOW_CARP: + if (encode) + *codecs = &nv_video_codecs_encode; + else + *codecs = &yc_video_codecs_decode; + return 0; case CHIP_BEIGE_GOBY: if (encode) *codecs = &bg_video_codecs_encode; From 6505d6fcc616472c1b4d6298beacf52673c7b072 Mon Sep 17 00:00:00 2001 From: Veerabadhran Gopalakrishnan Date: Tue, 13 Jul 2021 23:21:43 +0530 Subject: [PATCH 0536/1469] amdgpu/nv.c - Optimize code for video codec support structure Optimized the code for codec info structure initialization Signed-off-by: Veerabadhran Gopalakrishnan Reviewed-by: James Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 7 + drivers/gpu/drm/amd/amdgpu/nv.c | 223 ++++------------------------ drivers/gpu/drm/amd/amdgpu/soc15.c | 176 +++------------------- 3 files changed, 56 insertions(+), 350 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index c0316eaba547..8ac6eb9f1fdb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -619,6 +619,13 @@ struct amdgpu_video_codec_info { u32 max_level; }; +#define codec_info_build(type, width, height, level) \ + .codec_type = type,\ + .max_width = width,\ + .max_height = height,\ + .max_pixels_per_frame = height * width,\ + .max_level = level, + struct amdgpu_video_codecs { const u32 codec_count; const struct amdgpu_video_codec_info *codec_array; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 04f6cf38c552..cf73a6923203 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -64,32 +64,13 @@ #include "smuio_v11_0.h" #include "smuio_v11_0_6.h" -#define codec_info_build(type, width, height, level) \ - .codec_type = type,\ - .max_width = width,\ - .max_height = height,\ - .max_pixels_per_frame = height * width,\ - .max_level = level, - static const struct amd_ip_funcs nv_common_ip_funcs; /* Navi */ static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, }; static const struct amdgpu_video_codecs nv_video_codecs_encode = @@ -101,55 +82,13 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode = /* Navi1x */ static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs nv_video_codecs_decode = @@ -161,62 +100,14 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = /* Sienna Cichlid */ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs sc_video_codecs_decode = @@ -228,80 +119,20 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode = /* SRIOV Sienna Cichlid, not const since data is controlled by host */ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, }; static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 8192 * 4352, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static struct amdgpu_video_codecs sriov_sc_video_codecs_encode = diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index b02436401d46..b7d350be8050 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -88,20 +88,8 @@ /* Vega, Raven, Arcturus */ static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, }; static const struct amdgpu_video_codecs vega_video_codecs_encode = @@ -113,48 +101,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode = /* Vega */ static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, }; static const struct amdgpu_video_codecs vega_video_codecs_decode = @@ -166,55 +118,13 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode = /* Raven */ static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)}, }; static const struct amdgpu_video_codecs rv_video_codecs_decode = @@ -226,55 +136,13 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode = /* Renoir, Arcturus */ static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] = { - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 3, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 5, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 52, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 4, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 186, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, - .max_width = 4096, - .max_height = 4096, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, - { - .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, - .max_width = 8192, - .max_height = 4352, - .max_pixels_per_frame = 4096 * 4096, - .max_level = 0, - }, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs rn_video_codecs_decode = From 4fff6fbca12524358a32e56f125ae738141f62b4 Mon Sep 17 00:00:00 2001 From: Xiaojian Du Date: Wed, 14 Jul 2021 15:07:22 +0800 Subject: [PATCH 0537/1469] drm/amdgpu: update the golden setting for vangogh This patch is to update the golden setting for vangogh. Signed-off-by: Xiaojian Du Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f5e9c022960b..a86a0b347e73 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3379,6 +3379,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1_Vangogh, 0xffffffff, 0x00070103), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQG_CONFIG, 0x000017ff, 0x00001000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00400000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff), From 3e94b5965e624f7e6d8dd18eb8f3bf2bb99ba30d Mon Sep 17 00:00:00 2001 From: Likun Gao Date: Thu, 15 Jul 2021 11:08:48 +0800 Subject: [PATCH 0538/1469] drm/amdgpu: update golden setting for sienna_cichlid Update GFX golden setting for sienna_cichlid. Signed-off-by: Likun Gao Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index a86a0b347e73..f4771f39a280 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3300,6 +3300,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000) }; From cfe4e8f00f8f19ba305800f64962d1949ab5d4ca Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Thu, 15 Jul 2021 14:49:08 +0800 Subject: [PATCH 0539/1469] drm/amdgpu: update gc golden setting for dimgrey_cavefish Update gc_10_3_4 golden setting. Signed-off-by: Tao Zhou Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4771f39a280..a64b2c706090 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3447,6 +3447,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x01030000, 0x01030000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x03a00000, 0x00a00000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020) From bd89c991c6c26fb215c63bd21b6d56e7a4ba2ef6 Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Thu, 15 Jul 2021 14:52:37 +0800 Subject: [PATCH 0540/1469] drm/amd/pm: update DRIVER_IF_VERSION for beige_goby Update the version to 0xD for beige_goby. Signed-off-by: Tao Zhou Reviewed-by: Jack Gui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/smu_v11_0.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index 1962a5877191..f61b5c914a3d 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -34,7 +34,7 @@ #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE #define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03 #define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF -#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0x9 +#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0xD /* MP Apertures */ #define MP0_Public 0x03800000 From 353ca0fa56307bfc821a6fb444099e71899f199d Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Wed, 14 Jul 2021 09:06:52 +0100 Subject: [PATCH 0541/1469] drm/amd/display: Fix 10bit 4K display on CIK GPUs Commit 72a7cf0aec0c ("drm/amd/display: Keep linebuffer pixel depth at 30bpp for DCE-11.0.") doesn't seems to have fixed 10bit 4K rendering over DisplayPort for CIK GPUs. On my machine with a HAWAII GPU I get a broken image that looks like it has an effective resolution of 1920x1080 but scaled up in an irregular way. Reverting the commit or applying this patch fixes the problem on v5.14-rc1. Fixes: 72a7cf0aec0c ("drm/amd/display: Keep linebuffer pixel depth at 30bpp for DCE-11.0.") Acked-by: Mario Kleiner Reviewed-by: Harry Wentland Signed-off-by: Liviu Dudau Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index a6a67244a322..1596f6b7fed7 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1062,7 +1062,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) * so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3 * did not show such problems, so this seems to be the exception. */ - if (plane_state->ctx->dce_version != DCE_VERSION_11_0) + if (plane_state->ctx->dce_version > DCE_VERSION_11_0) pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP; else pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP; From 2cc3aeb5ecccec0d266813172fcd82b4b5fa5803 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Fri, 16 Jul 2021 10:02:18 +0300 Subject: [PATCH 0542/1469] skbuff: Fix a potential race while recycling page_pool packets As Alexander points out, when we are trying to recycle a cloned/expanded SKB we might trigger a race. The recycling code relies on the pp_recycle bit to trigger, which we carry over to cloned SKBs. If that cloned SKB gets expanded or if we get references to the frags, call skb_release_data() and overwrite skb->head, we are creating separate instances accessing the same page frags. Since the skb_release_data() will first try to recycle the frags, there's a potential race between the original and cloned SKB, since both will have the pp_recycle bit set. Fix this by explicitly those SKBs not recyclable. The atomic_sub_return effectively limits us to a single release case, and when we are calling skb_release_data we are also releasing the option to perform the recycling, or releasing the pages from the page pool. Fixes: 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling") Reported-by: Alexander Duyck Suggested-by: Alexander Duyck Reviewed-by: Alexander Duyck Acked-by: Jesper Dangaard Brouer Signed-off-by: Ilias Apalodimas Signed-off-by: David S. Miller --- net/core/skbuff.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f63de967ac25..0fe97d660790 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb->cloned && atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, &shinfo->dataref)) - return; + goto exit; skb_zcopy_clear(skb, true); @@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb) kfree_skb_list(shinfo->frag_list); skb_free_head(skb); +exit: + /* When we clone an SKB we copy the reycling bit. The pp_recycle + * bit is only set on the head though, so in order to avoid races + * while trying to recycle fragments on __skb_frag_unref() we need + * to make one SKB responsible for triggering the recycle path. + * So disable the recycling bit if an SKB is cloned and we have + * additional references to to the fragmented part of the SKB. + * Eventually the last SKB will have the recycling bit set and it's + * dataref set to 0, which will trigger the recycling + */ + skb->pp_recycle = 0; } /* From 11d8d98cbeef1496469b268d79938b05524731e8 Mon Sep 17 00:00:00 2001 From: Eric Woudstra Date: Fri, 16 Jul 2021 17:36:39 +0200 Subject: [PATCH 0543/1469] mt7530 fix mt7530_fdb_write vid missing ivl bit According to reference guides mt7530 (mt7620) and mt7531: NOTE: When IVL is reset, MAC[47:0] and FID[2:0] will be used to read/write the address table. When IVL is set, MAC[47:0] and CVID[11:0] will be used to read/write the address table. Since the function only fills in CVID and no FID, we need to set the IVL bit. The existing code does not set it. This is a fix for the issue I dropped here earlier: http://lists.infradead.org/pipermail/linux-mediatek/2021-June/025697.html With this patch, it is now possible to delete the 'self' fdb entry manually. However, wifi roaming still has the same issue, the entry does not get deleted automatically. Wifi roaming also needs a fix somewhere else to function correctly in combination with vlan. Signed-off-by: Eric Woudstra Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 1 + drivers/net/dsa/mt7530.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 93136f7e69f5..9e4df35f92cc 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -366,6 +366,7 @@ mt7530_fdb_write(struct mt7530_priv *priv, u16 vid, int i; reg[1] |= vid & CVID_MASK; + reg[1] |= ATA2_IVL; reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER; reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP; /* STATIC_ENT indicate that entry is static wouldn't diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 334d610a503d..b19b389ff10a 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -79,6 +79,7 @@ enum mt753x_bpdu_port_fw { #define STATIC_EMP 0 #define STATIC_ENT 3 #define MT7530_ATA2 0x78 +#define ATA2_IVL BIT(15) /* Register for address table write data */ #define MT7530_ATWD 0x7c From 5f291bfd33c8995c69f5a50f21445a4a93584ed2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 11:33:43 +0200 Subject: [PATCH 0544/1469] arm: Typo s/PCI_IXP4XX_LEGACY/IXP4XX_PCI_LEGACY/ Kconfig symbol PCI_IXP4XX_LEGACY does not exist, but IXP4XX_PCI_LEGACY does. Fixes: d5d9f7ac58ea1041 ("ARM/ixp4xx: Make NEED_MACH_IO_H optional") Signed-off-by: Geert Uytterhoeven Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/82ce37c617293521f095a945a255456b9512769c.1626255077.git.geert+renesas@glider.be' Signed-off-by: Arnd Bergmann --- arch/arm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3ea1c417339f..82f908fa5676 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -395,7 +395,7 @@ config ARCH_IXP4XX select IXP4XX_IRQ select IXP4XX_TIMER # With the new PCI driver this is not needed - select NEED_MACH_IO_H if PCI_IXP4XX_LEGACY + select NEED_MACH_IO_H if IXP4XX_PCI_LEGACY select USB_EHCI_BIG_ENDIAN_DESC select USB_EHCI_BIG_ENDIAN_MMIO help From 2096d6feec8359203de406c424242dcb977fe1d1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 14:27:03 +0200 Subject: [PATCH 0545/1469] ARM: configs: Update Integrator defconfig This updates the Integrator defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - Drop the unused Matrox FB drivers that are only used with specific PCI cards. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714122703.212609-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/integrator_defconfig | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index b06e537d5149..4dfe321a79f6 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -57,10 +57,7 @@ CONFIG_DRM=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_MATROX=y -CONFIG_FB_MATROX_MILLENIUM=y -CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_VGA_CONSOLE is not set CONFIG_LOGO=y From 56fa6e8a184489b47525488472e9bdcdcb59cd6f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 11:00:40 +0200 Subject: [PATCH 0546/1469] ARM: configs: Update RealView defconfig This updates the RealView defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - The CONFIG_FB_MODE_HELPERS are not needed when using DRM framebuffer emulation as DRM does. - Drop two unused penguin logos. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714090040.182381-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/realview_defconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig index 483c400dd391..4c01e313099f 100644 --- a/arch/arm/configs/realview_defconfig +++ b/arch/arm/configs/realview_defconfig @@ -64,11 +64,9 @@ CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set CONFIG_SOUND=y CONFIG_SND=y # CONFIG_SND_DRIVERS is not set From 850d8ec92735b3d58b81363c4ae29932a2ebbabb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 10:18:19 +0200 Subject: [PATCH 0547/1469] ARM: configs: Update Versatile defconfig This updates the Versatile defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - The CONFIG_FB_MODE_HELPERS are not needed when using DRM framebuffer emulation as DRM does. - The Acorn fonts are removed, the default framebuffer font works fine. I don't know why this was selected in the first place or how the Kconfig was altered so it was removed. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714081819.139210-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/versatile_defconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig index e7ecfb365e91..b703f4757021 100644 --- a/arch/arm/configs/versatile_defconfig +++ b/arch/arm/configs/versatile_defconfig @@ -60,7 +60,7 @@ CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y CONFIG_SOUND=y @@ -88,8 +88,6 @@ CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_NLS_CODEPAGE_850=m CONFIG_NLS_ISO8859_1=m -CONFIG_FONTS=y -CONFIG_FONT_ACORN_8x8=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y From 49e7757a73d181b35851cb01b5d285888014f8b2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 13 Jul 2021 15:37:08 +0200 Subject: [PATCH 0548/1469] ARM: configs: Update Vexpress defconfig This updates the Versatile Express defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - CONFIG_CMA options were moved around. - CONFIG_MODULES options were moved around. - CONFIG_CRYPTO_HW was moved around. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Acked-by: Sudeep Holla Cc: Kees Cook Cc: Sudeep Holla Link: https://lore.kernel.org/r/20210713133708.94397-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/vexpress_defconfig | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index 4479369540f2..b5e246dd23f4 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -11,9 +11,6 @@ CONFIG_CPUSETS=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_VEXPRESS_DCSCB=y CONFIG_ARCH_VEXPRESS_TC2_PM=y @@ -23,14 +20,17 @@ CONFIG_MCPM=y CONFIG_VMSPLIT_2G=y CONFIG_NR_CPUS=8 CONFIG_ARM_PSCI=y -CONFIG_CMA=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="console=ttyAMA0" CONFIG_CPU_IDLE=y CONFIG_VFP=y CONFIG_NEON=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_CMA=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -43,7 +43,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y @@ -59,7 +58,6 @@ CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y -# CONFIG_SATA_PMP is not set CONFIG_NETDEVICES=y CONFIG_VIRTIO_NET=y CONFIG_SMC91X=y @@ -81,11 +79,9 @@ CONFIG_DRM=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_SII902X=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set CONFIG_SOUND=y CONFIG_SND=y # CONFIG_SND_DRIVERS is not set @@ -136,10 +132,11 @@ CONFIG_ROOT_NFS=y CONFIG_9P_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y +# CONFIG_CRYPTO_HW is not set +CONFIG_DMA_CMA=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set CONFIG_DEBUG_USER=y -# CONFIG_CRYPTO_HW is not set From 042f2e107a2ea34605b3793a88b11761afc8e8e0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 12 Jul 2021 10:55:22 +0200 Subject: [PATCH 0549/1469] ARM: configs: Update u8500_defconfig The platform lost the framebuffer due to a commit solving a circular dependency in v5.14-rc1, so add it back in by explicitly selecting the framebuffer. The U8500 has also gained a few systems using touchscreens from Cypress, Melfas and Zinitix so add these at the same time as we're updating the defconfig anyway. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Cc: phone-devel@vger.kernel.org Cc: Kees Cook Cc: Arnd Bergmann Cc: Stephan Gerhold Cc: newbyte@disroot.org Link: https://lore.kernel.org/r/20210712085522.672482-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/u8500_defconfig | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index dbb1ef601762..3b30913d7d8d 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -61,6 +61,10 @@ CONFIG_INPUT_TOUCHSCREEN=y CONFIG_TOUCHSCREEN_ATMEL_MXT=y CONFIG_TOUCHSCREEN_BU21013=y CONFIG_TOUCHSCREEN_CY8CTMA140=y +CONFIG_TOUCHSCREEN_CYTTSP_CORE=y +CONFIG_TOUCHSCREEN_CYTTSP_SPI=y +CONFIG_TOUCHSCREEN_MMS114=y +CONFIG_TOUCHSCREEN_ZINITIX=y CONFIG_INPUT_MISC=y CONFIG_INPUT_AB8500_PONKEY=y CONFIG_INPUT_GPIO_VIBRA=y @@ -100,6 +104,7 @@ CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y CONFIG_DRM_PANEL_SONY_ACX424AKP=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_KTD253=y CONFIG_BACKLIGHT_GPIO=y From ab37a7a890c1176144a4c66ff3d51ef2c20ed486 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 10 Jul 2021 13:04:55 +0200 Subject: [PATCH 0550/1469] ARM: multi_v7_defconfig: Make NOP_USB_XCEIV driver built-in The usage of usb-nop-xceiv PHY on Raspberry Pi boards with BCM283x has been a "regression source" a lot of times. The last case is breakage of USB mass storage boot has been commit e590474768f1 ("driver core: Set fw_devlink=on by default") for multi_v7_defconfig. As long as NOP_USB_XCEIV is configured as module, the dwc2 USB driver defer probing endlessly and prevent booting from USB mass storage device. So make the driver built-in as in bcm2835_defconfig and arm64/defconfig. Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default") Reported-by: Ojaswin Mujoo Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/1625915095-23077-1-git-send-email-stefan.wahren@i2se.com' Signed-off-by: Arnd Bergmann --- arch/arm/configs/multi_v7_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 52a0400fdd92..d9abaae118dd 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -821,7 +821,7 @@ CONFIG_USB_ISP1760=y CONFIG_USB_HSIC_USB3503=y CONFIG_AB8500_USB=y CONFIG_KEYSTONE_USB_PHY=m -CONFIG_NOP_USB_XCEIV=m +CONFIG_NOP_USB_XCEIV=y CONFIG_AM335X_PHY_USB=m CONFIG_TWL6030_USB=m CONFIG_USB_GPIO_VBUS=y From 82a1c67554dff610d6be4e1982c425717b3c6a23 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 1 Jul 2021 14:21:18 +0100 Subject: [PATCH 0551/1469] ARM: dts: versatile: Fix up interrupt controller node names Once the new schema interrupt-controller/arm,vic.yaml is added, we get the below warnings: arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: $nodename:0: 'intc@10140000' does not match '^interrupt-controller(@[0-9a-f,]+)*$' arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: 'clear-mask' does not match any of the regexes Fix the node names for the interrupt controller to conform to the standard node name interrupt-controller@.. Also drop invalid clear-mask property. Signed-off-by: Sudeep Holla Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20210701132118.759454-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/versatile-ab.dts | 5 ++--- arch/arm/boot/dts/versatile-pb.dts | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 37bd41ff8dff..151c0220047d 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -195,16 +195,15 @@ #size-cells = <1>; ranges; - vic: intc@10140000 { + vic: interrupt-controller@10140000 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; reg = <0x10140000 0x1000>; - clear-mask = <0xffffffff>; valid-mask = <0xffffffff>; }; - sic: intc@10003000 { + sic: interrupt-controller@10003000 { compatible = "arm,versatile-sic"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index 06a0fdf24026..e7e751a858d8 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -7,7 +7,7 @@ amba { /* The Versatile PB is using more SIC IRQ lines than the AB */ - sic: intc@10003000 { + sic: interrupt-controller@10003000 { clear-mask = <0xffffffff>; /* * Valid interrupt lines mask according to From 5f119ba1d5771bbf46d57cff7417dcd84d3084ba Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Wed, 14 Jul 2021 17:13:20 +0800 Subject: [PATCH 0552/1469] net: decnet: Fix sleeping inside in af_decnet The release_sock() is blocking function, it would change the state after sleeping. use wait_woken() instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yajun Deng Signed-off-by: David S. Miller --- net/decnet/af_decnet.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 5dbd45dc35ad..dc92a67baea3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock) static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; if (scp->state != DN_CR) @@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk)); dn_send_conn_conf(sk, allocation); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err == 0) { sk->sk_socket->state = SS_CONNECTED; } else if (scp->state != DN_CC) { @@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) static int dn_wait_run(struct sock *sk, long *timeo) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err = 0; if (scp->state == DN_RUN) @@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo) if (!*timeo) return -EALREADY; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CI || scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo) err = -ETIMEDOUT; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); out: if (err == 0) { sk->sk_socket->state = SS_CONNECTED; @@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) { - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sk_buff *skb = NULL; int err = 0; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); skb = skb_dequeue(&sk->sk_receive_queue); } lock_sock(sk); @@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); return skb == NULL ? ERR_PTR(err) : skb; } From ba02920c51debb9198e72b3a8726a7c5ae4ffb41 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Tue, 13 Jul 2021 17:05:46 +0530 Subject: [PATCH 0553/1469] arm64: tegra: Enable SMMU support for PCIe on Tegra194 As of commit c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194"), SMMU support is enabled system-wide on Tegra194. However, there was a bit of overlap between the SMMU enablement and the PCIe support addition, so the PCIe device tree nodes are missing the iommus and interconnects properties. This in turn leads to SMMU faults for these devices, since by default the ARM SMMU will fault. Add the iommus and interconnects properties to all the PCIe device tree nodes to restore their functionality. Fixes: c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194") Signed-off-by: Vidya Sagar Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 60 +++++++++++++++++++++--- 1 file changed, 54 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 076d5efc4c3d..5ba7a4519b95 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1840,7 +1840,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE1R &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE1W &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE1>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE1 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie@14120000 { @@ -1890,7 +1894,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE2AR &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE2AW &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE2>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE2 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie@14140000 { @@ -1940,7 +1948,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE3R &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE3W &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE3>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE3 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie@14160000 { @@ -1990,7 +2002,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE4>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie@14180000 { @@ -2040,7 +2056,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE0>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie@141a0000 { @@ -2094,7 +2114,11 @@ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>, <&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>; - interconnect-names = "read", "write"; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE5>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie_ep@14160000 { @@ -2127,6 +2151,14 @@ nvidia,aspm-cmrt-us = <60>; nvidia,aspm-pwr-on-t-us = <20>; nvidia,aspm-l0s-entrance-latency-us = <3>; + + interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>, + <&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE4>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie_ep@14180000 { @@ -2159,6 +2191,14 @@ nvidia,aspm-cmrt-us = <60>; nvidia,aspm-pwr-on-t-us = <20>; nvidia,aspm-l0s-entrance-latency-us = <3>; + + interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>, + <&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE0>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; pcie_ep@141a0000 { @@ -2194,6 +2234,14 @@ nvidia,aspm-cmrt-us = <60>; nvidia,aspm-pwr-on-t-us = <20>; nvidia,aspm-l0s-entrance-latency-us = <3>; + + interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>, + <&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_PCIE5>; + iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>; + iommu-map-mask = <0x0>; + dma-coherent; }; sram@40000000 { From 5b69874f74cc5707edd95fcdaa757c507ac8af0f Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Fri, 16 Jul 2021 16:09:41 -0700 Subject: [PATCH 0554/1469] bonding: fix build issue The commit 9a5605505d9c (" bonding: Add struct bond_ipesc to manage SA") is causing following build error when XFRM is not selected in kernel config. lld: error: undefined symbol: xfrm_dev_state_flush >>> referenced by bond_main.c:3453 (drivers/net/bonding/bond_main.c:3453) >>> net/bonding/bond_main.o:(bond_netdev_event) in archive drivers/built-in.a Fixes: 9a5605505d9c (" bonding: Add struct bond_ipesc to manage SA") Signed-off-by: Mahesh Bandewar CC: Taehee Yoo CC: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d22d78303311..31730efa7538 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3450,7 +3450,9 @@ static int bond_master_netdev_event(unsigned long event, return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); +#ifdef CONFIG_XFRM_OFFLOAD xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); +#endif /* CONFIG_XFRM_OFFLOAD */ break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); From cfbe3650dd3ef2ea9a4420ca89d9a4df98af3fb6 Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Wed, 14 Jul 2021 11:27:03 +0800 Subject: [PATCH 0555/1469] netfilter: nf_tables: fix audit memory leak in nf_tables_commit In nf_tables_commit, if nf_tables_commit_audit_alloc fails, it does not free the adp variable. Fix this by adding nf_tables_commit_audit_free which frees the linked list with the head node adl. backtrace: kmalloc include/linux/slab.h:591 [inline] kzalloc include/linux/slab.h:721 [inline] nf_tables_commit_audit_alloc net/netfilter/nf_tables_api.c:8439 [inline] nf_tables_commit+0x16e/0x1760 net/netfilter/nf_tables_api.c:8508 nfnetlink_rcv_batch+0x512/0xa80 net/netfilter/nfnetlink.c:562 nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:634 [inline] nfnetlink_rcv+0x1fa/0x220 net/netfilter/nfnetlink.c:652 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x2c7/0x3e0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x36b/0x6b0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:702 [inline] sock_sendmsg+0x56/0x80 net/socket.c:722 Reported-by: syzbot Reported-by: kernel test robot Fixes: c520292f29b8 ("audit: log nftables configuration change events once per table") Signed-off-by: Dongliang Mu Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index de182d1f7c4e..081437dd75b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8445,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl, return 0; } +static void nf_tables_commit_audit_free(struct list_head *adl) +{ + struct nft_audit_data *adp, *adn; + + list_for_each_entry_safe(adp, adn, adl, list) { + list_del(&adp->list); + kfree(adp); + } +} + static void nf_tables_commit_audit_collect(struct list_head *adl, struct nft_table *table, u32 op) { @@ -8509,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || @@ -8518,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } } From bd31ecf44b8e18ccb1e5f6b50f85de6922a60de3 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 16 Jul 2021 12:43:09 +1000 Subject: [PATCH 0556/1469] KVM: PPC: Book3S: Fix CONFIG_TRANSACTIONAL_MEM=n crash When running CPU_FTR_P9_TM_HV_ASSIST, HFSCR[TM] is set for the guest even if the host has CONFIG_TRANSACTIONAL_MEM=n, which causes it to be unprepared to handle guest exits while transactional. Normal guests don't have a problem because the HTM capability will not be advertised, but a rogue or buggy one could crash the host. Fixes: 4bb3c7a0208f ("KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9") Reported-by: Alexey Kardashevskiy Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210716024310.164448-1-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 1d1fcc290fca..085fb8ecbf68 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2697,8 +2697,10 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX; if (cpu_has_feature(CPU_FTR_HVMODE)) { vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) vcpu->arch.hfscr |= HFSCR_TM; +#endif } if (cpu_has_feature(CPU_FTR_TM_COMP)) vcpu->arch.hfscr |= HFSCR_TM; From bc4188a2f56e821ea057aca6bf444e138d06c252 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 16 Jul 2021 12:43:10 +1000 Subject: [PATCH 0557/1469] KVM: PPC: Fix kvm_arch_vcpu_ioctl vcpu_load leak vcpu_put is not called if the user copy fails. This can result in preempt notifier corruption and crashes, among other issues. Fixes: b3cebfe8c1ca ("KVM: PPC: Move vcpu_load/vcpu_put down to each ioctl case in kvm_arch_vcpu_ioctl") Reported-by: Alexey Kardashevskiy Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210716024310.164448-2-npiggin@gmail.com --- arch/powerpc/kvm/powerpc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index be33b5321a76..b4e6f70b97b9 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -2048,9 +2048,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, { struct kvm_enable_cap cap; r = -EFAULT; - vcpu_load(vcpu); if (copy_from_user(&cap, argp, sizeof(cap))) goto out; + vcpu_load(vcpu); r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); vcpu_put(vcpu); break; @@ -2074,9 +2074,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_DIRTY_TLB: { struct kvm_dirty_tlb dirty; r = -EFAULT; - vcpu_load(vcpu); if (copy_from_user(&dirty, argp, sizeof(dirty))) goto out; + vcpu_load(vcpu); r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty); vcpu_put(vcpu); break; From 1c2b9519159b470ef24b2638f4794e86e2952ab7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 16 Jul 2021 15:27:23 +0200 Subject: [PATCH 0558/1469] ALSA: sb: Fix potential ABBA deadlock in CSP driver SB16 CSP driver may hit potentially a typical ABBA deadlock in two code paths: In snd_sb_csp_stop(): spin_lock_irqsave(&p->chip->mixer_lock, flags); spin_lock(&p->chip->reg_lock); In snd_sb_csp_load(): spin_lock_irqsave(&p->chip->reg_lock, flags); spin_lock(&p->chip->mixer_lock); Also the similar pattern is seen in snd_sb_csp_start(). Although the practical impact is very small (those states aren't triggered in the same running state and this happens only on a real hardware, decades old ISA sound boards -- which must be very difficult to find nowadays), it's a real scenario and has to be fixed. This patch addresses those deadlocks by splitting the locks in snd_sb_csp_start() and snd_sb_csp_stop() for avoiding the nested locks. Reported-by: Jia-Ju Bai Cc: Link: https://lore.kernel.org/r/7b0fcdaf-cd4f-4728-2eae-48c151a92e10@gmail.com Link: https://lore.kernel.org/r/20210716132723.13216-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/isa/sb/sb16_csp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c index 5bbe6695689d..7ad8c5f7b664 100644 --- a/sound/isa/sb/sb16_csp.c +++ b/sound/isa/sb/sb16_csp.c @@ -816,6 +816,7 @@ static int snd_sb_csp_start(struct snd_sb_csp * p, int sample_width, int channel mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7); + spin_unlock_irqrestore(&p->chip->mixer_lock, flags); spin_lock(&p->chip->reg_lock); set_mode_register(p->chip, 0xc0); /* c0 = STOP */ @@ -855,6 +856,7 @@ static int snd_sb_csp_start(struct snd_sb_csp * p, int sample_width, int channel spin_unlock(&p->chip->reg_lock); /* restore PCM volume */ + spin_lock_irqsave(&p->chip->mixer_lock, flags); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR); spin_unlock_irqrestore(&p->chip->mixer_lock, flags); @@ -880,6 +882,7 @@ static int snd_sb_csp_stop(struct snd_sb_csp * p) mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7); + spin_unlock_irqrestore(&p->chip->mixer_lock, flags); spin_lock(&p->chip->reg_lock); if (p->running & SNDRV_SB_CSP_ST_QSOUND) { @@ -894,6 +897,7 @@ static int snd_sb_csp_stop(struct snd_sb_csp * p) spin_unlock(&p->chip->reg_lock); /* restore PCM volume */ + spin_lock_irqsave(&p->chip->mixer_lock, flags); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL); snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR); spin_unlock_irqrestore(&p->chip->mixer_lock, flags); From 33f735f137c6539e3ceceb515cd1e2a644005b49 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 16 Jul 2021 15:56:00 +0200 Subject: [PATCH 0559/1469] ALSA: hdmi: Expose all pins on MSI MS-7C94 board The BIOS on MSI Mortar B550m WiFi (MS-7C94) board with AMDGPU seems disabling the other pins than HDMI although it has more outputs including DP. This patch adds the board to the allow list for enabling all pins. Reported-by: Damjan Georgievski Cc: Link: https://lore.kernel.org/r/CAEk1YH4Jd0a8vfZxORVu7qg+Zsc-K+pR187ezNq8QhJBPW4gpw@mail.gmail.com Link: https://lore.kernel.org/r/20210716135600.24176-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 4b2cc8cb55c4..84c088912b3c 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1940,6 +1940,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), + SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), {} }; From 7f5231b114da76bfd5d0fc685d5cf408d1bbfca7 Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Fri, 16 Jul 2021 21:08:02 +0530 Subject: [PATCH 0560/1469] platform/x86: amd-pmc: Fix undefined reference to __udivdi3 It was reported that on i386 config ------ on i386: ld: drivers/platform/x86/amd-pmc.o: in function `s0ix_stats_show': amd-pmc.c:(.text+0x100): undefined reference to `__udivdi3' ------- The reason for this is that 64-bit integer division is not supported on 32-bit architecture. Use do_div macro to fix this. Fixes: b9a4fa6978be ("platform/x86: amd-pmc: Add support for logging s0ix counters") Reported-by: Randy Dunlap Signed-off-by: Shyam Sundar S K Reviewed-by: Randy Dunlap # and build-tested Link: https://lore.kernel.org/r/20210716153802.2929670-1-Shyam-sundar.S-k@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 663a4ca0580d..3481479a2942 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -189,7 +189,8 @@ static int s0ix_stats_show(struct seq_file *s, void *unused) exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET); /* It's in 48MHz. We need to convert it */ - residency = (exit_time - entry_time) / 48; + residency = exit_time - entry_time; + do_div(residency, 48); seq_puts(s, "=== S0ix statistics ===\n"); seq_printf(s, "S0ix Entry Time: %lld\n", entry_time); From e62fb1e3faae60f483a96c359c8d72bb04a7b728 Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Sat, 17 Jul 2021 16:36:05 +0200 Subject: [PATCH 0561/1469] platform/x86: think-lmi: Move pending_reboot_attr to the attributes sysfs dir Move the pending_reboot node under attributes dir where it should live, as documented in: Documentation/ABI/testing/sysfs-class-firmware-attributes. Also move the create / remove code to be together with the other code populating / cleaning the attributes sysfs dir. In the removal path this is necessary so that the remove is done before the kset_unregister(tlmi_priv.attribute_kset) call. Signed-off-by: Mark Pearson Co-developed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210717143607.3580-1-hdegoede@redhat.com --- drivers/platform/x86/think-lmi.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 64dcec53a7a0..989a8221dcd8 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -672,6 +672,7 @@ static void tlmi_release_attr(void) kobject_put(&tlmi_priv.setting[i]->kobj); } } + sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr); kset_unregister(tlmi_priv.attribute_kset); /* Authentication structures */ @@ -680,7 +681,6 @@ static void tlmi_release_attr(void) sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group); kobject_put(&tlmi_priv.pwd_power->kobj); kset_unregister(tlmi_priv.authentication_kset); - sysfs_remove_file(&tlmi_priv.class_dev->kobj, &pending_reboot.attr); } static int tlmi_sysfs_init(void) @@ -733,6 +733,10 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; } + ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr); + if (ret) + goto fail_create_attr; + /* Create authentication entries */ tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL, &tlmi_priv.class_dev->kobj); @@ -760,11 +764,6 @@ static int tlmi_sysfs_init(void) if (ret) goto fail_create_attr; - /* Create global sysfs files */ - ret = sysfs_create_file(&tlmi_priv.class_dev->kobj, &pending_reboot.attr); - if (ret) - goto fail_create_attr; - return ret; fail_create_attr: From 30e78435d3bf803cabdc2a1c2eb36e6983aa4596 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 17 Jul 2021 16:36:06 +0200 Subject: [PATCH 0562/1469] platform/x86: think-lmi: Split kobject_init() and kobject_add() calls tlmi_sysfs_init() calls tlmi_release_attr() on errors which calls kobject_put() for attributes created by tlmi_analyze(), but if we bail early because of an error, then this means that some of the kobjects will not have been initialized yet; and we should thus not call kobject_put() on them. Switch from using kobject_init_and_add() inside tlmi_sysfs_init() to initializing all the created kobjects directly in tlmi_analyze() and only adding them from tlmi_sysfs_init(). This way all kobjects will always be initialized when tlmi_release_attr() gets called. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210717143607.3580-2-hdegoede@redhat.com --- drivers/platform/x86/think-lmi.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 989a8221dcd8..c22edcf26aaa 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -723,8 +723,8 @@ static int tlmi_sysfs_init(void) /* Build attribute */ tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset; - ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype, - NULL, "%s", tlmi_priv.setting[i]->display_name); + ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL, + "%s", tlmi_priv.setting[i]->display_name); if (ret) goto fail_create_attr; @@ -745,8 +745,7 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; } tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype, - NULL, "%s", "Admin"); + ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin"); if (ret) goto fail_create_attr; @@ -755,8 +754,7 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype, - NULL, "%s", "System"); + ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "System"); if (ret) goto fail_create_attr; @@ -836,6 +834,7 @@ static int tlmi_analyze(void) pr_info("Error retrieving possible values for %d : %s\n", i, setting->display_name); } + kobject_init(&setting->kobj, &tlmi_attr_setting_ktype); tlmi_priv.setting[i] = setting; tlmi_priv.settings_count++; kfree(item); @@ -862,6 +861,8 @@ static int tlmi_analyze(void) if (pwdcfg.password_state & TLMI_PAP_PWD) tlmi_priv.pwd_admin->valid = true; + kobject_init(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype); + tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL); if (!tlmi_priv.pwd_power) { ret = -ENOMEM; @@ -877,6 +878,8 @@ static int tlmi_analyze(void) if (pwdcfg.password_state & TLMI_POP_PWD) tlmi_priv.pwd_power->valid = true; + kobject_init(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype); + return 0; fail_clear_attr: From f7e506ec4a9966be8b2a87d3324302f0f5dd5a29 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 17 Jul 2021 16:36:07 +0200 Subject: [PATCH 0563/1469] platform/x86: think-lmi: Fix possible mem-leaks on tlmi_analyze() error-exit Fix 2 possible memleaks on error-exits from tlmi_analyze(): 1. If the kzalloc of pwd_power fails, then not only free the atributes, but also the allocated pwd_admin struct. 2. Freeing the attributes should also free the possible_values strings. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210717143607.3580-3-hdegoede@redhat.com --- drivers/platform/x86/think-lmi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index c22edcf26aaa..6cfed4427fb0 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -866,7 +866,7 @@ static int tlmi_analyze(void) tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL); if (!tlmi_priv.pwd_power) { ret = -ENOMEM; - goto fail_clear_attr; + goto fail_free_pwd_admin; } strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN); tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII; @@ -882,9 +882,15 @@ static int tlmi_analyze(void) return 0; +fail_free_pwd_admin: + kfree(tlmi_priv.pwd_admin); fail_clear_attr: - for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) - kfree(tlmi_priv.setting[i]); + for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) { + if (tlmi_priv.setting[i]) { + kfree(tlmi_priv.setting[i]->possible_values); + kfree(tlmi_priv.setting[i]); + } + } return ret; } From 9898cb24e454602beb6e17bacf9f97b26c85c955 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 9 Jul 2021 12:11:10 +0200 Subject: [PATCH 0564/1469] iio: adc: ti-ads7950: Ensure CS is deasserted after reading channels MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ADS7950 requires that CS is deasserted after each SPI word. Before commit e2540da86ef8 ("iio: adc: ti-ads7950: use SPI_CS_WORD to reduce CPU usage") the driver used a message with one spi transfer per channel where each but the last one had .cs_change set to enforce a CS toggle. This was wrongly translated into a message with a single transfer and .cs_change set which results in a CS toggle after each word but the last which corrupts the first adc conversion of all readouts after the first readout. Fixes: e2540da86ef8 ("iio: adc: ti-ads7950: use SPI_CS_WORD to reduce CPU usage") Signed-off-by: Uwe Kleine-König Reviewed-by: David Lechner Tested-by: David Lechner Cc: Link: https://lore.kernel.org/r/20210709101110.1814294-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti-ads7950.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 2383eacada87..a2b83f0bd526 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -568,7 +568,6 @@ static int ti_ads7950_probe(struct spi_device *spi) st->ring_xfer.tx_buf = &st->tx_buf[0]; st->ring_xfer.rx_buf = &st->rx_buf[0]; /* len will be set later */ - st->ring_xfer.cs_change = true; spi_message_add_tail(&st->ring_xfer, &st->ring_msg); From 7e77ef8b8d600cf8448a2bbd32f682c28884551f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Antti=20Ker=C3=A4nen?= Date: Thu, 8 Jul 2021 12:54:29 +0300 Subject: [PATCH 0565/1469] iio: adis: set GPIO reset pin direction MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Set reset pin direction to output as the reset pin needs to be an active low output pin. Co-developed-by: Hannu Hartikainen Signed-off-by: Hannu Hartikainen Signed-off-by: Antti Keränen Reviewed-by: Nuno Sá Fixes: ecb010d44108 ("iio: imu: adis: Refactor adis_initial_startup") Link: https://lore.kernel.org/r/20210708095425.13295-1-detegr@rbx.email Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/imu/adis.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index a5b421f42287..b9a06ca29bee 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -411,12 +411,11 @@ int __adis_initial_startup(struct adis *adis) int ret; /* check if the device has rst pin low */ - gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_ASIS); + gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(gpio)) return PTR_ERR(gpio); if (gpio) { - gpiod_set_value_cansleep(gpio, 1); msleep(10); /* bring device out of reset */ gpiod_set_value_cansleep(gpio, 0); From ec645dc96699ea6c37b6de86c84d7288ea9a4ddf Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Sat, 17 Jul 2021 14:33:28 +0200 Subject: [PATCH 0566/1469] block: increase BLKCG_MAX_POLS After mq-deadline learned to deal with cgroups, the BLKCG_MAX_POLS value became too small for all the elevators to be registered properly. The following issue is seen: ``` calling bfq_init+0x0/0x8b @ 1 blkcg_policy_register: BLKCG_MAX_POLS too small initcall bfq_init+0x0/0x8b returned -28 after 507 usecs ``` which renders BFQ non-functional. Increase BLKCG_MAX_POLS to allow enough space for everyone. Fixes: 08a9ad8bf607 ("block/mq-deadline: Add cgroup support") Link: https://lore.kernel.org/lkml/8988303.mDXGIdCtx8@natalenko.name/ Signed-off-by: Oleksandr Natalenko Link: https://lore.kernel.org/r/20210717123328.945810-1-oleksandr@natalenko.name Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c454fb446fd0..2e12320cb121 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -57,7 +57,7 @@ struct blk_keyslot_manager; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 5 +#define BLKCG_MAX_POLS 6 typedef void (rq_end_io_fn)(struct request *, blk_status_t); From ae14c63a9f20d49dacfb6f3fa3fb11b3b4eb11bf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 17 Jul 2021 13:27:00 -0700 Subject: [PATCH 0567/1469] Revert "mm/slub: use stackdepot to save stack trace in objects" This reverts commit 788691464c29455346dc613a3b43c2fb9e5757a4. It's not clear why, but it causes unexplained problems in entirely unrelated xfs code. The most likely explanation is some slab corruption, possibly triggered due to CONFIG_SLUB_DEBUG_ON. See [1]. It ends up having a few other problems too, like build errors on arch/arc, and Geert reporting it using much more memory on m68k [3] (it probably does so elsewhere too, but it is probably just more noticeable on m68k). The architecture issues (both build and memory use) are likely just because this change effectively force-enabled STACKDEPOT (along with a very bad default value for the stackdepot hash size). But together with the xfs issue, this all smells like "this commit was not ready" to me. Link: https://lore.kernel.org/linux-xfs/YPE3l82acwgI2OiV@infradead.org/ [1] Link: https://lore.kernel.org/lkml/202107150600.LkGNb4Vb-lkp@intel.com/ [2] Link: https://lore.kernel.org/lkml/CAMuHMdW=eoVzM1Re5FVoEN87nKfiLmM2+Ah7eNu2KXEhCvbZyA@mail.gmail.com/ [3] Reported-by: Christoph Hellwig Reported-by: kernel test robot Reported-by: Geert Uytterhoeven Cc: Andrew Morton Cc: Vlastimil Babka Cc: Randy Dunlap Signed-off-by: Linus Torvalds --- init/Kconfig | 1 - mm/slub.c | 79 ++++++++++++++++++++-------------------------------- 2 files changed, 30 insertions(+), 50 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index bb0d6e6262b1..55f9f7738ebb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1847,7 +1847,6 @@ config SLUB_DEBUG default y bool "Enable SLUB debugging support" if EXPERT depends on SLUB && SYSFS - select STACKDEPOT if STACKTRACE_SUPPORT help SLUB has extensive debug support features. Disabling these can result in significant savings in code size. This also disables diff --git a/mm/slub.c b/mm/slub.c index e1644ac6ee7b..090fa14628f9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -207,8 +206,8 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) #define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ -#ifdef CONFIG_STACKDEPOT - depot_stack_handle_t handle; +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ #endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ @@ -612,27 +611,22 @@ static struct track *get_track(struct kmem_cache *s, void *object, return kasan_reset_tag(p + alloc); } -#ifdef CONFIG_STACKDEPOT -static depot_stack_handle_t save_stack_depot_trace(gfp_t flags) -{ - unsigned long entries[TRACK_ADDRS_COUNT]; - depot_stack_handle_t handle; - unsigned int nr_entries; - - nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 4); - handle = stack_depot_save(entries, nr_entries, flags); - return handle; -} -#endif - static void set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { struct track *p = get_track(s, object, alloc); if (addr) { -#ifdef CONFIG_STACKDEPOT - p->handle = save_stack_depot_trace(GFP_NOWAIT); +#ifdef CONFIG_STACKTRACE + unsigned int nr_entries; + + metadata_access_enable(); + nr_entries = stack_trace_save(kasan_reset_tag(p->addrs), + TRACK_ADDRS_COUNT, 3); + metadata_access_disable(); + + if (nr_entries < TRACK_ADDRS_COUNT) + p->addrs[nr_entries] = 0; #endif p->addr = addr; p->cpu = smp_processor_id(); @@ -659,19 +653,14 @@ static void print_track(const char *s, struct track *t, unsigned long pr_time) pr_err("%s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid); -#ifdef CONFIG_STACKDEPOT +#ifdef CONFIG_STACKTRACE { - depot_stack_handle_t handle; - unsigned long *entries; - unsigned int nr_entries; - - handle = READ_ONCE(t->handle); - if (!handle) { - pr_err("object allocation/free stack trace missing\n"); - } else { - nr_entries = stack_depot_fetch(handle, &entries); - stack_trace_print(entries, nr_entries, 0); - } + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + pr_err("\t%pS\n", (void *)t->addrs[i]); + else + break; } #endif } @@ -4045,26 +4034,18 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) objp = fixup_red_left(s, objp); trackp = get_track(s, objp, TRACK_ALLOC); kpp->kp_ret = (void *)trackp->addr; -#ifdef CONFIG_STACKDEPOT - { - depot_stack_handle_t handle; - unsigned long *entries; - unsigned int nr_entries; +#ifdef CONFIG_STACKTRACE + for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { + kpp->kp_stack[i] = (void *)trackp->addrs[i]; + if (!kpp->kp_stack[i]) + break; + } - handle = READ_ONCE(trackp->handle); - if (handle) { - nr_entries = stack_depot_fetch(handle, &entries); - for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) - kpp->kp_stack[i] = (void *)entries[i]; - } - - trackp = get_track(s, objp, TRACK_FREE); - handle = READ_ONCE(trackp->handle); - if (handle) { - nr_entries = stack_depot_fetch(handle, &entries); - for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) - kpp->kp_free_stack[i] = (void *)entries[i]; - } + trackp = get_track(s, objp, TRACK_FREE); + for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { + kpp->kp_free_stack[i] = (void *)trackp->addrs[i]; + if (!kpp->kp_free_stack[i]) + break; } #endif #endif From e0fa7ab42232e742dcb3de9f3c1f6127b5adc019 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:25 +0200 Subject: [PATCH 0568/1469] perf probe-file: Delete namelist in del_events() on the error path ASan reports some memory leaks when running: # perf test "42: BPF filter" This second leak is caused by a strlist not being dellocated on error inside probe_file__del_events. This patch adds a goto label before the deallocation and makes the error path jump to it. Signed-off-by: Riccardo Mancini Fixes: e7895e422e4da63d ("perf probe: Split del_perf_probe_events()") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/174963c587ae77fa108af794669998e4ae558338.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index f9a6cbcd6415..3d50de3217d5 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -377,11 +377,11 @@ int probe_file__del_events(int fd, struct strfilter *filter) ret = probe_file__get_events(fd, filter, namelist); if (ret < 0) - return ret; + goto out; ret = probe_file__del_strlist(fd, namelist); +out: strlist__delete(namelist); - return ret; } From d4b3eedce151e63932ce4a00f1d0baa340a8b907 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Fri, 16 Jul 2021 16:11:20 +0200 Subject: [PATCH 0569/1469] perf data: Close all files in close_dir() When using 'perf report' in directory mode, the first file is not closed on exit, causing a memory leak. The problem is caused by the iterating variable never reaching 0. Fixes: 145520631130bd64 ("perf data: Add perf_data__(create_dir|close_dir) functions") Signed-off-by: Riccardo Mancini Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: Zhen Lei Link: http://lore.kernel.org/lkml/20210716141122.858082-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index a9c102e8e3c0..f5d260b1df4d 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -20,7 +20,7 @@ static void close_dir(struct perf_data_file *files, int nr) { - while (--nr >= 1) { + while (--nr >= 0) { close(files[nr].fd); zfree(&files[nr].path); } From 22a665513b34df458da1d3b7ee0b919c3f3d4653 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 15 Jul 2021 14:37:23 +0800 Subject: [PATCH 0570/1469] perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel The "address" member of "struct probe_trace_point" uses long data type. If kernel is 64-bit and perf program is 32-bit, size of "address" variable is 32 bits. As a result, upper 32 bits of address read from kernel are truncated, an error occurs during address comparison in kprobe_warn_out_range(). Before: # perf probe -a schedule schedule is out of .text, skip it. Error: Failed to add events. Solution: Change data type of "address" variable to u64 and change corresponding address printing and value assignment. After: # perf.new.new probe -a schedule Added new event: probe:schedule (on schedule) You can now use it in all perf tools, such as: perf record -e probe:schedule -aR sleep 1 # perf probe -l probe:schedule (on schedule@kernel/sched/core.c) # perf record -e probe:schedule -aR sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.156 MB perf.data (1366 samples) ] # perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 1K of event 'probe:schedule' # Event count (approx.): 1366 # # Overhead Command Shared Object Symbol # ........ ............... ................. ............ # 6.22% migration/0 [kernel.kallsyms] [k] schedule 6.22% migration/1 [kernel.kallsyms] [k] schedule 6.22% migration/2 [kernel.kallsyms] [k] schedule 6.22% migration/3 [kernel.kallsyms] [k] schedule 6.15% migration/10 [kernel.kallsyms] [k] schedule 6.15% migration/11 [kernel.kallsyms] [k] schedule 6.15% migration/12 [kernel.kallsyms] [k] schedule 6.15% migration/13 [kernel.kallsyms] [k] schedule 6.15% migration/14 [kernel.kallsyms] [k] schedule 6.15% migration/15 [kernel.kallsyms] [k] schedule 6.15% migration/4 [kernel.kallsyms] [k] schedule 6.15% migration/5 [kernel.kallsyms] [k] schedule 6.15% migration/6 [kernel.kallsyms] [k] schedule 6.15% migration/7 [kernel.kallsyms] [k] schedule 6.15% migration/8 [kernel.kallsyms] [k] schedule 6.15% migration/9 [kernel.kallsyms] [k] schedule 0.22% rcu_sched [kernel.kallsyms] [k] schedule ... # # (Cannot load tips.txt file, please install perf!) # Signed-off-by: Yang Jihong Acked-by: Masami Hiramatsu Cc: Alexander Shishkin Cc: Frank Ch. Eigler Cc: Ian Rogers Cc: Jianlin Lv Cc: Jin Yao Cc: Jiri Olsa Cc: Li Huafei Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Srikar Dronamraju Link: http://lore.kernel.org/lkml/20210715063723.11926-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 8 +++--- tools/perf/util/dwarf-aux.h | 2 +- tools/perf/util/probe-event.c | 49 ++++++++++++++++------------------ tools/perf/util/probe-event.h | 4 +-- tools/perf/util/probe-finder.c | 15 +++++------ tools/perf/util/probe-finder.h | 2 +- 6 files changed, 38 insertions(+), 42 deletions(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7d2ba8419b0c..609ca1671501 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -113,14 +113,14 @@ static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) * * Find a line number and file name for @addr in @cu_die. */ -int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, - const char **fname, int *lineno) +int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr, + const char **fname, int *lineno) { Dwarf_Line *line; Dwarf_Die die_mem; Dwarf_Addr faddr; - if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem) + if (die_find_realfunc(cu_die, addr, &die_mem) && die_entrypc(&die_mem, &faddr) == 0 && faddr == addr) { *fname = dwarf_decl_file(&die_mem); @@ -128,7 +128,7 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, goto out; } - line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr); + line = cu_getsrc_die(cu_die, addr); if (line && dwarf_lineno(line, lineno) == 0) { *fname = dwarf_linesrc(line, NULL, NULL); if (!*fname) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index cb99646843a9..7ee0fa19b5c4 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -19,7 +19,7 @@ const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname); const char *cu_get_comp_dir(Dwarf_Die *cu_die); /* Get a line number and file name for given address */ -int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, +int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr, const char **fname, int *lineno); /* Walk on functions at given address */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e05750cea34c..b2a02c9ab8ea 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -239,8 +239,8 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) clear_probe_trace_event(tevs + i); } -static bool kprobe_blacklist__listed(unsigned long address); -static bool kprobe_warn_out_range(const char *symbol, unsigned long address) +static bool kprobe_blacklist__listed(u64 address); +static bool kprobe_warn_out_range(const char *symbol, u64 address) { struct map *map; bool ret = false; @@ -400,8 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, pr_debug("Symbol %s address found : %" PRIx64 "\n", pp->function, address); - ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, - result); + ret = debuginfo__find_probe_point(dinfo, address, result); if (ret <= 0) ret = (!ret) ? -ENOENT : ret; else { @@ -589,7 +588,7 @@ static void debuginfo_cache__exit(void) } -static int get_text_start_address(const char *exec, unsigned long *address, +static int get_text_start_address(const char *exec, u64 *address, struct nsinfo *nsi) { Elf *elf; @@ -634,7 +633,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, bool is_kprobe) { struct debuginfo *dinfo = NULL; - unsigned long stext = 0; + u64 stext = 0; u64 addr = tp->address; int ret = -ENOENT; @@ -662,8 +661,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, dinfo = debuginfo_cache__open(tp->module, verbose <= 0); if (dinfo) - ret = debuginfo__find_probe_point(dinfo, - (unsigned long)addr, pp); + ret = debuginfo__find_probe_point(dinfo, addr, pp); else ret = -ENOENT; @@ -678,7 +676,7 @@ error: /* Adjust symbol name and address */ static int post_process_probe_trace_point(struct probe_trace_point *tp, - struct map *map, unsigned long offs) + struct map *map, u64 offs) { struct symbol *sym; u64 addr = tp->address - offs; @@ -721,7 +719,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *pathname) { struct map *map; - unsigned long stext = 0; + u64 stext = 0; int i, ret = 0; /* Prepare a map for offline binary */ @@ -747,7 +745,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, struct nsinfo *nsi) { int i, ret = 0; - unsigned long stext = 0; + u64 stext = 0; if (!exec) return 0; @@ -792,7 +790,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs, mod_name = find_module_name(module); for (i = 0; i < ntevs; i++) { ret = post_process_probe_trace_point(&tevs[i].point, - map, (unsigned long)text_offs); + map, text_offs); if (ret < 0) break; tevs[i].point.module = @@ -1536,7 +1534,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) * so tmp[1] should always valid (but could be '\0'). */ if (tmp && !strncmp(tmp, "0x", 2)) { - pp->abs_address = strtoul(pp->function, &tmp, 0); + pp->abs_address = strtoull(pp->function, &tmp, 0); if (*tmp != '\0') { semantic_error("Invalid absolute address.\n"); return -EINVAL; @@ -1911,7 +1909,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) argv[i] = NULL; argc -= 1; } else - tp->address = strtoul(fmt1_str, NULL, 0); + tp->address = strtoull(fmt1_str, NULL, 0); } else { /* Only the symbol-based probe has offset */ tp->symbol = strdup(fmt1_str); @@ -2157,7 +2155,7 @@ synthesize_uprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) return -EINVAL; /* Use the tp->address for uprobes */ - err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address); + err = strbuf_addf(buf, "%s:0x%" PRIx64, tp->module, tp->address); if (err >= 0 && tp->ref_ctr_offset) { if (!uprobe_ref_ctr_is_supported()) @@ -2172,7 +2170,7 @@ synthesize_kprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) { if (!strncmp(tp->symbol, "0x", 2)) { /* Absolute address. See try_to_find_absolute_address() */ - return strbuf_addf(buf, "%s%s0x%lx", tp->module ?: "", + return strbuf_addf(buf, "%s%s0x%" PRIx64, tp->module ?: "", tp->module ? ":" : "", tp->address); } else { return strbuf_addf(buf, "%s%s%s+%lu", tp->module ?: "", @@ -2271,7 +2269,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, pp->function = strdup(tp->symbol); pp->offset = tp->offset; } else { - ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + ret = e_snprintf(buf, 128, "0x%" PRIx64, tp->address); if (ret < 0) return ret; pp->function = strdup(buf); @@ -2452,8 +2450,8 @@ void clear_probe_trace_event(struct probe_trace_event *tev) struct kprobe_blacklist_node { struct list_head list; - unsigned long start; - unsigned long end; + u64 start; + u64 end; char *symbol; }; @@ -2498,7 +2496,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } INIT_LIST_HEAD(&node->list); list_add_tail(&node->list, blacklist); - if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + if (sscanf(buf, "0x%" PRIx64 "-0x%" PRIx64, &node->start, &node->end) != 2) { ret = -EINVAL; break; } @@ -2514,7 +2512,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) ret = -ENOMEM; break; } - pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + pr_debug2("Blacklist: 0x%" PRIx64 "-0x%" PRIx64 ", %s\n", node->start, node->end, node->symbol); ret++; } @@ -2526,8 +2524,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } static struct kprobe_blacklist_node * -kprobe_blacklist__find_by_address(struct list_head *blacklist, - unsigned long address) +kprobe_blacklist__find_by_address(struct list_head *blacklist, u64 address) { struct kprobe_blacklist_node *node; @@ -2555,7 +2552,7 @@ static void kprobe_blacklist__release(void) kprobe_blacklist__delete(&kprobe_blacklist); } -static bool kprobe_blacklist__listed(unsigned long address) +static bool kprobe_blacklist__listed(u64 address) { return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address); } @@ -3223,7 +3220,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, * In __add_probe_trace_events, a NULL symbol is interpreted as * invalid. */ - if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0) + if (asprintf(&tp->symbol, "0x%" PRIx64, tp->address) < 0) goto errout; /* For kprobe, check range */ @@ -3234,7 +3231,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, goto errout; } - if (asprintf(&tp->realname, "abs_%lx", tp->address) < 0) + if (asprintf(&tp->realname, "abs_%" PRIx64, tp->address) < 0) goto errout; if (pev->target) { diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 65769d7949a3..8ad5b1579f1d 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -33,7 +33,7 @@ struct probe_trace_point { char *module; /* Module name */ unsigned long offset; /* Offset from symbol */ unsigned long ref_ctr_offset; /* SDT reference counter offset */ - unsigned long address; /* Actual address of the trace point */ + u64 address; /* Actual address of the trace point */ bool retprobe; /* Return probe flag */ }; @@ -70,7 +70,7 @@ struct perf_probe_point { bool retprobe; /* Return probe flag */ char *lazy_line; /* Lazy matching pattern */ unsigned long offset; /* Offset from function entry */ - unsigned long abs_address; /* Absolute address of the point */ + u64 abs_address; /* Absolute address of the point */ }; /* Perf probe probing argument field chain */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 02ef0d78053b..50d861a80f57 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -668,7 +668,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, } tp->offset = (unsigned long)(paddr - eaddr); - tp->address = (unsigned long)paddr; + tp->address = paddr; tp->symbol = strdup(symbol); if (!tp->symbol) return -ENOMEM; @@ -1707,7 +1707,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, } /* Reverse search */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; @@ -1720,14 +1720,14 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - pr_warning("Failed to find debug information for address %lx\n", + pr_warning("Failed to find debug information for address %" PRIx64 "\n", addr); ret = -EINVAL; goto end; } /* Find a corresponding line (filename and lineno) */ - cu_find_lineinfo(&cudie, addr, &fname, &lineno); + cu_find_lineinfo(&cudie, (Dwarf_Addr)addr, &fname, &lineno); /* Don't care whether it failed or not */ /* Find a corresponding function (name, baseline and baseaddr) */ @@ -1742,7 +1742,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, } fname = dwarf_decl_file(&spdie); - if (addr == (unsigned long)baseaddr) { + if (addr == baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; goto post; @@ -1788,7 +1788,7 @@ post: if (lineno) ppt->line = lineno - baseline; else if (basefunc) { - ppt->offset = addr - (unsigned long)baseaddr; + ppt->offset = addr - baseaddr; func = basefunc; } @@ -1828,8 +1828,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, } static int line_range_walk_cb(const char *fname, int lineno, - Dwarf_Addr addr __maybe_unused, - void *data) + Dwarf_Addr addr, void *data) { struct line_finder *lf = data; const char *__fname; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 2febb5875678..8bc1c80d3c1c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -46,7 +46,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, struct probe_trace_event **tevs); /* Find a perf_probe_point from debuginfo */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt); int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, From b0f008551f0bf4d5f6db9b5f0e071b02790d6a2e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 13 Jul 2021 19:23:58 +0800 Subject: [PATCH 0571/1469] perf sched: Fix record failure when CONFIG_SCHEDSTATS is not set The tracepoints trace_sched_stat_{wait, sleep, iowait} are not exposed to user if CONFIG_SCHEDSTATS is not set, "perf sched record" records the three events. As a result, the command fails. Before: #perf sched record sleep 1 event syntax error: 'sched:sched_stat_wait' \___ unknown tracepoint Error: File /sys/kernel/tracing/events/sched/sched_stat_wait not found. Hint: Perhaps this kernel misses some CONFIG_ setting to enable this feature?. Run 'perf list' for a list of valid events Usage: perf record [] [] or: perf record [] -- [] -e, --event event selector. use 'perf list' to list available events Solution: Check whether schedstat tracepoints are exposed. If no, these events are not recorded. After: # perf sched record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.163 MB perf.data (1091 samples) ] # perf sched report run measurement overhead: 4736 nsecs sleep measurement overhead: 9059979 nsecs the run test took 999854 nsecs the sleep test took 8945271 nsecs nr_run_events: 716 nr_sleep_events: 785 nr_wakeup_events: 0 ... ------------------------------------------------------------ Fixes: 2a09b5de235a6 ("sched/fair: do not expose some tracepoints to user if CONFIG_SCHEDSTATS is not set") Signed-off-by: Yang Jihong Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Cc: Yafang Shao Link: http://lore.kernel.org/lkml/20210713112358.194693-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index aaf1cde476c9..1ff10d4bccf3 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options sort_dimension__add("pid", &sched->cmp_pid); } +static bool schedstat_events_exposed(void) +{ + /* + * Select "sched:sched_stat_wait" event to check + * whether schedstat tracepoints are exposed. + */ + return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; @@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv) "-m", "1024", "-c", "1", "-e", "sched:sched_switch", - "-e", "sched:sched_stat_wait", - "-e", "sched:sched_stat_sleep", - "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; + + /* + * The tracepoints trace_sched_stat_{wait, sleep, iowait} + * are not exposed to user if CONFIG_SCHEDSTATS is not set, + * to prevent "perf sched record" execution failure, determine + * whether to record schedstat events according to actual situation. + */ + const char * const schedstat_args[] = { + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + }; + unsigned int schedstat_argc = schedstat_events_exposed() ? + ARRAY_SIZE(schedstat_args) : 0; + struct tep_event *waking_event; /* * +2 for either "-e", "sched:sched_wakeup" or * "-e", "sched:sched_waking" */ - rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1; + rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv) else rec_argv[i++] = strdup("sched:sched_wakeup"); + for (j = 0; j < schedstat_argc; j++) + rec_argv[i++] = strdup(schedstat_args[j]); + for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; From ec7099fdea8025988710ee6fecfd4e4210c29ab5 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 2 Jul 2021 15:37:12 +0200 Subject: [PATCH 0572/1469] Revert "gpio: mpc8xxx: change the gpio interrupt flags." This reverts commit 3d5bfbd9716318b1ca5c38488aa69f64d38a9aa5. When booting with threadirqs, it causes a splat WARNING: CPU: 0 PID: 29 at kernel/irq/handle.c:159 __handle_irq_event_percpu+0x1ec/0x27c irq 66 handler irq_default_primary_handler+0x0/0x1c enabled interrupts That splat later went away with commit 81e2073c175b ("genirq: Disable interrupts for force threaded handlers"), which got backported to -stable. However, when running an -rt kernel, the splat still exists. Moreover, quoting Thomas Gleixner [1] But 3d5bfbd97163 ("gpio: mpc8xxx: change the gpio interrupt flags.") has nothing to do with that: "Delete the interrupt IRQF_NO_THREAD flags in order to gpio interrupts can be threaded to allow high-priority processes to preempt." This changelog is blatantly wrong. In mainline forced irq threads have always been invoked with softirqs disabled, which obviously makes them non-preemptible. So the patch didn't even do what its commit log said. [1] https://lore.kernel.org/lkml/871r8zey88.ffs@nanos.tec.linutronix.de/ Cc: stable@vger.kernel.org # v5.9+ Signed-off-by: Rasmus Villemoes Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mpc8xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 4b9157a69fca..50b321a1ab1b 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -405,7 +405,7 @@ static int mpc8xxx_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, mpc8xxx_gc->irqn, mpc8xxx_gpio_irq_cascade, - IRQF_SHARED, "gpio-cascade", + IRQF_NO_THREAD | IRQF_SHARED, "gpio-cascade", mpc8xxx_gc); if (ret) { dev_err(&pdev->dev, From 5df99bec210a2cf89dd91e52f0d0a714bf4cd96a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 12 Jul 2021 15:35:46 -0400 Subject: [PATCH 0573/1469] scripts/setlocalversion: fix a bug when LOCALVERSION is empty The commit 042da426f8eb ("scripts/setlocalversion: simplify the short version part") reduces indentation. Unfortunately, it also changes behavior in a subtle way - if the user has empty "LOCALVERSION" variable, the plus sign is appended to the kernel version. It wasn't appended before. This patch reverts to the old behavior - we append the plus sign only if the LOCALVERSION variable is not set. Fixes: 042da426f8eb ("scripts/setlocalversion: simplify the short version part") Signed-off-by: Mikulas Patocka Signed-off-by: Masahiro Yamada --- scripts/setlocalversion | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 151f04971faa..6b54e46a0f12 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -131,11 +131,14 @@ res="${res}${CONFIG_LOCALVERSION}${LOCALVERSION}" if test "$CONFIG_LOCALVERSION_AUTO" = "y"; then # full scm version string res="$res$(scm_version)" -elif [ -z "${LOCALVERSION}" ]; then - # append a plus sign if the repository is not in a clean - # annotated or signed tagged state (as git describe only - # looks at signed or annotated tags - git tag -a/-s) and - # LOCALVERSION= is not specified +elif [ "${LOCALVERSION+set}" != "set" ]; then + # If the variable LOCALVERSION is not set, append a plus + # sign if the repository is not in a clean annotated or + # signed tagged state (as git describe only looks at signed + # or annotated tags - git tag -a/-s). + # + # If the variable LOCALVERSION is set (including being set + # to an empty string), we don't want to append a plus sign. scm=$(scm_version --short) res="$res${scm:++}" fi From d952cfaf0cffdbbb0433c67206b645131f17ca5f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 14 Jul 2021 13:23:49 +0900 Subject: [PATCH 0574/1469] kbuild: do not suppress Kconfig prompts for silent build When a new CONFIG option is available, Kbuild shows a prompt to get the user input. $ make [ snip ] Core Scheduling for SMT (SCHED_CORE) [N/y/?] (NEW) This is the only interactive place in the build process. Commit 174a1dcc9642 ("kbuild: sink stdout from cmd for silent build") suppressed Kconfig prompts as well because syncconfig is invoked by the 'cmd' macro. You cannot notice the fact that Kconfig is waiting for the user input. Use 'kecho' to show the equivalent short log without suppressing stdout from sub-make. Fixes: 174a1dcc9642 ("kbuild: sink stdout from cmd for silent build") Reported-by: Tetsuo Handa Signed-off-by: Masahiro Yamada Tested-by: Tetsuo Handa --- Makefile | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index c3f9bd191b89..e264c5440f70 100644 --- a/Makefile +++ b/Makefile @@ -728,11 +728,12 @@ $(KCONFIG_CONFIG): # This exploits the 'multi-target pattern rule' trick. # The syncconfig should be executed only once to make all the targets. # (Note: use the grouped target '&:' when we bump to GNU Make 4.3) -quiet_cmd_syncconfig = SYNC $@ - cmd_syncconfig = $(MAKE) -f $(srctree)/Makefile syncconfig - +# +# Do not use $(call cmd,...) here. That would suppress prompts from syncconfig, +# so you cannot notice that Kconfig is waiting for the user input. %/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h: $(KCONFIG_CONFIG) - +$(call cmd,syncconfig) + $(Q)$(kecho) " SYNC $@" + $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig else # !may-sync-config # External modules and some install targets need include/generated/autoconf.h # and include/config/auto.conf but do not care if they are up-to-date. From 1d11053dc63094075bf9e4809fffd3bb5e72f9a6 Mon Sep 17 00:00:00 2001 From: Lecopzer Chen Date: Thu, 15 Jul 2021 15:37:16 +0800 Subject: [PATCH 0575/1469] Kbuild: lto: fix module versionings mismatch in GNU make 3.X When building modules(CONFIG_...=m), I found some of module versions are incorrect and set to 0. This can be found in build log for first clean build which shows WARNING: EXPORT symbol "XXXX" [drivers/XXX/XXX.ko] version generation failed, symbol will not be versioned. But in second build(incremental build), the WARNING disappeared and the module version becomes valid CRC and make someone who want to change modules without updating kernel image can't insert their modules. The problematic code is + $(foreach n, $(filter-out FORCE,$^), \ + $(if $(wildcard $(n).symversions), \ + ; cat $(n).symversions >> $@.symversions)) For example: rm -f fs/notify/built-in.a.symversions ; rm -f fs/notify/built-in.a; \ llvm-ar cDPrST fs/notify/built-in.a fs/notify/fsnotify.o \ fs/notify/notification.o fs/notify/group.o ... `foreach n` shows nothing to `cat` into $(n).symversions because `if $(wildcard $(n).symversions)` return nothing, but actually they do exist during this line was executed. -rw-r--r-- 1 root root 168580 Jun 13 19:10 fs/notify/fsnotify.o -rw-r--r-- 1 root root 111 Jun 13 19:10 fs/notify/fsnotify.o.symversions The reason is the $(n).symversions are generated at runtime, but Makefile wildcard function expends and checks the file exist or not during parsing the Makefile. Thus fix this by use `test` shell command to check the file existence in runtime. Rebase from both: 1. [https://lore.kernel.org/lkml/20210616080252.32046-1-lecopzer.chen@mediatek.com/] 2. [https://lore.kernel.org/lkml/20210702032943.7865-1-lecopzer.chen@mediatek.com/] Fixes: 38e891849003 ("kbuild: lto: fix module versioning") Co-developed-by: Sami Tolvanen Signed-off-by: Lecopzer Chen Signed-off-by: Masahiro Yamada --- scripts/Makefile.build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 10b2f2380d6f..02197cb8e3a7 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -386,7 +386,7 @@ ifeq ($(CONFIG_LTO_CLANG) $(CONFIG_MODVERSIONS),y y) cmd_update_lto_symversions = \ rm -f $@.symversions \ $(foreach n, $(filter-out FORCE,$^), \ - $(if $(wildcard $(n).symversions), \ + $(if $(shell test -s $(n).symversions && echo y), \ ; cat $(n).symversions >> $@.symversions)) else cmd_update_lto_symversions = echo >/dev/null From 5e60f363b38fd40e4d8838b5d6f4d4ecee92c777 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 15 Jul 2021 11:26:02 +0200 Subject: [PATCH 0576/1469] Documentation: Fix intiramfs script name Documentation was not changed when renaming the script in commit 80e715a06c2d ("initramfs: rename gen_initramfs_list.sh to gen_initramfs.sh"). Fixing this. Basically does: $ sed -i -e s/gen_initramfs_list.sh/gen_initramfs.sh/g $(git grep -l gen_initramfs_list.sh) Fixes: 80e715a06c2d ("initramfs: rename gen_initramfs_list.sh to gen_initramfs.sh") Signed-off-by: Robert Richter Signed-off-by: Masahiro Yamada --- .../early-userspace/early_userspace_support.rst | 8 ++++---- Documentation/filesystems/ramfs-rootfs-initramfs.rst | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/driver-api/early-userspace/early_userspace_support.rst b/Documentation/driver-api/early-userspace/early_userspace_support.rst index 8a58c61932ff..61bdeac1bae5 100644 --- a/Documentation/driver-api/early-userspace/early_userspace_support.rst +++ b/Documentation/driver-api/early-userspace/early_userspace_support.rst @@ -69,17 +69,17 @@ early userspace image can be built by an unprivileged user. As a technical note, when directories and files are specified, the entire CONFIG_INITRAMFS_SOURCE is passed to -usr/gen_initramfs_list.sh. This means that CONFIG_INITRAMFS_SOURCE +usr/gen_initramfs.sh. This means that CONFIG_INITRAMFS_SOURCE can really be interpreted as any legal argument to -gen_initramfs_list.sh. If a directory is specified as an argument then +gen_initramfs.sh. If a directory is specified as an argument then the contents are scanned, uid/gid translation is performed, and usr/gen_init_cpio file directives are output. If a directory is -specified as an argument to usr/gen_initramfs_list.sh then the +specified as an argument to usr/gen_initramfs.sh then the contents of the file are simply copied to the output. All of the output directives from directory scanning and file contents copying are processed by usr/gen_init_cpio. -See also 'usr/gen_initramfs_list.sh -h'. +See also 'usr/gen_initramfs.sh -h'. Where's this all leading? ========================= diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 4598b0d90b60..164960631925 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -170,7 +170,7 @@ Documentation/driver-api/early-userspace/early_userspace_support.rst for more de The kernel does not depend on external cpio tools. If you specify a directory instead of a configuration file, the kernel's build infrastructure creates a configuration file from that directory (usr/Makefile calls -usr/gen_initramfs_list.sh), and proceeds to package up that directory +usr/gen_initramfs.sh), and proceeds to package up that directory using the config file (by feeding it to usr/gen_init_cpio, which is created from usr/gen_init_cpio.c). The kernel's build-time cpio creation code is entirely self-contained, and the kernel's boot-time extractor is also From a17ad0961706244dce48ec941f7e476a38c0e727 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 15 Jul 2021 16:59:00 -0700 Subject: [PATCH 0577/1469] net: Fix zero-copy head len calculation. In some cases skb head could be locked and entire header data is pulled from skb. When skb_zerocopy() called in such cases, following BUG is triggered. This patch fixes it by copying entire skb in such cases. This could be optimized incase this is performance bottleneck. ---8<--- kernel BUG at net/core/skbuff.c:2961! invalid opcode: 0000 [#1] SMP PTI CPU: 2 PID: 0 Comm: swapper/2 Tainted: G OE 5.4.0-77-generic #86-Ubuntu Hardware name: OpenStack Foundation OpenStack Nova, BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:skb_zerocopy+0x37a/0x3a0 RSP: 0018:ffffbcc70013ca38 EFLAGS: 00010246 Call Trace: queue_userspace_packet+0x2af/0x5e0 [openvswitch] ovs_dp_upcall+0x3d/0x60 [openvswitch] ovs_dp_process_packet+0x125/0x150 [openvswitch] ovs_vport_receive+0x77/0xd0 [openvswitch] netdev_port_receive+0x87/0x130 [openvswitch] netdev_frame_hook+0x4b/0x60 [openvswitch] __netif_receive_skb_core+0x2b4/0xc90 __netif_receive_skb_one_core+0x3f/0xa0 __netif_receive_skb+0x18/0x60 process_backlog+0xa9/0x160 net_rx_action+0x142/0x390 __do_softirq+0xe1/0x2d6 irq_exit+0xae/0xb0 do_IRQ+0x5a/0xf0 common_interrupt+0xf/0xf Code that triggered BUG: int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/core/skbuff.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0fe97d660790..fc7942c0dddc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3022,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from) if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); + if (!hlen) + hlen = from->len; + } if (skb_has_frag_list(from)) hlen = from->len; From f5051bcece50140abd1a11a2d36dc3ec5484fc32 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Sat, 17 Jul 2021 14:29:33 +0300 Subject: [PATCH 0578/1469] net: sched: fix memory leak in tcindex_partial_destroy_work Syzbot reported memory leak in tcindex_set_parms(). The problem was in non-freed perfect hash in tcindex_partial_destroy_work(). In tcindex_set_parms() new tcindex_data is allocated and some fields from old one are copied to new one, but not the perfect hash. Since tcindex_partial_destroy_work() is the destroy function for old tcindex_data, we need to free perfect hash to avoid memory leak. Reported-and-tested-by: syzbot+f0bbb2287b8993d4fa74@syzkaller.appspotmail.com Fixes: 331b72922c5f ("net: sched: RCU cls_tcindex") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- net/sched/cls_tcindex.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 5b274534264c..e9a8a2c86bbd 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r, TCA_TCINDEX_POLICE); } +static void tcindex_free_perfect_hash(struct tcindex_data *cp); + static void tcindex_partial_destroy_work(struct work_struct *work) { struct tcindex_data *p = container_of(to_rcu_work(work), @@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work) rwork); rtnl_lock(); - kfree(p->perfect); + if (p->perfect) + tcindex_free_perfect_hash(p); kfree(p); rtnl_unlock(); } From 2f3fdd8d4805015fa964807e1c7f3d88f31bd389 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 17 Jul 2021 17:19:19 -0400 Subject: [PATCH 0579/1469] sctp: trim optlen when it's a huge value in sctp_setsockopt After commit ca84bd058dae ("sctp: copy the optval from user space in sctp_setsockopt"), it does memory allocation in sctp_setsockopt with the optlen, and it would fail the allocation and return error if the optlen from user space is a huge value. This breaks some sockopts, like SCTP_HMAC_IDENT, SCTP_RESET_STREAMS and SCTP_AUTH_KEY, as when processing these sockopts before, optlen would be trimmed to a biggest value it needs when optlen is a huge value, instead of failing the allocation and returning error. This patch is to fix the allocation failure when it's a huge optlen from user space by trimming it to the biggest size sctp sockopt may need when necessary, and this biggest size is from sctp_setsockopt_reset_streams() for SCTP_RESET_STREAMS, which is bigger than those for SCTP_HMAC_IDENT and SCTP_AUTH_KEY. Fixes: ca84bd058dae ("sctp: copy the optval from user space in sctp_setsockopt") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/socket.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e64e01f61b11..6b937bfd4751 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, } if (optlen > 0) { + /* Trim it to the biggest size sctp sockopt may need if necessary */ + optlen = min_t(unsigned int, optlen, + PAGE_ALIGN(USHRT_MAX + + sizeof(__u16) * sizeof(struct sctp_reset_streams))); kopt = memdup_sockptr(optval, optlen); if (IS_ERR(kopt)) return PTR_ERR(kopt); From 517a16b1a88bdb6b530f48d5d153478b2552d9a8 Mon Sep 17 00:00:00 2001 From: Nguyen Dinh Phi Date: Sun, 18 Jul 2021 22:40:13 +0800 Subject: [PATCH 0580/1469] netrom: Decrease sock refcount when sock timers expire Commit 63346650c1a9 ("netrom: switch to sock timer API") switched to use sock timer API. It replaces mod_timer() by sk_reset_timer(), and del_timer() by sk_stop_timer(). Function sk_reset_timer() will increase the refcount of sock if it is called on an inactive timer, hence, in case the timer expires, we need to decrease the refcount ourselves in the handler, otherwise, the sock refcount will be unbalanced and the sock will never be freed. Signed-off-by: Nguyen Dinh Phi Reported-by: syzbot+10f1194569953b72f1ae@syzkaller.appspotmail.com Fixes: 63346650c1a9 ("netrom: switch to sock timer API") Signed-off-by: David S. Miller --- net/netrom/nr_timer.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 9115f8a7dd45..a8da88db7893 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); - sock_put(sk); - return; + goto out; } break; @@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) nr_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } static void nr_t2timer_expiry(struct timer_list *t) @@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t) nr_enquiry_response(sk); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t4timer_expiry(struct timer_list *t) @@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t) bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); + sock_put(sk); } static void nr_idletimer_expiry(struct timer_list *t) @@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t1timer_expiry(struct timer_list *t) @@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); @@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); @@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_requeue_frames(sk); @@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t) } nr_start_t1timer(sk); +out: bh_unlock_sock(sk); + sock_put(sk); } From 2734d6c1b1a089fb593ef6a23d4b70903526fe0c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 18 Jul 2021 14:13:49 -0700 Subject: [PATCH 0581/1469] Linux 5.14-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 0517005d65fa..e4f5895badb5 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Opossums on Parade # *DOCUMENTATION* From e746f3451ec7f91dcc9fd67a631239c715850a34 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 30 Jun 2021 19:25:59 -0500 Subject: [PATCH 0582/1469] scsi: iscsi: Fix iface sysfs attr detection A ISCSI_IFACE_PARAM can have the same value as a ISCSI_NET_PARAM so when iscsi_iface_attr_is_visible tries to figure out the type by just checking the value, we can collide and return the wrong type. When we call into the driver we might not match and return that we don't want attr visible in sysfs. The patch fixes this by setting the type when we figure out what the param is. Link: https://lore.kernel.org/r/20210701002559.89533-1-michael.christie@oracle.com Fixes: 3e0f65b34cc9 ("[SCSI] iscsi_transport: Additional parameters for network settings") Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 90 +++++++++++------------------ 1 file changed, 34 insertions(+), 56 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index b07105ae7c91..d8b05d8b5470 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -439,39 +439,10 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj, struct device *dev = container_of(kobj, struct device, kobj); struct iscsi_iface *iface = iscsi_dev_to_iface(dev); struct iscsi_transport *t = iface->transport; - int param; - int param_type; + int param = -1; if (attr == &dev_attr_iface_enabled.attr) param = ISCSI_NET_PARAM_IFACE_ENABLE; - else if (attr == &dev_attr_iface_vlan_id.attr) - param = ISCSI_NET_PARAM_VLAN_ID; - else if (attr == &dev_attr_iface_vlan_priority.attr) - param = ISCSI_NET_PARAM_VLAN_PRIORITY; - else if (attr == &dev_attr_iface_vlan_enabled.attr) - param = ISCSI_NET_PARAM_VLAN_ENABLED; - else if (attr == &dev_attr_iface_mtu.attr) - param = ISCSI_NET_PARAM_MTU; - else if (attr == &dev_attr_iface_port.attr) - param = ISCSI_NET_PARAM_PORT; - else if (attr == &dev_attr_iface_ipaddress_state.attr) - param = ISCSI_NET_PARAM_IPADDR_STATE; - else if (attr == &dev_attr_iface_delayed_ack_en.attr) - param = ISCSI_NET_PARAM_DELAYED_ACK_EN; - else if (attr == &dev_attr_iface_tcp_nagle_disable.attr) - param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE; - else if (attr == &dev_attr_iface_tcp_wsf_disable.attr) - param = ISCSI_NET_PARAM_TCP_WSF_DISABLE; - else if (attr == &dev_attr_iface_tcp_wsf.attr) - param = ISCSI_NET_PARAM_TCP_WSF; - else if (attr == &dev_attr_iface_tcp_timer_scale.attr) - param = ISCSI_NET_PARAM_TCP_TIMER_SCALE; - else if (attr == &dev_attr_iface_tcp_timestamp_en.attr) - param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN; - else if (attr == &dev_attr_iface_cache_id.attr) - param = ISCSI_NET_PARAM_CACHE_ID; - else if (attr == &dev_attr_iface_redirect_en.attr) - param = ISCSI_NET_PARAM_REDIRECT_EN; else if (attr == &dev_attr_iface_def_taskmgmt_tmo.attr) param = ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO; else if (attr == &dev_attr_iface_header_digest.attr) @@ -508,6 +479,38 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj, param = ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN; else if (attr == &dev_attr_iface_initiator_name.attr) param = ISCSI_IFACE_PARAM_INITIATOR_NAME; + + if (param != -1) + return t->attr_is_visible(ISCSI_IFACE_PARAM, param); + + if (attr == &dev_attr_iface_vlan_id.attr) + param = ISCSI_NET_PARAM_VLAN_ID; + else if (attr == &dev_attr_iface_vlan_priority.attr) + param = ISCSI_NET_PARAM_VLAN_PRIORITY; + else if (attr == &dev_attr_iface_vlan_enabled.attr) + param = ISCSI_NET_PARAM_VLAN_ENABLED; + else if (attr == &dev_attr_iface_mtu.attr) + param = ISCSI_NET_PARAM_MTU; + else if (attr == &dev_attr_iface_port.attr) + param = ISCSI_NET_PARAM_PORT; + else if (attr == &dev_attr_iface_ipaddress_state.attr) + param = ISCSI_NET_PARAM_IPADDR_STATE; + else if (attr == &dev_attr_iface_delayed_ack_en.attr) + param = ISCSI_NET_PARAM_DELAYED_ACK_EN; + else if (attr == &dev_attr_iface_tcp_nagle_disable.attr) + param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE; + else if (attr == &dev_attr_iface_tcp_wsf_disable.attr) + param = ISCSI_NET_PARAM_TCP_WSF_DISABLE; + else if (attr == &dev_attr_iface_tcp_wsf.attr) + param = ISCSI_NET_PARAM_TCP_WSF; + else if (attr == &dev_attr_iface_tcp_timer_scale.attr) + param = ISCSI_NET_PARAM_TCP_TIMER_SCALE; + else if (attr == &dev_attr_iface_tcp_timestamp_en.attr) + param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN; + else if (attr == &dev_attr_iface_cache_id.attr) + param = ISCSI_NET_PARAM_CACHE_ID; + else if (attr == &dev_attr_iface_redirect_en.attr) + param = ISCSI_NET_PARAM_REDIRECT_EN; else if (iface->iface_type == ISCSI_IFACE_TYPE_IPV4) { if (attr == &dev_attr_ipv4_iface_ipaddress.attr) param = ISCSI_NET_PARAM_IPV4_ADDR; @@ -598,32 +601,7 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj, return 0; } - switch (param) { - case ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO: - case ISCSI_IFACE_PARAM_HDRDGST_EN: - case ISCSI_IFACE_PARAM_DATADGST_EN: - case ISCSI_IFACE_PARAM_IMM_DATA_EN: - case ISCSI_IFACE_PARAM_INITIAL_R2T_EN: - case ISCSI_IFACE_PARAM_DATASEQ_INORDER_EN: - case ISCSI_IFACE_PARAM_PDU_INORDER_EN: - case ISCSI_IFACE_PARAM_ERL: - case ISCSI_IFACE_PARAM_MAX_RECV_DLENGTH: - case ISCSI_IFACE_PARAM_FIRST_BURST: - case ISCSI_IFACE_PARAM_MAX_R2T: - case ISCSI_IFACE_PARAM_MAX_BURST: - case ISCSI_IFACE_PARAM_CHAP_AUTH_EN: - case ISCSI_IFACE_PARAM_BIDI_CHAP_EN: - case ISCSI_IFACE_PARAM_DISCOVERY_AUTH_OPTIONAL: - case ISCSI_IFACE_PARAM_DISCOVERY_LOGOUT_EN: - case ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN: - case ISCSI_IFACE_PARAM_INITIATOR_NAME: - param_type = ISCSI_IFACE_PARAM; - break; - default: - param_type = ISCSI_NET_PARAM; - } - - return t->attr_is_visible(param_type, param); + return t->attr_is_visible(ISCSI_NET_PARAM, param); } static struct attribute *iscsi_iface_attrs[] = { From 6d8e7e7c932162bccd06872362751b0e1d76f5af Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Fri, 2 Jul 2021 12:16:55 +0300 Subject: [PATCH 0583/1469] scsi: target: Fix protect handling in WRITE SAME(32) WRITE SAME(32) command handling reads WRPROTECT at the wrong offset in 1st byte instead of 10th byte. Link: https://lore.kernel.org/r/20210702091655.22818-1-d.bogdanov@yadro.com Fixes: afd73f1b60fc ("target: Perform PROTECT sanity checks for WRITE_SAME") Signed-off-by: Dmitry Bogdanov Signed-off-by: Martin K. Petersen --- drivers/target/target_core_sbc.c | 35 ++++++++++++++++---------------- 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index b32f4ee88e79..ca1b2312d6e7 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -25,7 +25,7 @@ #include "target_core_alua.h" static sense_reason_t -sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char *, u32, bool); +sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char, u32, bool); static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd); static sense_reason_t @@ -279,14 +279,14 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) } static sense_reason_t -sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops) +sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *ops) { struct se_device *dev = cmd->se_dev; sector_t end_lba = dev->transport->get_blocks(dev) + 1; unsigned int sectors = sbc_get_write_same_sectors(cmd); sense_reason_t ret; - if ((flags[0] & 0x04) || (flags[0] & 0x02)) { + if ((flags & 0x04) || (flags & 0x02)) { pr_err("WRITE_SAME PBDATA and LBDATA" " bits not supported for Block Discard" " Emulation\n"); @@ -308,7 +308,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o } /* We always have ANC_SUP == 0 so setting ANCHOR is always an error */ - if (flags[0] & 0x10) { + if (flags & 0x10) { pr_warn("WRITE SAME with ANCHOR not supported\n"); return TCM_INVALID_CDB_FIELD; } @@ -316,7 +316,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting * translated into block discard requests within backend code. */ - if (flags[0] & 0x08) { + if (flags & 0x08) { if (!ops->execute_unmap) return TCM_UNSUPPORTED_SCSI_OPCODE; @@ -331,7 +331,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o if (!ops->execute_write_same) return TCM_UNSUPPORTED_SCSI_OPCODE; - ret = sbc_check_prot(dev, cmd, &cmd->t_task_cdb[0], sectors, true); + ret = sbc_check_prot(dev, cmd, flags >> 5, sectors, true); if (ret) return ret; @@ -717,10 +717,9 @@ sbc_set_prot_op_checks(u8 protect, bool fabric_prot, enum target_prot_type prot_ } static sense_reason_t -sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, +sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char protect, u32 sectors, bool is_write) { - u8 protect = cdb[1] >> 5; int sp_ops = cmd->se_sess->sup_prot_ops; int pi_prot_type = dev->dev_attrib.pi_prot_type; bool fabric_prot = false; @@ -768,7 +767,7 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, fallthrough; default: pr_err("Unable to determine pi_prot_type for CDB: 0x%02x " - "PROTECT: 0x%02x\n", cdb[0], protect); + "PROTECT: 0x%02x\n", cmd->t_task_cdb[0], protect); return TCM_INVALID_CDB_FIELD; } @@ -843,7 +842,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret; @@ -857,7 +856,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret; @@ -871,7 +870,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret; @@ -892,7 +891,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret; @@ -906,7 +905,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret; @@ -921,7 +920,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD; - ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret; @@ -980,7 +979,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) size = sbc_get_size(cmd, 1); cmd->t_task_lba = get_unaligned_be64(&cdb[12]); - ret = sbc_setup_write_same(cmd, &cdb[10], ops); + ret = sbc_setup_write_same(cmd, cdb[10], ops); if (ret) return ret; break; @@ -1079,7 +1078,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) size = sbc_get_size(cmd, 1); cmd->t_task_lba = get_unaligned_be64(&cdb[2]); - ret = sbc_setup_write_same(cmd, &cdb[1], ops); + ret = sbc_setup_write_same(cmd, cdb[1], ops); if (ret) return ret; break; @@ -1097,7 +1096,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) * Follow sbcr26 with WRITE_SAME (10) and check for the existence * of byte 1 bit 3 UNMAP instead of original reserved field */ - ret = sbc_setup_write_same(cmd, &cdb[1], ops); + ret = sbc_setup_write_same(cmd, cdb[1], ops); if (ret) return ret; break; From a3a9ee4b5254f212c2adaa8cd8ca03bfa112f49d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 9 Jun 2021 19:25:56 +0200 Subject: [PATCH 0584/1469] drm/nouveau: init the base GEM fields for internal BOs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TTMs buffer objects are based on GEM objects for quite a while and rely on initializing those fields before initializing the TTM BO. Nouveau now doesn't init the GEM object for internally allocated BOs, so make sure that we at least initialize some necessary fields. Signed-off-by: Christian König Tested-by: Mikko Perttunen Reviewed-by: Matthew Auld Reviewed-by: Huang Rui Link: https://patchwork.freedesktop.org/patch/msgid/20210609172902.1937-1-christian.koenig@amd.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 4f3a5357dd56..6d07e653f82d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -149,6 +149,8 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo) */ if (bo->base.dev) drm_gem_object_release(&bo->base); + else + dma_resv_fini(&bo->base._resv); kfree(nvbo); } @@ -330,6 +332,10 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, if (IS_ERR(nvbo)) return PTR_ERR(nvbo); + nvbo->bo.base.size = size; + dma_resv_init(&nvbo->bo.base._resv); + drm_vma_node_reset(&nvbo->bo.base.vma_node); + ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj); if (ret) return ret; From e4efa82660e6d80338c554e45e903714e1b2c27b Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Mon, 19 Jul 2021 11:02:31 +0800 Subject: [PATCH 0585/1469] ALSA: hda/realtek: Fix pop noise and 2 Front Mic issues on a machine This is a Lenovo ThinkStation machine which uses the codec alc623. There are 2 issues on this machine, the 1st one is the pop noise in the lineout, the 2nd one is there are 2 Front Mics and pulseaudio can't handle them, After applying the fixup of ALC623_FIXUP_LENOVO_THINKSTATION_P340 to this machine, the 2 issues are fixed. Cc: Signed-off-by: Hui Wang Link: https://lore.kernel.org/r/20210719030231.6870-1-hui.wang@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1389cfd5e0db..caaf0e8aac11 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8626,6 +8626,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), From 7c9ff3deeee61b253715dcf968a6307af148c9b2 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 16 Jul 2021 11:21:13 -0700 Subject: [PATCH 0586/1469] Drivers: hv: vmbus: Fix duplicate CPU assignments within a device The vmbus module uses a rotational algorithm to assign target CPUs to a device's channels. Depending on the timing of different device's channel offers, different channels of a device may be assigned to the same CPU. For example on a VM with 2 CPUs, if NIC A and B's channels are offered in the following order, NIC A will have both channels on CPU0, and NIC B will have both channels on CPU1 -- see below. This kind of assignment causes RSS load that is spreading across different channels to end up on the same CPU. Timing of channel offers: NIC A channel 0 NIC B channel 0 NIC A channel 1 NIC B channel 1 VMBUS ID 14: Class_ID = {f8615163-df3e-46c5-913f-f2d2f965ed0e} - Synthetic network adapter Device_ID = {cab064cd-1f31-47d5-a8b4-9d57e320cccd} Sysfs path: /sys/bus/vmbus/devices/cab064cd-1f31-47d5-a8b4-9d57e320cccd Rel_ID=14, target_cpu=0 Rel_ID=17, target_cpu=0 VMBUS ID 16: Class_ID = {f8615163-df3e-46c5-913f-f2d2f965ed0e} - Synthetic network adapter Device_ID = {244225ca-743e-4020-a17d-d7baa13d6cea} Sysfs path: /sys/bus/vmbus/devices/244225ca-743e-4020-a17d-d7baa13d6cea Rel_ID=16, target_cpu=1 Rel_ID=18, target_cpu=1 Update the vmbus CPU assignment algorithm to avoid duplicate CPU assignments within a device. The new algorithm iterates num_online_cpus + 1 times. The existing rotational algorithm to find "next NUMA & CPU" is still here. But if the resulting CPU is already used by the same device, it will try the next CPU. In the last iteration, it assigns the channel to the next available CPU like the existing algorithm. This is not normally expected, because during device probe, we limit the number of channels of a device to be <= number of online CPUs. Signed-off-by: Haiyang Zhang Reviewed-by: Michael Kelley Tested-by: Michael Kelley Link: https://lore.kernel.org/r/1626459673-17420-1-git-send-email-haiyangz@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/channel_mgmt.c | 100 +++++++++++++++++++++++++------------- 1 file changed, 66 insertions(+), 34 deletions(-) diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index caf6d0c4bc1b..142308526ec6 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -605,6 +605,17 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) */ mutex_lock(&vmbus_connection.channel_mutex); + list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { + if (guid_equal(&channel->offermsg.offer.if_type, + &newchannel->offermsg.offer.if_type) && + guid_equal(&channel->offermsg.offer.if_instance, + &newchannel->offermsg.offer.if_instance)) { + fnew = false; + newchannel->primary_channel = channel; + break; + } + } + init_vp_index(newchannel); /* Remember the channels that should be cleaned up upon suspend. */ @@ -617,16 +628,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) */ atomic_dec(&vmbus_connection.offer_in_progress); - list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { - if (guid_equal(&channel->offermsg.offer.if_type, - &newchannel->offermsg.offer.if_type) && - guid_equal(&channel->offermsg.offer.if_instance, - &newchannel->offermsg.offer.if_instance)) { - fnew = false; - break; - } - } - if (fnew) { list_add_tail(&newchannel->listentry, &vmbus_connection.chn_list); @@ -647,7 +648,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) /* * Process the sub-channel. */ - newchannel->primary_channel = channel; list_add_tail(&newchannel->sc_list, &channel->sc_list); } @@ -683,6 +683,30 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) queue_work(wq, &newchannel->add_channel_work); } +/* + * Check if CPUs used by other channels of the same device. + * It should only be called by init_vp_index(). + */ +static bool hv_cpuself_used(u32 cpu, struct vmbus_channel *chn) +{ + struct vmbus_channel *primary = chn->primary_channel; + struct vmbus_channel *sc; + + lockdep_assert_held(&vmbus_connection.channel_mutex); + + if (!primary) + return false; + + if (primary->target_cpu == cpu) + return true; + + list_for_each_entry(sc, &primary->sc_list, sc_list) + if (sc != chn && sc->target_cpu == cpu) + return true; + + return false; +} + /* * We use this state to statically distribute the channel interrupt load. */ @@ -702,6 +726,7 @@ static int next_numa_node_id; static void init_vp_index(struct vmbus_channel *channel) { bool perf_chn = hv_is_perf_channel(channel); + u32 i, ncpu = num_online_cpus(); cpumask_var_t available_mask; struct cpumask *alloced_mask; u32 target_cpu; @@ -724,31 +749,38 @@ static void init_vp_index(struct vmbus_channel *channel) return; } - while (true) { - numa_node = next_numa_node_id++; - if (numa_node == nr_node_ids) { - next_numa_node_id = 0; - continue; + for (i = 1; i <= ncpu + 1; i++) { + while (true) { + numa_node = next_numa_node_id++; + if (numa_node == nr_node_ids) { + next_numa_node_id = 0; + continue; + } + if (cpumask_empty(cpumask_of_node(numa_node))) + continue; + break; } - if (cpumask_empty(cpumask_of_node(numa_node))) - continue; - break; + alloced_mask = &hv_context.hv_numa_map[numa_node]; + + if (cpumask_weight(alloced_mask) == + cpumask_weight(cpumask_of_node(numa_node))) { + /* + * We have cycled through all the CPUs in the node; + * reset the alloced map. + */ + cpumask_clear(alloced_mask); + } + + cpumask_xor(available_mask, alloced_mask, + cpumask_of_node(numa_node)); + + target_cpu = cpumask_first(available_mask); + cpumask_set_cpu(target_cpu, alloced_mask); + + if (channel->offermsg.offer.sub_channel_index >= ncpu || + i > ncpu || !hv_cpuself_used(target_cpu, channel)) + break; } - alloced_mask = &hv_context.hv_numa_map[numa_node]; - - if (cpumask_weight(alloced_mask) == - cpumask_weight(cpumask_of_node(numa_node))) { - /* - * We have cycled through all the CPUs in the node; - * reset the alloced map. - */ - cpumask_clear(alloced_mask); - } - - cpumask_xor(available_mask, alloced_mask, cpumask_of_node(numa_node)); - - target_cpu = cpumask_first(available_mask); - cpumask_set_cpu(target_cpu, alloced_mask); channel->target_cpu = target_cpu; From 21ed49265986931b8921a2404394426870245bd2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 12 Jul 2021 09:40:22 +0200 Subject: [PATCH 0587/1469] m68k: MAC should select HAVE_PATA_PLATFORM The defconfigs switched Mac from the deprecated CONFIG_BLK_DEV_PLATFORM to CONFIG_PATA_PLATFORM. However, the latter depends on CONFIG_HAVE_PATA_PLATFORM, which thus must be selected first. Fixes: b90257bfddbd01f3 ("m68k: use libata instead of the legacy ide driver") Signed-off-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210712074022.2116655-1-geert@linux-m68k.org --- arch/m68k/Kconfig.machine | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index d964c1f27399..6a07a6817885 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -33,6 +33,7 @@ config MAC depends on MMU select MMU_MOTOROLA if MMU select HAVE_ARCH_NVRAM_OPS + select HAVE_PATA_PLATFORM select LEGACY_TIMER_TICK help This option enables support for the Apple Macintosh series of From 78d2a05ef22e7b5863b01e073dd6a06b3979bb00 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Sat, 17 Jul 2021 15:28:18 +0300 Subject: [PATCH 0588/1469] ASoC: ti: j721e-evm: Fix unbalanced domain activity tracking during startup In case of an error within j721e_audio_startup() the domain->active must be decremented to avoid unbalanced counter. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210717122820.1467-2-peter.ujfalusi@gmail.com Signed-off-by: Mark Brown --- sound/soc/ti/j721e-evm.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/sound/soc/ti/j721e-evm.c b/sound/soc/ti/j721e-evm.c index a7c0484d44ec..017c4ad11ca6 100644 --- a/sound/soc/ti/j721e-evm.c +++ b/sound/soc/ti/j721e-evm.c @@ -278,23 +278,29 @@ static int j721e_audio_startup(struct snd_pcm_substream *substream) j721e_rule_rate, &priv->rate_range, SNDRV_PCM_HW_PARAM_RATE, -1); - mutex_unlock(&priv->mutex); if (ret) - return ret; + goto out; /* Reset TDM slots to 32 */ ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0x3, 0x3, 2, 32); if (ret && ret != -ENOTSUPP) - return ret; + goto out; for_each_rtd_codec_dais(rtd, i, codec_dai) { ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x3, 0x3, 2, 32); if (ret && ret != -ENOTSUPP) - return ret; + goto out; } - return 0; + if (ret == -ENOTSUPP) + ret = 0; +out: + if (ret) + domain->active--; + mutex_unlock(&priv->mutex); + + return ret; } static int j721e_audio_hw_params(struct snd_pcm_substream *substream, From 82d28b67f780910f816fe1cfb0f676fc38c4cbb3 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Sat, 17 Jul 2021 15:28:19 +0300 Subject: [PATCH 0589/1469] ASoC: ti: j721e-evm: Check for not initialized parent_clk_id During probe the parent_clk_id is set to -1 which should not be used to array index within hsdiv_rates[]. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210717122820.1467-3-peter.ujfalusi@gmail.com Signed-off-by: Mark Brown --- sound/soc/ti/j721e-evm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/ti/j721e-evm.c b/sound/soc/ti/j721e-evm.c index 017c4ad11ca6..265bbc5a2f96 100644 --- a/sound/soc/ti/j721e-evm.c +++ b/sound/soc/ti/j721e-evm.c @@ -197,7 +197,7 @@ static int j721e_configure_refclk(struct j721e_priv *priv, return ret; } - if (priv->hsdiv_rates[domain->parent_clk_id] != scki) { + if (domain->parent_clk_id == -1 || priv->hsdiv_rates[domain->parent_clk_id] != scki) { dev_dbg(priv->dev, "%s configuration for %u Hz: %s, %dxFS (SCKI: %u Hz)\n", audio_domain == J721E_AUDIO_DOMAIN_CPB ? "CPB" : "IVI", From 56912da7a68c8356df6a6740476237441b0b792a Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 16 Jul 2021 20:21:33 +0200 Subject: [PATCH 0590/1469] spi: cadence: Correct initialisation of runtime PM again The original implementation of RPM handling in probe() was mostly correct, except it failed to call pm_runtime_get_*() to activate the hardware. The subsequent fix, 734882a8bf98 ("spi: cadence: Correct initialisation of runtime PM"), breaks the implementation further, to the point where the system using this hard IP on ZynqMP hangs on boot, because it accesses hardware which is gated off. Undo 734882a8bf98 ("spi: cadence: Correct initialisation of runtime PM") and instead add missing pm_runtime_get_noresume() and move the RPM disabling all the way to the end of probe(). That makes ZynqMP not hang on boot yet again. Fixes: 734882a8bf98 ("spi: cadence: Correct initialisation of runtime PM") Signed-off-by: Marek Vasut Cc: Charles Keepax Cc: Mark Brown Link: https://lore.kernel.org/r/20210716182133.218640-1-marex@denx.de Signed-off-by: Mark Brown --- drivers/spi/spi-cadence.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index a3afd1b9ac56..ceb16e70d235 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -517,6 +517,12 @@ static int cdns_spi_probe(struct platform_device *pdev) goto clk_dis_apb; } + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT); + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + ret = of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs); if (ret < 0) master->num_chipselect = CDNS_SPI_DEFAULT_NUM_CS; @@ -531,11 +537,6 @@ static int cdns_spi_probe(struct platform_device *pdev) /* SPI controller initializations */ cdns_spi_init_hw(xspi); - pm_runtime_set_active(&pdev->dev); - pm_runtime_enable(&pdev->dev); - pm_runtime_use_autosuspend(&pdev->dev); - pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT); - irq = platform_get_irq(pdev, 0); if (irq <= 0) { ret = -ENXIO; @@ -566,6 +567,9 @@ static int cdns_spi_probe(struct platform_device *pdev) master->bits_per_word_mask = SPI_BPW_MASK(8); + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); + ret = spi_register_master(master); if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); From c9d9fdbc108af8915d3f497bbdf3898bf8f321b8 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 14 Jul 2021 14:34:15 -0500 Subject: [PATCH 0591/1469] drm/i915: Revert "drm/i915/gem: Asynchronous cmdparser" This reverts 686c7c35abc2 ("drm/i915/gem: Asynchronous cmdparser"). The justification for this commit in the git history was a vague comment about getting it out from under the struct_mutex. While this may improve perf for some workloads on Gen7 platforms where we rely on the command parser for features such as indirect rendering, no numbers were provided to prove such an improvement. It claims to closed two gitlab/bugzilla issues but with no explanation whatsoever as to why or what bug it's fixing. Meanwhile, by moving command parsing off to an async callback, it leaves us with a problem of what to do on error. When things were synchronous, EXECBUFFER2 would fail with an error code if parsing failed. When moving it to async, we needed another way to handle that error and the solution employed was to set an error on the dma_fence and then trust that said error gets propagated to the client eventually. Moving back to synchronous will help us untangle the fence error propagation mess. This also reverts most of 0edbb9ba1bfe ("drm/i915: Move cmd parser pinning to execbuffer") which is a refactor of some of our allocation paths for asynchronous parsing. Now that everything is synchronous, we don't need it. v2 (Daniel Vetter): - Add stabel Cc and Fixes tag Signed-off-by: Jason Ekstrand Cc: # v5.6+ Fixes: 9e31c1fe45d5 ("drm/i915: Propagate errors on awaiting already signaled fences") Cc: Maarten Lankhorst Reviewed-by: Jon Bloomfield Acked-by: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210714193419.1459723-2-jason@jlekstrand.net (cherry picked from commit 93b713304188844b8514074dc13ffd56d12235d3) Signed-off-by: Rodrigo Vivi --- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 227 +----------------- .../i915/gem/selftests/i915_gem_execbuffer.c | 4 + drivers/gpu/drm/i915/i915_cmd_parser.c | 126 +++++----- drivers/gpu/drm/i915/i915_drv.h | 7 +- 4 files changed, 88 insertions(+), 276 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index a8abc9af5ff4..4a6419d7be93 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -25,10 +25,8 @@ #include "i915_gem_clflush.h" #include "i915_gem_context.h" #include "i915_gem_ioctls.h" -#include "i915_sw_fence_work.h" #include "i915_trace.h" #include "i915_user_extensions.h" -#include "i915_memcpy.h" struct eb_vma { struct i915_vma *vma; @@ -1456,6 +1454,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, int err; struct intel_engine_cs *engine = eb->engine; + /* If we need to copy for the cmdparser, we will stall anyway */ + if (eb_use_cmdparser(eb)) + return ERR_PTR(-EWOULDBLOCK); + if (!reloc_can_use_engine(engine)) { engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0]; if (!engine) @@ -2372,217 +2374,6 @@ shadow_batch_pin(struct i915_execbuffer *eb, return vma; } -struct eb_parse_work { - struct dma_fence_work base; - struct intel_engine_cs *engine; - struct i915_vma *batch; - struct i915_vma *shadow; - struct i915_vma *trampoline; - unsigned long batch_offset; - unsigned long batch_length; - unsigned long *jump_whitelist; - const void *batch_map; - void *shadow_map; -}; - -static int __eb_parse(struct dma_fence_work *work) -{ - struct eb_parse_work *pw = container_of(work, typeof(*pw), base); - int ret; - bool cookie; - - cookie = dma_fence_begin_signalling(); - ret = intel_engine_cmd_parser(pw->engine, - pw->batch, - pw->batch_offset, - pw->batch_length, - pw->shadow, - pw->jump_whitelist, - pw->shadow_map, - pw->batch_map); - dma_fence_end_signalling(cookie); - - return ret; -} - -static void __eb_parse_release(struct dma_fence_work *work) -{ - struct eb_parse_work *pw = container_of(work, typeof(*pw), base); - - if (!IS_ERR_OR_NULL(pw->jump_whitelist)) - kfree(pw->jump_whitelist); - - if (pw->batch_map) - i915_gem_object_unpin_map(pw->batch->obj); - else - i915_gem_object_unpin_pages(pw->batch->obj); - - i915_gem_object_unpin_map(pw->shadow->obj); - - if (pw->trampoline) - i915_active_release(&pw->trampoline->active); - i915_active_release(&pw->shadow->active); - i915_active_release(&pw->batch->active); -} - -static const struct dma_fence_work_ops eb_parse_ops = { - .name = "eb_parse", - .work = __eb_parse, - .release = __eb_parse_release, -}; - -static inline int -__parser_mark_active(struct i915_vma *vma, - struct intel_timeline *tl, - struct dma_fence *fence) -{ - struct intel_gt_buffer_pool_node *node = vma->private; - - return i915_active_ref(&node->active, tl->fence_context, fence); -} - -static int -parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl) -{ - int err; - - mutex_lock(&tl->mutex); - - err = __parser_mark_active(pw->shadow, tl, &pw->base.dma); - if (err) - goto unlock; - - if (pw->trampoline) { - err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma); - if (err) - goto unlock; - } - -unlock: - mutex_unlock(&tl->mutex); - return err; -} - -static int eb_parse_pipeline(struct i915_execbuffer *eb, - struct i915_vma *shadow, - struct i915_vma *trampoline) -{ - struct eb_parse_work *pw; - struct drm_i915_gem_object *batch = eb->batch->vma->obj; - bool needs_clflush; - int err; - - GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset)); - GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length)); - - pw = kzalloc(sizeof(*pw), GFP_KERNEL); - if (!pw) - return -ENOMEM; - - err = i915_active_acquire(&eb->batch->vma->active); - if (err) - goto err_free; - - err = i915_active_acquire(&shadow->active); - if (err) - goto err_batch; - - if (trampoline) { - err = i915_active_acquire(&trampoline->active); - if (err) - goto err_shadow; - } - - pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB); - if (IS_ERR(pw->shadow_map)) { - err = PTR_ERR(pw->shadow_map); - goto err_trampoline; - } - - needs_clflush = - !(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ); - - pw->batch_map = ERR_PTR(-ENODEV); - if (needs_clflush && i915_has_memcpy_from_wc()) - pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC); - - if (IS_ERR(pw->batch_map)) { - err = i915_gem_object_pin_pages(batch); - if (err) - goto err_unmap_shadow; - pw->batch_map = NULL; - } - - pw->jump_whitelist = - intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len, - trampoline); - if (IS_ERR(pw->jump_whitelist)) { - err = PTR_ERR(pw->jump_whitelist); - goto err_unmap_batch; - } - - dma_fence_work_init(&pw->base, &eb_parse_ops); - - pw->engine = eb->engine; - pw->batch = eb->batch->vma; - pw->batch_offset = eb->batch_start_offset; - pw->batch_length = eb->batch_len; - pw->shadow = shadow; - pw->trampoline = trampoline; - - /* Mark active refs early for this worker, in case we get interrupted */ - err = parser_mark_active(pw, eb->context->timeline); - if (err) - goto err_commit; - - err = dma_resv_reserve_shared(pw->batch->resv, 1); - if (err) - goto err_commit; - - err = dma_resv_reserve_shared(shadow->resv, 1); - if (err) - goto err_commit; - - /* Wait for all writes (and relocs) into the batch to complete */ - err = i915_sw_fence_await_reservation(&pw->base.chain, - pw->batch->resv, NULL, false, - 0, I915_FENCE_GFP); - if (err < 0) - goto err_commit; - - /* Keep the batch alive and unwritten as we parse */ - dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma); - - /* Force execution to wait for completion of the parser */ - dma_resv_add_excl_fence(shadow->resv, &pw->base.dma); - - dma_fence_work_commit_imm(&pw->base); - return 0; - -err_commit: - i915_sw_fence_set_error_once(&pw->base.chain, err); - dma_fence_work_commit_imm(&pw->base); - return err; - -err_unmap_batch: - if (pw->batch_map) - i915_gem_object_unpin_map(batch); - else - i915_gem_object_unpin_pages(batch); -err_unmap_shadow: - i915_gem_object_unpin_map(shadow->obj); -err_trampoline: - if (trampoline) - i915_active_release(&trampoline->active); -err_shadow: - i915_active_release(&shadow->active); -err_batch: - i915_active_release(&eb->batch->vma->active); -err_free: - kfree(pw); - return err; -} - static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma) { /* @@ -2672,7 +2463,15 @@ static int eb_parse(struct i915_execbuffer *eb) goto err_trampoline; } - err = eb_parse_pipeline(eb, shadow, trampoline); + err = dma_resv_reserve_shared(shadow->resv, 1); + if (err) + goto err_trampoline; + + err = intel_engine_cmd_parser(eb->engine, + eb->batch->vma, + eb->batch_start_offset, + eb->batch_len, + shadow, trampoline); if (err) goto err_unpin_batch; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c index 4df505e4c53a..16162fc2782d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c @@ -125,6 +125,10 @@ static int igt_gpu_reloc(void *arg) intel_gt_pm_get(&eb.i915->gt); for_each_uabi_engine(eb.engine, eb.i915) { + if (intel_engine_requires_cmd_parser(eb.engine) || + intel_engine_using_cmd_parser(eb.engine)) + continue; + reloc_cache_init(&eb.reloc_cache, eb.i915); memset(map, POISON_INUSE, 4096); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 3992c25a191d..00ec618d0159 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1145,19 +1145,41 @@ find_reg(const struct intel_engine_cs *engine, u32 addr) static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, struct drm_i915_gem_object *src_obj, unsigned long offset, unsigned long length, - void *dst, const void *src) + bool *needs_clflush_after) { - bool needs_clflush = - !(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ); + unsigned int src_needs_clflush; + unsigned int dst_needs_clflush; + void *dst, *src; + int ret; - if (src) { - GEM_BUG_ON(!needs_clflush); - i915_unaligned_memcpy_from_wc(dst, src + offset, length); - } else { - struct scatterlist *sg; + ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush); + if (ret) + return ERR_PTR(ret); + + dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB); + i915_gem_object_finish_access(dst_obj); + if (IS_ERR(dst)) + return dst; + + ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush); + if (ret) { + i915_gem_object_unpin_map(dst_obj); + return ERR_PTR(ret); + } + + src = ERR_PTR(-ENODEV); + if (src_needs_clflush && i915_has_memcpy_from_wc()) { + src = i915_gem_object_pin_map(src_obj, I915_MAP_WC); + if (!IS_ERR(src)) { + i915_unaligned_memcpy_from_wc(dst, + src + offset, + length); + i915_gem_object_unpin_map(src_obj); + } + } + if (IS_ERR(src)) { + unsigned long x, n, remain; void *ptr; - unsigned int x, sg_ofs; - unsigned long remain; /* * We can avoid clflushing partial cachelines before the write @@ -1168,40 +1190,34 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, * validate up to the end of the batch. */ remain = length; - if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ)) + if (dst_needs_clflush & CLFLUSH_BEFORE) remain = round_up(remain, boot_cpu_data.x86_clflush_size); ptr = dst; x = offset_in_page(offset); - sg = i915_gem_object_get_sg(src_obj, offset >> PAGE_SHIFT, &sg_ofs, false); + for (n = offset >> PAGE_SHIFT; remain; n++) { + int len = min(remain, PAGE_SIZE - x); - while (remain) { - unsigned long sg_max = sg->length >> PAGE_SHIFT; + src = kmap_atomic(i915_gem_object_get_page(src_obj, n)); + if (src_needs_clflush) + drm_clflush_virt_range(src + x, len); + memcpy(ptr, src + x, len); + kunmap_atomic(src); - for (; remain && sg_ofs < sg_max; sg_ofs++) { - unsigned long len = min(remain, PAGE_SIZE - x); - void *map; - - map = kmap_atomic(nth_page(sg_page(sg), sg_ofs)); - if (needs_clflush) - drm_clflush_virt_range(map + x, len); - memcpy(ptr, map + x, len); - kunmap_atomic(map); - - ptr += len; - remain -= len; - x = 0; - } - - sg_ofs = 0; - sg = sg_next(sg); + ptr += len; + remain -= len; + x = 0; } } + i915_gem_object_finish_access(src_obj); + memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32)); /* dst_obj is returned with vmap pinned */ + *needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER; + return dst; } @@ -1360,6 +1376,9 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length, if (target_cmd_index == offset) return 0; + if (IS_ERR(jump_whitelist)) + return PTR_ERR(jump_whitelist); + if (!test_bit(target_cmd_index, jump_whitelist)) { DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n", jump_target); @@ -1369,28 +1388,10 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length, return 0; } -/** - * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser() - * @batch_length: length of the commands in batch_obj - * @trampoline: Whether jump trampolines are used. - * - * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser(). - * This has to be preallocated, because the command parser runs in signaling context, - * and may not allocate any memory. - * - * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use - * IS_ERR() to check for errors. Must bre freed() with kfree(). - * - * NULL is a valid value, meaning no allocation was required. - */ -unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length, - bool trampoline) +static unsigned long *alloc_whitelist(u32 batch_length) { unsigned long *jmp; - if (trampoline) - return NULL; - /* * We expect batch_length to be less than 256KiB for known users, * i.e. we need at most an 8KiB bitmap allocation which should be @@ -1425,21 +1426,21 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length, * Return: non-zero if the parser finds violations or otherwise fails; -EACCES * if the batch appears legal but should use hardware parsing */ + int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, unsigned long batch_offset, unsigned long batch_length, struct i915_vma *shadow, - unsigned long *jump_whitelist, - void *shadow_map, - const void *batch_map) + bool trampoline) { u32 *cmd, *batch_end, offset = 0; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; + bool needs_clflush_after = false; + unsigned long *jump_whitelist; u64 batch_addr, shadow_addr; int ret = 0; - bool trampoline = !jump_whitelist; GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd))); GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd))); @@ -1447,8 +1448,18 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, batch->size)); GEM_BUG_ON(!batch_length); - cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length, - shadow_map, batch_map); + cmd = copy_batch(shadow->obj, batch->obj, + batch_offset, batch_length, + &needs_clflush_after); + if (IS_ERR(cmd)) { + DRM_DEBUG("CMD: Failed to copy batch\n"); + return PTR_ERR(cmd); + } + + jump_whitelist = NULL; + if (!trampoline) + /* Defer failure until attempted use */ + jump_whitelist = alloc_whitelist(batch_length); shadow_addr = gen8_canonical_addr(shadow->node.start); batch_addr = gen8_canonical_addr(batch->node.start + batch_offset); @@ -1549,6 +1560,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, i915_gem_object_flush_map(shadow->obj); + if (!IS_ERR_OR_NULL(jump_whitelist)) + kfree(jump_whitelist); + i915_gem_object_unpin_map(shadow->obj); return ret; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 38ff2fb89744..b30397b04529 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1906,17 +1906,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); int intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length, - bool trampoline); - int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, unsigned long batch_offset, unsigned long batch_length, struct i915_vma *shadow, - unsigned long *jump_whitelist, - void *shadow_map, - const void *batch_map); + bool trampoline); #define I915_CMD_PARSER_TRAMPOLINE_SIZE 8 /* intel_device_info.c */ From 3761baae908a7b5012be08d70fa553cc2eb82305 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 14 Jul 2021 14:34:16 -0500 Subject: [PATCH 0592/1469] Revert "drm/i915: Propagate errors on awaiting already signaled fences" This reverts commit 9e31c1fe45d555a948ff66f1f0e3fe1f83ca63f7. Ever since that commit, we've been having issues where a hang in one client can propagate to another. In particular, a hang in an app can propagate to the X server which causes the whole desktop to lock up. Error propagation along fences sound like a good idea, but as your bug shows, surprising consequences, since propagating errors across security boundaries is not a good thing. What we do have is track the hangs on the ctx, and report information to userspace using RESET_STATS. That's how arb_robustness works. Also, if my understanding is still correct, the EIO from execbuf is when your context is banned (because not recoverable or too many hangs). And in all these cases it's up to userspace to figure out what is all impacted and should be reported to the application, that's not on the kernel to guess and automatically propagate. What's more, we're also building more features on top of ctx error reporting with RESET_STATS ioctl: Encrypted buffers use the same, and the userspace fence wait also relies on that mechanism. So it is the path going forward for reporting gpu hangs and resets to userspace. So all together that's why I think we should just bury this idea again as not quite the direction we want to go to, hence why I think the revert is the right option here. For backporters: Please note that you _must_ have a backport of https://lore.kernel.org/dri-devel/20210602164149.391653-2-jason@jlekstrand.net/ for otherwise backporting just this patch opens up a security bug. v2: Augment commit message. Also restore Jason's sob that I accidentally lost. v3: Add a note for backporters Signed-off-by: Jason Ekstrand Reported-by: Marcin Slusarz Cc: # v5.6+ Cc: Jason Ekstrand Cc: Marcin Slusarz Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/3080 Fixes: 9e31c1fe45d5 ("drm/i915: Propagate errors on awaiting already signaled fences") Acked-by: Daniel Vetter Reviewed-by: Jon Bloomfield Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210714193419.1459723-3-jason@jlekstrand.net (cherry picked from commit 93a2711cddd5760e2f0f901817d71c93183c3b87) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_request.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 1014c71cf7f5..37aef1308573 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1426,10 +1426,8 @@ i915_request_await_execution(struct i915_request *rq, do { fence = *child++; - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { - i915_sw_fence_set_error_once(&rq->submit, fence->error); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) continue; - } if (fence->context == rq->fence.context) continue; @@ -1527,10 +1525,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) do { fence = *child++; - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { - i915_sw_fence_set_error_once(&rq->submit, fence->error); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) continue; - } /* * Requests on the same timeline are explicitly ordered, along From d2cbbf1fe503c07e466c62f83aa1926d74d15821 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 15 Jul 2021 11:26:01 +0200 Subject: [PATCH 0593/1469] ACPI: Kconfig: Fix table override from built-in initrd During a rework of initramfs code the INITRAMFS_COMPRESSION config option was removed in commit 65e00e04e5ae. A leftover as a dependency broke the config option ACPI_TABLE_OVERRIDE_VIA_ BUILTIN_INITRD that is used to enable the overriding of ACPI tables from built-in initrd. Fixing the dependency. Fixes: 65e00e04e5ae ("initramfs: refactor the initramfs build rules") Signed-off-by: Robert Richter Signed-off-by: Rafael J. Wysocki --- drivers/acpi/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 9d872ea477a6..8f9940f40baa 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -370,7 +370,7 @@ config ACPI_TABLE_UPGRADE config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD bool "Override ACPI tables from built-in initrd" depends on ACPI_TABLE_UPGRADE - depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION="" + depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION_NONE help This option provides functionality to override arbitrary ACPI tables from built-in uncompressed initrd. From 71f6428332844f38c7cb10461d9f29e9c9b983a0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 21:21:21 +0300 Subject: [PATCH 0594/1469] ACPI: utils: Fix reference counting in for_each_acpi_dev_match() Currently it's possible to iterate over the dangling pointer in case the device suddenly disappears. This may happen becase callers put it at the end of a loop. Instead, let's move that call inside acpi_dev_get_next_match_dev(). Fixes: 803abec64ef9 ("media: ipu3-cio2: Add cio2-bridge to ipu3-cio2 driver") Fixes: bf263f64e804 ("media: ACPI / bus: Add acpi_dev_get_next_match_dev() and helper macro") Fixes: edbd1bc4951e ("efi/dev-path-parser: Switch to use for_each_acpi_dev_match()") Signed-off-by: Andy Shevchenko Reviewed-by: Daniel Scally Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 7 +++---- drivers/firmware/efi/dev-path-parser.c | 1 - drivers/media/pci/intel/ipu3/cio2-bridge.c | 6 ++---- include/acpi/acpi_bus.h | 5 ----- 4 files changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index e7ddd281afff..d5cedffeeff9 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -860,11 +860,9 @@ EXPORT_SYMBOL(acpi_dev_present); * Return the next match of ACPI device if another matching device was present * at the moment of invocation, or NULL otherwise. * - * FIXME: The function does not tolerate the sudden disappearance of @adev, e.g. - * in the case of a hotplug event. That said, the caller should ensure that - * this will never happen. - * * The caller is responsible for invoking acpi_dev_put() on the returned device. + * On the other hand the function invokes acpi_dev_put() on the given @adev + * assuming that its reference counter had been increased beforehand. * * See additional information in acpi_dev_present() as well. */ @@ -880,6 +878,7 @@ acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const cha match.hrv = hrv; dev = bus_find_device(&acpi_bus_type, start, &match, acpi_dev_match_cb); + acpi_dev_put(adev); return dev ? to_acpi_device(dev) : NULL; } EXPORT_SYMBOL(acpi_dev_get_next_match_dev); diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c index 10d4457417a4..eb9c65f97841 100644 --- a/drivers/firmware/efi/dev-path-parser.c +++ b/drivers/firmware/efi/dev-path-parser.c @@ -34,7 +34,6 @@ static long __init parse_acpi_path(const struct efi_dev_path *node, break; if (!adev->pnp.unique_id && node->acpi.uid == 0) break; - acpi_dev_put(adev); } if (!adev) return -ENODEV; diff --git a/drivers/media/pci/intel/ipu3/cio2-bridge.c b/drivers/media/pci/intel/ipu3/cio2-bridge.c index 4657e99df033..59a36f922675 100644 --- a/drivers/media/pci/intel/ipu3/cio2-bridge.c +++ b/drivers/media/pci/intel/ipu3/cio2-bridge.c @@ -173,10 +173,8 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, int ret; for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) { - if (!adev->status.enabled) { - acpi_dev_put(adev); + if (!adev->status.enabled) continue; - } if (bridge->n_sensors >= CIO2_NUM_PORTS) { acpi_dev_put(adev); @@ -185,7 +183,6 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, } sensor = &bridge->sensors[bridge->n_sensors]; - sensor->adev = adev; strscpy(sensor->name, cfg->hid, sizeof(sensor->name)); ret = cio2_bridge_read_acpi_buffer(adev, "SSDB", @@ -215,6 +212,7 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, goto err_free_swnodes; } + sensor->adev = acpi_dev_get(adev); adev->fwnode.secondary = fwnode; dev_info(&cio2->dev, "Found supported sensor %s\n", diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 1ae993fee4a5..b9d434a93632 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -707,11 +707,6 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); * @hrv: Hardware Revision of the device, pass -1 to not check _HRV * * The caller is responsible for invoking acpi_dev_put() on the returned device. - * - * FIXME: Due to above requirement there is a window that may invalidate @adev - * and next iteration will use a dangling pointer, e.g. in the case of a - * hotplug event. That said, the caller should ensure that this will never - * happen. */ #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \ From c81cfb6256d90ea5ba4a6fb280ea3b171be4e05c Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Sun, 18 Jul 2021 15:36:25 -0400 Subject: [PATCH 0595/1469] bnxt_en: don't disable an already disabled PCI device If device is already disabled in reset path and PCI io error is detected before the device could be enabled, driver could call pci_disable_device() for already disabled device. Fix this problem by calling pci_disable_device() only if the device is already enabled. Fixes: 6316ea6db93d ("bnxt_en: Enable AER support.") Signed-off-by: Kalesh AP Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f56245eeef7b..fdfb75a1608d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -13436,7 +13436,8 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, if (netif_running(netdev)) bnxt_close(netdev); - pci_disable_device(pdev); + if (pci_is_enabled(pdev)) + pci_disable_device(pdev); bnxt_free_ctx_mem(bp); kfree(bp->ctx); bp->ctx = NULL; From c08c59653415201ac46ab791c936ae804c45a11b Mon Sep 17 00:00:00 2001 From: Edwin Peer Date: Sun, 18 Jul 2021 15:36:26 -0400 Subject: [PATCH 0596/1469] bnxt_en: reject ETS settings that will starve a TC ETS proportions are presented to HWRM_QUEUE_COS2BW_CFG as minimum bandwidth constraints. Thus, zero is a legal value for a given TC. However, if all the other TCs sum up to 100%, then at least one hardware queue will starve, resulting in guaranteed TX timeouts. Reject such nonsensical configurations. Reviewed-by: Pavan Chebbi Signed-off-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 8e90224c43a2..8a68df4d9e59 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -433,6 +433,7 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app, static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc) { int total_ets_bw = 0; + bool zero = false; u8 max_tc = 0; int i; @@ -453,13 +454,20 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc) break; case IEEE_8021QAZ_TSA_ETS: total_ets_bw += ets->tc_tx_bw[i]; + zero = zero || !ets->tc_tx_bw[i]; break; default: return -ENOTSUPP; } } - if (total_ets_bw > 100) + if (total_ets_bw > 100) { + netdev_warn(bp->dev, "rejecting ETS config exceeding available bandwidth\n"); return -EINVAL; + } + if (zero && total_ets_bw == 100) { + netdev_warn(bp->dev, "rejecting ETS config starving a TC\n"); + return -EINVAL; + } if (max_tc >= bp->max_tc) *tc = bp->max_tc; From 2c9f046bc377efd1f5e26e74817d5f96e9506c86 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 18 Jul 2021 15:36:27 -0400 Subject: [PATCH 0597/1469] bnxt_en: Refresh RoCE capabilities in bnxt_ulp_probe() The capabilities can change after firmware upgrade/downgrade, so we should get the up-to-date RoCE capabilities everytime bnxt_ulp_probe() is called. Fixes: 2151fe0830fd ("bnxt_en: Handle RESET_NOTIFY async event from firmware.") Reviewed-by: Somnath Kotur Reviewed-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index a918e374f3c5..187ff643ad2a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -479,16 +479,17 @@ struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev) if (!edev) return ERR_PTR(-ENOMEM); edev->en_ops = &bnxt_en_ops_tbl; - if (bp->flags & BNXT_FLAG_ROCEV1_CAP) - edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; - if (bp->flags & BNXT_FLAG_ROCEV2_CAP) - edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; edev->net = dev; edev->pdev = bp->pdev; edev->l2_db_size = bp->db_size; edev->l2_db_size_nc = bp->db_size; bp->edev = edev; } + edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP; + if (bp->flags & BNXT_FLAG_ROCEV1_CAP) + edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; + if (bp->flags & BNXT_FLAG_ROCEV2_CAP) + edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; return bp->edev; } EXPORT_SYMBOL(bnxt_ulp_probe); From 6cd657cb3ee6f4de57e635b126ffbe0e51d00f1a Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 18 Jul 2021 15:36:28 -0400 Subject: [PATCH 0598/1469] bnxt_en: Add missing check for BNXT_STATE_ABORT_ERR in bnxt_fw_rset_task() In the BNXT_FW_RESET_STATE_POLL_VF state in bnxt_fw_reset_task() after all VFs have unregistered, we need to check for BNXT_STATE_ABORT_ERR after we acquire the rtnl_lock. If the flag is set, we need to abort. Fixes: 230d1f0de754 ("bnxt_en: Handle firmware reset.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fdfb75a1608d..39908a3d9460 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11992,6 +11992,10 @@ static void bnxt_fw_reset_task(struct work_struct *work) } bp->fw_reset_timestamp = jiffies; rtnl_lock(); + if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + rtnl_unlock(); + goto fw_reset_abort; + } bnxt_fw_reset_close(bp); if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) { bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN; From 3958b1da725a477b4a222183d16a14d85445d4b6 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Sun, 18 Jul 2021 15:36:29 -0400 Subject: [PATCH 0599/1469] bnxt_en: fix error path of FW reset When bnxt_open() fails in the firmware reset path, the driver needs to gracefully abort, but it is executing code that should be invoked only in the success path. Define a function to abort FW reset and consolidate all error paths to call this new function. Fixes: dab62e7c2de7 ("bnxt_en: Implement faster recovery for firmware fatal error.") Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 31 +++++++++++++++-------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 39908a3d9460..f2f1136fd492 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11959,10 +11959,21 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp) (bp->fw_reset_max_dsecs * HZ / 10)); } +static void bnxt_fw_reset_abort(struct bnxt *bp, int rc) +{ + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) { + bnxt_ulp_start(bp, rc); + bnxt_dl_health_status_update(bp, false); + } + bp->fw_reset_state = 0; + dev_close(bp->dev); +} + static void bnxt_fw_reset_task(struct work_struct *work) { struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work); - int rc; + int rc = 0; if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n"); @@ -11993,8 +12004,9 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_timestamp = jiffies; rtnl_lock(); if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + bnxt_fw_reset_abort(bp, rc); rtnl_unlock(); - goto fw_reset_abort; + return; } bnxt_fw_reset_close(bp); if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) { @@ -12043,6 +12055,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) if (val == 0xffff) { if (bnxt_fw_reset_timeout(bp)) { netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n"); + rc = -ETIMEDOUT; goto fw_reset_abort; } bnxt_queue_fw_reset_work(bp, HZ / 1000); @@ -12052,6 +12065,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); if (pci_enable_device(bp->pdev)) { netdev_err(bp->dev, "Cannot re-enable PCI device\n"); + rc = -ENODEV; goto fw_reset_abort; } pci_set_master(bp->pdev); @@ -12078,9 +12092,10 @@ static void bnxt_fw_reset_task(struct work_struct *work) } rc = bnxt_open(bp->dev); if (rc) { - netdev_err(bp->dev, "bnxt_open_nic() failed\n"); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - dev_close(bp->dev); + netdev_err(bp->dev, "bnxt_open() failed during FW reset\n"); + bnxt_fw_reset_abort(bp, rc); + rtnl_unlock(); + return; } bp->fw_reset_state = 0; @@ -12107,12 +12122,8 @@ fw_reset_abort_status: netdev_err(bp->dev, "fw_health_status 0x%x\n", sts); } fw_reset_abort: - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) - bnxt_dl_health_status_update(bp, false); - bp->fw_reset_state = 0; rtnl_lock(); - dev_close(bp->dev); + bnxt_fw_reset_abort(bp, rc); rtnl_unlock(); } From 96bdd4b9ea7ef9a12db8fdd0ce90e37dffbd3703 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 18 Jul 2021 15:36:30 -0400 Subject: [PATCH 0600/1469] bnxt_en: Validate vlan protocol ID on RX packets Only pass supported VLAN protocol IDs for stripped VLAN tags to the stack. The stack will hit WARN() if the protocol ID is unsupported. Existing firmware sets up the chip to strip 0x8100, 0x88a8, 0x9100. Only the 1st two protocols are supported by the kernel. Fixes: a196e96bb68f ("bnxt_en: clean up VLAN feature bit handling") Reviewed-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f2f1136fd492..169f093e01de 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1671,11 +1671,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) && (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) { - u16 vlan_proto = tpa_info->metadata >> - RX_CMP_FLAGS2_METADATA_TPID_SFT; + __be16 vlan_proto = htons(tpa_info->metadata >> + RX_CMP_FLAGS2_METADATA_TPID_SFT); u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK; - __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag); + if (eth_type_vlan(vlan_proto)) { + __vlan_hwaccel_put_tag(skb, vlan_proto, vtag); + } else { + dev_kfree_skb(skb); + return NULL; + } } skb_checksum_none_assert(skb); @@ -1897,9 +1902,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) { u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data); u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK; - u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT; + __be16 vlan_proto = htons(meta_data >> + RX_CMP_FLAGS2_METADATA_TPID_SFT); - __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag); + if (eth_type_vlan(vlan_proto)) { + __vlan_hwaccel_put_tag(skb, vlan_proto, vtag); + } else { + dev_kfree_skb(skb); + goto next_rx; + } } skb_checksum_none_assert(skb); From 11a39259ff79b74bc99f8b7c44075a2d6d5e7ab1 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Sun, 18 Jul 2021 15:36:31 -0400 Subject: [PATCH 0601/1469] bnxt_en: Check abort error state in bnxt_half_open_nic() bnxt_half_open_nic() is called during during ethtool self test and is protected by rtnl_lock. Firmware reset can be happening at the same time. Only critical portions of the entire firmware reset sequence are protected by the rtnl_lock. It is possible that bnxt_half_open_nic() can be called when the firmware reset sequence is aborting. In that case, bnxt_half_open_nic() needs to check if the ABORT_ERR flag is set and abort if it is. The ethtool self test will fail but the NIC will be brought to a consistent IF_DOWN state. Without this patch, if bnxt_half_open_nic() were to continue in this error state, it may crash like this: bnxt_en 0000:82:00.1 enp130s0f1np1: FW reset in progress during close, FW reset will be aborted Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 ... Process ethtool (pid: 333327, stack limit = 0x0000000046476577) Call trace: bnxt_alloc_mem+0x444/0xef0 [bnxt_en] bnxt_half_open_nic+0x24/0xb8 [bnxt_en] bnxt_self_test+0x2dc/0x390 [bnxt_en] ethtool_self_test+0xe0/0x1f8 dev_ethtool+0x1744/0x22d0 dev_ioctl+0x190/0x3e0 sock_ioctl+0x238/0x480 do_vfs_ioctl+0xc4/0x758 ksys_ioctl+0x84/0xb8 __arm64_sys_ioctl+0x28/0x38 el0_svc_handler+0xb0/0x180 el0_svc+0x8/0xc Fixes: a1301f08c5ac ("bnxt_en: Check abort error state in bnxt_open_nic().") Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 169f093e01de..31eb3c00851a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10208,6 +10208,12 @@ int bnxt_half_open_nic(struct bnxt *bp) { int rc = 0; + if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n"); + rc = -ENODEV; + goto half_open_err; + } + rc = bnxt_alloc_mem(bp, false); if (rc) { netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); From d7859afb6880249039b178fdfb1bef94fd954cf2 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 18 Jul 2021 15:36:32 -0400 Subject: [PATCH 0602/1469] bnxt_en: Move bnxt_ptp_init() to bnxt_open() The device needs to be in ifup state for PTP to function, so move bnxt_ptp_init() to bnxt_open(). This means that the PHC will be registered during bnxt_open(). This also makes firmware reset work correctly. PTP configurations may change after firmware upgrade or downgrade. bnxt_open() will be called after firmware reset, so it will work properly. bnxt_ptp_start() is now incorporated into bnxt_ptp_init(). We now also need to call bnxt_ptp_clear() in bnxt_close(). Fixes: 93cb62d98e9c ("bnxt_en: Enable hardware PTP support") Cc: Richard Cochran Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 16 +++++++------ drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 24 ++++++------------- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h | 1 - 3 files changed, 16 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 31eb3c00851a..b8b73c210995 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10134,7 +10134,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } } - bnxt_ptp_start(bp); rc = bnxt_init_nic(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); @@ -10273,9 +10272,16 @@ static int bnxt_open(struct net_device *dev) rc = bnxt_hwrm_if_change(bp, true); if (rc) return rc; + + if (bnxt_ptp_init(bp)) { + netdev_warn(dev, "PTP initialization failed.\n"); + kfree(bp->ptp_cfg); + bp->ptp_cfg = NULL; + } rc = __bnxt_open_nic(bp, true, true); if (rc) { bnxt_hwrm_if_change(bp, false); + bnxt_ptp_clear(bp); } else { if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) { if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { @@ -10366,6 +10372,7 @@ static int bnxt_close(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); + bnxt_ptp_clear(bp); bnxt_hwmon_close(bp); bnxt_close_nic(bp, true, true); bnxt_hwrm_shutdown_link(bp); @@ -11352,6 +11359,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp) bnxt_clear_int_mode(bp); pci_disable_device(bp->pdev); } + bnxt_ptp_clear(bp); __bnxt_close_nic(bp, true, false); bnxt_vf_reps_free(bp); bnxt_clear_int_mode(bp); @@ -12694,7 +12702,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); - bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); @@ -13278,11 +13285,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc); } - if (bnxt_ptp_init(bp)) { - netdev_warn(dev, "PTP initialization failed.\n"); - kfree(bp->ptp_cfg); - bp->ptp_cfg = NULL; - } bnxt_inv_fw_health_reg(bp); bnxt_dl_register(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index f698b6bd4ff8..9089e7f3fbd4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -385,22 +385,6 @@ int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts) return 0; } -void bnxt_ptp_start(struct bnxt *bp) -{ - struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; - - if (!ptp) - return; - - if (bp->flags & BNXT_FLAG_CHIP_P5) { - spin_lock_bh(&ptp->ptp_lock); - ptp->current_time = bnxt_refclk_read(bp, NULL); - WRITE_ONCE(ptp->old_time, ptp->current_time); - spin_unlock_bh(&ptp->ptp_lock); - ptp_schedule_worker(ptp->ptp_clock, 0); - } -} - static const struct ptp_clock_info bnxt_ptp_caps = { .owner = THIS_MODULE, .name = "bnxt clock", @@ -450,7 +434,13 @@ int bnxt_ptp_init(struct bnxt *bp) bnxt_unmap_ptp_regs(bp); return err; } - + if (bp->flags & BNXT_FLAG_CHIP_P5) { + spin_lock_bh(&ptp->ptp_lock); + ptp->current_time = bnxt_refclk_read(bp, NULL); + WRITE_ONCE(ptp->old_time, ptp->current_time); + spin_unlock_bh(&ptp->ptp_lock); + ptp_schedule_worker(ptp->ptp_clock, 0); + } return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 6b6245750e20..4135ea3ec788 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -75,7 +75,6 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts); -void bnxt_ptp_start(struct bnxt *bp); int bnxt_ptp_init(struct bnxt *bp); void bnxt_ptp_clear(struct bnxt *bp); #endif From de5bf19414fec860168f05d00d574562bd9d86d1 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 18 Jul 2021 15:36:33 -0400 Subject: [PATCH 0603/1469] bnxt_en: Fix PTP capability discovery The current PTP initialization logic does not account for firmware reset that may cause PTP capability to change. The valid pointer bp->ptp_cfg is used to indicate that the device is capable of PTP and that it has been initialized. So we must clean up bp->ptp_cfg and free it if the firmware after reset does not support PTP. Fixes: 93cb62d98e9c ("bnxt_en: Enable hardware PTP support") Cc: Richard Cochran Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b8b73c210995..4db162cee911 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7574,8 +7574,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->flags &= ~BNXT_FLAG_WOL_CAP; if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED) bp->flags |= BNXT_FLAG_WOL_CAP; - if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) + if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) { __bnxt_hwrm_ptp_qcfg(bp); + } else { + kfree(bp->ptp_cfg); + bp->ptp_cfg = NULL; + } } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; From b16f3299ae1aa3c327e1fb742d0379ae4d6e86f2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 18 Jul 2021 13:38:34 -0700 Subject: [PATCH 0604/1469] net: hisilicon: rename CACHE_LINE_MASK to avoid redefinition Building on ARCH=arc causes a "redefined" warning, so rename this driver's CACHE_LINE_MASK to avoid the warning. ../drivers/net/ethernet/hisilicon/hip04_eth.c:134: warning: "CACHE_LINE_MASK" redefined 134 | #define CACHE_LINE_MASK 0x3F In file included from ../include/linux/cache.h:6, from ../include/linux/printk.h:9, from ../include/linux/kernel.h:19, from ../include/linux/list.h:9, from ../include/linux/module.h:12, from ../drivers/net/ethernet/hisilicon/hip04_eth.c:7: ../arch/arc/include/asm/cache.h:17: note: this is the location of the previous definition 17 | #define CACHE_LINE_MASK (~(L1_CACHE_BYTES - 1)) Fixes: d413779cdd93 ("net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC") Signed-off-by: Randy Dunlap Cc: Vineet Gupta Cc: Jiangfeng Xiao Cc: "David S. Miller" Cc: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hip04_eth.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 12f6c2442a7a..e53512f6878a 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -131,7 +131,7 @@ /* buf unit size is cache_line_size, which is 64, so the shift is 6 */ #define PPE_BUF_SIZE_SHIFT 6 #define PPE_TX_BUF_HOLD BIT(31) -#define CACHE_LINE_MASK 0x3F +#define SOC_CACHE_LINE_MASK 0x3F #else #define PPE_CFG_QOS_VMID_GRP_SHIFT 8 #define PPE_CFG_RX_CTRL_ALIGN_SHIFT 11 @@ -531,8 +531,8 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) #if defined(CONFIG_HI13X1_GMAC) desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV | TX_RELEASE_TO_PPE | priv->port << TX_POOL_SHIFT); - desc->data_offset = (__force u32)cpu_to_be32(phys & CACHE_LINE_MASK); - desc->send_addr = (__force u32)cpu_to_be32(phys & ~CACHE_LINE_MASK); + desc->data_offset = (__force u32)cpu_to_be32(phys & SOC_CACHE_LINE_MASK); + desc->send_addr = (__force u32)cpu_to_be32(phys & ~SOC_CACHE_LINE_MASK); #else desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV); desc->send_addr = (__force u32)cpu_to_be32(phys); From bdad810eb97875813a067504424a483aaa309bad Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Mon, 19 Jul 2021 15:18:19 +0800 Subject: [PATCH 0605/1469] dt-bindings: net: snps,dwmac: add missing DWMAC IP version Add missing DWMAC IP version in snps,dwmac.yaml which found by below command, as NXP i.MX8 families support SNPS DWMAC 5.10a IP. $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- dt_binding_check DT_SCHEMA_FILES=Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml Documentation/devicetree/bindings/net/nxp,dwmac-imx.example.dt.yaml: ethernet@30bf0000: compatible: None of ['nxp,imx8mp-dwmac-eqos', 'snps,dwmac-5.10a'] are valid under the given schema Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/snps,dwmac.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index d7652596a09b..42689b7d03a2 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -28,6 +28,7 @@ select: - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a + - snps,dwmac-5.10a - snps,dwxgmac - snps,dwxgmac-2.10 @@ -82,6 +83,7 @@ properties: - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a + - snps,dwmac-5.10a - snps,dwxgmac - snps,dwxgmac-2.10 @@ -375,6 +377,7 @@ allOf: - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a + - snps,dwmac-5.10a - snps,dwxgmac - snps,dwxgmac-2.10 - st,spear600-gmac From e314a07ef263916f761b736ded7a30894709dfd7 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Mon, 19 Jul 2021 15:18:20 +0800 Subject: [PATCH 0606/1469] dt-bindings: net: imx-dwmac: convert imx-dwmac bindings to yaml In order to automate the verification of DT nodes covert imx-dwmac to nxp,dwmac-imx.yaml, and pass below checking. $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- dt_binding_check DT_SCHEMA_FILES=Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- dtbs_check DT_SCHEMA_FILES=Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- .../devicetree/bindings/net/imx-dwmac.txt | 56 ----------- .../bindings/net/nxp,dwmac-imx.yaml | 93 +++++++++++++++++++ 2 files changed, 93 insertions(+), 56 deletions(-) delete mode 100644 Documentation/devicetree/bindings/net/imx-dwmac.txt create mode 100644 Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml diff --git a/Documentation/devicetree/bindings/net/imx-dwmac.txt b/Documentation/devicetree/bindings/net/imx-dwmac.txt deleted file mode 100644 index 921d522fe8d7..000000000000 --- a/Documentation/devicetree/bindings/net/imx-dwmac.txt +++ /dev/null @@ -1,56 +0,0 @@ -IMX8 glue layer controller, NXP imx8 families support Synopsys MAC 5.10a IP. - -This file documents platform glue layer for IMX. -Please see stmmac.txt for the other unchanged properties. - -The device node has following properties. - -Required properties: -- compatible: Should be "nxp,imx8mp-dwmac-eqos" to select glue layer - and "snps,dwmac-5.10a" to select IP version. -- clocks: Must contain a phandle for each entry in clock-names. -- clock-names: Should be "stmmaceth" for the host clock. - Should be "pclk" for the MAC apb clock. - Should be "ptp_ref" for the MAC timer clock. - Should be "tx" for the MAC RGMII TX clock: - Should be "mem" for EQOS MEM clock. - - "mem" clock is required for imx8dxl platform. - - "mem" clock is not required for imx8mp platform. -- interrupt-names: Should contain a list of interrupt names corresponding to - the interrupts in the interrupts property, if available. - Should be "macirq" for the main MAC IRQ - Should be "eth_wake_irq" for the IT which wake up system -- intf_mode: Should be phandle/offset pair. The phandle to the syscon node which - encompases the GPR register, and the offset of the GPR register. - - required for imx8mp platform. - - is optional for imx8dxl platform. - -Optional properties: -- intf_mode: is optional for imx8dxl platform. -- snps,rmii_refclk_ext: to select RMII reference clock from external. - -Example: - eqos: ethernet@30bf0000 { - compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a"; - reg = <0x30bf0000 0x10000>; - interrupts = , - ; - interrupt-names = "eth_wake_irq", "macirq"; - clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>, - <&clk IMX8MP_CLK_QOS_ENET_ROOT>, - <&clk IMX8MP_CLK_ENET_QOS_TIMER>, - <&clk IMX8MP_CLK_ENET_QOS>; - clock-names = "stmmaceth", "pclk", "ptp_ref", "tx"; - assigned-clocks = <&clk IMX8MP_CLK_ENET_AXI>, - <&clk IMX8MP_CLK_ENET_QOS_TIMER>, - <&clk IMX8MP_CLK_ENET_QOS>; - assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_266M>, - <&clk IMX8MP_SYS_PLL2_100M>, - <&clk IMX8MP_SYS_PLL2_125M>; - assigned-clock-rates = <0>, <100000000>, <125000000>; - nvmem-cells = <ð_mac0>; - nvmem-cell-names = "mac-address"; - nvmem_macaddr_swap; - intf_mode = <&gpr 0x4>; - status = "disabled"; - }; diff --git a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml new file mode 100644 index 000000000000..5629b2e4ccf8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,dwmac-imx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP i.MX8 DWMAC glue layer Device Tree Bindings + +maintainers: + - Joakim Zhang + +# We need a select here so we don't match all nodes with 'snps,dwmac' +select: + properties: + compatible: + contains: + enum: + - nxp,imx8mp-dwmac-eqos + - nxp,imx8dxl-dwmac-eqos + required: + - compatible + +allOf: + - $ref: "snps,dwmac.yaml#" + +properties: + compatible: + oneOf: + - items: + - enum: + - nxp,imx8mp-dwmac-eqos + - nxp,imx8dxl-dwmac-eqos + - const: snps,dwmac-5.10a + + clocks: + minItems: 3 + maxItems: 5 + items: + - description: MAC host clock + - description: MAC apb clock + - description: MAC timer clock + - description: MAC RGMII TX clock + - description: EQOS MEM clock + + clock-names: + minItems: 3 + maxItems: 5 + contains: + enum: + - stmmaceth + - pclk + - ptp_ref + - tx + - mem + + intf_mode: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + Should be phandle/offset pair. The phandle to the syscon node which + encompases the GPR register, and the offset of the GPR register. + + snps,rmii_refclk_ext: + $ref: /schemas/types.yaml#/definitions/flag + description: + To select RMII reference clock from external. + +required: + - compatible + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + + eqos: ethernet@30bf0000 { + compatible = "nxp,imx8mp-dwmac-eqos","snps,dwmac-5.10a"; + reg = <0x30bf0000 0x10000>; + interrupts = , + ; + interrupt-names = "macirq", "eth_wake_irq"; + clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>, + <&clk IMX8MP_CLK_QOS_ENET_ROOT>, + <&clk IMX8MP_CLK_ENET_QOS_TIMER>, + <&clk IMX8MP_CLK_ENET_QOS>; + clock-names = "stmmaceth", "pclk", "ptp_ref", "tx"; + phy-mode = "rgmii"; + status = "disabled"; + }; From 77e5253deadf7fae59207330e3a639e592ee7892 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Mon, 19 Jul 2021 15:18:21 +0800 Subject: [PATCH 0607/1469] arm64: dts: imx8mp: change interrupt order per dt-binding This patch changs interrupt order which found by dtbs_check. $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- dtbs_check DT_SCHEMA_FILES=Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml arch/arm64/boot/dts/freescale/imx8mp-evk.dt.yaml: ethernet@30bf0000: interrupt-names:0: 'macirq' was expected arch/arm64/boot/dts/freescale/imx8mp-evk.dt.yaml: ethernet@30bf0000: interrupt-names:1: 'eth_wake_irq' was expected According to Documentation/devicetree/bindings/net/snps,dwmac.yaml, we should list interrupt in it's order. Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- arch/arm64/boot/dts/freescale/imx8mp.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 9f7c7f587d38..ca38d0d6c3c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -821,9 +821,9 @@ eqos: ethernet@30bf0000 { compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a"; reg = <0x30bf0000 0x10000>; - interrupts = , - ; - interrupt-names = "eth_wake_irq", "macirq"; + interrupts = , + ; + interrupt-names = "macirq", "eth_wake_irq"; clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>, <&clk IMX8MP_CLK_QOS_ENET_ROOT>, <&clk IMX8MP_CLK_ENET_QOS_TIMER>, From 6f20c8adb1813467ea52c1296d52c4e95978cb2f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Jul 2021 02:12:18 -0700 Subject: [PATCH 0608/1469] net/tcp_fastopen: fix data races around tfo_active_disable_stamp tfo_active_disable_stamp is read and written locklessly. We need to annotate these accesses appropriately. Then, we need to perform the atomic_inc(tfo_active_disable_times) after the timestamp has been updated, and thus add barriers to make sure tcp_fastopen_active_should_disable() wont read a stale timestamp. Fixes: cf1ef3f0719b ("net/tcp_fastopen: Disable active side TFO in certain scenarios") Signed-off-by: Eric Dumazet Cc: Wei Wang Cc: Yuchung Cheng Cc: Neal Cardwell Acked-by: Wei Wang Signed-off-by: David S. Miller --- net/ipv4/tcp_fastopen.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 47c32604d38f..b32af76e2132 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -507,8 +507,15 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); + /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ + WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). + * We want net->ipv4.tfo_active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); - net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } @@ -526,10 +533,16 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) if (!tfo_da_times) return false; + /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ + smp_rmb(); + /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * tfo_bh_timeout * HZ; - if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) + + /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ + timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + + multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO From fa2bf6baf2b1d8350e5193ce4014bdddc51a25d0 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Mon, 19 Jul 2021 14:29:32 +0530 Subject: [PATCH 0609/1469] octeontx2-af: Enable transmit side LBK link For enabling VF-VF switching the packets egressing out of CGX mapped VFs needed to be sent to LBK so that same packets are received back to the system. But the LBK link also needs to be enabled in addition to a VF's mapped CGX_LMAC link otherwise hardware raises send error interrupt indicating selected LBK link is not enabled in NIX_AF_TL3_TL2X_LINKX_CFG register. Hence this patch enables all LBK links in TL3_TL2_LINKX_CFG registers. Also to enable packet flow between PFs/VFs of NIX0 to PFs/VFs of NIX1(in 98xx silicon) the NPC TX DMAC rules has to be installed such that rules must be hit for any TX interface i.e., NIX0-TX or NIX1-TX provided DMAC match creteria is met. Hence this patch changes the behavior such that MCAM is programmed to match with any NIX0/1-TX interface for TX rules. Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/rvu.c | 6 ++++ .../net/ethernet/marvell/octeontx2/af/rvu.h | 2 ++ .../ethernet/marvell/octeontx2/af/rvu_nix.c | 32 +++++++++++++++++++ .../ethernet/marvell/octeontx2/af/rvu_npc.c | 15 +++++++-- .../marvell/octeontx2/af/rvu_npc_fs.c | 9 +++++- 5 files changed, 61 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 10cddf1ac7b9..086eb6d283ee 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2859,6 +2859,12 @@ static int rvu_enable_sriov(struct rvu *rvu) if (!vfs) return 0; + /* LBK channel number 63 is used for switching packets between + * CGX mapped VFs. Hence limit LBK pairs till 62 only. + */ + if (vfs > 62) + vfs = 62; + /* Save VFs number for reference in VF interrupts handlers. * Since interrupts might start arriving during SRIOV enablement * ordinary API cannot be used to get number of enabled VFs. diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 10e58a5d5861..e53f530e5e31 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -415,6 +415,8 @@ struct npc_kpu_profile_adapter { size_t kpus; }; +#define RVU_SWITCH_LBK_CHAN 63 + struct rvu { void __iomem *afreg_base; void __iomem *pfreg_base; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index aeae37704428..a2d69eaac4f8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1952,6 +1952,35 @@ static void nix_tl1_default_cfg(struct rvu *rvu, struct nix_hw *nix_hw, pfvf_map[schq] = TXSCH_SET_FLAG(pfvf_map[schq], NIX_TXSCHQ_CFG_DONE); } +static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, + u16 pcifunc, struct nix_txsch *txsch) +{ + struct rvu_hwinfo *hw = rvu->hw; + int lbk_link_start, lbk_links; + u8 pf = rvu_get_pf(pcifunc); + int schq; + + if (!is_pf_cgxmapped(rvu, pf)) + return; + + lbk_link_start = hw->cgx_links; + + for (schq = 0; schq < txsch->schq.max; schq++) { + if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) + continue; + /* Enable all LBK links with channel 63 by default so that + * packets can be sent to LBK with a NPC TX MCAM rule + */ + lbk_links = hw->lbk_links; + while (lbk_links--) + rvu_write64(rvu, blkaddr, + NIX_AF_TL3_TL2X_LINKX_CFG(schq, + lbk_link_start + + lbk_links), + BIT_ULL(12) | RVU_SWITCH_LBK_CHAN); + } +} + int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu, struct nix_txschq_config *req, struct msg_rsp *rsp) @@ -2040,6 +2069,9 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu, rvu_write64(rvu, blkaddr, reg, regval); } + rvu_nix_tx_tl2_cfg(rvu, blkaddr, pcifunc, + &nix_hw->txsch[NIX_TXSCH_LVL_TL2]); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 3612e0a2cab3..16c557cbe6a0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -468,6 +468,8 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, { int bank = npc_get_bank(mcam, index); int kw = 0, actbank, actindex; + u8 tx_intf_mask = ~intf & 0x3; + u8 tx_intf = intf; u64 cam0, cam1; actbank = bank; /* Save bank id, to set action later on */ @@ -488,12 +490,21 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, */ for (; bank < (actbank + mcam->banks_per_entry); bank++, kw = kw + 2) { /* Interface should be set in all banks */ + if (is_npc_intf_tx(intf)) { + /* Last bit must be set and rest don't care + * for TX interfaces + */ + tx_intf_mask = 0x1; + tx_intf = intf & tx_intf_mask; + tx_intf_mask = ~tx_intf & tx_intf_mask; + } + rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 1), - intf); + tx_intf); rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 0), - ~intf & 0x3); + tx_intf_mask); /* Set the match key */ npc_get_keyword(entry, kw, &cam0, &cam1); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 68633145a8b8..92d64bdff0ea 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -949,9 +949,16 @@ static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf, struct npc_install_flow_req *req, u16 target) { struct nix_tx_action action; + u64 mask = ~0ULL; + + /* If AF is installing then do not care about + * PF_FUNC in Send Descriptor + */ + if (is_pffunc_af(req->hdr.pcifunc)) + mask = 0; npc_update_entry(rvu, NPC_PF_FUNC, entry, (__force u16)htons(target), - 0, ~0ULL, 0, NIX_INTF_TX); + 0, mask, 0, NIX_INTF_TX); *(u64 *)&action = 0x00; action.op = req->op; From cb7a6b3bac1d0d773f2b6cc35f6bab61eb5de5ef Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Mon, 19 Jul 2021 14:29:33 +0530 Subject: [PATCH 0610/1469] octeontx2-af: Prepare for allocating MCAM rules for AF AF till now only manages the allocation and freeing of MCAM rules for other PF/VFs in system. To implement L2 switching between all CGX mapped PF and VFs, AF requires MCAM entries for DMAC rules for each PF and VF. This patch modifies AF driver such that AF can also allocate MCAM rules and install rules for other PFs and VFs. All the checks like channel verification for RX rules and PF_FUNC verification for TX rules are relaxed in case AF is allocating or installing rules. Also all the entry and counter to owner mappings are set to NPC_MCAM_INVALID_MAP when they are free indicating those are not allocated to AF nor PF/VFs. This patch also ensures that AF allocated and installed entries are displayed in debugfs. Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../marvell/octeontx2/af/rvu_debugfs.c | 5 +-- .../ethernet/marvell/octeontx2/af/rvu_npc.c | 32 +++++++++++++------ .../marvell/octeontx2/af/rvu_npc_fs.c | 11 ++++--- 3 files changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 370d4ca1e5ed..9b2dfbf90e51 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2113,9 +2113,6 @@ static void rvu_print_npc_mcam_info(struct seq_file *s, int entry_acnt, entry_ecnt; int cntr_acnt, cntr_ecnt; - /* Skip PF0 */ - if (!pcifunc) - return; rvu_npc_get_mcam_entry_alloc_info(rvu, pcifunc, blkaddr, &entry_acnt, &entry_ecnt); rvu_npc_get_mcam_counter_alloc_info(rvu, pcifunc, blkaddr, @@ -2298,7 +2295,7 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s, static void rvu_dbg_npc_mcam_show_action(struct seq_file *s, struct rvu_npc_mcam_rule *rule) { - if (rule->intf == NIX_INTF_TX) { + if (is_npc_intf_tx(rule->intf)) { switch (rule->tx_action.op) { case NIX_TX_ACTIONOP_DROP: seq_puts(s, "\taction: Drop\n"); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 16c557cbe6a0..1097291aaa45 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -442,7 +442,8 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, owner = mcam->entry2pfvf_map[index]; target_func = (entry->action >> 4) & 0xffff; /* do nothing when target is LBK/PF or owner is not PF */ - if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) || + if (is_pffunc_af(owner) || is_afvf(target_func) || + (owner & RVU_PFVF_FUNC_MASK) || !(target_func & RVU_PFVF_FUNC_MASK)) return; @@ -661,6 +662,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, eth_broadcast_addr((u8 *)&req.mask.dmac); req.features = BIT_ULL(NPC_DMAC); req.channel = chan; + req.chan_mask = 0xFFFU; req.intf = pfvf->nix_rx_intf; req.op = action.op; req.hdr.pcifunc = 0; /* AF is requester */ @@ -810,6 +812,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, eth_broadcast_addr((u8 *)&req.mask.dmac); req.features = BIT_ULL(NPC_DMAC); req.channel = chan; + req.chan_mask = 0xFFFU; req.intf = pfvf->nix_rx_intf; req.entry = index; req.hdr.pcifunc = 0; /* AF is requester */ @@ -1756,6 +1759,8 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr) int nixlf_count = rvu_get_nixlf_count(rvu); struct npc_mcam *mcam = &rvu->hw->mcam; int rsvd, err; + u16 index; + int cntr; u64 cfg; /* Actual number of MCAM entries vary by entry size */ @@ -1856,6 +1861,14 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr) if (!mcam->entry2target_pffunc) goto free_mem; + for (index = 0; index < mcam->bmap_entries; index++) { + mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; + mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP; + } + + for (cntr = 0; cntr < mcam->counters.max; cntr++) + mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP; + mutex_init(&mcam->lock); return 0; @@ -2573,7 +2586,7 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu, } /* Alloc request from PFFUNC with no NIXLF attached should be denied */ - if (!is_nixlf_attached(rvu, pcifunc)) + if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc)) return NPC_MCAM_ALLOC_DENIED; return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp); @@ -2593,7 +2606,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu, return NPC_MCAM_INVALID_REQ; /* Free request from PFFUNC with no NIXLF attached, ignore */ - if (!is_nixlf_attached(rvu, pcifunc)) + if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc)) return NPC_MCAM_INVALID_REQ; mutex_lock(&mcam->lock); @@ -2605,7 +2618,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu, if (rc) goto exit; - mcam->entry2pfvf_map[req->entry] = 0; + mcam->entry2pfvf_map[req->entry] = NPC_MCAM_INVALID_MAP; mcam->entry2target_pffunc[req->entry] = 0x0; npc_mcam_clear_bit(mcam, req->entry); npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false); @@ -2690,13 +2703,14 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu, else nix_intf = pfvf->nix_rx_intf; - if (npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) { + if (!is_pffunc_af(pcifunc) && + npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) { rc = NPC_MCAM_INVALID_REQ; goto exit; } - if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, - pcifunc)) { + if (!is_pffunc_af(pcifunc) && + npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) { rc = NPC_MCAM_INVALID_REQ; goto exit; } @@ -2847,7 +2861,7 @@ int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu, return NPC_MCAM_INVALID_REQ; /* If the request is from a PFFUNC with no NIXLF attached, ignore */ - if (!is_nixlf_attached(rvu, pcifunc)) + if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc)) return NPC_MCAM_INVALID_REQ; /* Since list of allocated counter IDs needs to be sent to requester, @@ -3092,7 +3106,7 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu, if (rc) { /* Free allocated MCAM entry */ mutex_lock(&mcam->lock); - mcam->entry2pfvf_map[entry] = 0; + mcam->entry2pfvf_map[entry] = NPC_MCAM_INVALID_MAP; npc_mcam_clear_bit(mcam, entry); mutex_unlock(&mcam->lock); return rc; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 92d64bdff0ea..c1f35a0971ad 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -913,11 +913,9 @@ static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf, struct npc_install_flow_req *req, u16 target) { struct nix_rx_action action; - u64 chan_mask; - chan_mask = req->chan_mask ? req->chan_mask : ~0ULL; - npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, chan_mask, 0, - NIX_INTF_RX); + npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, req->chan_mask, + 0, NIX_INTF_RX); *(u64 *)&action = 0x00; action.pf_func = target; @@ -1171,7 +1169,9 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, if (err) return err; - if (npc_mcam_verify_channel(rvu, target, req->intf, req->channel)) + /* Skip channel validation if AF is installing */ + if (!is_pffunc_af(req->hdr.pcifunc) && + npc_mcam_verify_channel(rvu, target, req->intf, req->channel)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, target); @@ -1187,6 +1187,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, eth_broadcast_addr((u8 *)&req->mask.dmac); } + /* Proceed if NIXLF is attached or not for TX rules */ err = nix_get_nixlf(rvu, target, &nixlf, NULL); if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac) return -EINVAL; From 23109f8dd06d0bd04c9360cf7c501c97b0ab1545 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Mon, 19 Jul 2021 14:29:34 +0530 Subject: [PATCH 0611/1469] octeontx2-af: Introduce internal packet switching As of now any communication between CGXs PFs and their VFs within the system is possible only by external switches sending packets back to the system. This patch adds internal switching support. Broadcast packet replication is not covered here. RVU admin function (AF) maintains MAC addresses of all interfaces in the system. When switching is enabled, MCAM entries are allocated to install rules such that packets with DMAC matching any of the internal interface MAC addresses is punted back into the system via the loopback channel. On the receive side the default unicast rules are modified to not check for ingress channel. So any packet with matching DMAC irrespective of which interface it is coming from will be forwarded to the respective PF/VF interface. The transmit side rules and default unicast rules are updated if user changes MAC address of an interface. Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/af/Makefile | 2 +- .../net/ethernet/marvell/octeontx2/af/rvu.c | 4 +- .../net/ethernet/marvell/octeontx2/af/rvu.h | 19 ++ .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 3 + .../marvell/octeontx2/af/rvu_devlink.c | 48 +++- .../ethernet/marvell/octeontx2/af/rvu_nix.c | 4 + .../marvell/octeontx2/af/rvu_npc_fs.c | 9 +- .../marvell/octeontx2/af/rvu_switch.c | 258 ++++++++++++++++++ 8 files changed, 336 insertions(+), 11 deletions(-) create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index 1a3455620b38..cc8ac36cf687 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -10,4 +10,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += rvu_af.o rvu_mbox-y := mbox.o rvu_trace.o rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \ rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \ - rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o + rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 086eb6d283ee..017163fb3cd5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1314,7 +1314,7 @@ int rvu_mbox_handler_detach_resources(struct rvu *rvu, return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc); } -static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) +int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); int blkaddr = BLKADDR_NIX0, vf; @@ -3007,6 +3007,8 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Initialize debugfs */ rvu_dbg_init(rvu); + mutex_init(&rvu->rswitch.switch_lock); + return 0; err_dl: rvu_unregister_dl(rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index e53f530e5e31..91503fb2762c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -417,6 +417,14 @@ struct npc_kpu_profile_adapter { #define RVU_SWITCH_LBK_CHAN 63 +struct rvu_switch { + struct mutex switch_lock; /* Serialize flow installation */ + u32 used_entries; + u16 *entry2pcifunc; + u16 mode; + u16 start_entry; +}; + struct rvu { void __iomem *afreg_base; void __iomem *pfreg_base; @@ -447,6 +455,7 @@ struct rvu { /* CGX */ #define PF_CGXMAP_BASE 1 /* PF 0 is reserved for RVU PF */ + u16 cgx_mapped_vfs; /* maximum CGX mapped VFs */ u8 cgx_mapped_pfs; u8 cgx_cnt_max; /* CGX port count max */ u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */ @@ -479,6 +488,9 @@ struct rvu { struct rvu_debugfs rvu_dbg; #endif struct rvu_devlink *rvu_dl; + + /* RVU switch implementation over NPC with DMAC rules */ + struct rvu_switch rswitch; }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) @@ -693,6 +705,7 @@ int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw, struct nix_cn10k_aq_enq_req *aq_req, struct nix_cn10k_aq_enq_rsp *aq_rsp, u16 pcifunc, u8 ctype, u32 qidx); +int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -770,4 +783,10 @@ void rvu_dbg_exit(struct rvu *rvu); static inline void rvu_dbg_init(struct rvu *rvu) {} static inline void rvu_dbg_exit(struct rvu *rvu) {} #endif + +/* RVU Switch */ +void rvu_switch_enable(struct rvu *rvu); +void rvu_switch_disable(struct rvu *rvu); +void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc); + #endif /* RVU_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 6cc8fbb7190c..fe99ac4a4dd8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -126,6 +126,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) unsigned long lmac_bmap; int size, free_pkind; int cgx, lmac, iter; + int numvfs, hwvfs; if (!cgx_cnt_max) return 0; @@ -166,6 +167,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16; rvu_map_cgx_nix_block(rvu, pf, cgx, lmac); rvu->cgx_mapped_pfs++; + rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvfs); + rvu->cgx_mapped_vfs += numvfs; pf++; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 10a98bcb7c54..2688186066d9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1364,6 +1364,44 @@ static void rvu_health_reporters_destroy(struct rvu *rvu) rvu_nix_health_reporters_destroy(rvu_dl); } +static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + struct rvu_devlink *rvu_dl = devlink_priv(devlink); + struct rvu *rvu = rvu_dl->rvu; + struct rvu_switch *rswitch; + + rswitch = &rvu->rswitch; + *mode = rswitch->mode; + + return 0; +} + +static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct rvu_devlink *rvu_dl = devlink_priv(devlink); + struct rvu *rvu = rvu_dl->rvu; + struct rvu_switch *rswitch; + + rswitch = &rvu->rswitch; + switch (mode) { + case DEVLINK_ESWITCH_MODE_LEGACY: + case DEVLINK_ESWITCH_MODE_SWITCHDEV: + if (rswitch->mode == mode) + return 0; + rswitch->mode = mode; + if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + rvu_switch_enable(rvu); + else + rvu_switch_disable(rvu); + break; + default: + return -EINVAL; + } + + return 0; +} + static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack) { @@ -1372,6 +1410,8 @@ static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req static const struct devlink_ops rvu_devlink_ops = { .info_get = rvu_devlink_info_get, + .eswitch_mode_get = rvu_devlink_eswitch_mode_get, + .eswitch_mode_set = rvu_devlink_eswitch_mode_set, }; int rvu_register_dl(struct rvu *rvu) @@ -1380,14 +1420,9 @@ int rvu_register_dl(struct rvu *rvu) struct devlink *dl; int err; - rvu_dl = kzalloc(sizeof(*rvu_dl), GFP_KERNEL); - if (!rvu_dl) - return -ENOMEM; - dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink)); if (!dl) { dev_warn(rvu->dev, "devlink_alloc failed\n"); - kfree(rvu_dl); return -ENOMEM; } @@ -1395,10 +1430,10 @@ int rvu_register_dl(struct rvu *rvu) if (err) { dev_err(rvu->dev, "devlink register failed with error %d\n", err); devlink_free(dl); - kfree(rvu_dl); return err; } + rvu_dl = devlink_priv(dl); rvu_dl->dl = dl; rvu_dl->rvu = rvu; rvu->rvu_dl = rvu_dl; @@ -1417,5 +1452,4 @@ void rvu_unregister_dl(struct rvu *rvu) rvu_health_reporters_destroy(rvu); devlink_unregister(dl); devlink_free(dl); - kfree(rvu_dl); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index a2d69eaac4f8..0933699a0d2d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3212,6 +3212,8 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu, if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf) ether_addr_copy(pfvf->default_mac, req->mac_addr); + rvu_switch_update_rules(rvu, pcifunc); + return 0; } @@ -3881,6 +3883,8 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); set_bit(NIXLF_INITIALIZED, &pfvf->flags); + rvu_switch_update_rules(rvu, pcifunc); + return rvu_cgx_start_stop_io(rvu, pcifunc, true); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index c1f35a0971ad..5c01cf4a9c5b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -910,10 +910,15 @@ static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc, static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf, struct mcam_entry *entry, - struct npc_install_flow_req *req, u16 target) + struct npc_install_flow_req *req, + u16 target, bool pf_set_vfs_mac) { + struct rvu_switch *rswitch = &rvu->rswitch; struct nix_rx_action action; + if (rswitch->mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && pf_set_vfs_mac) + req->chan_mask = 0x0; /* Do not care channel */ + npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, req->chan_mask, 0, NIX_INTF_RX); @@ -1007,7 +1012,7 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target, req->intf); if (is_npc_intf_rx(req->intf)) - npc_update_rx_entry(rvu, pfvf, entry, req, target); + npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac); else npc_update_tx_entry(rvu, pfvf, entry, req, target); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c new file mode 100644 index 000000000000..2e5379710aa5 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 RVU Admin Function driver + * + * Copyright (C) 2021 Marvell. + */ + +#include +#include "rvu.h" + +static int rvu_switch_install_rx_rule(struct rvu *rvu, u16 pcifunc, + u16 chan_mask) +{ + struct npc_install_flow_req req = { 0 }; + struct npc_install_flow_rsp rsp = { 0 }; + struct rvu_pfvf *pfvf; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + /* If the pcifunc is not initialized then nothing to do. + * This same function will be called again via rvu_switch_update_rules + * after pcifunc is initialized. + */ + if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags)) + return 0; + + ether_addr_copy(req.packet.dmac, pfvf->mac_addr); + eth_broadcast_addr((u8 *)&req.mask.dmac); + req.hdr.pcifunc = 0; /* AF is requester */ + req.vf = pcifunc; + req.features = BIT_ULL(NPC_DMAC); + req.channel = pfvf->rx_chan_base; + req.chan_mask = chan_mask; + req.intf = pfvf->nix_rx_intf; + req.op = NIX_RX_ACTION_DEFAULT; + req.default_rule = 1; + + return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +static int rvu_switch_install_tx_rule(struct rvu *rvu, u16 pcifunc, u16 entry) +{ + struct npc_install_flow_req req = { 0 }; + struct npc_install_flow_rsp rsp = { 0 }; + struct rvu_pfvf *pfvf; + u8 lbkid; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + /* If the pcifunc is not initialized then nothing to do. + * This same function will be called again via rvu_switch_update_rules + * after pcifunc is initialized. + */ + if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags)) + return 0; + + lbkid = pfvf->nix_blkaddr == BLKADDR_NIX0 ? 0 : 1; + ether_addr_copy(req.packet.dmac, pfvf->mac_addr); + eth_broadcast_addr((u8 *)&req.mask.dmac); + req.hdr.pcifunc = 0; /* AF is requester */ + req.vf = pcifunc; + req.entry = entry; + req.features = BIT_ULL(NPC_DMAC); + req.intf = pfvf->nix_tx_intf; + req.op = NIX_TX_ACTIONOP_UCAST_CHAN; + req.index = (lbkid << 8) | RVU_SWITCH_LBK_CHAN; + req.set_cntr = 1; + + return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +static int rvu_switch_install_rules(struct rvu *rvu) +{ + struct rvu_switch *rswitch = &rvu->rswitch; + u16 start = rswitch->start_entry; + struct rvu_hwinfo *hw = rvu->hw; + int pf, vf, numvfs, hwvf; + u16 pcifunc, entry = 0; + int err; + + for (pf = 1; pf < hw->total_pfs; pf++) { + if (!is_pf_cgxmapped(rvu, pf)) + continue; + + pcifunc = pf << 10; + /* rvu_get_nix_blkaddr sets up the corresponding NIX block + * address and NIX RX and TX interfaces for a pcifunc. + * Generally it is called during attach call of a pcifunc but it + * is called here since we are pre-installing rules before + * nixlfs are attached + */ + rvu_get_nix_blkaddr(rvu, pcifunc); + + /* MCAM RX rule for a PF/VF already exists as default unicast + * rules installed by AF. Hence change the channel in those + * rules to ignore channel so that packets with the required + * DMAC received from LBK(by other PF/VFs in system) or from + * external world (from wire) are accepted. + */ + err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0); + if (err) { + dev_err(rvu->dev, "RX rule for PF%d failed(%d)\n", + pf, err); + return err; + } + + err = rvu_switch_install_tx_rule(rvu, pcifunc, start + entry); + if (err) { + dev_err(rvu->dev, "TX rule for PF%d failed(%d)\n", + pf, err); + return err; + } + + rswitch->entry2pcifunc[entry++] = pcifunc; + + rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf); + for (vf = 0; vf < numvfs; vf++, hwvf++) { + pcifunc = pf << 10 | ((vf + 1) & 0x3FF); + rvu_get_nix_blkaddr(rvu, pcifunc); + + err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0); + if (err) { + dev_err(rvu->dev, + "RX rule for PF%dVF%d failed(%d)\n", + pf, vf, err); + return err; + } + + err = rvu_switch_install_tx_rule(rvu, pcifunc, + start + entry); + if (err) { + dev_err(rvu->dev, + "TX rule for PF%dVF%d failed(%d)\n", + pf, vf, err); + return err; + } + + rswitch->entry2pcifunc[entry++] = pcifunc; + } + } + + return 0; +} + +void rvu_switch_enable(struct rvu *rvu) +{ + struct npc_mcam_alloc_entry_req alloc_req = { 0 }; + struct npc_mcam_alloc_entry_rsp alloc_rsp = { 0 }; + struct npc_delete_flow_req uninstall_req = { 0 }; + struct npc_mcam_free_entry_req free_req = { 0 }; + struct rvu_switch *rswitch = &rvu->rswitch; + struct msg_rsp rsp; + int ret; + + alloc_req.contig = true; + alloc_req.count = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs; + ret = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req, + &alloc_rsp); + if (ret) { + dev_err(rvu->dev, + "Unable to allocate MCAM entries\n"); + goto exit; + } + + if (alloc_rsp.count != alloc_req.count) { + dev_err(rvu->dev, + "Unable to allocate %d MCAM entries, got %d\n", + alloc_req.count, alloc_rsp.count); + goto free_entries; + } + + rswitch->entry2pcifunc = kcalloc(alloc_req.count, sizeof(u16), + GFP_KERNEL); + if (!rswitch->entry2pcifunc) + goto free_entries; + + rswitch->used_entries = alloc_rsp.count; + rswitch->start_entry = alloc_rsp.entry; + + ret = rvu_switch_install_rules(rvu); + if (ret) + goto uninstall_rules; + + return; + +uninstall_rules: + uninstall_req.start = rswitch->start_entry; + uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1; + rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp); + kfree(rswitch->entry2pcifunc); +free_entries: + free_req.all = 1; + rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp); +exit: + return; +} + +void rvu_switch_disable(struct rvu *rvu) +{ + struct npc_delete_flow_req uninstall_req = { 0 }; + struct npc_mcam_free_entry_req free_req = { 0 }; + struct rvu_switch *rswitch = &rvu->rswitch; + struct rvu_hwinfo *hw = rvu->hw; + int pf, vf, numvfs, hwvf; + struct msg_rsp rsp; + u16 pcifunc; + int err; + + if (!rswitch->used_entries) + return; + + for (pf = 1; pf < hw->total_pfs; pf++) { + if (!is_pf_cgxmapped(rvu, pf)) + continue; + + pcifunc = pf << 10; + err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); + if (err) + dev_err(rvu->dev, + "Reverting RX rule for PF%d failed(%d)\n", + pf, err); + + for (vf = 0; vf < numvfs; vf++, hwvf++) { + pcifunc = pf << 10 | ((vf + 1) & 0x3FF); + err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); + if (err) + dev_err(rvu->dev, + "Reverting RX rule for PF%dVF%d failed(%d)\n", + pf, vf, err); + } + } + + uninstall_req.start = rswitch->start_entry; + uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1; + free_req.all = 1; + rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp); + rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp); + rswitch->used_entries = 0; + kfree(rswitch->entry2pcifunc); +} + +void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc) +{ + struct rvu_switch *rswitch = &rvu->rswitch; + u32 max = rswitch->used_entries; + u16 entry; + + if (!rswitch->used_entries) + return; + + for (entry = 0; entry < max; entry++) { + if (rswitch->entry2pcifunc[entry] == pcifunc) + break; + } + + if (entry >= max) + return; + + rvu_switch_install_tx_rule(rvu, pcifunc, rswitch->start_entry + entry); + rvu_switch_install_rx_rule(rvu, pcifunc, 0x0); +} From 615c77eb5e870d1ffa95f4001cba3612bd2f2332 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 15 Jul 2021 00:10:26 -0500 Subject: [PATCH 0612/1469] powerpc/pasemi: Fix fall-through warning for Clang Fix the following fallthrough warning: arch/powerpc/platforms/pasemi/idle.c:45:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60efbf18.d9n6eXv275OJcc7T%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/powerpc/platforms/pasemi/idle.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c index 9b88e3cded7d..534b0317fc15 100644 --- a/arch/powerpc/platforms/pasemi/idle.c +++ b/arch/powerpc/platforms/pasemi/idle.c @@ -42,6 +42,7 @@ static int pasemi_system_reset_exception(struct pt_regs *regs) switch (regs->msr & SRR1_WAKEMASK) { case SRR1_WAKEDEC: set_dec(1); + break; case SRR1_WAKEEE: /* * Handle these when interrupts get re-enabled and we take From d6371c76e20d7d3f61b05fd67b596af4d14a8886 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 19 Jul 2021 09:51:34 +0100 Subject: [PATCH 0613/1469] bpf: Fix OOB read when printing XDP link fdinfo We got the following UBSAN report on one of our testing machines: ================================================================================ UBSAN: array-index-out-of-bounds in kernel/bpf/syscall.c:2389:24 index 6 is out of range for type 'char *[6]' CPU: 43 PID: 930921 Comm: systemd-coredum Tainted: G O 5.10.48-cloudflare-kasan-2021.7.0 #1 Hardware name: Call Trace: dump_stack+0x7d/0xa3 ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds.cold+0x43/0x48 ? seq_printf+0x17d/0x250 bpf_link_show_fdinfo+0x329/0x380 ? bpf_map_value_size+0xe0/0xe0 ? put_files_struct+0x20/0x2d0 ? __kasan_kmalloc.constprop.0+0xc2/0xd0 seq_show+0x3f7/0x540 seq_read_iter+0x3f8/0x1040 seq_read+0x329/0x500 ? seq_read_iter+0x1040/0x1040 ? __fsnotify_parent+0x80/0x820 ? __fsnotify_update_child_dentry_flags+0x380/0x380 vfs_read+0x123/0x460 ksys_read+0xed/0x1c0 ? __x64_sys_pwrite64+0x1f0/0x1f0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ================================================================================ ================================================================================ UBSAN: object-size-mismatch in kernel/bpf/syscall.c:2384:2 From the report, we can infer that some array access in bpf_link_show_fdinfo at index 6 is out of bounds. The obvious candidate is bpf_link_type_strs[BPF_LINK_TYPE_XDP] with BPF_LINK_TYPE_XDP == 6. It turns out that BPF_LINK_TYPE_XDP is missing from bpf_types.h and therefore doesn't have an entry in bpf_link_type_strs: pos: 0 flags: 02000000 mnt_id: 13 link_type: (null) link_id: 4 prog_tag: bcf7977d3b93787c prog_id: 4 ifindex: 1 Fixes: aa8d3a716b59 ("bpf, xdp: Add bpf_link-based XDP attachment API") Signed-off-by: Lorenz Bauer Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210719085134.43325-2-lmb@cloudflare.com --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a9db1eae6796..ae3ac3a2018c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif From 8cae8cd89f05f6de223d63e6d15e31c8ba9cf53b Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 13 Jul 2021 17:49:23 +0200 Subject: [PATCH 0614/1469] seq_file: disallow extremely large seq buffer allocations There is no reasonable need for a buffer larger than this, and it avoids int overflow pitfalls. Fixes: 058504edd026 ("fs/seq_file: fallback to vmalloc allocation") Suggested-by: Al Viro Reported-by: Qualys Security Advisory Signed-off-by: Eric Sandeen Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/seq_file.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/seq_file.c b/fs/seq_file.c index b117b212ef28..4a2cda04d3e2 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -32,6 +32,9 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { + if (unlikely(size > MAX_RW_COUNT)) + return NULL; + return kvmalloc(size, GFP_KERNEL_ACCOUNT); } From 8d4abca95ecc82fc8c41912fa0085281f19cc29f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 19 Apr 2021 18:43:32 -0500 Subject: [PATCH 0615/1469] media: ngene: Fix out-of-bounds bug in ngene_command_config_free_buf() Fix an 11-year old bug in ngene_command_config_free_buf() while addressing the following warnings caught with -Warray-bounds: arch/alpha/include/asm/string.h:22:16: warning: '__builtin_memcpy' offset [12, 16] from the object at 'com' is out of the bounds of referenced subobject 'config' with type 'unsigned char' at offset 10 [-Warray-bounds] arch/x86/include/asm/string_32.h:182:25: warning: '__builtin_memcpy' offset [12, 16] from the object at 'com' is out of the bounds of referenced subobject 'config' with type 'unsigned char' at offset 10 [-Warray-bounds] The problem is that the original code is trying to copy 6 bytes of data into a one-byte size member _config_ of the wrong structue FW_CONFIGURE_BUFFERS, in a single call to memcpy(). This causes a legitimate compiler warning because memcpy() overruns the length of &com.cmd.ConfigureBuffers.config. It seems that the right structure is FW_CONFIGURE_FREE_BUFFERS, instead, because it contains 6 more members apart from the header _hdr_. Also, the name of the function ngene_command_config_free_buf() suggests that the actual intention is to ConfigureFreeBuffers, instead of ConfigureBuffers (which takes place in the function ngene_command_config_buf(), above). Fix this by enclosing those 6 members of struct FW_CONFIGURE_FREE_BUFFERS into new struct config, and use &com.cmd.ConfigureFreeBuffers.config as the destination address, instead of &com.cmd.ConfigureBuffers.config, when calling memcpy(). This also helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy(). Link: https://github.com/KSPP/linux/issues/109 Fixes: dae52d009fc9 ("V4L/DVB: ngene: Initial check-in") Cc: stable@vger.kernel.org Reported-by: kernel test robot Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/linux-hardening/20210420001631.GA45456@embeddedor/ --- drivers/media/pci/ngene/ngene-core.c | 2 +- drivers/media/pci/ngene/ngene.h | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/media/pci/ngene/ngene-core.c b/drivers/media/pci/ngene/ngene-core.c index 07f342db6701..7481f553f959 100644 --- a/drivers/media/pci/ngene/ngene-core.c +++ b/drivers/media/pci/ngene/ngene-core.c @@ -385,7 +385,7 @@ static int ngene_command_config_free_buf(struct ngene *dev, u8 *config) com.cmd.hdr.Opcode = CMD_CONFIGURE_FREE_BUFFER; com.cmd.hdr.Length = 6; - memcpy(&com.cmd.ConfigureBuffers.config, config, 6); + memcpy(&com.cmd.ConfigureFreeBuffers.config, config, 6); com.in_len = 6; com.out_len = 0; diff --git a/drivers/media/pci/ngene/ngene.h b/drivers/media/pci/ngene/ngene.h index 84f04e0e0cb9..3d296f1998a1 100644 --- a/drivers/media/pci/ngene/ngene.h +++ b/drivers/media/pci/ngene/ngene.h @@ -407,12 +407,14 @@ enum _BUFFER_CONFIGS { struct FW_CONFIGURE_FREE_BUFFERS { struct FW_HEADER hdr; - u8 UVI1_BufferLength; - u8 UVI2_BufferLength; - u8 TVO_BufferLength; - u8 AUD1_BufferLength; - u8 AUD2_BufferLength; - u8 TVA_BufferLength; + struct { + u8 UVI1_BufferLength; + u8 UVI2_BufferLength; + u8 TVO_BufferLength; + u8 AUD1_BufferLength; + u8 AUD2_BufferLength; + u8 TVA_BufferLength; + } __packed config; } __attribute__ ((__packed__)); struct FW_CONFIGURE_UART { From fae21608c31ca987d9dfc0422ac9b5bd21c213a6 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Mon, 5 Jul 2021 20:29:50 +0530 Subject: [PATCH 0616/1469] scsi: mpt3sas: Transition IOC to Ready state during shutdown The IOC firmware assumes that the host driver is still alive after shutdown and continues to post events to host memory (due to faulty expander phy links, etc). This leads to 0x2666 (a bus fault occurred during a host-IOC memory access). Perform an IOC soft reset as part of shutdown to disable event posting. Link: https://lore.kernel.org/r/20210705145951.32258-1-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 32 ++++++++++++++-------------- drivers/scsi/mpt3sas/mpt3sas_base.h | 4 ++++ drivers/scsi/mpt3sas/mpt3sas_scsih.c | 7 +++++- 3 files changed, 26 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index c39955239d1c..19b1c0cf5f2a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2983,13 +2983,13 @@ _base_check_enable_msix(struct MPT3SAS_ADAPTER *ioc) } /** - * _base_free_irq - free irq + * mpt3sas_base_free_irq - free irq * @ioc: per adapter object * * Freeing respective reply_queue from the list. */ -static void -_base_free_irq(struct MPT3SAS_ADAPTER *ioc) +void +mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc) { struct adapter_reply_queue *reply_q, *next; @@ -3191,12 +3191,12 @@ _base_check_and_enable_high_iops_queues(struct MPT3SAS_ADAPTER *ioc, } /** - * _base_disable_msix - disables msix + * mpt3sas_base_disable_msix - disables msix * @ioc: per adapter object * */ -static void -_base_disable_msix(struct MPT3SAS_ADAPTER *ioc) +void +mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc) { if (!ioc->msix_enable) return; @@ -3304,8 +3304,8 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc) for (i = 0; i < ioc->reply_queue_count; i++) { r = _base_request_irq(ioc, i); if (r) { - _base_free_irq(ioc); - _base_disable_msix(ioc); + mpt3sas_base_free_irq(ioc); + mpt3sas_base_disable_msix(ioc); goto try_ioapic; } } @@ -3342,8 +3342,8 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc) dexitprintk(ioc, ioc_info(ioc, "%s\n", __func__)); - _base_free_irq(ioc); - _base_disable_msix(ioc); + mpt3sas_base_free_irq(ioc); + mpt3sas_base_disable_msix(ioc); kfree(ioc->replyPostRegisterIndex); ioc->replyPostRegisterIndex = NULL; @@ -7613,14 +7613,14 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc) } /** - * _base_make_ioc_ready - put controller in READY state + * mpt3sas_base_make_ioc_ready - put controller in READY state * @ioc: per adapter object * @type: FORCE_BIG_HAMMER or SOFT_RESET * * Return: 0 for success, non-zero for failure. */ -static int -_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type) +int +mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type) { u32 ioc_state; int rc; @@ -7897,7 +7897,7 @@ mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc) if (ioc->chip_phys && ioc->chip) { mpt3sas_base_mask_interrupts(ioc); ioc->shost_recovery = 1; - _base_make_ioc_ready(ioc, SOFT_RESET); + mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET); ioc->shost_recovery = 0; } @@ -8017,7 +8017,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->build_sg_mpi = &_base_build_sg; ioc->build_zero_len_sge_mpi = &_base_build_zero_len_sge; - r = _base_make_ioc_ready(ioc, SOFT_RESET); + r = mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET); if (r) goto out_free_resources; @@ -8471,7 +8471,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc, _base_pre_reset_handler(ioc); mpt3sas_wait_for_commands_to_complete(ioc); mpt3sas_base_mask_interrupts(ioc); - r = _base_make_ioc_ready(ioc, type); + r = mpt3sas_base_make_ioc_ready(ioc, type); if (r) goto out; _base_clear_outstanding_commands(ioc); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index d4834c8ee9c0..0c6c3df0038d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1730,6 +1730,10 @@ do { ioc_err(ioc, "In func: %s\n", __func__); \ status, mpi_request, sz); } while (0) int mpt3sas_wait_for_ioc(struct MPT3SAS_ADAPTER *ioc, int wait_count); +int +mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type); +void mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc); +void mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc); /* scsih shared API */ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 866d118f7931..8e64a6f14542 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11295,7 +11295,12 @@ scsih_shutdown(struct pci_dev *pdev) _scsih_ir_shutdown(ioc); _scsih_nvme_shutdown(ioc); - mpt3sas_base_detach(ioc); + mpt3sas_base_mask_interrupts(ioc); + ioc->shost_recovery = 1; + mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET); + ioc->shost_recovery = 0; + mpt3sas_base_free_irq(ioc); + mpt3sas_base_disable_msix(ioc); } From 114613f62f42e7cbc1242c4e82076a0153043761 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 19 Jul 2021 18:17:46 -0500 Subject: [PATCH 0617/1469] ALSA: hda: intel-dsp-cfg: add missing ElkhartLake PCI ID We missed the fact that ElkhartLake platforms have two different PCI IDs. We only added one so the SOF driver is never selected by the autodetection logic for the missing configuration. BugLink: https://github.com/thesofproject/linux/issues/2990 Fixes: cc8f81c7e625 ('ALSA: hda: fix intel DSP config') Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210719231746.557325-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai --- sound/hda/intel-dsp-config.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index d8be146793ee..c9d0ba353463 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -319,6 +319,10 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC, .device = 0x4b55, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC, + .device = 0x4b58, + }, #endif /* Alder Lake */ From e9db418d4b828dd049caaf5ed65dc86f93bb1a0c Mon Sep 17 00:00:00 2001 From: Ian Ray Date: Mon, 19 Jul 2021 18:43:49 +0200 Subject: [PATCH 0618/1469] USB: serial: cp210x: fix comments for GE CS1000 Fix comments for GE CS1000 CP210x USB ID assignments. Fixes: 42213a0190b5 ("USB: serial: cp210x: add some more GE USB IDs") Signed-off-by: Ian Ray Signed-off-by: Sebastian Reichel Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 09b845d0da41..af286240807e 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -202,8 +202,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ { USB_DEVICE(0x1901, 0x0195) }, /* GE B850/B650/B450 CP2104 DP UART interface */ { USB_DEVICE(0x1901, 0x0196) }, /* GE B850 CP2105 DP UART interface */ - { USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 Display serial interface */ - { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 M.2 Key E serial interface */ + { USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 M.2 Key E serial interface */ + { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 Display serial interface */ { USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */ { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ From 47e1e233e9d822dfda068383fb9a616451bda703 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 20 Jul 2021 09:28:09 +0200 Subject: [PATCH 0619/1469] efi/mokvar: Reserve the table only if it is in boot services data One of the SUSE QA tests triggered: localhost kernel: efi: Failed to lookup EFI memory descriptor for 0x000000003dcf8000 which comes from x86's version of efi_arch_mem_reserve() trying to reserve a memory region. Usually, that function expects EFI_BOOT_SERVICES_DATA memory descriptors but the above case is for the MOKvar table which is allocated in the EFI shim as runtime services. That lead to a fix changing the allocation of that table to boot services. However, that fix broke booting SEV guests with that shim leading to this kernel fix 8d651ee9c71b ("x86/ioremap: Map EFI-reserved memory as encrypted for SEV") which extended the ioremap hint to map reserved EFI boot services as decrypted too. However, all that wasn't needed, IMO, because that error message in efi_arch_mem_reserve() was innocuous in this case - if the MOKvar table is not in boot services, then it doesn't need to be reserved in the first place because it is, well, in runtime services which *should* be reserved anyway. So do that reservation for the MOKvar table only if it is allocated in boot services data. I couldn't find any requirement about where that table should be allocated in, unlike the ESRT which allocation is mandated to be done in boot services data by the UEFI spec. Signed-off-by: Borislav Petkov Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/mokvar-table.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c index d8bc01340686..38722d2009e2 100644 --- a/drivers/firmware/efi/mokvar-table.c +++ b/drivers/firmware/efi/mokvar-table.c @@ -180,7 +180,10 @@ void __init efi_mokvar_table_init(void) pr_err("EFI MOKvar config table is not valid\n"); return; } - efi_mem_reserve(efi.mokvar_table, map_size_needed); + + if (md.type == EFI_BOOT_SERVICES_DATA) + efi_mem_reserve(efi.mokvar_table, map_size_needed); + efi_mokvar_table_size = map_size_needed; } From c4824ae7db418aee6f50f308a20b832e58e997fd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 20 Jul 2021 11:26:40 +0200 Subject: [PATCH 0620/1469] ALSA: pcm: Fix mmap capability check The hw_support_mmap() doesn't cover all memory allocation types and might use a wrong device pointer for checking the capability. Check the all memory allocation types more completely. Cc: Link: https://lore.kernel.org/r/20210720092640.12338-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index c88c4316c417..6919d2943b9d 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -246,12 +246,18 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP)) return false; - if (substream->ops->mmap || - (substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV && - substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV_UC)) + if (substream->ops->mmap) return true; - return dma_can_mmap(substream->dma_buffer.dev.dev); + switch (substream->dma_buffer.dev.type) { + case SNDRV_DMA_TYPE_UNKNOWN: + return false; + case SNDRV_DMA_TYPE_CONTINUOUS: + case SNDRV_DMA_TYPE_VMALLOC: + return true; + default: + return dma_can_mmap(substream->dma_buffer.dev.dev); + } } static int constrain_mask_params(struct snd_pcm_substream *substream, From d371588910715ebf7fa8e3a5d21ea5169c852927 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 20 Jul 2021 11:27:32 +0200 Subject: [PATCH 0621/1469] ALSA: pcm: Fix mmap without buffer preallocation The recent rewrite of the memory allocation helpers also changed the page extraction to a common helper, snd_sgbuf_get_page(). But this assumes implicitly that the buffer was allocated via the standard helper (usually via preallocation), and didn't consider the case of the manual buffer handling. This patch fixes it and also covers the manual buffer management. Fixes: 37af81c5998f ("ALSA: core: Abstract memory alloc helpers") Link: https://lore.kernel.org/r/20210720092732.12412-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 6919d2943b9d..6a2971a7e6a1 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3675,6 +3675,8 @@ static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; if (substream->ops->page) page = substream->ops->page(substream, offset); + else if (!snd_pcm_get_dma_buf(substream)) + page = virt_to_page(runtime->dma_area + offset); else page = snd_sgbuf_get_page(snd_pcm_get_dma_buf(substream), offset); if (!page) From 2d85a1b31dde84038ea07ad825c3d8d3e71f4344 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 19 Jul 2021 10:55:14 +0300 Subject: [PATCH 0622/1469] ipv6: ip6_finish_output2: set sk into newly allocated nskb skb_set_owner_w() should set sk not to old skb but to new nskb. Fixes: 5796015fa968 ("ipv6: allocate enough headroom in ip6_finish_output2()") Signed-off-by: Vasily Averin Link: https://lore.kernel.org/r/70c0744f-89ae-1869-7e3e-4fa292158f4b@virtuozzo.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 01bea76e3891..e1b9f7ac8bad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -74,7 +74,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (likely(nskb)) { if (skb->sk) - skb_set_owner_w(skb, skb->sk); + skb_set_owner_w(nskb, skb->sk); consume_skb(skb); } else { kfree_skb(skb); From 749468760b952e555529ca8a71256b991455101e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Jul 2021 02:20:28 -0700 Subject: [PATCH 0623/1469] net/tcp_fastopen: remove obsolete extern After cited commit, sysctl_tcp_fastopen_blackhole_timeout is no longer a global variable. Fixes: 3733be14a32b ("ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob") Signed-off-by: Eric Dumazet Cc: Haishuang Yan Cc: Yuchung Cheng Cc: Neal Cardwell Acked-by: Wei Wang Link: https://lore.kernel.org/r/20210719092028.3016745-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 17df9b047ee4..784d5c3ef1c5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1709,7 +1709,6 @@ struct tcp_fastopen_context { struct rcu_head rcu; }; -extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); From 6c2d125823ae89d10293437c6fb8a2f3406d721a Mon Sep 17 00:00:00 2001 From: Landen Chao Date: Tue, 20 Jul 2021 11:50:07 +0800 Subject: [PATCH 0624/1469] net: Update MAINTAINERS for MediaTek switch driver Update maintainers for MediaTek switch driver with Deng Qingfang who has contributed many high-quality patches (interrupt, VLAN, GPIO, and etc.) and will help maintenance. Signed-off-by: Landen Chao Signed-off-by: DENG Qingfang Reviewed-by: Florian Fainelli Acked-by: Vladimir Oltean Link: https://lore.kernel.org/r/49e1aa8aac58dcbf1b5e036d09b3fa3bbb1d94d0.1626751861.git.landen.chao@mediatek.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 5779f6cacff7..e5ec539b15ed 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11757,6 +11757,7 @@ F: drivers/char/hw_random/mtk-rng.c MEDIATEK SWITCH DRIVER M: Sean Wang M: Landen Chao +M: DENG Qingfang L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530.* From cbb56b03ec3f317e3728d0f68d25d4b9e590cdc9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 12:39:16 +0300 Subject: [PATCH 0625/1469] net: bridge: do not replay fdb entries pointing towards the bridge twice This simple script: ip link add br0 type bridge ip link set swp2 master br0 ip link set br0 address 00:01:02:03:04:05 ip link del br0 produces this result on a DSA switch: [ 421.306399] br0: port 1(swp2) entered blocking state [ 421.311445] br0: port 1(swp2) entered disabled state [ 421.472553] device swp2 entered promiscuous mode [ 421.488986] device swp2 left promiscuous mode [ 421.493508] br0: port 1(swp2) entered disabled state [ 421.886107] sja1105 spi0.1: port 1 failed to delete 00:01:02:03:04:05 vid 1 from fdb: -ENOENT [ 421.894374] sja1105 spi0.1: port 1 failed to delete 00:01:02:03:04:05 vid 0 from fdb: -ENOENT [ 421.943982] br0: port 1(swp2) entered blocking state [ 421.949030] br0: port 1(swp2) entered disabled state [ 422.112504] device swp2 entered promiscuous mode A very simplified view of what happens is: (1) the bridge port is created, and the bridge device inherits its MAC address (2) when joining, the bridge port (DSA) requests a replay of the addition of all FDB entries towards this bridge port and towards the bridge device itself. In fact, DSA calls br_fdb_replay() twice: br_fdb_replay(br, brport_dev); br_fdb_replay(br, br); DSA uses reference counting for the FDB entries. So the MAC address of the bridge is simply kept with refcount 2. When the bridge port leaves under normal circumstances, everything cancels out since the replay of the FDB entry deletion is also done twice per VLAN. (3) when the bridge MAC address changes, switchdev is notified of the deletion of the old address and of the insertion of the new one. But the old address does not really go away, since it had refcount 2, and the new address is added "only" with refcount 1. (4) when the bridge port leaves now, it will replay a deletion of the FDB entries pointing towards the bridge twice. Then DSA will complain that it can't delete something that no longer exists. It is clear that the problem is that the FDB entries towards the bridge are replayed too many times, so let's fix that problem. Fixes: 63c51453c82c ("net: dsa: replay the local bridge FDB entries pointing to the bridge dev too") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210719093916.4099032-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- net/bridge/br_fdb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2b862cffc03a..a16191dcaed1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; - if (dst_dev != br_dev && dst_dev != dev) + if (dst_dev && dst_dev != dev) continue; err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); From 1b713d14dc3c077ec45e65dab4ea01a8bc41b8c1 Mon Sep 17 00:00:00 2001 From: Chengwen Feng Date: Mon, 19 Jul 2021 17:13:05 +0800 Subject: [PATCH 0626/1469] net: hns3: fix possible mismatches resp of mailbox Currently, the mailbox synchronous communication between VF and PF use the following fields to maintain communication: 1. Origin_mbx_msg which was combined by message code and subcode, used to match request and response. 2. Received_resp which means whether received response. There may possible mismatches of the following situation: 1. VF sends message A with code=1 subcode=1. 2. PF was blocked about 500ms when processing the message A. 3. VF will detect message A timeout because it can't get the response within 500ms. 4. VF sends message B with code=1 subcode=1 which equal message A. 5. PF processes the first message A and send the response message to VF. 6. VF will identify the response matched the message B because the code/subcode is the same. This will lead to mismatch of request and response. To fix the above bug, we use the following scheme: 1. The message sent from VF was labelled with match_id which was a unique 16-bit non-zero value. 2. The response sent from PF will label with match_id which got from the request. 3. The VF uses the match_id to match request and response message. As for PF driver, it only needs to copy the match_id from request to response. Fixes: dde1a86e93ca ("net: hns3: Add mailbox support to PF driver") Signed-off-by: Chengwen Feng Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 6 ++++-- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 0a6cda309b24..56b573e47072 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -143,7 +143,8 @@ struct hclge_mbx_vf_to_pf_cmd { u8 mbx_need_resp; u8 rsv1[1]; u8 msg_len; - u8 rsv2[3]; + u8 rsv2; + u16 match_id; struct hclge_vf_to_pf_msg msg; }; @@ -153,7 +154,8 @@ struct hclge_mbx_pf_to_vf_cmd { u8 dest_vfid; u8 rsv[3]; u8 msg_len; - u8 rsv1[3]; + u8 rsv1; + u16 match_id; struct hclge_pf_to_vf_msg msg; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index e10a2c36b706..c0a478ae9583 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -47,6 +47,7 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport, resp_pf_to_vf->dest_vfid = vf_to_pf_req->mbx_src_vfid; resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len; + resp_pf_to_vf->match_id = vf_to_pf_req->match_id; resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP; resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code; From 4671042f1ef0d37137884811afcc4ae67685ce07 Mon Sep 17 00:00:00 2001 From: Peng Li Date: Mon, 19 Jul 2021 17:13:06 +0800 Subject: [PATCH 0627/1469] net: hns3: add match_id to check mailbox response from PF to VF When VF need response from PF, VF will wait (1us - 1s) to receive the response, or it will wait timeout and the VF action fails. If VF do not receive response in 1st action because timeout, the 2nd action may receive response for the 1st action, and get incorrect response data.VF must reciveve the right response from PF,or it will cause unexpected error. This patch adds match_id to check mailbox response from PF to VF, to make sure VF get the right response: 1. The message sent from VF was labelled with match_id which was a unique 16-bit non-zero value. 2. The response sent from PF will label with match_id which got from the request. 3. The VF uses the match_id to match request and response message. This scheme depends on PF driver supports match_id, if PF driver doesn't support then VF will uses the original scheme. Signed-off-by: Peng Li Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- .../net/ethernet/hisilicon/hns3/hclge_mbx.h | 1 + .../hisilicon/hns3/hns3vf/hclgevf_mbx.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 56b573e47072..aa86a81c8f4a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -98,6 +98,7 @@ struct hclgevf_mbx_resp_status { u32 origin_mbx_msg; bool received_resp; int resp_status; + u16 match_id; u8 additional_info[HCLGE_MBX_MAX_RESP_DATA_SIZE]; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index 9b17735b9f4c..772b2f8acd2e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -13,6 +13,7 @@ static int hclgevf_resp_to_errno(u16 resp_code) return resp_code ? -resp_code : 0; } +#define HCLGEVF_MBX_MATCH_ID_START 1 static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev) { /* this function should be called with mbx_resp.mbx_mutex held @@ -21,6 +22,10 @@ static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev) hdev->mbx_resp.received_resp = false; hdev->mbx_resp.origin_mbx_msg = 0; hdev->mbx_resp.resp_status = 0; + hdev->mbx_resp.match_id++; + /* Update match_id and ensure the value of match_id is not zero */ + if (hdev->mbx_resp.match_id == 0) + hdev->mbx_resp.match_id = HCLGEVF_MBX_MATCH_ID_START; memset(hdev->mbx_resp.additional_info, 0, HCLGE_MBX_MAX_RESP_DATA_SIZE); } @@ -115,6 +120,7 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, if (need_resp) { mutex_lock(&hdev->mbx_resp.mbx_mutex); hclgevf_reset_mbx_resp_status(hdev); + req->match_id = hdev->mbx_resp.match_id; status = hclgevf_cmd_send(&hdev->hw, &desc, 1); if (status) { dev_err(&hdev->pdev->dev, @@ -211,6 +217,19 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) resp->additional_info[i] = *temp; temp++; } + + /* If match_id is not zero, it means PF support + * match_id. If the match_id is right, VF get the + * right response, otherwise ignore the response. + * Driver will clear hdev->mbx_resp when send + * next message which need response. + */ + if (req->match_id) { + if (req->match_id == resp->match_id) + resp->received_resp = true; + } else { + resp->received_resp = true; + } break; case HCLGE_MBX_LINK_STAT_CHANGE: case HCLGE_MBX_ASSERTING_RESET: From 184cd221a86321e53df9389c4b35a247b60c1e77 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Mon, 19 Jul 2021 17:13:07 +0800 Subject: [PATCH 0628/1469] net: hns3: disable port VLAN filter when support function level VLAN filter control For hardware limitation, port VLAN filter is port level, and effective for all the functions of the port. So if not support port VLAN bypass, it's necessary to disable the port VLAN filter, in order to support function level VLAN filter control. Fixes: 2ba306627f59 ("net: hns3: add support for modify VLAN filter state") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index dd3354a57c62..ebeaf12e409b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9552,13 +9552,17 @@ static int hclge_set_vport_vlan_filter(struct hclge_vport *vport, bool enable) if (ret) return ret; - if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) + if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) { ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id, !enable); - else if (!vport->vport_id) + } else if (!vport->vport_id) { + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps)) + enable = false; + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, HCLGE_FILTER_FE_INGRESS, enable, 0); + } return ret; } From bbfd4506f962e7e6fff8f37f017154a3c3791264 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Mon, 19 Jul 2021 17:13:08 +0800 Subject: [PATCH 0629/1469] net: hns3: fix rx VLAN offload state inconsistent issue Currently, VF doesn't enable rx VLAN offload when initializating, and PF does it for VFs. If user disable the rx VLAN offload for VF with ethtool -K, and reload the VF driver, it may cause the rx VLAN offload state being inconsistent between hardware and software. Fixes it by enabling rx VLAN offload when VF initializing. Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- .../net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 52eaf82b7cd7..8784d61e833f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2641,6 +2641,16 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev) static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev) { + struct hnae3_handle *nic = &hdev->nic; + int ret; + + ret = hclgevf_en_hw_strip_rxvtag(nic, true); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to enable rx vlan offload, ret = %d\n", ret); + return ret; + } + return hclgevf_set_vlan_filter(&hdev->nic, htons(ETH_P_8021Q), 0, false); } From c45c1e82bba130db4f19d9dbc1deefcf4ea994ed Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Sat, 17 Jul 2021 00:02:45 +0300 Subject: [PATCH 0630/1469] spi: spi-bcm2835: Fix deadlock The bcm2835_spi_transfer_one function can create a deadlock if it is called while another thread already has the CCF lock. Signed-off-by: Alexandru Tachici Fixes: f8043872e796 ("spi: add driver for BCM2835") Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20210716210245.13240-2-alexandru.tachici@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-bcm2835.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 5f8771fe1a31..775c0bf2f923 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -83,6 +83,7 @@ MODULE_PARM_DESC(polling_limit_us, * struct bcm2835_spi - BCM2835 SPI controller * @regs: base address of register map * @clk: core clock, divided to calculate serial clock + * @clk_hz: core clock cached speed * @irq: interrupt, signals TX FIFO empty or RX FIFO ¾ full * @tfr: SPI transfer currently processed * @ctlr: SPI controller reverse lookup @@ -116,6 +117,7 @@ MODULE_PARM_DESC(polling_limit_us, struct bcm2835_spi { void __iomem *regs; struct clk *clk; + unsigned long clk_hz; int irq; struct spi_transfer *tfr; struct spi_controller *ctlr; @@ -1045,19 +1047,18 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, { struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); struct bcm2835_spidev *slv = spi_get_ctldata(spi); - unsigned long spi_hz, clk_hz, cdiv; + unsigned long spi_hz, cdiv; unsigned long hz_per_byte, byte_limit; u32 cs = slv->prepare_cs; /* set clock */ spi_hz = tfr->speed_hz; - clk_hz = clk_get_rate(bs->clk); - if (spi_hz >= clk_hz / 2) { + if (spi_hz >= bs->clk_hz / 2) { cdiv = 2; /* clk_hz/2 is the fastest we can go */ } else if (spi_hz) { /* CDIV must be a multiple of two */ - cdiv = DIV_ROUND_UP(clk_hz, spi_hz); + cdiv = DIV_ROUND_UP(bs->clk_hz, spi_hz); cdiv += (cdiv % 2); if (cdiv >= 65536) @@ -1065,7 +1066,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, } else { cdiv = 0; /* 0 is the slowest we can go */ } - tfr->effective_speed_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536); + tfr->effective_speed_hz = cdiv ? (bs->clk_hz / cdiv) : (bs->clk_hz / 65536); bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv); /* handle all the 3-wire mode */ @@ -1354,6 +1355,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) return bs->irq ? bs->irq : -ENODEV; clk_prepare_enable(bs->clk); + bs->clk_hz = clk_get_rate(bs->clk); err = bcm2835_dma_init(ctlr, &pdev->dev, bs); if (err) From 68b11e8b1562986c134764433af64e97d30c9fc0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 20 Jul 2021 10:50:43 +0100 Subject: [PATCH 0631/1469] io_uring: explicitly count entries for poll reqs If __io_queue_proc() fails to add a second poll entry, e.g. kmalloc() failed, but it goes on with a third waitqueue, it may succeed and overwrite the error status. Count the number of poll entries we added, so we can set pt->error to zero at the beginning and find out when the mentioned scenario happens. Cc: stable@vger.kernel.org Fixes: 18bceab101add ("io_uring: allow POLL_ADD with double poll_wait() users") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9d6b9e561f88bcc0163623b74a76c39f712151c3.1626774457.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 0cac361bf6b8..6668902cf50c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4802,6 +4802,7 @@ IO_NETOP_FN(recv); struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; + int nr_entries; int error; }; @@ -4995,11 +4996,11 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, struct io_kiocb *req = pt->req; /* - * If poll->head is already set, it's because the file being polled - * uses multiple waitqueues for poll handling (eg one for read, one - * for write). Setup a separate io_poll_iocb if this happens. + * The file being polled uses multiple waitqueues for poll handling + * (e.g. one for read, one for write). Setup a separate io_poll_iocb + * if this happens. */ - if (unlikely(poll->head)) { + if (unlikely(pt->nr_entries)) { struct io_poll_iocb *poll_one = poll; /* already have a 2nd entry, fail a third attempt */ @@ -5027,7 +5028,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, *poll_ptr = poll; } - pt->error = 0; + pt->nr_entries++; poll->head = head; if (poll->events & EPOLLEXCLUSIVE) @@ -5104,9 +5105,12 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, ipt->pt._key = mask; ipt->req = req; - ipt->error = -EINVAL; + ipt->error = 0; + ipt->nr_entries = 0; mask = vfs_poll(req->file, &ipt->pt) & poll->events; + if (unlikely(!ipt->nr_entries) && !ipt->error) + ipt->error = -EINVAL; spin_lock_irq(&ctx->completion_lock); if (likely(poll->head)) { From 46fee9ab02cb24979bbe07631fc3ae95ae08aa3e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 20 Jul 2021 10:50:44 +0100 Subject: [PATCH 0632/1469] io_uring: remove double poll entry on arm failure __io_queue_proc() can enqueue both poll entries and still fail afterwards, so the callers trying to cancel it should also try to remove the second poll entry (if any). For example, it may leave the request alive referencing a io_uring context but not accessible for cancellation: [ 282.599913][ T1620] task:iou-sqp-23145 state:D stack:28720 pid:23155 ppid: 8844 flags:0x00004004 [ 282.609927][ T1620] Call Trace: [ 282.613711][ T1620] __schedule+0x93a/0x26f0 [ 282.634647][ T1620] schedule+0xd3/0x270 [ 282.638874][ T1620] io_uring_cancel_generic+0x54d/0x890 [ 282.660346][ T1620] io_sq_thread+0xaac/0x1250 [ 282.696394][ T1620] ret_from_fork+0x1f/0x30 Cc: stable@vger.kernel.org Fixes: 18bceab101add ("io_uring: allow POLL_ADD with double poll_wait() users") Reported-and-tested-by: syzbot+ac957324022b7132accf@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0ec1228fc5eda4cb524eeda857da8efdc43c331c.1626774457.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6668902cf50c..6486b54a0f62 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5113,6 +5113,8 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, ipt->error = -EINVAL; spin_lock_irq(&ctx->completion_lock); + if (ipt->error) + io_poll_remove_double(req); if (likely(poll->head)) { spin_lock(&poll->head->lock); if (unlikely(list_empty(&poll->wait.entry))) { From 362a9e65289284f36403058eea2462d0330c1f24 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 20 Jul 2021 16:38:05 +0800 Subject: [PATCH 0633/1469] io_uring: fix memleak in io_init_wq_offload() I got memory leak report when doing fuzz test: BUG: memory leak unreferenced object 0xffff888107310a80 (size 96): comm "syz-executor.6", pid 4610, jiffies 4295140240 (age 20.135s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... backtrace: [<000000001974933b>] kmalloc include/linux/slab.h:591 [inline] [<000000001974933b>] kzalloc include/linux/slab.h:721 [inline] [<000000001974933b>] io_init_wq_offload fs/io_uring.c:7920 [inline] [<000000001974933b>] io_uring_alloc_task_context+0x466/0x640 fs/io_uring.c:7955 [<0000000039d0800d>] __io_uring_add_tctx_node+0x256/0x360 fs/io_uring.c:9016 [<000000008482e78c>] io_uring_add_tctx_node fs/io_uring.c:9052 [inline] [<000000008482e78c>] __do_sys_io_uring_enter fs/io_uring.c:9354 [inline] [<000000008482e78c>] __se_sys_io_uring_enter fs/io_uring.c:9301 [inline] [<000000008482e78c>] __x64_sys_io_uring_enter+0xabc/0xc20 fs/io_uring.c:9301 [<00000000b875f18f>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000b875f18f>] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 [<000000006b0a8484>] entry_SYSCALL_64_after_hwframe+0x44/0xae CPU0 CPU1 io_uring_enter io_uring_enter io_uring_add_tctx_node io_uring_add_tctx_node __io_uring_add_tctx_node __io_uring_add_tctx_node io_uring_alloc_task_context io_uring_alloc_task_context io_init_wq_offload io_init_wq_offload hash = kzalloc hash = kzalloc ctx->hash_map = hash ctx->hash_map = hash <- one of the hash is leaked When calling io_uring_enter() in parallel, the 'hash_map' will be leaked, add uring_lock to protect 'hash_map'. Fixes: e941894eae31 ("io-wq: make buffered file write hashed work map per-ctx") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20210720083805.3030730-1-yangyingliang@huawei.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6486b54a0f62..fe3d948658ad 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7905,15 +7905,19 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, struct io_wq_data data; unsigned int concurrency; + mutex_lock(&ctx->uring_lock); hash = ctx->hash_map; if (!hash) { hash = kzalloc(sizeof(*hash), GFP_KERNEL); - if (!hash) + if (!hash) { + mutex_unlock(&ctx->uring_lock); return ERR_PTR(-ENOMEM); + } refcount_set(&hash->refs, 1); init_waitqueue_head(&hash->wait); ctx->hash_map = hash; } + mutex_unlock(&ctx->uring_lock); data.hash = hash; data.task = task; From 3abab27c322e0f2acf981595aa8040c9164dc9fb Mon Sep 17 00:00:00 2001 From: Charles Baylis Date: Fri, 16 Jul 2021 17:43:12 +0100 Subject: [PATCH 0634/1469] drm: Return -ENOTTY for non-drm ioctls drm: Return -ENOTTY for non-drm ioctls Return -ENOTTY from drm_ioctl() when userspace passes in a cmd number which doesn't relate to the drm subsystem. Glibc uses the TCGETS ioctl to implement isatty(), and without this change isatty() returns it incorrectly returns true for drm devices. To test run this command: $ if [ -t 0 ]; then echo is a tty; fi < /dev/dri/card0 which shows "is a tty" without this patch. This may also modify memory which the userspace application is not expecting. Signed-off-by: Charles Baylis Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/YPG3IBlzaMhfPqCr@stando.fishzet.co.uk --- drivers/gpu/drm/drm_ioctl.c | 3 +++ include/drm/drm_ioctl.h | 1 + 2 files changed, 4 insertions(+) diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 98ae00661656..f454e0424086 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -834,6 +834,9 @@ long drm_ioctl(struct file *filp, if (drm_dev_is_unplugged(dev)) return -ENODEV; + if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE) + return -ENOTTY; + is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END; if (is_driver_ioctl) { diff --git a/include/drm/drm_ioctl.h b/include/drm/drm_ioctl.h index 10100a4bbe2a..afb27cb6a7bd 100644 --- a/include/drm/drm_ioctl.h +++ b/include/drm/drm_ioctl.h @@ -68,6 +68,7 @@ typedef int drm_ioctl_compat_t(struct file *filp, unsigned int cmd, unsigned long arg); #define DRM_IOCTL_NR(n) _IOC_NR(n) +#define DRM_IOCTL_TYPE(n) _IOC_TYPE(n) #define DRM_MAJOR 226 /** From 7e777021780e9c373fc0c04d40b8407ce8c3b5d5 Mon Sep 17 00:00:00 2001 From: Eric Woudstra Date: Mon, 19 Jul 2021 20:23:57 +0200 Subject: [PATCH 0635/1469] mt7530 mt7530_fdb_write only set ivl bit vid larger than 1 Fixes my earlier patch which broke vlan unaware bridges. The IVL bit now only gets set for vid's larger than 1. Fixes: 11d8d98cbeef ("mt7530 fix mt7530_fdb_write vid missing ivl bit") Signed-off-by: Eric Woudstra Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 9e4df35f92cc..69f21b71614c 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -366,7 +366,8 @@ mt7530_fdb_write(struct mt7530_priv *priv, u16 vid, int i; reg[1] |= vid & CVID_MASK; - reg[1] |= ATA2_IVL; + if (vid > 1) + reg[1] |= ATA2_IVL; reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER; reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP; /* STATIC_ENT indicate that entry is static wouldn't From 727d6a8b7ef3d25080fad228b2c4a1d4da5999c6 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Mon, 19 Jul 2021 16:41:24 -0700 Subject: [PATCH 0636/1469] net/sched: act_skbmod: Skip non-Ethernet packets Currently tcf_skbmod_act() assumes that packets use Ethernet as their L2 protocol, which is not always the case. As an example, for CAN devices: $ ip link add dev vcan0 type vcan $ ip link set up vcan0 $ tc qdisc add dev vcan0 root handle 1: htb $ tc filter add dev vcan0 parent 1: protocol ip prio 10 \ matchall action skbmod swap mac Doing the above silently corrupts all the packets. Do not perform skbmod actions for non-Ethernet packets. Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Reviewed-by: Cong Wang Signed-off-by: Peilin Ye Signed-off-by: David S. Miller --- net/sched/act_skbmod.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 81a1c67335be..8d17a543cc9f 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + if (!skb->dev || skb->dev->type != ARPHRD_ETHER) + return action; + /* XXX: if you are going to edit more fields beyond ethernet header * (example when you add IP header replacement or vlan swap) * then MAX_EDIT_LEN needs to change appropriately @@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; - action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) - goto drop; - p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) From 75d5641497a60bb5d36ff77fd3f526906cbc148c Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Tue, 20 Jul 2021 08:08:38 +0300 Subject: [PATCH 0637/1469] fsl/fman: Add fibre support Set SUPPORTED_FIBRE to mac_dev->if_support. It allows proper usage of PHYs with optical/fiber support. Signed-off-by: Maxim Kochetkov Acked-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/mac.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 46ecb42f2ef8..d9fc5c456bf3 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -524,6 +524,7 @@ static void setup_memac(struct mac_device *mac_dev) | SUPPORTED_Autoneg \ | SUPPORTED_Pause \ | SUPPORTED_Asym_Pause \ + | SUPPORTED_FIBRE \ | SUPPORTED_MII) static DEFINE_MUTEX(eth_lock); From 8fb4792f091e608a0a1d353dfdf07ef55a719db5 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jul 2021 15:08:40 +0200 Subject: [PATCH 0638/1469] ipv6: fix another slab-out-of-bounds in fib6_nh_flush_exceptions While running the self-tests on a KASAN enabled kernel, I observed a slab-out-of-bounds splat very similar to the one reported in commit 821bbf79fe46 ("ipv6: Fix KASAN: slab-out-of-bounds Read in fib6_nh_flush_exceptions"). We additionally need to take care of fib6_metrics initialization failure when the caller provides an nh. The fix is similar, explicitly free the route instead of calling fib6_info_release on a half-initialized object. Fixes: f88d8ea67fbdb ("ipv6: Plumb support for nexthop object in a fib6_info") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7b756a7dc036..b6ddf23d3833 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; - goto out; + goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) From 91bed5565bba03b2a9f7334b58ae4be9df7c3840 Mon Sep 17 00:00:00 2001 From: Jia He Date: Tue, 20 Jul 2021 21:26:55 +0800 Subject: [PATCH 0639/1469] Revert "qed: fix possible unpaired spin_{un}lock_bh in _qed_mcp_cmd_and_union()" This reverts commit 6206b7981a36476f4695d661ae139f7db36a802d. That patch added additional spin_{un}lock_bh(), which was harmless but pointless. The orginal code path has guaranteed the pair of spin_{un}lock_bh(). We'd better revert it before we find the exact root cause of the bug_on mentioned in that patch. Fixes: 6206b7981a36 ("qed: fix possible unpaired spin_{un}lock_bh in _qed_mcp_cmd_and_union()") Cc: David S. Miller Cc: Prabhakar Kushwaha Signed-off-by: Jia He Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 79d879a5d663..4387292c37e2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -474,18 +474,14 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); - if (!qed_mcp_has_pending_cmd(p_hwfn)) { - spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); + if (!qed_mcp_has_pending_cmd(p_hwfn)) break; - } rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt); - if (!rc) { - spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); + if (!rc) break; - } else if (rc != -EAGAIN) { + else if (rc != -EAGAIN) goto err; - } spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); @@ -502,8 +498,6 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EAGAIN; } - spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); - /* Send the mailbox command */ qed_mcp_reread_offsets(p_hwfn, p_ptt); seq_num = ++p_hwfn->mcp_info->drv_mb_seq; @@ -530,18 +524,14 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); - if (p_cmd_elem->b_is_completed) { - spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); + if (p_cmd_elem->b_is_completed) break; - } rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt); - if (!rc) { - spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); + if (!rc) break; - } else if (rc != -EAGAIN) { + else if (rc != -EAGAIN) goto err; - } spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); } while (++cnt < max_retries); @@ -564,7 +554,6 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EAGAIN; } - spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem); spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); From 4152433c397697acc4b02c4a10d17d5859c2730d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 20 Jul 2021 21:14:05 +1000 Subject: [PATCH 0640/1469] arm64: efi: kaslr: Fix occasional random alloc (and boot) failure The EFI stub random allocator used for kaslr on arm64 has a subtle bug. In function get_entry_num_slots() which counts the number of possible allocation "slots" for the image in a given chunk of free EFI memory, "last_slot" can become negative if the chunk is smaller than the requested allocation size. The test "if (first_slot > last_slot)" doesn't catch it because both first_slot and last_slot are unsigned. I chose not to make them signed to avoid problems if this is ever used on architectures where there are meaningful addresses with the top bit set. Instead, fix it with an additional test against the allocation size. This can cause a boot failure in addition to a loss of randomisation due to another bug in the arm64 stub fixed separately. Signed-off-by: Benjamin Herrenschmidt Fixes: 2ddbfc81eac8 ("efi: stub: add implementation of efi_random_alloc()") Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/randomalloc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index a408df474d83..724155b9e10d 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -30,6 +30,8 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, (u64)ULONG_MAX); + if (region_end < size) + return 0; first_slot = round_up(md->phys_addr, align); last_slot = round_down(region_end - size + 1, align); From e81d71e343c6c62cf323042caed4b7ca049deda5 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Tue, 20 Jul 2021 18:32:16 +0300 Subject: [PATCH 0641/1469] ALSA: hda/hdmi: Add quirk to force pin connectivity on NUC10 On some Intel NUC10 variants, codec reports AC_JACK_PORT_NONE as pin default config for all pins. This results in broken audio. Add a quirk to force connectivity. BugLink: https://github.com/clearlinux/distribution/issues/2396 Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20210720153216.2200938-1-kai.vehmanen@linux.intel.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 84c088912b3c..e143e69d8184 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1941,6 +1941,7 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), + SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1), {} }; From 8798d070d416d18a75770fc19787e96705073f43 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 3 Jul 2021 11:56:55 +0200 Subject: [PATCH 0642/1469] rbd: always kick acquire on "acquired" and "released" notifications Skipping the "lock has been released" notification if the lock owner is not what we expect based on owner_cid can lead to I/O hangs. One example is our own notifications: because owner_cid is cleared in rbd_unlock(), when we get our own notification it is processed as unexpected/duplicate and maybe_kick_acquire() isn't called. If a peer that requested the lock then doesn't go through with acquiring it, I/O requests that came in while the lock was being quiesced would be stalled until another I/O request is submitted and kicks acquire from rbd_img_exclusive_lock(). This makes the comment in rbd_release_lock() actually true: prior to this change the canceled work was being requeued in response to the "lock has been acquired" notification from rbd_handle_acquired_lock(). Cc: stable@vger.kernel.org # 5.3+ Signed-off-by: Ilya Dryomov Tested-by: Robin Geuze --- drivers/block/rbd.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 531d390902dd..e77cea6a6189 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4203,15 +4203,11 @@ static void rbd_handle_acquired_lock(struct rbd_device *rbd_dev, u8 struct_v, if (!rbd_cid_equal(&cid, &rbd_empty_cid)) { down_write(&rbd_dev->lock_rwsem); if (rbd_cid_equal(&cid, &rbd_dev->owner_cid)) { - /* - * we already know that the remote client is - * the owner - */ - up_write(&rbd_dev->lock_rwsem); - return; + dout("%s rbd_dev %p cid %llu-%llu == owner_cid\n", + __func__, rbd_dev, cid.gid, cid.handle); + } else { + rbd_set_owner_cid(rbd_dev, &cid); } - - rbd_set_owner_cid(rbd_dev, &cid); downgrade_write(&rbd_dev->lock_rwsem); } else { down_read(&rbd_dev->lock_rwsem); @@ -4236,14 +4232,12 @@ static void rbd_handle_released_lock(struct rbd_device *rbd_dev, u8 struct_v, if (!rbd_cid_equal(&cid, &rbd_empty_cid)) { down_write(&rbd_dev->lock_rwsem); if (!rbd_cid_equal(&cid, &rbd_dev->owner_cid)) { - dout("%s rbd_dev %p unexpected owner, cid %llu-%llu != owner_cid %llu-%llu\n", + dout("%s rbd_dev %p cid %llu-%llu != owner_cid %llu-%llu\n", __func__, rbd_dev, cid.gid, cid.handle, rbd_dev->owner_cid.gid, rbd_dev->owner_cid.handle); - up_write(&rbd_dev->lock_rwsem); - return; + } else { + rbd_set_owner_cid(rbd_dev, &rbd_empty_cid); } - - rbd_set_owner_cid(rbd_dev, &rbd_empty_cid); downgrade_write(&rbd_dev->lock_rwsem); } else { down_read(&rbd_dev->lock_rwsem); From ed9eb71085ecb7ded9a5118cec2ab70667cc7350 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 3 Jul 2021 11:31:26 +0200 Subject: [PATCH 0643/1469] rbd: don't hold lock_rwsem while running_list is being drained Currently rbd_quiesce_lock() holds lock_rwsem for read while blocking on releasing_wait completion. On the I/O completion side, each image request also needs to take lock_rwsem for read. Because rw_semaphore implementation doesn't allow new readers after a writer has indicated interest in the lock, this can result in a deadlock if something that needs to take lock_rwsem for write gets involved. For example: 1. watch error occurs 2. rbd_watch_errcb() takes lock_rwsem for write, clears owner_cid and releases lock_rwsem 3. after reestablishing the watch, rbd_reregister_watch() takes lock_rwsem for write and calls rbd_reacquire_lock() 4. rbd_quiesce_lock() downgrades lock_rwsem to for read and blocks on releasing_wait until running_list becomes empty 5. another watch error occurs 6. rbd_watch_errcb() blocks trying to take lock_rwsem for write 7. no in-flight image request can complete and delete itself from running_list because lock_rwsem won't be granted anymore A similar scenario can occur with "lock has been acquired" and "lock has been released" notification handers which also take lock_rwsem for write to update owner_cid. We don't actually get anything useful from sitting on lock_rwsem in rbd_quiesce_lock() -- owner_cid updates certainly don't need to be synchronized with. In fact the whole owner_cid tracking logic could probably be removed from the kernel client because we don't support proxied maintenance operations. Cc: stable@vger.kernel.org # 5.3+ URL: https://tracker.ceph.com/issues/42757 Signed-off-by: Ilya Dryomov Tested-by: Robin Geuze --- drivers/block/rbd.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index e77cea6a6189..784797fa9a53 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4100,8 +4100,6 @@ again: static bool rbd_quiesce_lock(struct rbd_device *rbd_dev) { - bool need_wait; - dout("%s rbd_dev %p\n", __func__, rbd_dev); lockdep_assert_held_write(&rbd_dev->lock_rwsem); @@ -4113,11 +4111,11 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev) */ rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING; rbd_assert(!completion_done(&rbd_dev->releasing_wait)); - need_wait = !list_empty(&rbd_dev->running_list); - downgrade_write(&rbd_dev->lock_rwsem); - if (need_wait) - wait_for_completion(&rbd_dev->releasing_wait); - up_read(&rbd_dev->lock_rwsem); + if (list_empty(&rbd_dev->running_list)) + return true; + + up_write(&rbd_dev->lock_rwsem); + wait_for_completion(&rbd_dev->releasing_wait); down_write(&rbd_dev->lock_rwsem); if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING) From cdb330f4b41ab55feb35487729e883c9e08b8a54 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Thu, 15 Jul 2021 14:40:39 +0100 Subject: [PATCH 0644/1469] ceph: don't WARN if we're still opening a session to an MDS If MDSs aren't available while mounting a filesystem, the session state will transition from SESSION_OPENING to SESSION_CLOSING. And in that scenario check_session_state() will be called from delayed_work() and trigger this WARN. Avoid this by only WARNing after a session has already been established (i.e., the s_ttl will be different from 0). Fixes: 62575e270f66 ("ceph: check session state after bumping session->s_seq") Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a818213c972f..9db1b39df773 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4456,7 +4456,7 @@ bool check_session_state(struct ceph_mds_session *s) break; case CEPH_MDS_SESSION_CLOSING: /* Should never reach this when we're unmounting */ - WARN_ON_ONCE(true); + WARN_ON_ONCE(s->s_ttl); fallthrough; case CEPH_MDS_SESSION_NEW: case CEPH_MDS_SESSION_RESTARTING: From 463f36c76fa4ec015c640ff63ccf52e7527abee0 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Fri, 16 Jul 2021 22:00:22 +0200 Subject: [PATCH 0645/1469] s390/boot: fix use of expolines in the DMA code The DMA code section of the decompressor must be compiled with expolines if Spectre V2 mitigation has been enabled for the decompressed kernel. This is required because although the decompressor's image contains the DMA code section, it is handed over to the decompressed kernel for use. Because the DMA code is already slow w/o expolines, use expolines always regardless whether the decompressed kernel is using them or not. This simplifies the DMA code by dropping the conditional compilation of expolines. Fixes: bf72630130c2 ("s390: use proper expoline sections for .dma code") Cc: # 5.2 Signed-off-by: Alexander Egorenkov Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens --- arch/s390/boot/text_dma.S | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S index f7c77cd518f2..5ff5fee02801 100644 --- a/arch/s390/boot/text_dma.S +++ b/arch/s390/boot/text_dma.S @@ -9,16 +9,6 @@ #include #include -#ifdef CC_USING_EXPOLINE - .pushsection .dma.text.__s390_indirect_jump_r14,"axG" -__dma__s390_indirect_jump_r14: - larl %r1,0f - ex 0,0(%r1) - j . -0: br %r14 - .popsection -#endif - .section .dma.text,"ax" /* * Simplified version of expoline thunk. The normal thunks can not be used here, @@ -27,11 +17,10 @@ __dma__s390_indirect_jump_r14: * affects a few functions that are not performance-relevant. */ .macro BR_EX_DMA_r14 -#ifdef CC_USING_EXPOLINE - jg __dma__s390_indirect_jump_r14 -#else - br %r14 -#endif + larl %r1,0f + ex 0,0(%r1) + j . +0: br %r14 .endm /* From 7d244643758e4cb51a29f948f6be3edd15d92cc3 Mon Sep 17 00:00:00 2001 From: kernel test robot Date: Mon, 19 Jul 2021 12:41:41 +0800 Subject: [PATCH 0646/1469] s390/cpumf: fix semicolon.cocci warnings arch/s390/kernel/perf_cpum_cf.c:748:2-3: Unneeded semicolon Remove unneeded semicolon. Generated by: scripts/coccinelle/misc/semicolon.cocci Fixes: a029a4eab39e ("s390/cpumf: Allow concurrent access for CPU Measurement Counter Facility") CC: Thomas Richter Reported-by: kernel test robot Signed-off-by: kernel test robot Signed-off-by: Heiko Carstens --- arch/s390/kernel/perf_cpum_cf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 975a00c8c564..d7dc36ec0a60 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -745,7 +745,7 @@ static int __init cpumf_pmu_init(void) if (!cf_dbg) { pr_err("Registration of s390dbf(cpum_cf) failed\n"); return -ENOMEM; - }; + } debug_register_view(cf_dbg, &debug_sprintf_view); cpumf_pmu.attr_groups = cpumf_cf_event_group(); From 0cde560a8bfc3cb790715f39d4535129cca9e6ae Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 19 Jul 2021 21:58:21 +0200 Subject: [PATCH 0647/1469] s390: update defconfigs Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 24 ++++++++++++++++-------- arch/s390/configs/defconfig | 24 +++++++++++++++++------- arch/s390/configs/zfcpdump_defconfig | 3 +-- 3 files changed, 34 insertions(+), 17 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 55cb846cda37..7de253f766e8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -5,7 +5,12 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_LSM=y CONFIG_PREEMPT=y +CONFIG_SCHED_CORE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -28,14 +33,13 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y +CONFIG_CGROUP_MISC=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_BPF_LSM=y -CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y @@ -76,6 +80,7 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BLK_INLINE_ENCRYPTION=y CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y @@ -95,6 +100,7 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y +CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y @@ -158,6 +164,7 @@ CONFIG_IPV6_RPL_LWTUNNEL=y CONFIG_MPTCP=y CONFIG_NETFILTER=y CONFIG_BRIDGE_NETFILTER=m +CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -280,6 +287,7 @@ CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NFT_FIB_IPV4=m CONFIG_NF_TABLES_ARP=y +CONFIG_NF_LOG_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -384,12 +392,11 @@ CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y -CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y -CONFIG_PCI_IOV=y # CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y +CONFIG_PCI_IOV=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y @@ -496,6 +503,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MICROSOFT is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m @@ -552,7 +560,6 @@ CONFIG_INPUT_EVDEV=y CONFIG_LEGACY_PTY_COUNT=0 CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m -CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y CONFIG_PPS=m @@ -575,7 +582,6 @@ CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m -CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y @@ -620,6 +626,7 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m +CONFIG_NETFS_STATS=y CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -655,7 +662,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y @@ -683,6 +689,7 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y @@ -697,6 +704,7 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECDSA=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m @@ -844,7 +852,6 @@ CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m -CONFIG_TEST_LIST_SORT=y CONFIG_TEST_MIN_HEAP=y CONFIG_TEST_SORT=y CONFIG_KPROBES_SANITY_TEST=y @@ -854,3 +861,4 @@ CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m +CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 5d847ab5feaa..b671642967ba 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -4,6 +4,11 @@ CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_LSM=y +CONFIG_SCHED_CORE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -26,14 +31,13 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y +CONFIG_CGROUP_MISC=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_BPF_LSM=y -CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y @@ -70,6 +74,7 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BLK_INLINE_ENCRYPTION=y CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y @@ -87,6 +92,7 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y +CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y @@ -149,6 +155,7 @@ CONFIG_IPV6_RPL_LWTUNNEL=y CONFIG_MPTCP=y CONFIG_NETFILTER=y CONFIG_BRIDGE_NETFILTER=m +CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -271,6 +278,7 @@ CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NFT_FIB_IPV4=m CONFIG_NF_TABLES_ARP=y +CONFIG_NF_LOG_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -374,11 +382,10 @@ CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y -CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y -CONFIG_PCI_IOV=y # CONFIG_PCIEASPM is not set +CONFIG_PCI_IOV=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y @@ -488,6 +495,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MICROSOFT is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m @@ -544,7 +552,6 @@ CONFIG_INPUT_EVDEV=y CONFIG_LEGACY_PTY_COUNT=0 CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m -CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y # CONFIG_PTP_1588_CLOCK is not set @@ -567,7 +574,6 @@ CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m -CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y @@ -608,6 +614,7 @@ CONFIG_FUSE_FS=y CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m +CONFIG_NETFS_STATS=y CONFIG_FSCACHE=m CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y @@ -643,7 +650,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y @@ -670,6 +676,7 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y @@ -685,6 +692,7 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECDSA=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m @@ -755,6 +763,7 @@ CONFIG_CRC8=m CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y @@ -782,3 +791,4 @@ CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m +CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 76123a4b26ab..d576aaab27c9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -29,9 +29,9 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set # CONFIG_MIGRATION is not set -# CONFIG_BOUNCE is not set CONFIG_NET=y # CONFIG_IUCV is not set +# CONFIG_PCPU_DEV_REFCNT is not set # CONFIG_ETHTOOL_NETLINK is not set CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_RAM=y @@ -51,7 +51,6 @@ CONFIG_ZFCP=y # CONFIG_SERIO is not set # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set -CONFIG_RAW_DRIVER=y # CONFIG_HMC_DRV is not set # CONFIG_S390_TAPE is not set # CONFIG_VMCP is not set From 8ba89a3c7967808f33478a8573277cf6a7412c4c Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 14 Jul 2021 11:38:41 -0700 Subject: [PATCH 0648/1469] dmaengine: idxd: fix desc->vector that isn't being updated Missing update for desc->vector when the wq vector gets updated. This causes the desc->vector to always be at 0. Fixes: da435aedb00a ("dmaengine: idxd: fix array index when int_handles are being used") Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162628784374.353761.4736602409627820431.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/submit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index e29887528077..21d7d09f73dd 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -25,11 +25,10 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu) * Descriptor completion vectors are 1...N for MSIX. We will round * robin through the N vectors. */ - wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1; + wq->vec_ptr = desc->vector = (wq->vec_ptr % idxd->num_wq_irqs) + 1; if (!idxd->int_handles) { desc->hw->int_handle = wq->vec_ptr; } else { - desc->vector = wq->vec_ptr; /* * int_handles are only for descriptor completion. However for device * MSIX enumeration, vec 0 is used for misc interrupts. Therefore even From 7eb25da161befbc9a80e94e1bd90d6c06aa645cf Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 14 Jul 2021 14:57:19 -0700 Subject: [PATCH 0649/1469] dmaengine: idxd: fix sequence for pci driver remove() and shutdown() ->shutdown() call should only be responsible for quiescing the device. Currently it is doing PCI device tear down. This causes issue when things like MMIO mapping is removed while idxd_unregister_devices() will trigger removal of idxd device sub-driver and still initiates MMIO writes to the device. Another issue is with the unregistering of idxd 'struct device', the memory context gets freed. So the teardown calls are accessing freed memory and can cause kernel oops. Move all the teardown bits that doesn't belong in shutdown to ->remove() call. Move unregistering of the idxd conf_dev 'struct device' to after doing all the teardown to free all the memory that's no longer needed. Fixes: 47c16ac27d4c ("dmaengine: idxd: fix idxd conf_dev 'struct device' lifetime") Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162629983901.395844.17964803190905549615.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/init.c | 26 +++++++++++++++++--------- drivers/dma/idxd/sysfs.c | 2 -- 2 files changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 4e32a4dcc3ab..c0f4c0422f32 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -760,32 +760,40 @@ static void idxd_shutdown(struct pci_dev *pdev) for (i = 0; i < msixcnt; i++) { irq_entry = &idxd->irq_entries[i]; synchronize_irq(irq_entry->vector); - free_irq(irq_entry->vector, irq_entry); if (i == 0) continue; idxd_flush_pending_llist(irq_entry); idxd_flush_work_list(irq_entry); } - - idxd_msix_perm_clear(idxd); - idxd_release_int_handles(idxd); - pci_free_irq_vectors(pdev); - pci_iounmap(pdev, idxd->reg_base); - pci_disable_device(pdev); - destroy_workqueue(idxd->wq); + flush_workqueue(idxd->wq); } static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); + struct idxd_irq_entry *irq_entry; + int msixcnt = pci_msix_vec_count(pdev); + int i; dev_dbg(&pdev->dev, "%s called\n", __func__); idxd_shutdown(pdev); if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); idxd_unregister_devices(idxd); - perfmon_pmu_remove(idxd); + + for (i = 0; i < msixcnt; i++) { + irq_entry = &idxd->irq_entries[i]; + free_irq(irq_entry->vector, irq_entry); + } + idxd_msix_perm_clear(idxd); + idxd_release_int_handles(idxd); + pci_free_irq_vectors(pdev); + pci_iounmap(pdev, idxd->reg_base); iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + pci_disable_device(pdev); + destroy_workqueue(idxd->wq); + perfmon_pmu_remove(idxd); + device_unregister(&idxd->conf_dev); } static struct pci_driver idxd_pci_driver = { diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 0460d58e3941..bb4df63906a7 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1744,8 +1744,6 @@ void idxd_unregister_devices(struct idxd_device *idxd) device_unregister(&group->conf_dev); } - - device_unregister(&idxd->conf_dev); } int idxd_register_bus_type(void) From 6b4b87f2c31ac1af4f244990a7cbfb50d3f3e33f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 14 Jul 2021 11:50:06 -0700 Subject: [PATCH 0650/1469] dmaengine: idxd: fix submission race window Konstantin observed that when descriptors are submitted, the descriptor is added to the pending list after the submission. This creates a race window with the slight possibility that the descriptor can complete before it gets added to the pending list and this window would cause the completion handler to miss processing the descriptor. To address the issue, the addition of the descriptor to the pending list must be done before it gets submitted to the hardware. However, submitting to swq with ENQCMDS instruction can cause a failure with the condition of either wq is full or wq is not "active". With the descriptor allocation being the gate to the wq capacity, it is not possible to hit a retry with ENQCMDS submission to the swq. The only possible failure can happen is when wq is no longer "active" due to hw error and therefore we are moving towards taking down the portal. Given this is a rare condition and there's no longer concern over I/O performance, the driver can walk the completion lists in order to retrieve and abort the descriptor. The error path will set the descriptor to aborted status. It will take the work list lock to prevent further processing of worklist. It will do a delete_all on the pending llist to retrieve all descriptors on the pending llist. The delete_all action does not require a lock. It will walk through the acquired llist to find the aborted descriptor while add all remaining descriptors to the work list since it holds the lock. If it does not find the aborted descriptor on the llist, it will walk through the work list. And if it still does not find the descriptor, then it means the interrupt handler has removed the desc from the llist but is pending on the work list lock and will process it once the error path releases the lock. Fixes: eb15e7154fbf ("dmaengine: idxd: add interrupt handle request and release support") Reported-by: Konstantin Ananyev Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162628855747.360485.10101925573082466530.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/idxd.h | 14 +++++++ drivers/dma/idxd/irq.c | 27 +++++++++----- drivers/dma/idxd/submit.c | 78 ++++++++++++++++++++++++++++++++++----- 3 files changed, 101 insertions(+), 18 deletions(-) diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 26482c7d4c3a..fc708be7ad9a 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -294,6 +294,14 @@ struct idxd_desc { struct idxd_wq *wq; }; +/* + * This is software defined error for the completion status. We overload the error code + * that will never appear in completion status and only SWERR register. + */ +enum idxd_completion_status { + IDXD_COMP_DESC_ABORT = 0xff, +}; + #define confdev_to_idxd(dev) container_of(dev, struct idxd_device, conf_dev) #define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev) @@ -482,4 +490,10 @@ static inline void perfmon_init(void) {} static inline void perfmon_exit(void) {} #endif +static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason) +{ + idxd_dma_complete_txd(desc, reason); + idxd_free_desc(desc->wq, desc); +} + #endif diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index ae68e1e5487a..4e3a7198c0ca 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -245,12 +245,6 @@ static inline bool match_fault(struct idxd_desc *desc, u64 fault_addr) return false; } -static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason) -{ - idxd_dma_complete_txd(desc, reason); - idxd_free_desc(desc->wq, desc); -} - static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry, enum irq_work_type wtype, int *processed, u64 data) @@ -272,8 +266,16 @@ static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry, reason = IDXD_COMPLETE_DEV_FAIL; llist_for_each_entry_safe(desc, t, head, llnode) { - if (desc->completion->status) { - if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS) + u8 status = desc->completion->status & DSA_COMP_STATUS_MASK; + + if (status) { + if (unlikely(status == IDXD_COMP_DESC_ABORT)) { + complete_desc(desc, IDXD_COMPLETE_ABORT); + (*processed)++; + continue; + } + + if (unlikely(status != DSA_COMP_SUCCESS)) match_fault(desc, data); complete_desc(desc, reason); (*processed)++; @@ -329,7 +331,14 @@ static int irq_process_work_list(struct idxd_irq_entry *irq_entry, spin_unlock_irqrestore(&irq_entry->list_lock, flags); list_for_each_entry(desc, &flist, list) { - if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS) + u8 status = desc->completion->status & DSA_COMP_STATUS_MASK; + + if (unlikely(status == IDXD_COMP_DESC_ABORT)) { + complete_desc(desc, IDXD_COMPLETE_ABORT); + continue; + } + + if (unlikely(status != DSA_COMP_SUCCESS)) match_fault(desc, data); complete_desc(desc, reason); } diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 21d7d09f73dd..36c9c1a89b7e 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -87,9 +87,64 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc) sbitmap_queue_clear(&wq->sbq, desc->id, cpu); } +static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, + struct idxd_desc *desc) +{ + struct idxd_desc *d, *n; + + lockdep_assert_held(&ie->list_lock); + list_for_each_entry_safe(d, n, &ie->work_list, list) { + if (d == desc) { + list_del(&d->list); + return d; + } + } + + /* + * At this point, the desc needs to be aborted is held by the completion + * handler where it has taken it off the pending list but has not added to the + * work list. It will be cleaned up by the interrupt handler when it sees the + * IDXD_COMP_DESC_ABORT for completion status. + */ + return NULL; +} + +static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, + struct idxd_desc *desc) +{ + struct idxd_desc *d, *t, *found = NULL; + struct llist_node *head; + unsigned long flags; + + desc->completion->status = IDXD_COMP_DESC_ABORT; + /* + * Grab the list lock so it will block the irq thread handler. This allows the + * abort code to locate the descriptor need to be aborted. + */ + spin_lock_irqsave(&ie->list_lock, flags); + head = llist_del_all(&ie->pending_llist); + if (head) { + llist_for_each_entry_safe(d, t, head, llnode) { + if (d == desc) { + found = desc; + continue; + } + list_add_tail(&desc->list, &ie->work_list); + } + } + + if (!found) + found = list_abort_desc(wq, ie, desc); + spin_unlock_irqrestore(&ie->list_lock, flags); + + if (found) + complete_desc(found, IDXD_COMPLETE_ABORT); +} + int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) { struct idxd_device *idxd = wq->idxd; + struct idxd_irq_entry *ie = NULL; void __iomem *portal; int rc; @@ -107,6 +162,16 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) * even on UP because the recipient is a device. */ wmb(); + + /* + * Pending the descriptor to the lockless list for the irq_entry + * that we designated the descriptor to. + */ + if (desc->hw->flags & IDXD_OP_FLAG_RCI) { + ie = &idxd->irq_entries[desc->vector]; + llist_add(&desc->llnode, &ie->pending_llist); + } + if (wq_dedicated(wq)) { iosubmit_cmds512(portal, desc->hw, 1); } else { @@ -117,18 +182,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) * device is not accepting descriptor at all. */ rc = enqcmds(portal, desc->hw); - if (rc < 0) + if (rc < 0) { + if (ie) + llist_abort_desc(wq, ie, desc); return rc; + } } percpu_ref_put(&wq->wq_active); - - /* - * Pending the descriptor to the lockless list for the irq_entry - * that we designated the descriptor to. - */ - if (desc->hw->flags & IDXD_OP_FLAG_RCI) - llist_add(&desc->llnode, &idxd->irq_entries[desc->vector].pending_llist); - return 0; } From 4a8ac5e45cdaa88884b4ce05303e304cbabeb367 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Fri, 16 Jul 2021 08:58:32 +1200 Subject: [PATCH 0651/1469] i2c: mpc: Poll for MCF During some transfers the bus can still be busy when an interrupt is received. Commit 763778cd7926 ("i2c: mpc: Restore reread of I2C status register") attempted to address this by re-reading MPC_I2C_SR once but that just made it less likely to happen without actually preventing it. Instead of a single re-read, poll with a timeout so that the bus is given enough time to settle but a genuine stuck SCL is still noticed. Fixes: 1538d82f4647 ("i2c: mpc: Interrupt driven transfer") Signed-off-by: Chris Packham Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-mpc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 6d5014ebaab5..a6ea1eb1394e 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -635,8 +635,8 @@ static irqreturn_t mpc_i2c_isr(int irq, void *dev_id) status = readb(i2c->base + MPC_I2C_SR); if (status & CSR_MIF) { - /* Read again to allow register to stabilise */ - status = readb(i2c->base + MPC_I2C_SR); + /* Wait up to 100us for transfer to properly complete */ + readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100); writeb(0, i2c->base + MPC_I2C_SR); mpc_i2c_do_intr(i2c, status); return IRQ_HANDLED; From 09cfae9f13d51700b0fecf591dcd658fc5375428 Mon Sep 17 00:00:00 2001 From: Markus Boehme Date: Tue, 20 Jul 2021 16:26:19 -0700 Subject: [PATCH 0652/1469] ixgbe: Fix packet corruption due to missing DMA sync When receiving a packet with multiple fragments, hardware may still touch the first fragment until the entire packet has been received. The driver therefore keeps the first fragment mapped for DMA until end of packet has been asserted, and delays its dma_sync call until then. The driver tries to fit multiple receive buffers on one page. When using 3K receive buffers (e.g. using Jumbo frames and legacy-rx is turned off/build_skb is being used) on an architecture with 4K pages, the driver allocates an order 1 compound page and uses one page per receive buffer. To determine the correct offset for a delayed DMA sync of the first fragment of a multi-fragment packet, the driver then cannot just use PAGE_MASK on the DMA address but has to construct a mask based on the actual size of the backing page. Using PAGE_MASK in the 3K RX buffer/4K page architecture configuration will always sync the first page of a compound page. With the SWIOTLB enabled this can lead to corrupted packets (zeroed out first fragment, re-used garbage from another packet) and various consequences, such as slow/stalling data transfers and connection resets. For example, testing on a link with MTU exceeding 3058 bytes on a host with SWIOTLB enabled (e.g. "iommu=soft swiotlb=262144,force") TCP transfers quickly fizzle out without this patch. Cc: stable@vger.kernel.org Fixes: 0c5661ecc5dd7 ("ixgbe: fix crash in build_skb Rx code path") Signed-off-by: Markus Boehme Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 913253f8ecb4..14aea40da50f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1825,7 +1825,8 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { if (ring_uses_build_skb(rx_ring)) { - unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK; + unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1; + unsigned long offset = (unsigned long)(skb->data) & mask; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, From a47fa41381a09e5997afd762664db4f5f6657e03 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Wed, 21 Jul 2021 00:55:22 +0200 Subject: [PATCH 0653/1469] scsi: target: Fix NULL dereference on XCOPY completion CPU affinity control added with commit 39ae3edda325 ("scsi: target: core: Make completion affinity configurable") makes target_complete_cmd() queue work on a CPU based on se_tpg->se_tpg_wwn->cmd_compl_affinity state. LIO's EXTENDED COPY worker is a special case in that read/write cmds are dispatched using the global xcopy_pt_tpg, which carries a NULL se_tpg_wwn pointer following initialization in target_xcopy_setup_pt(). The NULL xcopy_pt_tpg->se_tpg_wwn pointer is dereferenced on completion of any EXTENDED COPY initiated read/write cmds. E.g using the libiscsi SCSI.ExtendedCopy.Simple test: BUG: kernel NULL pointer dereference, address: 00000000000001a8 RIP: 0010:target_complete_cmd+0x9d/0x130 [target_core_mod] Call Trace: fd_execute_rw+0x148/0x42a [target_core_file] ? __dynamic_pr_debug+0xa7/0xe0 ? target_check_reservation+0x5b/0x940 [target_core_mod] __target_execute_cmd+0x1e/0x90 [target_core_mod] transport_generic_new_cmd+0x17c/0x330 [target_core_mod] target_xcopy_issue_pt_cmd+0x9/0x60 [target_core_mod] target_xcopy_read_source.isra.7+0x10b/0x1b0 [target_core_mod] ? target_check_fua+0x40/0x40 [target_core_mod] ? transport_complete_task_attr+0x130/0x130 [target_core_mod] target_xcopy_do_work+0x61f/0xc00 [target_core_mod] This fix makes target_complete_cmd() queue work on se_cmd->cpuid if se_tpg_wwn is NULL. Link: https://lore.kernel.org/r/20210720225522.26291-1-ddiss@suse.de Fixes: 39ae3edda325 ("scsi: target: core: Make completion affinity configurable") Cc: Lee Duncan Cc: Mike Christie Reviewed-by: Mike Christie Signed-off-by: David Disseldorp Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 7e35eddd9eb7..26ceabe34de5 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -886,7 +886,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) INIT_WORK(&cmd->work, success ? target_complete_ok_work : target_complete_failure_work); - if (wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID) + if (!wwn || wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID) cpu = cmd->cpuid; else cpu = wwn->cmd_compl_affinity; From ec185dd3ab257dc2a60953fdf1b6622f524cc5b7 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Mon, 14 Jun 2021 17:33:10 -0500 Subject: [PATCH 0654/1469] optee: Fix memory leak when failing to register shm pages Free the previously allocated pages when we encounter an error condition while attempting to register the pages with the secure world. Fixes: a249dd200d03 ("tee: optee: Fix dynamic shm pool allocations") Fixes: 5a769f6ff439 ("optee: Fix multi page dynamic shm pool alloc") Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/shm_pool.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c index d767eebf30bd..da06ce9b9313 100644 --- a/drivers/tee/optee/shm_pool.c +++ b/drivers/tee/optee/shm_pool.c @@ -32,8 +32,10 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm, struct page **pages; pages = kcalloc(nr_pages, sizeof(pages), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + rc = -ENOMEM; + goto err; + } for (i = 0; i < nr_pages; i++) { pages[i] = page; @@ -44,8 +46,14 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm, rc = optee_shm_register(shm->ctx, shm, pages, nr_pages, (unsigned long)shm->kaddr); kfree(pages); + if (rc) + goto err; } + return 0; + +err: + __free_pages(page, order); return rc; } From adf752af454e91e123e85e3784972d166837af73 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Mon, 14 Jun 2021 17:33:11 -0500 Subject: [PATCH 0655/1469] optee: Refuse to load the driver under the kdump kernel Fix a hung task issue, seen when booting the kdump kernel, that is caused by all of the secure world threads being in a permanent suspended state: INFO: task swapper/0:1 blocked for more than 120 seconds. Not tainted 5.4.83 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. swapper/0 D 0 1 0 0x00000028 Call trace: __switch_to+0xc8/0x118 __schedule+0x2e0/0x700 schedule+0x38/0xb8 schedule_timeout+0x258/0x388 wait_for_completion+0x16c/0x4b8 optee_cq_wait_for_completion+0x28/0xa8 optee_disable_shm_cache+0xb8/0xf8 optee_probe+0x560/0x61c platform_drv_probe+0x58/0xa8 really_probe+0xe0/0x338 driver_probe_device+0x5c/0xf0 device_driver_attach+0x74/0x80 __driver_attach+0x64/0xe0 bus_for_each_dev+0x84/0xd8 driver_attach+0x30/0x40 bus_add_driver+0x188/0x1e8 driver_register+0x64/0x110 __platform_driver_register+0x54/0x60 optee_driver_init+0x20/0x28 do_one_initcall+0x54/0x24c kernel_init_freeable+0x1e8/0x2c0 kernel_init+0x18/0x118 ret_from_fork+0x10/0x18 The invoke_fn hook returned OPTEE_SMC_RETURN_ETHREAD_LIMIT, indicating that the secure world threads were all in a suspended state at the time of the kernel crash. This intermittently prevented the kdump kernel from booting, resulting in a failure to collect the kernel dump. Make kernel dump collection more reliable on systems utilizing OP-TEE by refusing to load the driver under the kdump kernel. Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index ddb8f9ecf307..5288cd767d82 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -612,6 +613,16 @@ static int optee_probe(struct platform_device *pdev) u32 sec_caps; int rc; + /* + * The kernel may have crashed at the same time that all available + * secure world threads were suspended and we cannot reschedule the + * suspended threads without access to the crashed kernel's wait_queue. + * Therefore, we cannot reliably initialize the OP-TEE driver in the + * kdump kernel. + */ + if (is_kdump_kernel()) + return -ENODEV; + invoke_fn = get_invoke_func(&pdev->dev); if (IS_ERR(invoke_fn)) return PTR_ERR(invoke_fn); From f25889f93184db8b07a543cc2bbbb9a8fcaf4333 Mon Sep 17 00:00:00 2001 From: Allen Pais Date: Mon, 14 Jun 2021 17:33:12 -0500 Subject: [PATCH 0656/1469] optee: fix tee out of memory failure seen during kexec reboot The following out of memory errors are seen on kexec reboot from the optee core. [ 0.368428] tee_bnxt_fw optee-clnt0: tee_shm_alloc failed [ 0.368461] tee_bnxt_fw: probe of optee-clnt0 failed with error -22 tee_shm_release() is not invoked on dma shm buffer. Implement .shutdown() method to handle the release of the buffers correctly. More info: https://github.com/OP-TEE/optee_os/issues/3637 Cc: stable@vger.kernel.org Signed-off-by: Allen Pais Reviewed-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/core.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index 5288cd767d82..0987074d7ed0 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -573,6 +573,13 @@ static optee_invoke_fn *get_invoke_func(struct device *dev) return ERR_PTR(-EINVAL); } +/* optee_remove - Device Removal Routine + * @pdev: platform device information struct + * + * optee_remove is called by platform subsystem to alert the driver + * that it should release the device + */ + static int optee_remove(struct platform_device *pdev) { struct optee *optee = platform_get_drvdata(pdev); @@ -603,6 +610,18 @@ static int optee_remove(struct platform_device *pdev) return 0; } +/* optee_shutdown - Device Removal Routine + * @pdev: platform device information struct + * + * platform_shutdown is called by the platform subsystem to alert + * the driver that a shutdown, reboot, or kexec is happening and + * device must be disabled. + */ +static void optee_shutdown(struct platform_device *pdev) +{ + optee_disable_shm_cache(platform_get_drvdata(pdev)); +} + static int optee_probe(struct platform_device *pdev) { optee_invoke_fn *invoke_fn; @@ -739,6 +758,7 @@ MODULE_DEVICE_TABLE(of, optee_dt_match); static struct platform_driver optee_driver = { .probe = optee_probe, .remove = optee_remove, + .shutdown = optee_shutdown, .driver = { .name = "optee", .of_match_table = optee_dt_match, From b5c10dd04b7418793517e3286cde5c04759a86de Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Mon, 14 Jun 2021 17:33:13 -0500 Subject: [PATCH 0657/1469] optee: Clear stale cache entries during initialization The shm cache could contain invalid addresses if optee_disable_shm_cache() was not called from the .shutdown hook of the previous kernel before a kexec. These addresses could be unmapped or they could point to mapped but unintended locations in memory. Clear the shared memory cache, while being careful to not translate the addresses returned from OPTEE_SMC_DISABLE_SHM_CACHE, during driver initialization. Once all pre-cache shm objects are removed, proceed with enabling the cache so that we know that we can handle cached shm objects with confidence later in the .shutdown hook. Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/call.c | 36 ++++++++++++++++++++++++++++--- drivers/tee/optee/core.c | 9 ++++++++ drivers/tee/optee/optee_private.h | 1 + 3 files changed, 43 insertions(+), 3 deletions(-) diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 6e6eb836e9b6..387e94768182 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -416,11 +416,13 @@ void optee_enable_shm_cache(struct optee *optee) } /** - * optee_disable_shm_cache() - Disables caching of some shared memory allocation - * in OP-TEE + * __optee_disable_shm_cache() - Disables caching of some shared memory + * allocation in OP-TEE * @optee: main service struct + * @is_mapped: true if the cached shared memory addresses were mapped by this + * kernel, are safe to dereference, and should be freed */ -void optee_disable_shm_cache(struct optee *optee) +static void __optee_disable_shm_cache(struct optee *optee, bool is_mapped) { struct optee_call_waiter w; @@ -439,6 +441,13 @@ void optee_disable_shm_cache(struct optee *optee) if (res.result.status == OPTEE_SMC_RETURN_OK) { struct tee_shm *shm; + /* + * Shared memory references that were not mapped by + * this kernel must be ignored to prevent a crash. + */ + if (!is_mapped) + continue; + shm = reg_pair_to_ptr(res.result.shm_upper32, res.result.shm_lower32); tee_shm_free(shm); @@ -449,6 +458,27 @@ void optee_disable_shm_cache(struct optee *optee) optee_cq_wait_final(&optee->call_queue, &w); } +/** + * optee_disable_shm_cache() - Disables caching of mapped shared memory + * allocations in OP-TEE + * @optee: main service struct + */ +void optee_disable_shm_cache(struct optee *optee) +{ + return __optee_disable_shm_cache(optee, true); +} + +/** + * optee_disable_unmapped_shm_cache() - Disables caching of shared memory + * allocations in OP-TEE which are not + * currently mapped + * @optee: main service struct + */ +void optee_disable_unmapped_shm_cache(struct optee *optee) +{ + return __optee_disable_shm_cache(optee, false); +} + #define PAGELIST_ENTRIES_PER_PAGE \ ((OPTEE_MSG_NONCONTIG_PAGE_SIZE / sizeof(u64)) - 1) diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index 0987074d7ed0..651d49b53d3b 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -716,6 +716,15 @@ static int optee_probe(struct platform_device *pdev) optee->memremaped_shm = memremaped_shm; optee->pool = pool; + /* + * Ensure that there are no pre-existing shm objects before enabling + * the shm cache so that there's no chance of receiving an invalid + * address during shutdown. This could occur, for example, if we're + * kexec booting from an older kernel that did not properly cleanup the + * shm cache. + */ + optee_disable_unmapped_shm_cache(optee); + optee_enable_shm_cache(optee); if (optee->sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM) diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h index e25b216a14ef..dbdd367be156 100644 --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -159,6 +159,7 @@ int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session); void optee_enable_shm_cache(struct optee *optee); void optee_disable_shm_cache(struct optee *optee); +void optee_disable_unmapped_shm_cache(struct optee *optee); int optee_shm_register(struct tee_context *ctx, struct tee_shm *shm, struct page **pages, size_t num_pages, From dc7019b7d0e188d4093b34bd0747ed0d668c63bf Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 14 Jun 2021 17:33:14 -0500 Subject: [PATCH 0658/1469] tee: add tee_shm_alloc_kernel_buf() Adds a new function tee_shm_alloc_kernel_buf() to allocate shared memory from a kernel driver. This function can later be made more lightweight by unnecessary dma-buf export. Cc: stable@vger.kernel.org Reviewed-by: Tyler Hicks Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/tee_shm.c | 18 ++++++++++++++++++ include/linux/tee_drv.h | 1 + 2 files changed, 19 insertions(+) diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 00472f5ce22e..c65e44707cd6 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -193,6 +193,24 @@ err_dev_put: } EXPORT_SYMBOL_GPL(tee_shm_alloc); +/** + * tee_shm_alloc_kernel_buf() - Allocate shared memory for kernel buffer + * @ctx: Context that allocates the shared memory + * @size: Requested size of shared memory + * + * The returned memory registered in secure world and is suitable to be + * passed as a memory buffer in parameter argument to + * tee_client_invoke_func(). The memory allocated is later freed with a + * call to tee_shm_free(). + * + * @returns a pointer to 'struct tee_shm' + */ +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) +{ + return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); +} +EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf); + struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, size_t length, u32 flags) { diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 54269e47ac9a..8990f7628387 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -332,6 +332,7 @@ void *tee_get_drvdata(struct tee_device *teedev); * @returns a pointer to 'struct tee_shm' */ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** * tee_shm_register() - Register shared memory buffer From 376e4199e327a5cf29b8ec8fb0f64f3d8b429819 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Mon, 14 Jun 2021 17:33:15 -0500 Subject: [PATCH 0659/1469] tee: Correct inappropriate usage of TEE_SHM_DMA_BUF flag Currently TEE_SHM_DMA_BUF flag has been inappropriately used to not register shared memory allocated for private usage by underlying TEE driver: OP-TEE in this case. So rather add a new flag as TEE_SHM_PRIV that can be utilized by underlying TEE drivers for private allocation and usage of shared memory. With this corrected, allow tee_shm_alloc_kernel_buf() to allocate a shared memory region without the backing of dma-buf. Cc: stable@vger.kernel.org Signed-off-by: Sumit Garg Co-developed-by: Tyler Hicks Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/call.c | 2 +- drivers/tee/optee/core.c | 3 ++- drivers/tee/optee/rpc.c | 5 +++-- drivers/tee/optee/shm_pool.c | 8 ++++++-- drivers/tee/tee_shm.c | 4 ++-- include/linux/tee_drv.h | 1 + 6 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 387e94768182..945f03da0223 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -184,7 +184,7 @@ static struct tee_shm *get_msg_arg(struct tee_context *ctx, size_t num_params, struct optee_msg_arg *ma; shm = tee_shm_alloc(ctx, OPTEE_MSG_GET_ARG_SIZE(num_params), - TEE_SHM_MAPPED); + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (IS_ERR(shm)) return shm; diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index 651d49b53d3b..5ce13b099d7d 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -278,7 +278,8 @@ static void optee_release(struct tee_context *ctx) if (!ctxdata) return; - shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (!IS_ERR(shm)) { arg = tee_shm_get_va(shm, 0); /* diff --git a/drivers/tee/optee/rpc.c b/drivers/tee/optee/rpc.c index 1849180b0278..efbaff7ad7e5 100644 --- a/drivers/tee/optee/rpc.c +++ b/drivers/tee/optee/rpc.c @@ -314,7 +314,7 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, shm = cmd_alloc_suppl(ctx, sz); break; case OPTEE_RPC_SHM_TYPE_KERNEL: - shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED | TEE_SHM_PRIV); break; default: arg->ret = TEEC_ERROR_BAD_PARAMETERS; @@ -502,7 +502,8 @@ void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param, switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) { case OPTEE_SMC_RPC_FUNC_ALLOC: - shm = tee_shm_alloc(ctx, param->a1, TEE_SHM_MAPPED); + shm = tee_shm_alloc(ctx, param->a1, + TEE_SHM_MAPPED | TEE_SHM_PRIV); if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) { reg_pair_from_64(¶m->a1, ¶m->a2, pa); reg_pair_from_64(¶m->a4, ¶m->a5, diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c index da06ce9b9313..c41a9a501a6e 100644 --- a/drivers/tee/optee/shm_pool.c +++ b/drivers/tee/optee/shm_pool.c @@ -27,7 +27,11 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm, shm->paddr = page_to_phys(page); shm->size = PAGE_SIZE << order; - if (shm->flags & TEE_SHM_DMA_BUF) { + /* + * Shared memory private to the OP-TEE driver doesn't need + * to be registered with OP-TEE. + */ + if (!(shm->flags & TEE_SHM_PRIV)) { unsigned int nr_pages = 1 << order, i; struct page **pages; @@ -60,7 +64,7 @@ err: static void pool_op_free(struct tee_shm_pool_mgr *poolm, struct tee_shm *shm) { - if (shm->flags & TEE_SHM_DMA_BUF) + if (!(shm->flags & TEE_SHM_PRIV)) optee_shm_unregister(shm->ctx, shm); free_pages((unsigned long)shm->kaddr, get_order(shm->size)); diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index c65e44707cd6..8a9384a64f3e 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -117,7 +117,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) return ERR_PTR(-EINVAL); } - if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF))) { + if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF | TEE_SHM_PRIV))) { dev_err(teedev->dev.parent, "invalid shm flags 0x%x", flags); return ERR_PTR(-EINVAL); } @@ -207,7 +207,7 @@ EXPORT_SYMBOL_GPL(tee_shm_alloc); */ struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) { - return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); + return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED); } EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf); diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 8990f7628387..3ebfea0781f1 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -27,6 +27,7 @@ #define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ #define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ +#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ struct device; struct tee_device; From dfb703ad2a8d366b829818a558337be779746575 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Mon, 14 Jun 2021 17:33:16 -0500 Subject: [PATCH 0660/1469] tpm_ftpm_tee: Free and unregister TEE shared memory during kexec dma-buf backed shared memory cannot be reliably freed and unregistered during a kexec operation even when tee_shm_free() is called on the shm from a .shutdown hook. The problem occurs because dma_buf_put() calls fput() which then uses task_work_add(), with the TWA_RESUME parameter, to queue tee_shm_release() to be called before the current task returns to user mode. However, the current task never returns to user mode before the kexec completes so the memory is never freed nor unregistered. Use tee_shm_alloc_kernel_buf() to avoid dma-buf backed shared memory allocation so that tee_shm_free() can directly call tee_shm_release(). This will ensure that the shm can be freed and unregistered during a kexec operation. Fixes: 09e574831b27 ("tpm/tpm_ftpm_tee: A driver for firmware TPM running inside TEE") Fixes: 1760eb689ed6 ("tpm/tpm_ftpm_tee: add shutdown call back") Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks Reviewed-by: Sumit Garg Acked-by: Jarkko Sakkinen Signed-off-by: Jens Wiklander --- drivers/char/tpm/tpm_ftpm_tee.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c index 2ccdf8ac6994..6e3235565a4d 100644 --- a/drivers/char/tpm/tpm_ftpm_tee.c +++ b/drivers/char/tpm/tpm_ftpm_tee.c @@ -254,11 +254,11 @@ static int ftpm_tee_probe(struct device *dev) pvt_data->session = sess_arg.session; /* Allocate dynamic shared memory with fTPM TA */ - pvt_data->shm = tee_shm_alloc(pvt_data->ctx, - MAX_COMMAND_SIZE + MAX_RESPONSE_SIZE, - TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); + pvt_data->shm = tee_shm_alloc_kernel_buf(pvt_data->ctx, + MAX_COMMAND_SIZE + + MAX_RESPONSE_SIZE); if (IS_ERR(pvt_data->shm)) { - dev_err(dev, "%s: tee_shm_alloc failed\n", __func__); + dev_err(dev, "%s: tee_shm_alloc_kernel_buf failed\n", __func__); rc = -ENOMEM; goto out_shm_alloc; } From 914ab19e471d8fb535ed50dff108b0a615f3c2d8 Mon Sep 17 00:00:00 2001 From: Allen Pais Date: Mon, 14 Jun 2021 17:33:17 -0500 Subject: [PATCH 0661/1469] firmware: tee_bnxt: Release TEE shm, session, and context during kexec Implement a .shutdown hook that will be called during a kexec operation so that the TEE shared memory, session, and context that were set up during .probe can be properly freed/closed. Additionally, don't use dma-buf backed shared memory for the fw_shm_pool. dma-buf backed shared memory cannot be reliably freed and unregistered during a kexec operation even when tee_shm_free() is called on the shm from a .shutdown hook. The problem occurs because dma_buf_put() calls fput() which then uses task_work_add(), with the TWA_RESUME parameter, to queue tee_shm_release() to be called before the current task returns to user mode. However, the current task never returns to user mode before the kexec completes so the memory is never freed nor unregistered. Use tee_shm_alloc_kernel_buf() to avoid dma-buf backed shared memory allocation so that tee_shm_free() can directly call tee_shm_release(). This will ensure that the shm can be freed and unregistered during a kexec operation. Fixes: 246880958ac9 ("firmware: broadcom: add OP-TEE based BNXT f/w manager") Cc: stable@vger.kernel.org Signed-off-by: Allen Pais Co-developed-by: Tyler Hicks Signed-off-by: Tyler Hicks Reviewed-by: Sumit Garg Acked-by: Florian Fainelli Signed-off-by: Jens Wiklander --- drivers/firmware/broadcom/tee_bnxt_fw.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/broadcom/tee_bnxt_fw.c b/drivers/firmware/broadcom/tee_bnxt_fw.c index ed10da5313e8..a5bf4c3f6dc7 100644 --- a/drivers/firmware/broadcom/tee_bnxt_fw.c +++ b/drivers/firmware/broadcom/tee_bnxt_fw.c @@ -212,10 +212,9 @@ static int tee_bnxt_fw_probe(struct device *dev) pvt_data.dev = dev; - fw_shm_pool = tee_shm_alloc(pvt_data.ctx, MAX_SHM_MEM_SZ, - TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); + fw_shm_pool = tee_shm_alloc_kernel_buf(pvt_data.ctx, MAX_SHM_MEM_SZ); if (IS_ERR(fw_shm_pool)) { - dev_err(pvt_data.dev, "tee_shm_alloc failed\n"); + dev_err(pvt_data.dev, "tee_shm_alloc_kernel_buf failed\n"); err = PTR_ERR(fw_shm_pool); goto out_sess; } @@ -242,6 +241,14 @@ static int tee_bnxt_fw_remove(struct device *dev) return 0; } +static void tee_bnxt_fw_shutdown(struct device *dev) +{ + tee_shm_free(pvt_data.fw_shm_pool); + tee_client_close_session(pvt_data.ctx, pvt_data.session_id); + tee_client_close_context(pvt_data.ctx); + pvt_data.ctx = NULL; +} + static const struct tee_client_device_id tee_bnxt_fw_id_table[] = { {UUID_INIT(0x6272636D, 0x2019, 0x0716, 0x42, 0x43, 0x4D, 0x5F, 0x53, 0x43, 0x48, 0x49)}, @@ -257,6 +264,7 @@ static struct tee_client_driver tee_bnxt_fw_driver = { .bus = &tee_bus_type, .probe = tee_bnxt_fw_probe, .remove = tee_bnxt_fw_remove, + .shutdown = tee_bnxt_fw_shutdown, }, }; From 235c3610d5f02ee91244239b43cd9ae8b4859dff Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Tue, 20 Jul 2021 13:13:55 -0500 Subject: [PATCH 0662/1469] drm/ttm: Force re-init if ttm_global_init() fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we have a failure, decrement the reference count so that the next call to ttm_global_init() will actually do something instead of assume everything is all set up. Signed-off-by: Jason Ekstrand Fixes: 62b53b37e4b1 ("drm/ttm: use a static ttm_bo_global instance") Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210720181357.2760720-5-jason@jlekstrand.net Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 5f31acec3ad7..519deea8e39b 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -100,6 +100,8 @@ static int ttm_global_init(void) debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root, &glob->bo_count); out: + if (ret) + --ttm_glob_use_count; mutex_unlock(&ttm_global_mutex); return ret; } From 44cf53602f5a0db80d53c8fff6cdbcae59650a42 Mon Sep 17 00:00:00 2001 From: Moritz Fischer Date: Mon, 19 Jul 2021 00:05:19 -0700 Subject: [PATCH 0663/1469] Revert "usb: renesas-xhci: Fix handling of unknown ROM state" This reverts commit d143825baf15f204dac60acdf95e428182aa3374. Justin reports some of his systems now fail as result of this commit: xhci_hcd 0000:04:00.0: Direct firmware load for renesas_usb_fw.mem failed with error -2 xhci_hcd 0000:04:00.0: request_firmware failed: -2 xhci_hcd: probe of 0000:04:00.0 failed with error -2 The revert brings back the original issue the commit tried to solve but at least unbreaks existing systems relying on previous behavior. Cc: stable@vger.kernel.org Cc: Mathias Nyman Cc: Vinod Koul Cc: Justin Forbes Reported-by: Justin Forbes Signed-off-by: Moritz Fischer Fixes: d143825baf15 ("usb: renesas-xhci: Fix handling of unknown ROM state") Link: https://lore.kernel.org/r/20210719070519.41114-1-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci-renesas.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c index 1da647961c25..5923844ed821 100644 --- a/drivers/usb/host/xhci-pci-renesas.c +++ b/drivers/usb/host/xhci-pci-renesas.c @@ -207,8 +207,7 @@ static int renesas_check_rom_state(struct pci_dev *pdev) return 0; case RENESAS_ROM_STATUS_NO_RESULT: /* No result yet */ - dev_dbg(&pdev->dev, "Unknown ROM status ...\n"); - break; + return 0; case RENESAS_ROM_STATUS_ERROR: /* Error State */ default: /* All other states are marked as "Reserved states" */ @@ -225,12 +224,13 @@ static int renesas_fw_check_running(struct pci_dev *pdev) u8 fw_state; int err; - /* - * Only if device has ROM and loaded FW we can skip loading and - * return success. Otherwise (even unknown state), attempt to load FW. - */ - if (renesas_check_rom(pdev) && !renesas_check_rom_state(pdev)) - return 0; + /* Check if device has ROM and loaded, if so skip everything */ + err = renesas_check_rom(pdev); + if (err) { /* we have rom */ + err = renesas_check_rom_state(pdev); + if (!err) + return err; + } /* * Test if the device is actually needing the firmware. As most From 72f68bf5c756f5ce1139b31daae2684501383ad5 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 15 Jul 2021 18:06:51 +0300 Subject: [PATCH 0664/1469] xhci: Fix lost USB 2 remote wake There's a small window where a USB 2 remote wake may be left unhandled due to a race between hub thread and xhci port event interrupt handler. When the resume event is detected in the xhci interrupt handler it kicks the hub timer, which should move the port from resume to U0 once resume has been signalled for long enough. To keep the hub "thread" running we set a bus_state->resuming_ports flag. This flag makes sure hub timer function kicks itself. checking this flag was not properly protected by the spinlock. Flag was copied to a local variable before lock was taken. The local variable was then checked later with spinlock held. If interrupt is handled right after copying the flag to the local variable we end up stopping the hub thread before it can handle the USB 2 resume. CPU0 CPU1 (hub thread) (xhci event handler) xhci_hub_status_data() status = bus_state->resuming_ports; handle_port_status() spin_lock() bus_state->resuming_ports = 1 set_flag(HCD_FLAG_POLL_RH) spin_unlock() spin_lock() if (!status) clear_flag(HCD_FLAG_POLL_RH) spin_unlock() Fix this by taking the lock a bit earlier so that it covers the resuming_ports flag copy in the hub thread Cc: Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210715150651.1996099-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-hub.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index e9b18fc17617..151e93c4bd57 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1638,11 +1638,12 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf) * Inform the usbcore about resume-in-progress by returning * a non-zero value even if there are no status changes. */ + spin_lock_irqsave(&xhci->lock, flags); + status = bus_state->resuming_ports; mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC; - spin_lock_irqsave(&xhci->lock, flags); /* For each port, did anything change? If so, set that bit in buf. */ for (i = 0; i < max_ports; i++) { temp = readl(ports[i]->addr); From 57560ee95cb7f91cf0bc31d4ae8276e0dcfe17aa Mon Sep 17 00:00:00 2001 From: Martin Kepplinger Date: Wed, 14 Jul 2021 08:18:07 +0200 Subject: [PATCH 0665/1469] usb: typec: tipd: Don't block probing of consumer of "connector" nodes Similar as with tcpm this patch lets fw_devlink know not to wait on the fwnode to be populated as a struct device. Without this patch, USB functionality can be broken on some previously supported boards. Fixes: 28ec344bb891 ("usb: typec: tcpm: Don't block probing of consumers of "connector" nodes") Cc: stable Acked-by: Heikki Krogerus Signed-off-by: Martin Kepplinger Link: https://lore.kernel.org/r/20210714061807.5737-1-martin.kepplinger@puri.sm Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 938219bc1b4b..21b3ae25c76d 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -629,6 +629,15 @@ static int tps6598x_probe(struct i2c_client *client) if (!fwnode) return -ENODEV; + /* + * This fwnode has a "compatible" property, but is never populated as a + * struct device. Instead we simply parse it to read the properties. + * This breaks fw_devlink=on. To maintain backward compatibility + * with existing DT files, we work around this by deleting any + * fwnode_links to/from this fwnode. + */ + fw_devlink_purge_absent_suppliers(fwnode); + tps->role_sw = fwnode_usb_role_switch_get(fwnode); if (IS_ERR(tps->role_sw)) { ret = PTR_ERR(tps->role_sw); From 1bf2761c837571a66ec290fb66c90413821ffda2 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 15 Jul 2021 18:01:21 +0300 Subject: [PATCH 0666/1469] usb: hub: Fix link power management max exit latency (MEL) calculations Maximum Exit Latency (MEL) value is used by host to know how much in advance it needs to start waking up a U1/U2 suspended link in order to service a periodic transfer in time. Current MEL calculation only includes the time to wake up the path from U1/U2 to U0. This is called tMEL1 in USB 3.1 section C 1.5.2 Total MEL = tMEL1 + tMEL2 +tMEL3 + tMEL4 which should additinally include: - tMEL2 which is the time it takes for PING message to reach device - tMEL3 time for device to process the PING and submit a PING_RESPONSE - tMEL4 time for PING_RESPONSE to traverse back upstream to host. Add the missing tMEL2, tMEL3 and tMEL4 to MEL calculation. Cc: # v3.5 Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210715150122.1995966-1-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 52 +++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 24 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index d1efc7141333..a35d0bedafa3 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -48,6 +48,7 @@ #define USB_TP_TRANSMISSION_DELAY 40 /* ns */ #define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */ +#define USB_PING_RESPONSE_TIME 400 /* ns */ /* Protect struct usb_device->state and ->children members * Note: Both are also protected by ->dev.sem, except that ->state can @@ -182,8 +183,9 @@ int usb_device_supports_lpm(struct usb_device *udev) } /* - * Set the Maximum Exit Latency (MEL) for the host to initiate a transition from - * either U1 or U2. + * Set the Maximum Exit Latency (MEL) for the host to wakup up the path from + * U1/U2, send a PING to the device and receive a PING_RESPONSE. + * See USB 3.1 section C.1.5.2 */ static void usb_set_lpm_mel(struct usb_device *udev, struct usb3_lpm_parameters *udev_lpm_params, @@ -193,35 +195,37 @@ static void usb_set_lpm_mel(struct usb_device *udev, unsigned int hub_exit_latency) { unsigned int total_mel; - unsigned int device_mel; - unsigned int hub_mel; /* - * Calculate the time it takes to transition all links from the roothub - * to the parent hub into U0. The parent hub must then decode the - * packet (hub header decode latency) to figure out which port it was - * bound for. - * - * The Hub Header decode latency is expressed in 0.1us intervals (0x1 - * means 0.1us). Multiply that by 100 to get nanoseconds. + * tMEL1. time to transition path from host to device into U0. + * MEL for parent already contains the delay up to parent, so only add + * the exit latency for the last link (pick the slower exit latency), + * and the hub header decode latency. See USB 3.1 section C 2.2.1 + * Store MEL in nanoseconds */ total_mel = hub_lpm_params->mel + - (hub->descriptor->u.ss.bHubHdrDecLat * 100); + max(udev_exit_latency, hub_exit_latency) * 1000 + + hub->descriptor->u.ss.bHubHdrDecLat * 100; /* - * How long will it take to transition the downstream hub's port into - * U0? The greater of either the hub exit latency or the device exit - * latency. - * - * The BOS U1/U2 exit latencies are expressed in 1us intervals. - * Multiply that by 1000 to get nanoseconds. + * tMEL2. Time to submit PING packet. Sum of tTPTransmissionDelay for + * each link + wHubDelay for each hub. Add only for last link. + * tMEL4, the time for PING_RESPONSE to traverse upstream is similar. + * Multiply by 2 to include it as well. */ - device_mel = udev_exit_latency * 1000; - hub_mel = hub_exit_latency * 1000; - if (device_mel > hub_mel) - total_mel += device_mel; - else - total_mel += hub_mel; + total_mel += (__le16_to_cpu(hub->descriptor->u.ss.wHubDelay) + + USB_TP_TRANSMISSION_DELAY) * 2; + + /* + * tMEL3, tPingResponse. Time taken by device to generate PING_RESPONSE + * after receiving PING. Also add 2100ns as stated in USB 3.1 C 1.5.2.4 + * to cover the delay if the PING_RESPONSE is queued behind a Max Packet + * Size DP. + * Note these delays should be added only once for the entire path, so + * add them to the MEL of the device connected to the roothub. + */ + if (!hub->hdev->parent) + total_mel += USB_PING_RESPONSE_TIME + 2100; udev_lpm_params->mel = total_mel; } From 1b7f56fbc7a1b66967b6114d1b5f5a257c3abae6 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 15 Jul 2021 18:01:22 +0300 Subject: [PATCH 0667/1469] usb: hub: Disable USB 3 device initiated lpm if exit latency is too high The device initiated link power management U1/U2 states should not be enabled in case the system exit latency plus one bus interval (125us) is greater than the shortest service interval of any periodic endpoint. This is the case for both U1 and U2 sytstem exit latencies and link states. See USB 3.2 section 9.4.9 "Set Feature" for more details Note, before this patch the host and device initiated U1/U2 lpm states were both enabled with lpm. After this patch it's possible to end up with only host inititated U1/U2 lpm in case the exit latencies won't allow device initiated lpm. If this case we still want to set the udev->usb3_lpm_ux_enabled flag so that sysfs users can see the link may go to U1/U2. Signed-off-by: Mathias Nyman Cc: stable Link: https://lore.kernel.org/r/20210715150122.1995966-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 68 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 56 insertions(+), 12 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index a35d0bedafa3..86658a81d284 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4116,6 +4116,47 @@ static int usb_set_lpm_timeout(struct usb_device *udev, return 0; } +/* + * Don't allow device intiated U1/U2 if the system exit latency + one bus + * interval is greater than the minimum service interval of any active + * periodic endpoint. See USB 3.2 section 9.4.9 + */ +static bool usb_device_may_initiate_lpm(struct usb_device *udev, + enum usb3_link_state state) +{ + unsigned int sel; /* us */ + int i, j; + + if (state == USB3_LPM_U1) + sel = DIV_ROUND_UP(udev->u1_params.sel, 1000); + else if (state == USB3_LPM_U2) + sel = DIV_ROUND_UP(udev->u2_params.sel, 1000); + else + return false; + + for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { + struct usb_interface *intf; + struct usb_endpoint_descriptor *desc; + unsigned int interval; + + intf = udev->actconfig->interface[i]; + if (!intf) + continue; + + for (j = 0; j < intf->cur_altsetting->desc.bNumEndpoints; j++) { + desc = &intf->cur_altsetting->endpoint[j].desc; + + if (usb_endpoint_xfer_int(desc) || + usb_endpoint_xfer_isoc(desc)) { + interval = (1 << (desc->bInterval - 1)) * 125; + if (sel + 125 > interval) + return false; + } + } + } + return true; +} + /* * Enable the hub-initiated U1/U2 idle timeouts, and enable device-initiated * U1/U2 entry. @@ -4188,20 +4229,23 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, * U1/U2_ENABLE */ if (udev->actconfig && - usb_set_device_initiated_lpm(udev, state, true) == 0) { - if (state == USB3_LPM_U1) - udev->usb3_lpm_u1_enabled = 1; - else if (state == USB3_LPM_U2) - udev->usb3_lpm_u2_enabled = 1; - } else { - /* Don't request U1/U2 entry if the device - * cannot transition to U1/U2. - */ - usb_set_lpm_timeout(udev, state, 0); - hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + usb_device_may_initiate_lpm(udev, state)) { + if (usb_set_device_initiated_lpm(udev, state, true)) { + /* + * Request to enable device initiated U1/U2 failed, + * better to turn off lpm in this case. + */ + usb_set_lpm_timeout(udev, state, 0); + hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + return; + } } -} + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 1; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 1; +} /* * Disable the hub-initiated U1/U2 idle timeouts, and disable device-initiated * U1/U2 entry. From 0b60557230adfdeb8164e0b342ac9cd469a75759 Mon Sep 17 00:00:00 2001 From: David Jeffery Date: Thu, 15 Jul 2021 17:37:44 -0400 Subject: [PATCH 0668/1469] usb: ehci: Prevent missed ehci interrupts with edge-triggered MSI When MSI is used by the ehci-hcd driver, it can cause lost interrupts which results in EHCI only continuing to work due to a polling fallback. But the reliance of polling drastically reduces performance of any I/O through EHCI. Interrupts are lost as the EHCI interrupt handler does not safely handle edge-triggered interrupts. It fails to ensure all interrupt status bits are cleared, which works with level-triggered interrupts but not the edge-triggered interrupts typical from using MSI. To fix this problem, check if the driver may have raced with the hardware setting additional interrupt status bits and clear status until it is in a stable state. Fixes: 306c54d0edb6 ("usb: hcd: Try MSI interrupts on PCI devices") Tested-by: Laurence Oberman Reviewed-by: Andy Shevchenko Acked-by: Alan Stern Signed-off-by: David Jeffery Link: https://lore.kernel.org/r/20210715213744.GA44506@redhat Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-hcd.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 36f5bf6a0752..10b0365f3439 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -703,24 +703,28 @@ EXPORT_SYMBOL_GPL(ehci_setup); static irqreturn_t ehci_irq (struct usb_hcd *hcd) { struct ehci_hcd *ehci = hcd_to_ehci (hcd); - u32 status, masked_status, pcd_status = 0, cmd; + u32 status, current_status, masked_status, pcd_status = 0; + u32 cmd; int bh; spin_lock(&ehci->lock); - status = ehci_readl(ehci, &ehci->regs->status); + status = 0; + current_status = ehci_readl(ehci, &ehci->regs->status); +restart: /* e.g. cardbus physical eject */ - if (status == ~(u32) 0) { + if (current_status == ~(u32) 0) { ehci_dbg (ehci, "device removed\n"); goto dead; } + status |= current_status; /* * We don't use STS_FLR, but some controllers don't like it to * remain on, so mask it out along with the other status bits. */ - masked_status = status & (INTR_MASK | STS_FLR); + masked_status = current_status & (INTR_MASK | STS_FLR); /* Shared IRQ? */ if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) { @@ -730,6 +734,12 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) /* clear (just) interrupts */ ehci_writel(ehci, masked_status, &ehci->regs->status); + + /* For edge interrupts, don't race with an interrupt bit being raised */ + current_status = ehci_readl(ehci, &ehci->regs->status); + if (current_status & INTR_MASK) + goto restart; + cmd = ehci_readl(ehci, &ehci->regs->command); bh = 0; From 6abf2fe6b4bf6e5256b80c5817908151d2d33e9f Mon Sep 17 00:00:00 2001 From: Julian Sikorski Date: Tue, 20 Jul 2021 19:19:10 +0200 Subject: [PATCH 0669/1469] USB: usb-storage: Add LaCie Rugged USB3-FW to IGNORE_UAS LaCie Rugged USB3-FW appears to be incompatible with UAS. It generates errors like: [ 1151.582598] sd 14:0:0:0: tag#16 uas_eh_abort_handler 0 uas-tag 1 inflight: IN [ 1151.582602] sd 14:0:0:0: tag#16 CDB: Report supported operation codes a3 0c 01 12 00 00 00 00 02 00 00 00 [ 1151.588594] scsi host14: uas_eh_device_reset_handler start [ 1151.710482] usb 2-4: reset SuperSpeed Gen 1 USB device number 2 using xhci_hcd [ 1151.741398] scsi host14: uas_eh_device_reset_handler success [ 1181.785534] scsi host14: uas_eh_device_reset_handler start Signed-off-by: Julian Sikorski Cc: stable Link: https://lore.kernel.org/r/20210720171910.36497-1-belegdol+github@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/unusual_uas.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index f9677a5ec31b..c35a6db993f1 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -45,6 +45,13 @@ UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME), +/* Reported-by: Julian Sikorski */ +UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999, + "LaCie", + "Rugged USB3-FW", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? From 86762ad4abcc549deb7a155c8e5e961b9755bcf0 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Fri, 16 Jul 2021 14:07:17 +0200 Subject: [PATCH 0670/1469] usb: typec: stusb160x: register role switch before interrupt registration During interrupt registration, attach state is checked. If attached, then the Type-C state is updated with typec_set_xxx functions and role switch is set with usb_role_switch_set_role(). If the usb_role_switch parameter is error or null, the function simply returns 0. So, to update usb_role_switch role if a device is attached before the irq is registered, usb_role_switch must be registered before irq registration. Fixes: da0cb6310094 ("usb: typec: add support for STUSB160x Type-C controller family") Cc: stable Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20210716120718.20398-2-amelie.delaunay@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/stusb160x.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c index 6eaeba9b096e..3d3848e7c2c2 100644 --- a/drivers/usb/typec/stusb160x.c +++ b/drivers/usb/typec/stusb160x.c @@ -739,10 +739,6 @@ static int stusb160x_probe(struct i2c_client *client) typec_set_pwr_opmode(chip->port, chip->pwr_opmode); if (client->irq) { - ret = stusb160x_irq_init(chip, client->irq); - if (ret) - goto port_unregister; - chip->role_sw = fwnode_usb_role_switch_get(fwnode); if (IS_ERR(chip->role_sw)) { ret = PTR_ERR(chip->role_sw); @@ -752,6 +748,10 @@ static int stusb160x_probe(struct i2c_client *client) ret); goto port_unregister; } + + ret = stusb160x_irq_init(chip, client->irq); + if (ret) + goto role_sw_put; } else { /* * If Source or Dual power role, need to enable VDD supply @@ -775,6 +775,9 @@ static int stusb160x_probe(struct i2c_client *client) return 0; +role_sw_put: + if (chip->role_sw) + usb_role_switch_put(chip->role_sw); port_unregister: typec_unregister_port(chip->port); all_reg_disable: From 6b63376722d9e1b915a2948e9b30f4ba2712e3f5 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Fri, 16 Jul 2021 14:07:18 +0200 Subject: [PATCH 0671/1469] usb: typec: stusb160x: Don't block probing of consumer of "connector" nodes Similar as with tcpm this patch lets fw_devlink know not to wait on the fwnode to be populated as a struct device. Without this patch, USB functionality can be broken on some previously supported boards. Fixes: 28ec344bb891 ("usb: typec: tcpm: Don't block probing of consumers of "connector" nodes") Cc: stable Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20210716120718.20398-3-amelie.delaunay@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/stusb160x.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c index 3d3848e7c2c2..e7745d1c2a5c 100644 --- a/drivers/usb/typec/stusb160x.c +++ b/drivers/usb/typec/stusb160x.c @@ -685,6 +685,15 @@ static int stusb160x_probe(struct i2c_client *client) if (!fwnode) return -ENODEV; + /* + * This fwnode has a "compatible" property, but is never populated as a + * struct device. Instead we simply parse it to read the properties. + * This it breaks fw_devlink=on. To maintain backward compatibility + * with existing DT files, we work around this by deleting any + * fwnode_links to/from this fwnode. + */ + fw_devlink_purge_absent_suppliers(fwnode); + /* * When both VDD and VSYS power supplies are present, the low power * supply VSYS is selected when VSYS voltage is above 3.1 V. From a6b125621c081bef519fd78cf336de351390da3f Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 1 Jul 2021 11:39:03 +0200 Subject: [PATCH 0672/1469] MAINTAINERS: repair reference in USB IP DRIVER FOR HISILICON KIRIN 970 Commit 8de6b7edd493 ("phy: phy-hi3670-usb3: move driver from staging into phy") moves phy-hi3670-usb3.c from ./drivers/staging/hikey9xx/ to ./drivers/phy/hisilicon/, but the new file entry in MAINTAINERS refers to ./drivers/phy/hisilicon/phy-kirin970-usb3.c. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains: warning: no file matches F: drivers/phy/hisilicon/phy-kirin970-usb3.c Repair the file entry by referring to the right location. Fixes: 8de6b7edd493 ("phy: phy-hi3670-usb3: move driver from staging into phy") Acked-by: Mauro Carvalho Chehab Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20210701093903.28733-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..6f86a58930bf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19114,7 +19114,7 @@ M: Mauro Carvalho Chehab L: linux-usb@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml -F: drivers/phy/hisilicon/phy-kirin970-usb3.c +F: drivers/phy/hisilicon/phy-hi3670-usb3.c USB ISP116X DRIVER M: Olav Kongas From 5b01248156bd75303e66985c351dee648c149979 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Fri, 18 Jun 2021 22:14:41 +0800 Subject: [PATCH 0673/1469] usb: gadget: Fix Unbalanced pm_runtime_enable in tegra_xudc_probe Add missing pm_runtime_disable() when probe error out. It could avoid pm_runtime implementation complains when removing and probing again the driver. Fixes: 49db427232fe ("usb: gadget: Add UDC driver for tegra XUSB device mode controller") Cc: stable Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20210618141441.107817-1-zhangqilong3@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/tegra-xudc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index a54d1cef17db..c0ca7144e512 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3853,6 +3853,7 @@ static int tegra_xudc_probe(struct platform_device *pdev) return 0; free_eps: + pm_runtime_disable(&pdev->dev); tegra_xudc_free_eps(xudc); free_event_ring: tegra_xudc_free_event_ring(xudc); From b5fdf5c6e6bee35837e160c00ac89327bdad031b Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Fri, 25 Jun 2021 15:14:56 +1200 Subject: [PATCH 0674/1469] usb: max-3421: Prevent corruption of freed memory The MAX-3421 USB driver remembers the state of the USB toggles for a device/endpoint. To save SPI writes, this was only done when a new device/endpoint was being used. Unfortunately, if the old device was removed, this would cause writes to freed memory. To fix this, a simpler scheme is used. The toggles are read from hardware when a URB is completed, and the toggles are always written to hardware when any URB transaction is started. This will cause a few more SPI transactions, but no causes kernel panics. Fixes: 2d53139f3162 ("Add support for using a MAX3421E chip as a host driver.") Cc: stable Signed-off-by: Mark Tomlinson Link: https://lore.kernel.org/r/20210625031456.8632-1-mark.tomlinson@alliedtelesis.co.nz Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/max3421-hcd.c | 44 +++++++++++----------------------- 1 file changed, 14 insertions(+), 30 deletions(-) diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index e7a8e0609853..59cc1bc7f12f 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -153,8 +153,6 @@ struct max3421_hcd { */ struct urb *curr_urb; enum scheduling_pass sched_pass; - struct usb_device *loaded_dev; /* dev that's loaded into the chip */ - int loaded_epnum; /* epnum whose toggles are loaded */ int urb_done; /* > 0 -> no errors, < 0: errno */ size_t curr_len; u8 hien; @@ -492,39 +490,17 @@ max3421_set_speed(struct usb_hcd *hcd, struct usb_device *dev) * Caller must NOT hold HCD spinlock. */ static void -max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum, - int force_toggles) +max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum) { - struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd); - int old_epnum, same_ep, rcvtog, sndtog; - struct usb_device *old_dev; + int rcvtog, sndtog; u8 hctl; - old_dev = max3421_hcd->loaded_dev; - old_epnum = max3421_hcd->loaded_epnum; - - same_ep = (dev == old_dev && epnum == old_epnum); - if (same_ep && !force_toggles) - return; - - if (old_dev && !same_ep) { - /* save the old end-points toggles: */ - u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL); - - rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1; - sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1; - - /* no locking: HCD (i.e., we) own toggles, don't we? */ - usb_settoggle(old_dev, old_epnum, 0, rcvtog); - usb_settoggle(old_dev, old_epnum, 1, sndtog); - } /* setup new endpoint's toggle bits: */ rcvtog = usb_gettoggle(dev, epnum, 0); sndtog = usb_gettoggle(dev, epnum, 1); hctl = (BIT(rcvtog + MAX3421_HCTL_RCVTOG0_BIT) | BIT(sndtog + MAX3421_HCTL_SNDTOG0_BIT)); - max3421_hcd->loaded_epnum = epnum; spi_wr8(hcd, MAX3421_REG_HCTL, hctl); /* @@ -532,7 +508,6 @@ max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum, * address-assignment so it's best to just always load the * address whenever the end-point changed/was forced. */ - max3421_hcd->loaded_dev = dev; spi_wr8(hcd, MAX3421_REG_PERADDR, dev->devnum); } @@ -667,7 +642,7 @@ max3421_select_and_start_urb(struct usb_hcd *hcd) struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd); struct urb *urb, *curr_urb = NULL; struct max3421_ep *max3421_ep; - int epnum, force_toggles = 0; + int epnum; struct usb_host_endpoint *ep; struct list_head *pos; unsigned long flags; @@ -777,7 +752,6 @@ done: usb_settoggle(urb->dev, epnum, 0, 1); usb_settoggle(urb->dev, epnum, 1, 1); max3421_ep->pkt_state = PKT_STATE_SETUP; - force_toggles = 1; } else max3421_ep->pkt_state = PKT_STATE_TRANSFER; } @@ -785,7 +759,7 @@ done: spin_unlock_irqrestore(&max3421_hcd->lock, flags); max3421_ep->last_active = max3421_hcd->frame_number; - max3421_set_address(hcd, urb->dev, epnum, force_toggles); + max3421_set_address(hcd, urb->dev, epnum); max3421_set_speed(hcd, urb->dev); max3421_next_transfer(hcd, 0); return 1; @@ -1379,6 +1353,16 @@ max3421_urb_done(struct usb_hcd *hcd) status = 0; urb = max3421_hcd->curr_urb; if (urb) { + /* save the old end-points toggles: */ + u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL); + int rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1; + int sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1; + int epnum = usb_endpoint_num(&urb->ep->desc); + + /* no locking: HCD (i.e., we) own toggles, don't we? */ + usb_settoggle(urb->dev, epnum, 0, rcvtog); + usb_settoggle(urb->dev, epnum, 1, sndtog); + max3421_hcd->curr_urb = NULL; spin_lock_irqsave(&max3421_hcd->lock, flags); usb_hcd_unlink_urb_from_ep(hcd, urb); From 40edb52298df4c1dbbdb30b19e3ce92cf612a918 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Tue, 29 Jun 2021 09:51:18 +0800 Subject: [PATCH 0675/1469] usb: dwc3: avoid NULL access of usb_gadget_driver we found crash in dwc3_disconnect_gadget(), it is because dwc->gadget_driver become NULL before async access. 7dc0c55e9f30 ('USB: UDC core: Add udc_async_callbacks gadget op') suggest a common way to avoid such kind of issue. this change implment the callback in dwc3 and change related functions which have callback to usb gadget driver. Acked-by: Alan Stern Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/20210629015118.7944-1-linyyuan@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 1 + drivers/usb/dwc3/ep0.c | 10 ++++++---- drivers/usb/dwc3/gadget.c | 21 ++++++++++++++++----- 3 files changed, 23 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index dccdf13b5f9e..5991766239ba 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1279,6 +1279,7 @@ struct dwc3 { unsigned dis_metastability_quirk:1; unsigned dis_split_quirk:1; + unsigned async_callbacks:1; u16 imod_interval; }; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 3cd294264372..2f9e45eed228 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -597,11 +597,13 @@ static int dwc3_ep0_set_address(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) static int dwc3_ep0_delegate_req(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) { - int ret; + int ret = -EINVAL; - spin_unlock(&dwc->lock); - ret = dwc->gadget_driver->setup(dwc->gadget, ctrl); - spin_lock(&dwc->lock); + if (dwc->async_callbacks) { + spin_unlock(&dwc->lock); + ret = dwc->gadget_driver->setup(dwc->gadget, ctrl); + spin_lock(&dwc->lock); + } return ret; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index af6d7f157989..45f2bc0807e8 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2585,6 +2585,16 @@ static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA) return ret; } +static void dwc3_gadget_async_callbacks(struct usb_gadget *g, bool enable) +{ + struct dwc3 *dwc = gadget_to_dwc(g); + unsigned long flags; + + spin_lock_irqsave(&dwc->lock, flags); + dwc->async_callbacks = enable; + spin_unlock_irqrestore(&dwc->lock, flags); +} + static const struct usb_gadget_ops dwc3_gadget_ops = { .get_frame = dwc3_gadget_get_frame, .wakeup = dwc3_gadget_wakeup, @@ -2596,6 +2606,7 @@ static const struct usb_gadget_ops dwc3_gadget_ops = { .udc_set_ssp_rate = dwc3_gadget_set_ssp_rate, .get_config_params = dwc3_gadget_config_params, .vbus_draw = dwc3_gadget_vbus_draw, + .udc_async_callbacks = dwc3_gadget_async_callbacks, }; /* -------------------------------------------------------------------------- */ @@ -3231,7 +3242,7 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc, static void dwc3_disconnect_gadget(struct dwc3 *dwc) { - if (dwc->gadget_driver && dwc->gadget_driver->disconnect) { + if (dwc->async_callbacks && dwc->gadget_driver->disconnect) { spin_unlock(&dwc->lock); dwc->gadget_driver->disconnect(dwc->gadget); spin_lock(&dwc->lock); @@ -3240,7 +3251,7 @@ static void dwc3_disconnect_gadget(struct dwc3 *dwc) static void dwc3_suspend_gadget(struct dwc3 *dwc) { - if (dwc->gadget_driver && dwc->gadget_driver->suspend) { + if (dwc->async_callbacks && dwc->gadget_driver->suspend) { spin_unlock(&dwc->lock); dwc->gadget_driver->suspend(dwc->gadget); spin_lock(&dwc->lock); @@ -3249,7 +3260,7 @@ static void dwc3_suspend_gadget(struct dwc3 *dwc) static void dwc3_resume_gadget(struct dwc3 *dwc) { - if (dwc->gadget_driver && dwc->gadget_driver->resume) { + if (dwc->async_callbacks && dwc->gadget_driver->resume) { spin_unlock(&dwc->lock); dwc->gadget_driver->resume(dwc->gadget); spin_lock(&dwc->lock); @@ -3261,7 +3272,7 @@ static void dwc3_reset_gadget(struct dwc3 *dwc) if (!dwc->gadget_driver) return; - if (dwc->gadget->speed != USB_SPEED_UNKNOWN) { + if (dwc->async_callbacks && dwc->gadget->speed != USB_SPEED_UNKNOWN) { spin_unlock(&dwc->lock); usb_gadget_udc_reset(dwc->gadget, dwc->gadget_driver); spin_lock(&dwc->lock); @@ -3585,7 +3596,7 @@ static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc) * implemented. */ - if (dwc->gadget_driver && dwc->gadget_driver->resume) { + if (dwc->async_callbacks && dwc->gadget_driver->resume) { spin_unlock(&dwc->lock); dwc->gadget_driver->resume(dwc->gadget); spin_lock(&dwc->lock); From 4bb233b7ba87785c7ac519863f51ba61f4dbc459 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 1 Jul 2021 15:43:05 +0100 Subject: [PATCH 0676/1469] usb: gadget: u_serial: remove WARN_ON on null port Loading and then unloading module g_dpgp on a VM that does not support the driver currently throws a WARN_ON message because the port has not been initialized. Removing an unused driver is a valid use-case and the WARN_ON kernel warning is a bit excessive, so remove it. Cleans up: [27654.638698] ------------[ cut here ]------------ [27654.638705] WARNING: CPU: 6 PID: 2956336 at drivers/usb/gadget/function/u_serial.c:1201 gserial_free_line+0x7c/0x90 [u_serial] [27654.638728] Modules linked in: g_dbgp(-) u_serial usb_f_tcm target_core_mod libcomposite udc_core vmw_vmci mcb i2c_nforce2 i2c_amd756 nfit cx8800 videobuf2_dma_sg videobuf2_memops videobuf2_v4l2 cx88xx tveeprom videobuf2_common videodev mc ccp hid_generic hid intel_ishtp cros_ec mc13xxx_core vfio_mdev mdev i915 i2c_algo_bit kvm ppdev parport zatm eni suni uPD98402 atm rio_scan binder_linux hwmon_vid video ipmi_devintf ipmi_msghandler zstd nls_utf8 decnet qrtr ns sctp ip6_udp_tunnel udp_tunnel fcrypt pcbc nhc_udp nhc_ipv6 nhc_routing nhc_mobility nhc_hop nhc_dest nhc_fragment 6lowpan ts_kmp dccp_ipv6 dccp_ipv4 dccp snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq_dummy snd_seq snd_seq_device xen_front_pgdir_shbuf binfmt_misc nls_iso8859_1 dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua intel_rapl_msr intel_rapl_common snd_hda_codec_generic ledtrig_audio snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer snd rapl soundcore joydev input_leds mac_hid serio_raw efi_pstore [27654.638880] qemu_fw_cfg sch_fq_codel msr virtio_rng autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear qxl drm_ttm_helper crct10dif_pclmul ttm drm_kms_helper syscopyarea sysfillrect sysimgblt virtio_net fb_sys_fops cec net_failover rc_core ahci psmouse drm libahci lpc_ich virtio_blk failover [last unloaded: u_ether] [27654.638949] CPU: 6 PID: 2956336 Comm: modprobe Tainted: P O 5.13.0-9-generic #9 [27654.638956] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 [27654.638969] RIP: 0010:gserial_free_line+0x7c/0x90 [u_serial] [27654.638981] Code: 20 00 00 00 00 e8 74 1a ba c9 4c 89 e7 e8 8c fe ff ff 48 8b 3d 75 3b 00 00 44 89 f6 e8 3d 7c 69 c9 5b 41 5c 41 5d 41 5e 5d c3 <0f> 0b 4c 89 ef e8 4a 1a ba c9 5b 41 5c 41 5d 41 5e 5d c3 90 0f 1f [27654.638986] RSP: 0018:ffffba0b81403da0 EFLAGS: 00010246 [27654.638992] RAX: 0000000000000000 RBX: ffffffffc0eaf6a0 RCX: 0000000000000000 [27654.638996] RDX: ffff8e21c0cac8c0 RSI: 0000000000000006 RDI: ffffffffc0eaf6a0 [27654.639000] RBP: ffffba0b81403dc0 R08: ffffba0b81403de0 R09: fefefefefefefeff [27654.639003] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [27654.639006] R13: ffffffffc0eaf6a0 R14: 0000000000000000 R15: 0000000000000000 [27654.639010] FS: 00007faa1935e740(0000) GS:ffff8e223bd80000(0000) knlGS:0000000000000000 [27654.639015] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [27654.639019] CR2: 00007ffc840cd4e8 CR3: 000000000e1ac006 CR4: 0000000000370ee0 [27654.639028] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [27654.639031] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [27654.639035] Call Trace: [27654.639044] dbgp_exit+0x1c/0xa1a [g_dbgp] [27654.639054] __do_sys_delete_module.constprop.0+0x144/0x260 [27654.639066] ? call_rcu+0xe/0x10 [27654.639073] __x64_sys_delete_module+0x12/0x20 [27654.639081] do_syscall_64+0x61/0xb0 [27654.639092] ? exit_to_user_mode_loop+0xec/0x160 [27654.639098] ? exit_to_user_mode_prepare+0x37/0xb0 [27654.639104] ? syscall_exit_to_user_mode+0x27/0x50 [27654.639110] ? __x64_sys_close+0x12/0x40 [27654.639119] ? do_syscall_64+0x6e/0xb0 [27654.639126] ? exit_to_user_mode_prepare+0x37/0xb0 [27654.639132] ? syscall_exit_to_user_mode+0x27/0x50 [27654.639137] ? __x64_sys_newfstatat+0x1e/0x20 [27654.639146] ? do_syscall_64+0x6e/0xb0 [27654.639154] ? exc_page_fault+0x8f/0x170 [27654.639159] ? asm_exc_page_fault+0x8/0x30 [27654.639166] entry_SYSCALL_64_after_hwframe+0x44/0xae [27654.639173] RIP: 0033:0x7faa194a4b2b [27654.639179] Code: 73 01 c3 48 8b 0d 3d 73 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 0d 73 0c 00 f7 d8 64 89 01 48 [27654.639185] RSP: 002b:00007ffc840d0578 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [27654.639191] RAX: ffffffffffffffda RBX: 000056060f9f4e70 RCX: 00007faa194a4b2b [27654.639194] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000056060f9f4ed8 [27654.639197] RBP: 000056060f9f4e70 R08: 0000000000000000 R09: 0000000000000000 [27654.639200] R10: 00007faa1951eac0 R11: 0000000000000206 R12: 000056060f9f4ed8 [27654.639203] R13: 0000000000000000 R14: 000056060f9f4ed8 R15: 00007ffc840d06c8 [27654.639219] ---[ end trace 8dd0ea0bb32ce94a ]--- Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20210701144305.110078-1-colin.king@canonical.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index bffef8e47dac..281ca766698a 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1198,7 +1198,7 @@ void gserial_free_line(unsigned char port_num) struct gs_port *port; mutex_lock(&ports[port_num].lock); - if (WARN_ON(!ports[port_num].port)) { + if (!ports[port_num].port) { mutex_unlock(&ports[port_num].lock); return; } From 0665e387318607d8269bfdea60723c627c8bae43 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Fri, 2 Jul 2021 00:12:24 -0700 Subject: [PATCH 0677/1469] usb: xhci: avoid renesas_usb_fw.mem when it's unusable Commit a66d21d7dba8 ("usb: xhci: Add support for Renesas controller with memory") added renesas_usb_fw.mem firmware reference to xhci-pci. Thus modinfo indicates xhci-pci.ko has "firmware: renesas_usb_fw.mem". But the firmware is only actually used with CONFIG_USB_XHCI_PCI_RENESAS. An unusable firmware reference can trigger safety checkers which look for drivers with unmet firmware dependencies. Avoid referring to renesas_usb_fw.mem in circumstances when it cannot be loaded (when CONFIG_USB_XHCI_PCI_RENESAS isn't set). Fixes: a66d21d7dba8 ("usb: xhci: Add support for Renesas controller with memory") Cc: stable Signed-off-by: Greg Thelen Link: https://lore.kernel.org/r/20210702071224.3673568-1-gthelen@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 18c2bbddf080..1c9a7957c45c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -636,7 +636,14 @@ static const struct pci_device_id pci_ids[] = { { /* end: all zeroes */ } }; MODULE_DEVICE_TABLE(pci, pci_ids); + +/* + * Without CONFIG_USB_XHCI_PCI_RENESAS renesas_xhci_check_request_fw() won't + * load firmware, so don't encumber the xhci-pci driver with it. + */ +#if IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS) MODULE_FIRMWARE("renesas_usb_fw.mem"); +#endif /* pci driver glue; this is a "new style" PCI driver module */ static struct pci_driver xhci_pci_driver = { From 3d11de2d57b92e943767d7d070b0df9b18089d56 Mon Sep 17 00:00:00 2001 From: Artur Petrosyan Date: Sat, 10 Jul 2021 13:22:46 +0400 Subject: [PATCH 0678/1469] usb: phy: Fix page fault from usb_phy_uevent When the dwc2 platform device is removed, it unregisters the generic phy. usb_remove_phy() is called and the dwc2 usb_phy is removed from the "phy_list", but the uevent may still attempt to get the usb_phy from the list, resulting in a page fault bug. Currently we can't access the usb_phy from the "phy_list" after the device is removed. As a fix check to make sure that we can get the usb_phy before moving forward with the uevent. [ 84.949345] BUG: unable to handle page fault for address:00000007935688d8 [ 84.949349] #PF: supervisor read access in kernel mode [ 84.949351] #PF: error_code(0x0000) - not-present page [ 84.949353] PGD 0 P4D 0 [ 84.949356] Oops: 0000 [#1] SMP PTI [ 84.949360] CPU: 2 PID: 2081 Comm: rmmod Not tainted 5.13.0-rc4-snps-16547-ga8534cb092d7-dirty #32 [ 84.949363] Hardware name: Hewlett-Packard HP Z400 Workstation/0B4Ch, BIOS 786G3 v03.54 11/02/2011 [ 84.949365] RIP: 0010:usb_phy_uevent+0x99/0x121 [ 84.949372] Code: 8d 83 f8 00 00 00 48 3d b0 12 22 94 74 05 4c 3b 23 75 5b 8b 83 9c 00 00 00 be 32 00 00 00 48 8d 7c 24 04 48 c7 c2 d4 5d 7b 93 <48> 8b 0c c5 e0 88 56 93 e8 0f 63 8a ff 8b 83 98 00 00 00 be 32 00 [ 84.949375] RSP: 0018:ffffa46bc0f2fc70 EFLAGS: 00010246 [ 84.949378] RAX: 00000000ffffffff RBX: ffffffff942211b8 RCX: 0000000000000027 [ 84.949380] RDX: ffffffff937b5dd4 RSI: 0000000000000032 RDI: ffffa46bc0f2fc74 [ 84.949383] RBP: ffff94a306613000 R08: 0000000000000000 R09: 00000000fffeffff [ 84.949385] R10: ffffa46bc0f2faa8 R11: ffffa46bc0f2faa0 R12: ffff94a30186d410 [ 84.949387] R13: ffff94a32d188a80 R14: ffff94a30029f960 R15: ffffffff93522dd0 [ 84.949389] FS: 00007efdbd417540(0000) GS:ffff94a513a80000(0000) knlGS:0000000000000000 [ 84.949392] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 84.949394] CR2: 00000007935688d8 CR3: 0000000165606000 CR4: 00000000000006e0 [ 84.949396] Call Trace: [ 84.949401] dev_uevent+0x190/0x1ad [ 84.949408] kobject_uevent_env+0x18e/0x46c [ 84.949414] device_release_driver_internal+0x17f/0x18e [ 84.949418] bus_remove_device+0xd3/0xe5 [ 84.949421] device_del+0x1c3/0x31d [ 84.949425] ? kobject_put+0x97/0xa8 [ 84.949428] platform_device_del+0x1c/0x63 [ 84.949432] platform_device_unregister+0xa/0x11 [ 84.949436] dwc2_pci_remove+0x1e/0x2c [dwc2_pci] [ 84.949440] pci_device_remove+0x31/0x81 [ 84.949445] device_release_driver_internal+0xea/0x18e [ 84.949448] driver_detach+0x68/0x72 [ 84.949450] bus_remove_driver+0x63/0x82 [ 84.949453] pci_unregister_driver+0x1a/0x75 [ 84.949457] __do_sys_delete_module+0x149/0x1e9 [ 84.949462] ? task_work_run+0x64/0x6e [ 84.949465] ? exit_to_user_mode_prepare+0xd4/0x10d [ 84.949471] do_syscall_64+0x5d/0x70 [ 84.949475] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 84.949480] RIP: 0033:0x7efdbd563bcb [ 84.949482] Code: 73 01 c3 48 8b 0d c5 82 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 95 82 0c 00 f7 d8 64 89 01 48 [ 84.949485] RSP: 002b:00007ffe944d7d98 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 84.949489] RAX: ffffffffffffffda RBX: 00005651072eb700 RCX: 00007efdbd563bcb [ 84.949491] RDX: 000000000000000a RSI: 0000000000000800 RDI: 00005651072eb768 [ 84.949493] RBP: 00007ffe944d7df8 R08: 0000000000000000 R09: 0000000000000000 [ 84.949495] R10: 00007efdbd5dfac0 R11: 0000000000000206 R12: 00007ffe944d7fd0 [ 84.949497] R13: 00007ffe944d8610 R14: 00005651072eb2a0 R15: 00005651072eb700 [ 84.949500] Modules linked in: uas configfs dwc2_pci(-) phy_generic fuse crc32c_intel [last unloaded: udc_core] [ 84.949508] CR2: 00000007935688d8 [ 84.949510] ---[ end trace e40c871ca3e4dc9e ]--- [ 84.949512] RIP: 0010:usb_phy_uevent+0x99/0x121 Fixes: a8534cb092d7 ("usb: phy: introduce usb_phy device type with its own uevent handler") Reviewed-by: Peter Chen Signed-off-by: Artur Petrosyan Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/20210710092247.D7AFEA005D@mailhost.synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 83ed5089475a..1b24492bb4e5 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -86,10 +86,10 @@ static struct usb_phy *__device_to_usb_phy(struct device *dev) list_for_each_entry(usb_phy, &phy_list, head) { if (usb_phy->dev == dev) - break; + return usb_phy; } - return usb_phy; + return NULL; } static void usb_phy_set_default_current(struct usb_phy *usb_phy) @@ -150,8 +150,14 @@ static int usb_phy_uevent(struct device *dev, struct kobj_uevent_env *env) struct usb_phy *usb_phy; char uchger_state[50] = { 0 }; char uchger_type[50] = { 0 }; + unsigned long flags; + spin_lock_irqsave(&phy_lock, flags); usb_phy = __device_to_usb_phy(dev); + spin_unlock_irqrestore(&phy_lock, flags); + + if (!usb_phy) + return -ENODEV; snprintf(uchger_state, ARRAY_SIZE(uchger_state), "USB_CHARGER_STATE=%s", usb_chger_state[usb_phy->chg_state]); From fecb3a171db425e5068b27231f8efe154bf72637 Mon Sep 17 00:00:00 2001 From: Minas Harutyunyan Date: Tue, 13 Jul 2021 09:32:55 +0400 Subject: [PATCH 0679/1469] usb: dwc2: gadget: Fix GOUTNAK flow for Slave mode. Because of dwc2_hsotg_ep_stop_xfr() function uses poll mode, first need to mask GINTSTS_GOUTNAKEFF interrupt. In Slave mode GINTSTS_GOUTNAKEFF interrupt will be aserted only after pop OUT NAK status packet from RxFIFO. In dwc2_hsotg_ep_sethalt() function before setting DCTL_SGOUTNAK need to unmask GOUTNAKEFF interrupt. Tested by USBCV CH9 and MSC tests set in Slave, BDMA and DDMA. All tests are passed. Fixes: a4f827714539a ("usb: dwc2: gadget: Disable enabled HW endpoint in dwc2_hsotg_ep_disable") Fixes: 6070636c4918c ("usb: dwc2: Fix Stalling a Non-Isochronous OUT EP") Cc: stable Signed-off-by: Minas Harutyunyan Link: https://lore.kernel.org/r/e17fad802bbcaf879e1ed6745030993abb93baf8.1626152924.git.Minas.Harutyunyan@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/gadget.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index c581ee41ac81..74d25019272f 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3900,9 +3900,27 @@ static void dwc2_hsotg_ep_stop_xfr(struct dwc2_hsotg *hsotg, __func__); } } else { + /* Mask GINTSTS_GOUTNAKEFF interrupt */ + dwc2_hsotg_disable_gsint(hsotg, GINTSTS_GOUTNAKEFF); + if (!(dwc2_readl(hsotg, GINTSTS) & GINTSTS_GOUTNAKEFF)) dwc2_set_bit(hsotg, DCTL, DCTL_SGOUTNAK); + if (!using_dma(hsotg)) { + /* Wait for GINTSTS_RXFLVL interrupt */ + if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, + GINTSTS_RXFLVL, 100)) { + dev_warn(hsotg->dev, "%s: timeout GINTSTS.RXFLVL\n", + __func__); + } else { + /* + * Pop GLOBAL OUT NAK status packet from RxFIFO + * to assert GOUTNAKEFF interrupt + */ + dwc2_readl(hsotg, GRXSTSP); + } + } + /* Wait for global nak to take effect */ if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_GOUTNAKEFF, 100)) @@ -4348,6 +4366,9 @@ static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now) epctl = dwc2_readl(hs, epreg); if (value) { + /* Unmask GOUTNAKEFF interrupt */ + dwc2_hsotg_en_gsint(hs, GINTSTS_GOUTNAKEFF); + if (!(dwc2_readl(hs, GINTSTS) & GINTSTS_GOUTNAKEFF)) dwc2_set_bit(hs, DCTL, DCTL_SGOUTNAK); // STALL bit will be set in GOUTNAKEFF interrupt handler From 5719df243e118fb343725e8b2afb1637e1af1373 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 24 Jun 2021 21:20:39 +0900 Subject: [PATCH 0680/1469] usb: renesas_usbhs: Fix superfluous irqs happen after usb_pkt_pop() This driver has a potential issue which this driver is possible to cause superfluous irqs after usb_pkt_pop() is called. So, after the commit 3af32605289e ("usb: renesas_usbhs: fix error return code of usbhsf_pkt_handler()") had been applied, we could observe the following error happened when we used g_audio. renesas_usbhs e6590000.usb: irq_ready run_error 1 : -22 To fix the issue, disable the tx or rx interrupt in usb_pkt_pop(). Fixes: 2743e7f90dc0 ("usb: renesas_usbhs: fix the usb_pkt_pop()") Cc: # v4.4+ Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20210624122039.596528-1-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/renesas_usbhs/fifo.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index b5e7991dc7d9..a3c2b01ccf7b 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -101,6 +101,8 @@ static struct dma_chan *usbhsf_dma_chan_get(struct usbhs_fifo *fifo, #define usbhsf_dma_map(p) __usbhsf_dma_map_ctrl(p, 1) #define usbhsf_dma_unmap(p) __usbhsf_dma_map_ctrl(p, 0) static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map); +static void usbhsf_tx_irq_ctrl(struct usbhs_pipe *pipe, int enable); +static void usbhsf_rx_irq_ctrl(struct usbhs_pipe *pipe, int enable); struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt) { struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); @@ -123,6 +125,11 @@ struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt) if (chan) { dmaengine_terminate_all(chan); usbhsf_dma_unmap(pkt); + } else { + if (usbhs_pipe_is_dir_in(pipe)) + usbhsf_rx_irq_ctrl(pipe, 0); + else + usbhsf_tx_irq_ctrl(pipe, 0); } usbhs_pipe_clear_without_sequence(pipe, 0, 0); From c4a0f7a6ab5417eb6105b0e1d7e6e67f6ef7d4e5 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 16 Jul 2021 07:01:27 +0200 Subject: [PATCH 0681/1469] usb: dwc2: Skip clock gating on Samsung SoCs Commit 0112b7ce68ea ("usb: dwc2: Update dwc2_handle_usb_suspend_intr function.") changed the way the driver handles power down modes in a such way that it uses clock gating when no other power down mode is available. This however doesn't work well on the DWC2 implementation used on the Samsung SoCs. When a clock gating is enabled, system hangs. It looks that the proper clock gating requires some additional glue code in the shared USB2 PHY and/or Samsung glue code for the DWC2. To restore driver operation on the Samsung SoCs simply skip enabling clock gating mode until one finds what is really needed to make it working reliably. Fixes: 0112b7ce68ea ("usb: dwc2: Update dwc2_handle_usb_suspend_intr function.") Cc: stable Acked-by: Krzysztof Kozlowski Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20210716050127.4406-1-m.szyprowski@samsung.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/core.h | 4 ++++ drivers/usb/dwc2/core_intr.c | 3 ++- drivers/usb/dwc2/hcd.c | 6 ++++-- drivers/usb/dwc2/params.c | 1 + 4 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index ab6b815e0089..483de2bbfaab 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -383,6 +383,9 @@ enum dwc2_ep0_state { * 0 - No (default) * 1 - Partial power down * 2 - Hibernation + * @no_clock_gating: Specifies whether to avoid clock gating feature. + * 0 - No (use clock gating) + * 1 - Yes (avoid it) * @lpm: Enable LPM support. * 0 - No * 1 - Yes @@ -480,6 +483,7 @@ struct dwc2_core_params { #define DWC2_POWER_DOWN_PARAM_NONE 0 #define DWC2_POWER_DOWN_PARAM_PARTIAL 1 #define DWC2_POWER_DOWN_PARAM_HIBERNATION 2 + bool no_clock_gating; bool lpm; bool lpm_clock_gating; diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index a5ab03808da6..a5c52b237e72 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -556,7 +556,8 @@ static void dwc2_handle_usb_suspend_intr(struct dwc2_hsotg *hsotg) * If neither hibernation nor partial power down are supported, * clock gating is used to save power. */ - dwc2_gadget_enter_clock_gating(hsotg); + if (!hsotg->params.no_clock_gating) + dwc2_gadget_enter_clock_gating(hsotg); } /* diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 035d4911a3c3..2a7828971d05 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -3338,7 +3338,8 @@ int dwc2_port_suspend(struct dwc2_hsotg *hsotg, u16 windex) * If not hibernation nor partial power down are supported, * clock gating is used to save power. */ - dwc2_host_enter_clock_gating(hsotg); + if (!hsotg->params.no_clock_gating) + dwc2_host_enter_clock_gating(hsotg); break; } @@ -4402,7 +4403,8 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) * If not hibernation nor partial power down are supported, * clock gating is used to save power. */ - dwc2_host_enter_clock_gating(hsotg); + if (!hsotg->params.no_clock_gating) + dwc2_host_enter_clock_gating(hsotg); /* After entering suspend, hardware is not accessible */ clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index 67c5eb140232..59e119345994 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -76,6 +76,7 @@ static void dwc2_set_s3c6400_params(struct dwc2_hsotg *hsotg) struct dwc2_core_params *p = &hsotg->params; p->power_down = DWC2_POWER_DOWN_PARAM_NONE; + p->no_clock_gating = true; p->phy_utmi_width = 8; } From d53dc38857f6dbefabd9eecfcbf67b6eac9a1ef4 Mon Sep 17 00:00:00 2001 From: Minas Harutyunyan Date: Tue, 20 Jul 2021 05:41:24 -0700 Subject: [PATCH 0682/1469] usb: dwc2: gadget: Fix sending zero length packet in DDMA mode. Sending zero length packet in DDMA mode perform by DMA descriptor by setting SP (short packet) flag. For DDMA in function dwc2_hsotg_complete_in() does not need to send zlp. Tested by USBCV MSC tests. Fixes: f71b5e2533de ("usb: dwc2: gadget: fix zero length packet transfers") Cc: stable Signed-off-by: Minas Harutyunyan Link: https://lore.kernel.org/r/967bad78c55dd2db1c19714eee3d0a17cf99d74a.1626777738.git.Minas.Harutyunyan@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/gadget.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 74d25019272f..3146df6e6510 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -2749,12 +2749,14 @@ static void dwc2_hsotg_complete_in(struct dwc2_hsotg *hsotg, return; } - /* Zlp for all endpoints, for ep0 only in DATA IN stage */ + /* Zlp for all endpoints in non DDMA, for ep0 only in DATA IN stage */ if (hs_ep->send_zlp) { - dwc2_hsotg_program_zlp(hsotg, hs_ep); hs_ep->send_zlp = 0; - /* transfer will be completed on next complete interrupt */ - return; + if (!using_desc_dma(hsotg)) { + dwc2_hsotg_program_zlp(hsotg, hs_ep); + /* transfer will be completed on next complete interrupt */ + return; + } } if (hs_ep->index == 0 && hsotg->ep0_state == DWC2_EP0_DATA_IN) { From 4e9505064f58d1252805952f8547a5b7dbc5c111 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Sat, 17 Jul 2021 16:02:21 +0100 Subject: [PATCH 0683/1469] net/xfrm/compat: Copy xfrm_spdattr_type_t atributes The attribute-translator has to take in mind maxtype, that is xfrm_link::nla_max. When it is set, attributes are not of xfrm_attr_type_t. Currently, they can be only XFRMA_SPD_MAX (message XFRM_MSG_NEWSPDINFO), their UABI is the same for 64/32-bit, so just copy them. Thanks to YueHaibing for reporting this: In xfrm_user_rcv_msg_compat() if maxtype is not zero and less than XFRMA_MAX, nlmsg_parse_deprecated() do not initialize attrs array fully. xfrm_xlate32() will access uninit 'attrs[i]' while iterating all attrs array. KASAN: probably user-memory-access in range [0x0000000041b58ab0-0x0000000041b58ab7] CPU: 0 PID: 15799 Comm: syz-executor.2 Tainted: G W 5.14.0-rc1-syzkaller #0 RIP: 0010:nla_type include/net/netlink.h:1130 [inline] RIP: 0010:xfrm_xlate32_attr net/xfrm/xfrm_compat.c:410 [inline] RIP: 0010:xfrm_xlate32 net/xfrm/xfrm_compat.c:532 [inline] RIP: 0010:xfrm_user_rcv_msg_compat+0x5e5/0x1070 net/xfrm/xfrm_compat.c:577 [...] Call Trace: xfrm_user_rcv_msg+0x556/0x8b0 net/xfrm/xfrm_user.c:2774 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 xfrm_netlink_rcv+0x6b/0x90 net/xfrm/xfrm_user.c:2824 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:702 [inline] Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Cc: Reported-by: YueHaibing Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_compat.c | 49 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 44 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a20aec9d7393..2bf269390163 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -298,8 +298,16 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { - int err = xfrm_xlate64_attr(dst, nla); + int err; + switch (type) { + case XFRM_MSG_NEWSPDINFO: + err = xfrm_nla_cpy(dst, nla, nla_len(nla)); + break; + default: + err = xfrm_xlate64_attr(dst, nla); + break; + } if (err) return err; } @@ -341,7 +349,8 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, - struct nlattr *attrs[XFRMA_MAX+1]) + struct nlattr *attrs[XFRMA_MAX + 1], + int maxtype) { size_t len = nlmsg_len(src); @@ -358,10 +367,20 @@ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, case XFRM_MSG_POLEXPIRE: len += 8; break; + case XFRM_MSG_NEWSPDINFO: + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + return len; default: break; } + /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please + * correct both 64=>32-bit and 32=>64-bit translators to copy + * new attributes. + */ + if (WARN_ON_ONCE(maxtype)) + return len; + if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) @@ -440,7 +459,8 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], - size_t size, u8 type, struct netlink_ext_ack *extack) + size_t size, u8 type, int maxtype, + struct netlink_ext_ack *extack) { size_t pos; int i; @@ -520,6 +540,25 @@ static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, } pos = dst->nlmsg_len; + if (maxtype) { + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); + + for (i = 1; i <= maxtype; i++) { + int err; + + if (!attrs[i]) + continue; + + /* just copy - no need for translation */ + err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, + nla_len(attrs[i]), nla_len(attrs[i])); + if (err) + return err; + } + return 0; + } + for (i = 1; i < XFRMA_MAX + 1; i++) { int err; @@ -564,7 +603,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (err < 0) return ERR_PTR(err); - len = xfrm_user_rcv_calculate_len64(h32, attrs); + len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; @@ -574,7 +613,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (!h64) return ERR_PTR(-ENOMEM); - err = xfrm_xlate32(h64, h32, attrs, len, type, extack); + err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); From 70bfdf62e93a4d73cfbaf83a3ac708a483ef7a71 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Sat, 17 Jul 2021 16:02:22 +0100 Subject: [PATCH 0684/1469] selftests/net/ipsec: Add test for xfrm_spdattr_type_t Set hthresh, dump it again and verify thresh.lbits && thresh.rbits. They are passed as attributes of xfrm_spdattr_type_t, different from other message attributes that use xfrm_attr_type_t. Also, test attribute that is bigger than XFRMA_SPD_MAX, currently it should be silently ignored. Cc: Shuah Khan Cc: linux-kselftest@vger.kernel.org Signed-off-by: Dmitry Safonov Signed-off-by: Steffen Klassert --- tools/testing/selftests/net/ipsec.c | 165 +++++++++++++++++++++++++++- 1 file changed, 163 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index f23438d512c5..3d7dde2c321b 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -484,13 +484,16 @@ enum desc_type { MONITOR_ACQUIRE, EXPIRE_STATE, EXPIRE_POLICY, + SPDINFO_ATTRS, }; const char *desc_name[] = { "create tunnel", "alloc spi", "monitor acquire", "expire state", - "expire policy" + "expire policy", + "spdinfo attributes", + "" }; struct xfrm_desc { enum desc_type type; @@ -1593,6 +1596,155 @@ out_close: return ret; } +static int xfrm_spdinfo_set_thresh(int xfrm_sock, uint32_t *seq, + unsigned thresh4_l, unsigned thresh4_r, + unsigned thresh6_l, unsigned thresh6_r, + bool add_bad_attr) + +{ + struct { + struct nlmsghdr nh; + union { + uint32_t unused; + int error; + }; + char attrbuf[MAX_PAYLOAD]; + } req; + struct xfrmu_spdhthresh thresh; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused)); + req.nh.nlmsg_type = XFRM_MSG_NEWSPDINFO; + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_seq = (*seq)++; + + thresh.lbits = thresh4_l; + thresh.rbits = thresh4_r; + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV4_HTHRESH, &thresh, sizeof(thresh))) + return -1; + + thresh.lbits = thresh6_l; + thresh.rbits = thresh6_r; + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV6_HTHRESH, &thresh, sizeof(thresh))) + return -1; + + if (add_bad_attr) { + BUILD_BUG_ON(XFRMA_IF_ID <= XFRMA_SPD_MAX + 1); + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) { + pr_err("adding attribute failed: no space"); + return -1; + } + } + + if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) { + pr_err("send()"); + return -1; + } + + if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) { + pr_err("recv()"); + return -1; + } else if (req.nh.nlmsg_type != NLMSG_ERROR) { + printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type); + return -1; + } + + if (req.error) { + printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error)); + return -1; + } + + return 0; +} + +static int xfrm_spdinfo_attrs(int xfrm_sock, uint32_t *seq) +{ + struct { + struct nlmsghdr nh; + union { + uint32_t unused; + int error; + }; + char attrbuf[MAX_PAYLOAD]; + } req; + + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 31, 120, 16, false)) { + pr_err("Can't set SPD HTHRESH"); + return KSFT_FAIL; + } + + memset(&req, 0, sizeof(req)); + + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused)); + req.nh.nlmsg_type = XFRM_MSG_GETSPDINFO; + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_seq = (*seq)++; + if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) { + pr_err("send()"); + return KSFT_FAIL; + } + + if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) { + pr_err("recv()"); + return KSFT_FAIL; + } else if (req.nh.nlmsg_type == XFRM_MSG_NEWSPDINFO) { + size_t len = NLMSG_PAYLOAD(&req.nh, sizeof(req.unused)); + struct rtattr *attr = (void *)req.attrbuf; + int got_thresh = 0; + + for (; RTA_OK(attr, len); attr = RTA_NEXT(attr, len)) { + if (attr->rta_type == XFRMA_SPD_IPV4_HTHRESH) { + struct xfrmu_spdhthresh *t = RTA_DATA(attr); + + got_thresh++; + if (t->lbits != 32 || t->rbits != 31) { + pr_err("thresh differ: %u, %u", + t->lbits, t->rbits); + return KSFT_FAIL; + } + } + if (attr->rta_type == XFRMA_SPD_IPV6_HTHRESH) { + struct xfrmu_spdhthresh *t = RTA_DATA(attr); + + got_thresh++; + if (t->lbits != 120 || t->rbits != 16) { + pr_err("thresh differ: %u, %u", + t->lbits, t->rbits); + return KSFT_FAIL; + } + } + } + if (got_thresh != 2) { + pr_err("only %d thresh returned by XFRM_MSG_GETSPDINFO", got_thresh); + return KSFT_FAIL; + } + } else if (req.nh.nlmsg_type != NLMSG_ERROR) { + printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type); + return KSFT_FAIL; + } else { + printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error)); + return -1; + } + + /* Restore the default */ + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, false)) { + pr_err("Can't restore SPD HTHRESH"); + return KSFT_FAIL; + } + + /* + * At this moment xfrm uses nlmsg_parse_deprecated(), which + * implies NL_VALIDATE_LIBERAL - ignoring attributes with + * (type > maxtype). nla_parse_depricated_strict() would enforce + * it. Or even stricter nla_parse(). + * Right now it's not expected to fail, but to be ignored. + */ + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, true)) + return KSFT_PASS; + + return KSFT_PASS; +} + static int child_serv(int xfrm_sock, uint32_t *seq, unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc) { @@ -1717,6 +1869,9 @@ static int child_f(unsigned int nr, int test_desc_fd, int cmd_fd, void *buf) case EXPIRE_POLICY: ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc); break; + case SPDINFO_ATTRS: + ret = xfrm_spdinfo_attrs(xfrm_sock, &seq); + break; default: printk("Unknown desc type %d", desc.type); exit(KSFT_FAIL); @@ -1994,8 +2149,10 @@ static int write_proto_plan(int fd, int proto) * sizeof(xfrm_user_polexpire) = 168 | sizeof(xfrm_user_polexpire) = 176 * * Check the affected by the UABI difference structures. + * Also, check translation for xfrm_set_spdinfo: it has it's own attributes + * which needs to be correctly copied, but not translated. */ -const unsigned int compat_plan = 4; +const unsigned int compat_plan = 5; static int write_compat_struct_tests(int test_desc_fd) { struct xfrm_desc desc = {}; @@ -2019,6 +2176,10 @@ static int write_compat_struct_tests(int test_desc_fd) if (__write_desc(test_desc_fd, &desc)) return -1; + desc.type = SPDINFO_ATTRS; + if (__write_desc(test_desc_fd, &desc)) + return -1; + return 0; } From 1f958f3dff42a7239bbfdd9a33db5f11574d16bf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Jul 2021 09:55:38 +0200 Subject: [PATCH 0685/1469] Revert "arm64: dts: qcom: Harmonize DWC USB3 DT nodes name" This reverts commit eb9b7bfd5954f5f6ac4d57313541dd0294660aad as it breaks working userspace implementations (i.e. Android systems) The device node name here is part of configfs, so it is a user-visable api that can not be changed. Reported-by: John Stultz Cc: Serge Semin Cc: Krzysztof Kozlowski Cc: Bjorn Andersson Link: https://lore.kernel.org/r/CALAqxLX_FNvFndEDWtGbFPjSzuAbfqxQE07diBJFZtftwEJX5A@mail.gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi | 4 ++-- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 4 ++-- arch/arm64/boot/dts/qcom/msm8996.dtsi | 4 ++-- arch/arm64/boot/dts/qcom/msm8998.dtsi | 2 +- arch/arm64/boot/dts/qcom/qcs404-evb.dtsi | 2 +- arch/arm64/boot/dts/qcom/qcs404.dtsi | 4 ++-- arch/arm64/boot/dts/qcom/sc7180.dtsi | 2 +- arch/arm64/boot/dts/qcom/sdm845.dtsi | 4 ++-- arch/arm64/boot/dts/qcom/sm8150.dtsi | 2 +- 9 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index 068692350e00..51e17094d7b1 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -1063,7 +1063,7 @@ status = "okay"; extcon = <&usb2_id>; - usb@7600000 { + dwc3@7600000 { extcon = <&usb2_id>; dr_mode = "otg"; maximum-speed = "high-speed"; @@ -1074,7 +1074,7 @@ status = "okay"; extcon = <&usb3_id>; - usb@6a00000 { + dwc3@6a00000 { extcon = <&usb3_id>; dr_mode = "otg"; }; diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 95d6cb8cd4c0..f39bc10cc5bd 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -443,7 +443,7 @@ resets = <&gcc GCC_USB0_BCR>; status = "disabled"; - dwc_0: usb@8a00000 { + dwc_0: dwc3@8a00000 { compatible = "snps,dwc3"; reg = <0x8a00000 0xcd00>; interrupts = ; @@ -484,7 +484,7 @@ resets = <&gcc GCC_USB1_BCR>; status = "disabled"; - dwc_1: usb@8c00000 { + dwc_1: dwc3@8c00000 { compatible = "snps,dwc3"; reg = <0x8c00000 0xcd00>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 0e1bc4669d7e..78c55ca10ba9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -2566,7 +2566,7 @@ power-domains = <&gcc USB30_GDSC>; status = "disabled"; - usb@6a00000 { + dwc3@6a00000 { compatible = "snps,dwc3"; reg = <0x06a00000 0xcc00>; interrupts = <0 131 IRQ_TYPE_LEVEL_HIGH>; @@ -2873,7 +2873,7 @@ qcom,select-utmi-as-pipe-clk; status = "disabled"; - usb@7600000 { + dwc3@7600000 { compatible = "snps,dwc3"; reg = <0x07600000 0xcc00>; interrupts = <0 138 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 6f294f9c0cdf..e9d3ce29937c 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1964,7 +1964,7 @@ resets = <&gcc GCC_USB_30_BCR>; - usb3_dwc3: usb@a800000 { + usb3_dwc3: dwc3@a800000 { compatible = "snps,dwc3"; reg = <0x0a800000 0xcd00>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi index f8a55307b855..a80c578484ba 100644 --- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi @@ -337,7 +337,7 @@ &usb3 { status = "okay"; - usb@7580000 { + dwc3@7580000 { dr_mode = "host"; }; }; diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi index 9c4be020d568..339790ba585d 100644 --- a/arch/arm64/boot/dts/qcom/qcs404.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi @@ -544,7 +544,7 @@ assigned-clock-rates = <19200000>, <200000000>; status = "disabled"; - usb@7580000 { + dwc3@7580000 { compatible = "snps,dwc3"; reg = <0x07580000 0xcd00>; interrupts = ; @@ -573,7 +573,7 @@ assigned-clock-rates = <19200000>, <133333333>; status = "disabled"; - usb@78c0000 { + dwc3@78c0000 { compatible = "snps,dwc3"; reg = <0x078c0000 0xcc00>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index a5d58eb92896..a9a052f8c63c 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2756,7 +2756,7 @@ <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3 0>; interconnect-names = "usb-ddr", "apps-usb"; - usb_1_dwc3: usb@a600000 { + usb_1_dwc3: dwc3@a600000 { compatible = "snps,dwc3"; reg = <0 0x0a600000 0 0xe000>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 1796ae8372be..0a86fe71a66d 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -3781,7 +3781,7 @@ <&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_0 0>; interconnect-names = "usb-ddr", "apps-usb"; - usb_1_dwc3: usb@a600000 { + usb_1_dwc3: dwc3@a600000 { compatible = "snps,dwc3"; reg = <0 0x0a600000 0 0xcd00>; interrupts = ; @@ -3829,7 +3829,7 @@ <&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_1 0>; interconnect-names = "usb-ddr", "apps-usb"; - usb_2_dwc3: usb@a800000 { + usb_2_dwc3: dwc3@a800000 { compatible = "snps,dwc3"; reg = <0 0x0a800000 0 0xcd00>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 612dda0fef43..eef9d79157e9 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -2344,7 +2344,7 @@ resets = <&gcc GCC_USB30_PRIM_BCR>; - usb_1_dwc3: usb@a600000 { + usb_1_dwc3: dwc3@a600000 { compatible = "snps,dwc3"; reg = <0 0x0a600000 0 0xcd00>; interrupts = ; From 7764656b108cd308c39e9a8554353b8f9ca232a3 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Mon, 5 Jul 2021 21:38:29 +0800 Subject: [PATCH 0686/1469] nvme-pci: don't WARN_ON in nvme_reset_work if ctrl.state is not RESETTING Followling process: nvme_probe nvme_reset_ctrl nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) queue_work(nvme_reset_wq, &ctrl->reset_work) --------------> nvme_remove nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING) worker_thread process_one_work nvme_reset_work WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING) , which will trigger WARN_ON in nvme_reset_work(): [ 127.534298] WARNING: CPU: 0 PID: 139 at drivers/nvme/host/pci.c:2594 [ 127.536161] CPU: 0 PID: 139 Comm: kworker/u8:7 Not tainted 5.13.0 [ 127.552518] Call Trace: [ 127.552840] ? kvm_sched_clock_read+0x25/0x40 [ 127.553936] ? native_send_call_func_single_ipi+0x1c/0x30 [ 127.555117] ? send_call_function_single_ipi+0x9b/0x130 [ 127.556263] ? __smp_call_single_queue+0x48/0x60 [ 127.557278] ? ttwu_queue_wakelist+0xfa/0x1c0 [ 127.558231] ? try_to_wake_up+0x265/0x9d0 [ 127.559120] ? ext4_end_io_rsv_work+0x160/0x290 [ 127.560118] process_one_work+0x28c/0x640 [ 127.561002] worker_thread+0x39a/0x700 [ 127.561833] ? rescuer_thread+0x580/0x580 [ 127.562714] kthread+0x18c/0x1e0 [ 127.563444] ? set_kthread_struct+0x70/0x70 [ 127.564347] ret_from_fork+0x1f/0x30 The preceding problem can be easily reproduced by executing following script (based on blktests suite): test() { pdev="$(_get_pci_dev_from_blkdev)" sysfs="/sys/bus/pci/devices/${pdev}" for ((i = 0; i < 10; i++)); do echo 1 > "$sysfs/remove" echo 1 > /sys/bus/pci/rescan done } Since the device ctrl could be updated as an non-RESETTING state by repeating probe/remove in userspace (which is a normal situation), we can replace stack dumping WARN_ON with a warnning message. Fixes: 82b057caefaff ("nvme-pci: fix multiple ctrl removal schedulin") Signed-off-by: Zhihao Cheng --- drivers/nvme/host/pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 320051f5a3dd..51852085239e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2631,7 +2631,9 @@ static void nvme_reset_work(struct work_struct *work) bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result; - if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) { + if (dev->ctrl.state != NVME_CTRL_RESETTING) { + dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n", + dev->ctrl.state); result = -ENODEV; goto out; } From 5396fdac56d87d04e75e5068c0c92d33625f51e7 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 16 Jul 2021 13:30:35 +0200 Subject: [PATCH 0687/1469] nvme: fix refcounting imbalance when all paths are down When the last path to a ns_head drops the current code removes the ns_head from the subsystem list, but will only delete the disk itself if the last reference to the ns_head drops. This is causing an refcounting imbalance eg when applications have a reference to the disk, as then they'll never get notified that the disk is in fact dead. This patch moves the call 'del_gendisk' into nvme_mpath_check_last_path(), ensuring that the disk can be properly removed and applications get the appropriate notifications. Signed-off-by: Hannes Reinecke Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 14 +++++++++++--- drivers/nvme/host/multipath.c | 9 ++++++++- drivers/nvme/host/nvme.h | 11 ++--------- 3 files changed, 21 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 11779be42186..17c05a4595f0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3807,6 +3807,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, static void nvme_ns_remove(struct nvme_ns *ns) { + bool last_path = false; + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; @@ -3815,8 +3817,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) mutex_lock(&ns->ctrl->subsys->lock); list_del_rcu(&ns->siblings); - if (list_empty(&ns->head->list)) - list_del_init(&ns->head->entry); mutex_unlock(&ns->ctrl->subsys->lock); synchronize_rcu(); /* guarantee not available in head->list */ @@ -3836,7 +3836,15 @@ static void nvme_ns_remove(struct nvme_ns *ns) list_del_init(&ns->list); up_write(&ns->ctrl->namespaces_rwsem); - nvme_mpath_check_last_path(ns); + /* Synchronize with nvme_init_ns_head() */ + mutex_lock(&ns->head->subsys->lock); + if (list_empty(&ns->head->list)) { + list_del_init(&ns->head->entry); + last_path = true; + } + mutex_unlock(&ns->head->subsys->lock); + if (last_path) + nvme_mpath_shutdown_disk(ns->head); nvme_put_ns(ns); } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 0ea5298469c3..3f32c5e86bfc 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -760,14 +760,21 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) #endif } -void nvme_mpath_remove_disk(struct nvme_ns_head *head) +void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) { if (!head->disk) return; + kblockd_schedule_work(&head->requeue_work); if (head->disk->flags & GENHD_FL_UP) { nvme_cdev_del(&head->cdev, &head->cdev_device); del_gendisk(head->disk); } +} + +void nvme_mpath_remove_disk(struct nvme_ns_head *head) +{ + if (!head->disk) + return; blk_set_queue_dying(head->disk->queue); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 18ef8dd03a90..5cd1fa3b8464 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -716,14 +716,7 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); - -static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) -{ - struct nvme_ns_head *head = ns->head; - - if (head->disk && list_empty(&head->list)) - kblockd_schedule_work(&head->requeue_work); -} +void nvme_mpath_shutdown_disk(struct nvme_ns_head *head); static inline void nvme_trace_bio_complete(struct request *req) { @@ -772,7 +765,7 @@ static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns) static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) { } -static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) +static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) { } static inline void nvme_trace_bio_complete(struct request *req) From 234211b8dd161fa25f192c78d5a8d2dd6bf920a0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 19 Jul 2021 09:44:39 -0700 Subject: [PATCH 0688/1469] nvme: fix nvme_setup_command metadata trace event The metadata address is set after the trace event, so the trace is not capturing anything useful. Rather than logging the memory address, it's useful to know if the command carries a metadata payload, so change the trace event to log that true/false state instead. Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/trace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index daaf700eae79..35bac7a25422 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -56,7 +56,7 @@ TRACE_EVENT(nvme_setup_cmd, __field(u8, fctype) __field(u16, cid) __field(u32, nsid) - __field(u64, metadata) + __field(bool, metadata) __array(u8, cdw10, 24) ), TP_fast_assign( @@ -66,13 +66,13 @@ TRACE_EVENT(nvme_setup_cmd, __entry->flags = cmd->common.flags; __entry->cid = cmd->common.command_id; __entry->nsid = le32_to_cpu(cmd->common.nsid); - __entry->metadata = le64_to_cpu(cmd->common.metadata); + __entry->metadata = !!blk_integrity_rq(req); __entry->fctype = cmd->fabrics.fctype; __assign_disk_name(__entry->disk, req->rq_disk); memcpy(__entry->cdw10, &cmd->common.cdw10, sizeof(__entry->cdw10)); ), - TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)", + TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)", __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->nsid, __entry->flags, __entry->metadata, From 5c912e679506ef72adb95616d2f56a8a1b079a3d Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 21 May 2021 02:10:10 +0000 Subject: [PATCH 0689/1469] usb: cdc-wdm: fix build error when CONFIG_WWAN_CORE is not set Gcc report build error as following when CONFIG_WWAN_CORE is not set: x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_disconnect': cdc-wdm.c:(.text+0xb2a): undefined reference to `wwan_remove_port' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_in_callback': cdc-wdm.c:(.text+0xf23): undefined reference to `wwan_port_rx' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_wwan_port_stop': cdc-wdm.c:(.text+0x127d): undefined reference to `wwan_port_get_drvdata' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_wwan_port_tx': cdc-wdm.c:(.text+0x12d9): undefined reference to `wwan_port_get_drvdata' x86_64-linux-gnu-ld: cdc-wdm.c:(.text+0x13c1): undefined reference to `wwan_port_txoff' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_wwan_port_start': cdc-wdm.c:(.text+0x13e0): undefined reference to `wwan_port_get_drvdata' x86_64-linux-gnu-ld: cdc-wdm.c:(.text+0x1431): undefined reference to `wwan_port_txon' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_wwan_port_tx_complete': cdc-wdm.c:(.text+0x14a4): undefined reference to `wwan_port_txon' x86_64-linux-gnu-ld: drivers/usb/class/cdc-wdm.o: in function `wdm_create.cold': cdc-wdm.c:(.text.unlikely+0x209): undefined reference to `wwan_create_port' Using CONFIG_WWAN_CORE instead of CONFIG_WWAN to avoid build error. Fixes: cac6fb015f71 ("usb: class: cdc-wdm: WWAN framework integration") Reported-by: Hulk Robot Reviewed-by: Loic Poulain Signed-off-by: Wei Yongjun Link: https://lore.kernel.org/r/20210521021010.2490930-1-weiyongjun1@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-wdm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index fdf79bcf7eb0..35d5908b5478 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -824,7 +824,7 @@ static struct usb_class_driver wdm_class = { }; /* --- WWAN framework integration --- */ -#ifdef CONFIG_WWAN +#ifdef CONFIG_WWAN_CORE static int wdm_wwan_port_start(struct wwan_port *port) { struct wdm_device *desc = wwan_port_get_drvdata(port); @@ -963,11 +963,11 @@ static void wdm_wwan_rx(struct wdm_device *desc, int length) /* inbuf has been copied, it is safe to check for outstanding data */ schedule_work(&desc->service_outs_intr); } -#else /* CONFIG_WWAN */ +#else /* CONFIG_WWAN_CORE */ static void wdm_wwan_init(struct wdm_device *desc) {} static void wdm_wwan_deinit(struct wdm_device *desc) {} static void wdm_wwan_rx(struct wdm_device *desc, int length) {} -#endif /* CONFIG_WWAN */ +#endif /* CONFIG_WWAN_CORE */ /* --- error handling --- */ static void wdm_rxwork(struct work_struct *work) From f3a1a937f7b240be623d989c8553a6d01465d04f Mon Sep 17 00:00:00 2001 From: Vincent Palatin Date: Wed, 21 Jul 2021 11:25:16 +0200 Subject: [PATCH 0690/1469] Revert "USB: quirks: ignore remote wake-up on Fibocom L850-GL LTE modem" This reverts commit 0bd860493f81eb2a46173f6f5e44cc38331c8dbd. While the patch was working as stated,ie preventing the L850-GL LTE modem from crashing on some U3 wake-ups due to a race condition between the host wake-up and the modem-side wake-up, when using the MBIM interface, this would force disabling the USB runtime PM on the device. The increased power consumption is significant for LTE laptops, and given that with decently recent modem firmwares, when the modem hits the bug, it automatically recovers (ie it drops from the bus, but automatically re-enumerates after less than half a second, rather than being stuck until a power cycle as it was doing with ancient firmware), for most people, the trade-off now seems in favor of re-enabling it by default. For people with access to the platform code, the bug can also be worked-around successfully by changing the USB3 LFPM polling off-time for the XHCI controller in the BIOS code. Signed-off-by: Vincent Palatin Link: https://lore.kernel.org/r/20210721092516.2775971-1-vpalatin@chromium.org Fixes: 0bd860493f81 ("USB: quirks: ignore remote wake-up on Fibocom L850-GL LTE modem") Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6114cf83bb44..8239fe7129dd 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -501,10 +501,6 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, - /* Fibocom L850-GL LTE Modem */ - { USB_DEVICE(0x2cb7, 0x0007), .driver_info = - USB_QUIRK_IGNORE_REMOTE_WAKEUP }, - /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, From 990e4ad3ddcb72216caeddd6e62c5f45a21e8121 Mon Sep 17 00:00:00 2001 From: Xiangyang Zhang Date: Mon, 28 Jun 2021 23:22:39 +0800 Subject: [PATCH 0691/1469] staging: rtl8723bs: Fix a resource leak in sd_int_dpc The "c2h_evt" variable is not freed when function call "c2h_evt_read_88xx" failed Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver") Reviewed-by: Hans de Goede Signed-off-by: Xiangyang Zhang Cc: stable Link: https://lore.kernel.org/r/20210628152239.5475-1-xyz.sun.ok@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/sdio_ops.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/rtl8723bs/hal/sdio_ops.c b/drivers/staging/rtl8723bs/hal/sdio_ops.c index 2dd251ce177e..a545832a468e 100644 --- a/drivers/staging/rtl8723bs/hal/sdio_ops.c +++ b/drivers/staging/rtl8723bs/hal/sdio_ops.c @@ -909,6 +909,8 @@ void sd_int_dpc(struct adapter *adapter) } else { rtw_c2h_wk_cmd(adapter, (u8 *)c2h_evt); } + } else { + kfree(c2h_evt); } } else { /* Error handling for malloc fail */ From a7c3acca53801e10a77ede6b759a73f5ac4bc261 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 21 Jul 2021 09:18:35 +0200 Subject: [PATCH 0692/1469] arm64: smccc: Save lr before calling __arm_smccc_sve_check() Commit cfa7ff959a78 ("arm64: smccc: Support SMCCC v1.3 SVE register saving hint") added a call to __arm_smccc_sve_check() which clobbers the lr (register x30), causing __arm_smccc_hvc() to return to itself and crash. Save lr on the stack before calling __arm_smccc_sve_check(). Save the frame pointer (x29) to complete the frame record, and adjust the offsets used to access stack parameters. Acked-by: Ard Biesheuvel Acked-by: Mark Brown Fixes: cfa7ff959a78 ("arm64: smccc: Support SMCCC v1.3 SVE register saving hint") Signed-off-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20210721071834.69130-1-jean-philippe@linaro.org Signed-off-by: Will Deacon --- arch/arm64/kernel/smccc-call.S | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S index d3d37f932b97..487381164ff6 100644 --- a/arch/arm64/kernel/smccc-call.S +++ b/arch/arm64/kernel/smccc-call.S @@ -32,20 +32,23 @@ SYM_FUNC_END(__arm_smccc_sve_check) EXPORT_SYMBOL(__arm_smccc_sve_check) .macro SMCCC instr + stp x29, x30, [sp, #-16]! + mov x29, sp alternative_if ARM64_SVE bl __arm_smccc_sve_check alternative_else_nop_endif \instr #0 - ldr x4, [sp] + ldr x4, [sp, #16] stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS] stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS] - ldr x4, [sp, #8] + ldr x4, [sp, #24] cbz x4, 1f /* no quirk structure */ ldr x9, [x4, #ARM_SMCCC_QUIRK_ID_OFFS] cmp x9, #ARM_SMCCC_QUIRK_QCOM_A6 b.ne 1f str x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS] -1: ret +1: ldp x29, x30, [sp], #16 + ret .endm /* From d8a719059b9dc963aa190598778ac804ff3e6a87 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Wed, 21 Jul 2021 17:02:13 +1000 Subject: [PATCH 0693/1469] Revert "mm/pgtable: add stubs for {pmd/pub}_{set/clear}_huge" This reverts commit c742199a014de23ee92055c2473d91fe5561ffdf. c742199a014d ("mm/pgtable: add stubs for {pmd/pub}_{set/clear}_huge") breaks arm64 in at least two ways for configurations where PUD or PMD folding occur: 1. We no longer install huge-vmap mappings and silently fall back to page-granular entries, despite being able to install block entries at what is effectively the PGD level. 2. If the linear map is backed with block mappings, these will now silently fail to be created in alloc_init_pud(), causing a panic early during boot. The pgtable selftests caught this, although a fix has not been forthcoming and Christophe is AWOL at the moment, so just revert the change for now to get a working -rc3 on which we can queue patches for 5.15. A simple revert breaks the build for 32-bit PowerPC 8xx machines, which rely on the default function definitions when the corresponding page-table levels are folded, since commit a6a8f7c4aa7e ("powerpc/8xx: add support for huge pages on VMAP and VMALLOC"), eg: powerpc64-linux-ld: mm/vmalloc.o: in function `vunmap_pud_range': linux/mm/vmalloc.c:362: undefined reference to `pud_clear_huge' To avoid that, add stubs for pud_clear_huge() and pmd_clear_huge() in arch/powerpc/mm/nohash/8xx.c as suggested by Christophe. Cc: Christophe Leroy Cc: Catalin Marinas Cc: Andrew Morton Cc: Nicholas Piggin Cc: Mike Rapoport Cc: Mark Rutland Cc: Geert Uytterhoeven Fixes: c742199a014d ("mm/pgtable: add stubs for {pmd/pub}_{set/clear}_huge") Signed-off-by: Jonathan Marek Reviewed-by: Ard Biesheuvel Acked-by: Marc Zyngier [mpe: Fold in 8xx.c changes from Christophe and mention in change log] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/linux-arm-kernel/CAMuHMdXShORDox-xxaeUfDW3wx2PeggFSqhVSHVZNKCGK-y_vQ@mail.gmail.com/ Link: https://lore.kernel.org/r/20210717160118.9855-1-jonathan@marek.ca Link: https://lore.kernel.org/r/87r1fs1762.fsf@mpe.ellerman.id.au Signed-off-by: Will Deacon --- arch/arm64/mm/mmu.c | 20 ++++++++------------ arch/powerpc/mm/nohash/8xx.c | 10 ++++++++++ arch/x86/mm/pgtable.c | 34 +++++++++++++++------------------- include/linux/pgtable.h | 26 +------------------------- 4 files changed, 34 insertions(+), 56 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d74586508448..9ff0de1b2b93 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1339,7 +1339,6 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } -#if CONFIG_PGTABLE_LEVELS > 3 int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot)); @@ -1354,16 +1353,6 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) return 1; } -int pud_clear_huge(pud_t *pudp) -{ - if (!pud_sect(READ_ONCE(*pudp))) - return 0; - pud_clear(pudp); - return 1; -} -#endif - -#if CONFIG_PGTABLE_LEVELS > 2 int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot)); @@ -1378,6 +1367,14 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) return 1; } +int pud_clear_huge(pud_t *pudp) +{ + if (!pud_sect(READ_ONCE(*pudp))) + return 0; + pud_clear(pudp); + return 1; +} + int pmd_clear_huge(pmd_t *pmdp) { if (!pmd_sect(READ_ONCE(*pmdp))) @@ -1385,7 +1382,6 @@ int pmd_clear_huge(pmd_t *pmdp) pmd_clear(pmdp); return 1; } -#endif int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index 60780e089118..0df9fe29dd56 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -240,3 +240,13 @@ void __init setup_kuap(bool disabled) mtspr(SPRN_MD_AP, MD_APG_KUAP); } #endif + +int pud_clear_huge(pud_t *pud) +{ + return 0; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3364fe62b903..3481b35cb4ec 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -682,7 +682,6 @@ int p4d_clear_huge(p4d_t *p4d) } #endif -#if CONFIG_PGTABLE_LEVELS > 3 /** * pud_set_huge - setup kernel PUD mapping * @@ -721,23 +720,6 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 1; } -/** - * pud_clear_huge - clear kernel PUD mapping when it is set - * - * Returns 1 on success and 0 on failure (no PUD map is found). - */ -int pud_clear_huge(pud_t *pud) -{ - if (pud_large(*pud)) { - pud_clear(pud); - return 1; - } - - return 0; -} -#endif - -#if CONFIG_PGTABLE_LEVELS > 2 /** * pmd_set_huge - setup kernel PMD mapping * @@ -768,6 +750,21 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ +int pud_clear_huge(pud_t *pud) +{ + if (pud_large(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} + /** * pmd_clear_huge - clear kernel PMD mapping when it is set * @@ -782,7 +779,6 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } -#endif #ifdef CONFIG_X86_64 /** diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index d147480cdefc..e24d2c992b11 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1397,34 +1397,10 @@ static inline int p4d_clear_huge(p4d_t *p4d) } #endif /* !__PAGETABLE_P4D_FOLDED */ -#ifndef __PAGETABLE_PUD_FOLDED int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); -int pud_clear_huge(pud_t *pud); -#else -static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) -{ - return 0; -} -static inline int pud_clear_huge(pud_t *pud) -{ - return 0; -} -#endif /* !__PAGETABLE_PUD_FOLDED */ - -#ifndef __PAGETABLE_PMD_FOLDED int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); +int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); -#else -static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) -{ - return 0; -} -static inline int pmd_clear_huge(pmd_t *pmd) -{ - return 0; -} -#endif /* !__PAGETABLE_PMD_FOLDED */ - int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); From 61acabaae5ba58b3c32e6e90d24c2c0827fd27a8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 25 Jun 2021 18:37:33 +0300 Subject: [PATCH 0694/1469] serial: max310x: Unprepare and disable clock in error path In one error case the clock may be left prepared and enabled. Unprepare and disable clock in that case to balance state of the hardware. Fixes: d4d6f03c4fb3 ("serial: max310x: Try to get crystal clock rate from property") Reported-by: Dan Carpenter Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210625153733.12911-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/max310x.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 0c1e4df52215..ef11860cd69e 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1293,7 +1293,8 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty freq = uartclk; if (freq == 0) { dev_err(dev, "Cannot get clock rate\n"); - return -EINVAL; + ret = -EINVAL; + goto out_clk; } if (xtal) { From e5227c51090e165db4b48dcaa300605bfced7014 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Sat, 26 Jun 2021 06:11:05 +0200 Subject: [PATCH 0695/1469] serial: 8250: Mask out floating 16/32-bit bus bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make sure only actual 8 bits of the IIR register are used in determining the port type in `autoconfig'. The `serial_in' port accessor returns the `unsigned int' type, meaning that with UPIO_AU, UPIO_MEM16, UPIO_MEM32, and UPIO_MEM32BE access types more than 8 bits of data are returned, of which the high order bits will often come from bus lines that are left floating in the data phase. For example with the MIPS Malta board's CBUS UART, where the registers are aligned on 8-byte boundaries and which uses 32-bit accesses, data as follows is returned: YAMON> dump -32 0xbf000900 0x40 BF000900: 1F000942 1F000942 1F000900 1F000900 ...B...B........ BF000910: 1F000901 1F000901 1F000900 1F000900 ................ BF000920: 1F000900 1F000900 1F000960 1F000960 ...........`...` BF000930: 1F000900 1F000900 1F0009FF 1F0009FF ................ YAMON> Evidently high-order 24 bits return values previously driven in the address phase (the 3 highest order address bits used with the command above are masked out in the simple virtual address mapping used here and come out at zeros on the external bus), a common scenario with bus lines left floating, due to bus capacitance. Consequently when the value of IIR, mapped at 0x1f000910, is retrieved in `autoconfig', it comes out at 0x1f0009c1 and when it is right-shifted by 6 and then assigned to 8-bit `scratch' variable, the value calculated is 0x27, not one of 0, 1, 2, 3 expected in port type determination. Fix the issue then, by assigning the value returned from `serial_in' to `scratch' first, which masks out 24 high-order bits retrieved, and only then right-shift the resulting 8-bit data quantity, producing the value of 3 in this case, as expected. Fix the same issue in `serial_dl_read'. The problem first appeared with Linux 2.6.9-rc3 which predates our repo history, but the origin could be identified with the old MIPS/Linux repo also at: as commit e0d2356c0777 ("Merge with Linux 2.6.9-rc3."), where code in `serial_in' was updated with this case: + case UPIO_MEM32: + return readl(up->port.membase + offset); + which made it produce results outside the unsigned 8-bit range for the first time, though obviously it is system dependent what actual values appear in the high order bits retrieved and it may well have been zeros in the relevant positions with the system the change originally was intended for. It is at that point that code in `autoconf' should have been updated accordingly, but clearly it was overlooked. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org # v2.6.12+ Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Maciej W. Rozycki Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106260516220.37803@angie.orcam.me.uk Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 2164290cbd31..2e7000f79b03 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -311,7 +311,11 @@ static const struct serial8250_config uart_config[] = { /* Uart divisor latch read */ static int default_serial_dl_read(struct uart_8250_port *up) { - return serial_in(up, UART_DLL) | serial_in(up, UART_DLM) << 8; + /* Assign these in pieces to truncate any bits above 7. */ + unsigned char dll = serial_in(up, UART_DLL); + unsigned char dlm = serial_in(up, UART_DLM); + + return dll | dlm << 8; } /* Uart divisor latch write */ @@ -1297,9 +1301,11 @@ static void autoconfig(struct uart_8250_port *up) serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); - scratch = serial_in(up, UART_IIR) >> 6; - switch (scratch) { + /* Assign this as it is to truncate any bits above 7. */ + scratch = serial_in(up, UART_IIR); + + switch (scratch >> 6) { case 0: autoconfig_8250(up); break; From 9a936d6c3d3d6c33ecbadf72dccdb567b5cd3c72 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Sat, 26 Jun 2021 06:11:13 +0200 Subject: [PATCH 0696/1469] MIPS: Malta: Do not byte-swap accesses to the CBUS UART MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Correct big-endian accesses to the CBUS UART, a Malta on-board discrete TI16C550C part wired directly to the system controller's device bus, and do not use byte swapping with the 32-bit accesses to the device. The CBUS is used for devices such as the boot flash memory needed early on in system bootstrap even before PCI has been initialised. Therefore it uses the system controller's device bus, which follows the endianness set with the CPU, which means no byte-swapping is ever required for data accesses to CBUS, unlike with PCI. The CBUS UART uses the UPIO_MEM32 access method, that is the `readl' and `writel' MMIO accessors, which on the MIPS platform imply byte-swapping with PCI systems. Consequently the wrong byte lane is accessed with the big-endian configuration and the UART is not correctly accessed. As it happens the UPIO_MEM32BE access method makes use of the `ioread32' and `iowrite32' MMIO accessors, which still use `readl' and `writel' respectively, however they byte-swap data passed, effectively cancelling swapping done with the accessors themselves and making it suitable for the CBUS UART. Make the CBUS UART switch between UPIO_MEM32 and UPIO_MEM32BE then, based on the endianness selected. With this change in place the device is correctly recognised with big-endian Malta at boot, along with the Super I/O devices behind PCI: Serial: 8250/16550 driver, 5 ports, IRQ sharing enabled printk: console [ttyS0] disabled serial8250.0: ttyS0 at I/O 0x3f8 (irq = 4, base_baud = 115200) is a 16550A printk: console [ttyS0] enabled printk: bootconsole [uart8250] disabled serial8250.0: ttyS1 at I/O 0x2f8 (irq = 3, base_baud = 115200) is a 16550A serial8250.0: ttyS2 at MMIO 0x1f000900 (irq = 20, base_baud = 230400) is a 16550A Fixes: e7c4782f92fc ("[MIPS] Put an end to 's long and annyoing existence") Cc: stable@vger.kernel.org # v2.6.23+ Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Maciej W. Rozycki Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106260524430.37803@angie.orcam.me.uk Signed-off-by: Greg Kroah-Hartman --- arch/mips/mti-malta/malta-platform.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c index ee7471984fe7..4ffbcc58c6f6 100644 --- a/arch/mips/mti-malta/malta-platform.c +++ b/arch/mips/mti-malta/malta-platform.c @@ -48,7 +48,8 @@ static struct plat_serial8250_port uart8250_data[] = { .mapbase = 0x1f000900, /* The CBUS UART */ .irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB2, .uartclk = 3686400, /* Twice the usual clk! */ - .iotype = UPIO_MEM32, + .iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ? + UPIO_MEM32BE : UPIO_MEM32, .flags = CBUS_UART_FLAGS, .regshift = 3, }, From cc9ca4d95846cbbece48d9cd385550f8fba6a3c1 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 30 Jun 2021 13:56:43 +0100 Subject: [PATCH 0697/1469] serial: tegra: Only print FIFO error message when an error occurs The Tegra serial driver always prints an error message when enabling the FIFO for devices that have support for checking the FIFO enable status. Fix this by displaying the error message, only when an error occurs. Finally, update the error message to make it clear that enabling the FIFO failed and display the error code. Fixes: 222dcdff3405 ("serial: tegra: check for FIFO mode enabled status") Cc: Acked-by: Thierry Reding Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20210630125643.264264-1-jonathanh@nvidia.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial-tegra.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 222032792d6c..eba5b9ecba34 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -1045,9 +1045,11 @@ static int tegra_uart_hw_init(struct tegra_uart_port *tup) if (tup->cdata->fifo_mode_enable_status) { ret = tegra_uart_wait_fifo_mode_enabled(tup); - dev_err(tup->uport.dev, "FIFO mode not enabled\n"); - if (ret < 0) + if (ret < 0) { + dev_err(tup->uport.dev, + "Failed to enable FIFO mode: %d\n", ret); return ret; + } } else { /* * For all tegra devices (up to t210), there is a hardware From 853a9ae29e978d37f5dfa72622a68c9ae3d7fa89 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 14 Jul 2021 10:04:27 +0200 Subject: [PATCH 0698/1469] serial: 8250: fix handle_irq locking The 8250 handle_irq callback is not just called from the interrupt handler but also from a timer callback when polling (e.g. for ports without an interrupt line). Consequently the callback must explicitly disable interrupts to avoid a potential deadlock with another interrupt in polled mode. Add back an irqrestore-version of the sysrq port-unlock helper and use it in the 8250 callbacks that need it. Fixes: 75f4e830fa9c ("serial: do not restore interrupt state in sysrq helper") Cc: stable@vger.kernel.org # 5.13 Cc: Joel Stanley Cc: Andrew Jeffery Reported-by: kernel test robot Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210714080427.28164-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_aspeed_vuart.c | 5 +++-- drivers/tty/serial/8250/8250_fsl.c | 5 +++-- drivers/tty/serial/8250/8250_port.c | 5 +++-- include/linux/serial_core.h | 24 +++++++++++++++++++++ 4 files changed, 33 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index 4caab8714e2c..2350fb3bb5e4 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -329,6 +329,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int iir, lsr; + unsigned long flags; unsigned int space, count; iir = serial_port_in(port, UART_IIR); @@ -336,7 +337,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) if (iir & UART_IIR_NO_INT) return 0; - spin_lock(&port->lock); + spin_lock_irqsave(&port->lock, flags); lsr = serial_port_in(port, UART_LSR); @@ -370,7 +371,7 @@ static int aspeed_vuart_handle_irq(struct uart_port *port) if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); - uart_unlock_and_check_sysrq(port); + uart_unlock_and_check_sysrq_irqrestore(port, flags); return 1; } diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c index 4e75d2e4f87c..fc65a2293ce9 100644 --- a/drivers/tty/serial/8250/8250_fsl.c +++ b/drivers/tty/serial/8250/8250_fsl.c @@ -30,10 +30,11 @@ struct fsl8250_data { int fsl8250_handle_irq(struct uart_port *port) { unsigned char lsr, orig_lsr; + unsigned long flags; unsigned int iir; struct uart_8250_port *up = up_to_u8250p(port); - spin_lock(&up->port.lock); + spin_lock_irqsave(&up->port.lock, flags); iir = port->serial_in(port, UART_IIR); if (iir & UART_IIR_NO_INT) { @@ -82,7 +83,7 @@ int fsl8250_handle_irq(struct uart_port *port) up->lsr_saved_flags = orig_lsr; - uart_unlock_and_check_sysrq(&up->port); + uart_unlock_and_check_sysrq_irqrestore(&up->port, flags); return 1; } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 2e7000f79b03..1da29a219842 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1899,11 +1899,12 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) unsigned char status; struct uart_8250_port *up = up_to_u8250p(port); bool skip_rx = false; + unsigned long flags; if (iir & UART_IIR_NO_INT) return 0; - spin_lock(&port->lock); + spin_lock_irqsave(&port->lock, flags); status = serial_port_in(port, UART_LSR); @@ -1929,7 +1930,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) (up->ier & UART_IER_THRI)) serial8250_tx_chars(up); - uart_unlock_and_check_sysrq(port); + uart_unlock_and_check_sysrq_irqrestore(port, flags); return 1; } diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 52d7fb92a69d..c58cc142d23f 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -518,6 +518,25 @@ static inline void uart_unlock_and_check_sysrq(struct uart_port *port) if (sysrq_ch) handle_sysrq(sysrq_ch); } + +static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, + unsigned long flags) +{ + int sysrq_ch; + + if (!port->has_sysrq) { + spin_unlock_irqrestore(&port->lock, flags); + return; + } + + sysrq_ch = port->sysrq_ch; + port->sysrq_ch = 0; + + spin_unlock_irqrestore(&port->lock, flags); + + if (sysrq_ch) + handle_sysrq(sysrq_ch); +} #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { @@ -531,6 +550,11 @@ static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { spin_unlock(&port->lock); } +static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, + unsigned long flags) +{ + spin_unlock_irqrestore(&port->lock, flags); +} #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* From 7f0909db761535aefafa77031062603a71557267 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 13 Jul 2021 13:17:39 +0300 Subject: [PATCH 0699/1469] serial: 8250_pci: Enumerate Elkhart Lake UARTs via dedicated driver Elkhart Lake UARTs are PCI enumerated Synopsys DesignWare v4.0+ UART integrated with Intel iDMA 32-bit DMA controller. There is a specific driver to handle them, i.e. 8250_lpss. Hence, disable 8250_pci enumeration for these UARTs. Fixes: 1b91d97c66ef ("serial: 8250_lpss: Add ->setup() for Elkhart Lake ports") Fixes: 4f912b898dc2 ("serial: 8250_lpss: Enable HS UART on Elkhart Lake") Cc: stable Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210713101739.36962-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 75827b608fdb..02985cf90ef2 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -3836,6 +3836,12 @@ static const struct pci_device_id blacklist[] = { { PCI_VDEVICE(INTEL, 0x0f0c), }, { PCI_VDEVICE(INTEL, 0x228a), }, { PCI_VDEVICE(INTEL, 0x228c), }, + { PCI_VDEVICE(INTEL, 0x4b96), }, + { PCI_VDEVICE(INTEL, 0x4b97), }, + { PCI_VDEVICE(INTEL, 0x4b98), }, + { PCI_VDEVICE(INTEL, 0x4b99), }, + { PCI_VDEVICE(INTEL, 0x4b9a), }, + { PCI_VDEVICE(INTEL, 0x4b9b), }, { PCI_VDEVICE(INTEL, 0x9ce3), }, { PCI_VDEVICE(INTEL, 0x9ce4), }, From 2dbd9c27eda5cf83aa990266a3355960d860da71 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 8 Jul 2021 14:25:18 +0300 Subject: [PATCH 0700/1469] drm/ttm: add missing NULL checks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit My local syzbot instance hit GPF in ttm_bo_release(). Unfortunately, syzbot didn't produce a reproducer for this, but I found out possible scenario: drm_gem_vram_create() <-- drm_gem_vram_object kzalloced (bo embedded in this object) ttm_bo_init() ttm_bo_init_reserved() ttm_resource_alloc() man->func->alloc() <-- allocation failure ttm_bo_put() ttm_bo_release() ttm_mem_io_free() <-- bo->resource == NULL passed as second argument *GPF* Added NULL check inside ttm_mem_io_free() to prevent reported GPF and make this function NULL save in future. Same problem was in ttm_bo_move_to_lru_tail() as Christian reported. ttm_bo_move_to_lru_tail() is called in ttm_bo_release() and mem pointer can be NULL as well as in ttm_mem_io_free(). Fail log: KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] ... RIP: 0010:ttm_mem_io_free+0x28/0x170 drivers/gpu/drm/ttm/ttm_bo_util.c:66 .. Call Trace: ttm_bo_release+0xd94/0x10a0 drivers/gpu/drm/ttm/ttm_bo.c:422 kref_put include/linux/kref.h:65 [inline] ttm_bo_put drivers/gpu/drm/ttm/ttm_bo.c:470 [inline] ttm_bo_init_reserved+0x7cb/0x960 drivers/gpu/drm/ttm/ttm_bo.c:1050 ttm_bo_init+0x105/0x270 drivers/gpu/drm/ttm/ttm_bo.c:1074 drm_gem_vram_create+0x332/0x4c0 drivers/gpu/drm/drm_gem_vram_helper.c:228 Fixes: d3116756a710 ("drm/ttm: rename bo->mem and make it a pointer") Signed-off-by: Pavel Skripkin Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210708112518.17271-1-paskripkin@gmail.com --- drivers/gpu/drm/ttm/ttm_bo.c | 3 +++ drivers/gpu/drm/ttm/ttm_bo_util.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 1b950b45cf4b..8d7fd65ccced 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -102,6 +102,9 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, return; } + if (!mem) + return; + man = ttm_manager_type(bdev, mem->mem_type); list_move_tail(&bo->lru, &man->lru[bo->priority]); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 2f57f824e6db..763fa6f4e07d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -63,6 +63,9 @@ int ttm_mem_io_reserve(struct ttm_device *bdev, void ttm_mem_io_free(struct ttm_device *bdev, struct ttm_resource *mem) { + if (!mem) + return; + if (!mem->bus.offset && !mem->bus.addr) return; From 56f6f4c4eb2a710ec8878dd9373d3d2b2eb75f5c Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Fri, 16 Jul 2021 13:21:04 +0530 Subject: [PATCH 0701/1469] bus: mhi: pci_generic: Apply no-op for wake using sideband wake boolean Devices such as SDX24 do not have the provision for inband wake doorbell in the form of channel 127 and instead have a sideband GPIO for it. Newer devices such as SDX55 or SDX65 support inband wake method by default. Ensure the functionality is used based on this such that device wake stays held when a client driver uses mhi_device_get() API or the equivalent debugfs entry. Link: https://lore.kernel.org/r/1624560809-30610-1-git-send-email-bbhatt@codeaurora.org Fixes: e3e5e6508fc1 ("bus: mhi: pci_generic: No-Op for device_wake operations") Cc: stable@vger.kernel.org #5.12 Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210716075106.49938-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/pci_generic.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c index ca3bc40427f8..3396cb30ebec 100644 --- a/drivers/bus/mhi/pci_generic.c +++ b/drivers/bus/mhi/pci_generic.c @@ -32,6 +32,8 @@ * @edl: emergency download mode firmware path (if any) * @bar_num: PCI base address register to use for MHI MMIO register space * @dma_data_width: DMA transfer word size (32 or 64 bits) + * @sideband_wake: Devices using dedicated sideband GPIO for wakeup instead + * of inband wake support (such as sdx24) */ struct mhi_pci_dev_info { const struct mhi_controller_config *config; @@ -40,6 +42,7 @@ struct mhi_pci_dev_info { const char *edl; unsigned int bar_num; unsigned int dma_data_width; + bool sideband_wake; }; #define MHI_CHANNEL_CONFIG_UL(ch_num, ch_name, el_count, ev_ring) \ @@ -242,7 +245,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx65_info = { .edl = "qcom/sdx65m/edl.mbn", .config = &modem_qcom_v1_mhiv_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .sideband_wake = false, }; static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = { @@ -251,7 +255,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = { .edl = "qcom/sdx55m/edl.mbn", .config = &modem_qcom_v1_mhiv_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .sideband_wake = false, }; static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = { @@ -259,7 +264,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = { .edl = "qcom/prog_firehose_sdx24.mbn", .config = &modem_qcom_v1_mhiv_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .sideband_wake = true, }; static const struct mhi_channel_config mhi_quectel_em1xx_channels[] = { @@ -301,7 +307,8 @@ static const struct mhi_pci_dev_info mhi_quectel_em1xx_info = { .edl = "qcom/prog_firehose_sdx24.mbn", .config = &modem_quectel_em1xx_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .sideband_wake = true, }; static const struct mhi_channel_config mhi_foxconn_sdx55_channels[] = { @@ -339,7 +346,8 @@ static const struct mhi_pci_dev_info mhi_foxconn_sdx55_info = { .edl = "qcom/sdx55m/edl.mbn", .config = &modem_foxconn_sdx55_config, .bar_num = MHI_PCI_DEFAULT_BAR_NUM, - .dma_data_width = 32 + .dma_data_width = 32, + .sideband_wake = false, }; static const struct pci_device_id mhi_pci_id_table[] = { @@ -640,9 +648,12 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mhi_cntrl->status_cb = mhi_pci_status_cb; mhi_cntrl->runtime_get = mhi_pci_runtime_get; mhi_cntrl->runtime_put = mhi_pci_runtime_put; - mhi_cntrl->wake_get = mhi_pci_wake_get_nop; - mhi_cntrl->wake_put = mhi_pci_wake_put_nop; - mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop; + + if (info->sideband_wake) { + mhi_cntrl->wake_get = mhi_pci_wake_get_nop; + mhi_cntrl->wake_put = mhi_pci_wake_put_nop; + mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop; + } err = mhi_pci_claim(mhi_cntrl, info->bar_num, DMA_BIT_MASK(info->dma_data_width)); if (err) From 546362a9ef2ef40b57c6605f14e88ced507f8dd0 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Fri, 16 Jul 2021 13:21:05 +0530 Subject: [PATCH 0702/1469] bus: mhi: core: Validate channel ID when processing command completions MHI reads the channel ID from the event ring element sent by the device which can be any value between 0 and 255. In order to prevent any out of bound accesses, add a check against the maximum number of channels supported by the controller and those channels not configured yet so as to skip processing of that event ring element. Link: https://lore.kernel.org/r/1624558141-11045-1-git-send-email-bbhatt@codeaurora.org Fixes: 1d3173a3bae7 ("bus: mhi: core: Add support for processing events from client device") Cc: stable@vger.kernel.org #5.10 Reviewed-by: Hemant Kumar Reviewed-by: Manivannan Sadhasivam Reviewed-by: Jeffrey Hugo Signed-off-by: Bhaumik Bhatt Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210716075106.49938-3-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/core/main.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index 22acde118bc3..fc9196f11cb7 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -773,11 +773,18 @@ static void mhi_process_cmd_completion(struct mhi_controller *mhi_cntrl, cmd_pkt = mhi_to_virtual(mhi_ring, ptr); chan = MHI_TRE_GET_CMD_CHID(cmd_pkt); - mhi_chan = &mhi_cntrl->mhi_chan[chan]; - write_lock_bh(&mhi_chan->lock); - mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre); - complete(&mhi_chan->completion); - write_unlock_bh(&mhi_chan->lock); + + if (chan < mhi_cntrl->max_chan && + mhi_cntrl->mhi_chan[chan].configured) { + mhi_chan = &mhi_cntrl->mhi_chan[chan]; + write_lock_bh(&mhi_chan->lock); + mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre); + complete(&mhi_chan->completion); + write_unlock_bh(&mhi_chan->lock); + } else { + dev_err(&mhi_cntrl->mhi_dev->dev, + "Completion packet for invalid channel ID: %d\n", chan); + } mhi_del_ring_element(mhi_cntrl, mhi_ring); } From b8a97f2a65388394f433bf0730293a94f7d49046 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Fri, 16 Jul 2021 13:21:06 +0530 Subject: [PATCH 0703/1469] bus: mhi: pci_generic: Fix inbound IPCR channel The qrtr-mhi client driver assumes that inbound buffers are automatically allocated and queued by the MHI core, but this doesn't happen for mhi pci devices since IPCR inbound channel is not flagged with auto_queue, causing unusable IPCR (qrtr) feature. Fix that. Link: https://lore.kernel.org/r/1625736749-24947-1-git-send-email-loic.poulain@linaro.org [mani: fixed a spelling mistake in commit description] Fixes: 855a70c12021 ("bus: mhi: Add MHI PCI support for WWAN modems") Cc: stable@vger.kernel.org #5.10 Reviewed-by: Hemant kumar Reviewed-by: Manivannan Sadhasivam Signed-off-by: Loic Poulain Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210716075106.49938-4-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/pci_generic.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c index 3396cb30ebec..4dd1077354af 100644 --- a/drivers/bus/mhi/pci_generic.c +++ b/drivers/bus/mhi/pci_generic.c @@ -75,6 +75,22 @@ struct mhi_pci_dev_info { .doorbell_mode_switch = false, \ } +#define MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(ch_num, ch_name, el_count, ev_ring) \ + { \ + .num = ch_num, \ + .name = ch_name, \ + .num_elements = el_count, \ + .event_ring = ev_ring, \ + .dir = DMA_FROM_DEVICE, \ + .ee_mask = BIT(MHI_EE_AMSS), \ + .pollcfg = 0, \ + .doorbell = MHI_DB_BRST_DISABLE, \ + .lpm_notify = false, \ + .offload_channel = false, \ + .doorbell_mode_switch = false, \ + .auto_queue = true, \ + } + #define MHI_EVENT_CONFIG_CTRL(ev_ring, el_count) \ { \ .num_elements = el_count, \ @@ -213,7 +229,7 @@ static const struct mhi_channel_config modem_qcom_v1_mhi_channels[] = { MHI_CHANNEL_CONFIG_UL(14, "QMI", 4, 0), MHI_CHANNEL_CONFIG_DL(15, "QMI", 4, 0), MHI_CHANNEL_CONFIG_UL(20, "IPCR", 8, 0), - MHI_CHANNEL_CONFIG_DL(21, "IPCR", 8, 0), + MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(21, "IPCR", 8, 0), MHI_CHANNEL_CONFIG_UL_FP(34, "FIREHOSE", 32, 0), MHI_CHANNEL_CONFIG_DL_FP(35, "FIREHOSE", 32, 0), MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0", 128, 2), From e703eaff5089da93fd379678f0371f52497042ba Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Wed, 21 Jul 2021 03:02:46 -0700 Subject: [PATCH 0704/1469] MAINTAINERS: Update for VMCI driver Add maintainer info for the VMware VMCI driver. v2: moved pv-drivers to L: as private list Acked-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/1626861766-11115-1-git-send-email-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6c8be735cc91..61ff28cfdcde 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19800,6 +19800,14 @@ L: netdev@vger.kernel.org S: Supported F: drivers/ptp/ptp_vmw.c +VMWARE VMCI DRIVER +M: Jorgen Hansen +M: Vishnu Dasa +L: linux-kernel@vger.kernel.org +L: pv-drivers@vmware.com (private) +S: Maintained +F: drivers/misc/vmw_vmci/ + VMWARE VMMOUSE SUBDRIVER M: "VMware Graphics" M: "VMware, Inc." From ebea6761b620d758ed77d2df70fab1ae7a363151 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Wed, 14 Jul 2021 16:26:14 +0800 Subject: [PATCH 0705/1469] MAINTAINERS: Change ACRN HSM driver maintainer Shuo steps down, Fei will take over. Acked-by: Fei Li Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210714082614.88560-1-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 61ff28cfdcde..99316c4370a9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -445,7 +445,7 @@ F: drivers/platform/x86/wmi.c F: include/uapi/linux/wmi.h ACRN HYPERVISOR SERVICE MODULE -M: Shuo Liu +M: Fei Li L: acrn-dev@lists.projectacrn.org (subscribers-only) S: Supported W: https://projectacrn.org From c453db6cd96418c79702eaf38259002755ab23ff Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 29 Jun 2021 12:40:24 +0200 Subject: [PATCH 0706/1469] nds32: fix up stack guard gap Commit 1be7107fbe18 ("mm: larger stack guard gap, between vmas") fixed up all architectures to deal with the stack guard gap. But when nds32 was added to the tree, it forgot to do the same thing. Resolve this by properly fixing up the nsd32's version of arch_get_unmapped_area() Cc: Nick Hu Cc: Greentime Hu Cc: Vincent Chen Cc: Michal Hocko Cc: Hugh Dickins Cc: Qiang Liu Cc: stable Reported-by: iLifetruth Acked-by: Hugh Dickins Link: https://lore.kernel.org/r/20210629104024.2293615-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/nds32/mm/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/nds32/mm/mmap.c b/arch/nds32/mm/mmap.c index c206b31ce07a..1bdf5e7d1b43 100644 --- a/arch/nds32/mm/mmap.c +++ b/arch/nds32/mm/mmap.c @@ -59,7 +59,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } From 6c881ca0b3040f3e724eae513117ba4ddef86057 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 15 Jun 2021 11:57:26 +0100 Subject: [PATCH 0707/1469] afs: Fix tracepoint string placement with built-in AFS To quote Alexey[1]: I was adding custom tracepoint to the kernel, grabbed full F34 kernel .config, disabled modules and booted whole shebang as VM kernel. Then did perf record -a -e ... It crashed: general protection fault, probably for non-canonical address 0x435f5346592e4243: 0000 [#1] SMP PTI CPU: 1 PID: 842 Comm: cat Not tainted 5.12.6+ #26 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 RIP: 0010:t_show+0x22/0xd0 Then reproducer was narrowed to # cat /sys/kernel/tracing/printk_formats Original F34 kernel with modules didn't crash. So I started to disable options and after disabling AFS everything started working again. The root cause is that AFS was placing char arrays content into a section full of _pointers_ to strings with predictable consequences. Non canonical address 435f5346592e4243 is "CB.YFS_" which came from CM_NAME macro. Steps to reproduce: CONFIG_AFS=y CONFIG_TRACING=y # cat /sys/kernel/tracing/printk_formats Fix this by the following means: (1) Add enum->string translation tables in the event header with the AFS and YFS cache/callback manager operations listed by RPC operation ID. (2) Modify the afs_cb_call tracepoint to print the string from the translation table rather than using the string at the afs_call name pointer. (3) Switch translation table depending on the service we're being accessed as (AFS or YFS) in the tracepoint print clause. Will this cause problems to userspace utilities? Note that the symbolic representation of the YFS service ID isn't available to this header, so I've put it in as a number. I'm not sure if this is the best way to do this. (4) Remove the name wrangling (CM_NAME) macro and put the names directly into the afs_call_type structs in cmservice.c. Fixes: 8e8d7f13b6d5a9 ("afs: Add some tracepoints") Reported-by: Alexey Dobriyan (SK hynix) Signed-off-by: David Howells Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Marc Dionne cc: Andrew Morton cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/YLAXfvZ+rObEOdc%2F@localhost.localdomain/ [1] Link: https://lore.kernel.org/r/643721.1623754699@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162430903582.2896199.6098150063997983353.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/162609463957.3133237.15916579353149746363.stgit@warthog.procyon.org.uk/ # v1 (repost) Link: https://lore.kernel.org/r/162610726860.3408253.445207609466288531.stgit@warthog.procyon.org.uk/ # v2 --- fs/afs/cmservice.c | 25 ++++---------- include/trace/events/afs.h | 67 +++++++++++++++++++++++++++++++++++--- 2 files changed, 69 insertions(+), 23 deletions(-) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index d3c6bb22c5f4..a3f5de28be79 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -29,16 +29,11 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); static int afs_deliver_yfs_cb_callback(struct afs_call *); -#define CM_NAME(name) \ - char afs_SRXCB##name##_name[] __tracepoint_string = \ - "CB." #name - /* * CB.CallBack operation type */ -static CM_NAME(CallBack); static const struct afs_call_type afs_SRXCBCallBack = { - .name = afs_SRXCBCallBack_name, + .name = "CB.CallBack", .deliver = afs_deliver_cb_callback, .destructor = afs_cm_destructor, .work = SRXAFSCB_CallBack, @@ -47,9 +42,8 @@ static const struct afs_call_type afs_SRXCBCallBack = { /* * CB.InitCallBackState operation type */ -static CM_NAME(InitCallBackState); static const struct afs_call_type afs_SRXCBInitCallBackState = { - .name = afs_SRXCBInitCallBackState_name, + .name = "CB.InitCallBackState", .deliver = afs_deliver_cb_init_call_back_state, .destructor = afs_cm_destructor, .work = SRXAFSCB_InitCallBackState, @@ -58,9 +52,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState = { /* * CB.InitCallBackState3 operation type */ -static CM_NAME(InitCallBackState3); static const struct afs_call_type afs_SRXCBInitCallBackState3 = { - .name = afs_SRXCBInitCallBackState3_name, + .name = "CB.InitCallBackState3", .deliver = afs_deliver_cb_init_call_back_state3, .destructor = afs_cm_destructor, .work = SRXAFSCB_InitCallBackState, @@ -69,9 +62,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState3 = { /* * CB.Probe operation type */ -static CM_NAME(Probe); static const struct afs_call_type afs_SRXCBProbe = { - .name = afs_SRXCBProbe_name, + .name = "CB.Probe", .deliver = afs_deliver_cb_probe, .destructor = afs_cm_destructor, .work = SRXAFSCB_Probe, @@ -80,9 +72,8 @@ static const struct afs_call_type afs_SRXCBProbe = { /* * CB.ProbeUuid operation type */ -static CM_NAME(ProbeUuid); static const struct afs_call_type afs_SRXCBProbeUuid = { - .name = afs_SRXCBProbeUuid_name, + .name = "CB.ProbeUuid", .deliver = afs_deliver_cb_probe_uuid, .destructor = afs_cm_destructor, .work = SRXAFSCB_ProbeUuid, @@ -91,9 +82,8 @@ static const struct afs_call_type afs_SRXCBProbeUuid = { /* * CB.TellMeAboutYourself operation type */ -static CM_NAME(TellMeAboutYourself); static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { - .name = afs_SRXCBTellMeAboutYourself_name, + .name = "CB.TellMeAboutYourself", .deliver = afs_deliver_cb_tell_me_about_yourself, .destructor = afs_cm_destructor, .work = SRXAFSCB_TellMeAboutYourself, @@ -102,9 +92,8 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { /* * YFS CB.CallBack operation type */ -static CM_NAME(YFS_CallBack); static const struct afs_call_type afs_SRXYFSCB_CallBack = { - .name = afs_SRXCBYFS_CallBack_name, + .name = "YFSCB.CallBack", .deliver = afs_deliver_yfs_cb_callback, .destructor = afs_cm_destructor, .work = SRXAFSCB_CallBack, diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 3ccf591b2374..9f73ed2cf061 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -174,6 +174,34 @@ enum afs_vl_operation { afs_VL_GetCapabilities = 65537, /* AFS Get VL server capabilities */ }; +enum afs_cm_operation { + afs_CB_CallBack = 204, /* AFS break callback promises */ + afs_CB_InitCallBackState = 205, /* AFS initialise callback state */ + afs_CB_Probe = 206, /* AFS probe client */ + afs_CB_GetLock = 207, /* AFS get contents of CM lock table */ + afs_CB_GetCE = 208, /* AFS get cache file description */ + afs_CB_GetXStatsVersion = 209, /* AFS get version of extended statistics */ + afs_CB_GetXStats = 210, /* AFS get contents of extended statistics data */ + afs_CB_InitCallBackState3 = 213, /* AFS initialise callback state, version 3 */ + afs_CB_ProbeUuid = 214, /* AFS check the client hasn't rebooted */ +}; + +enum yfs_cm_operation { + yfs_CB_Probe = 206, /* YFS probe client */ + yfs_CB_GetLock = 207, /* YFS get contents of CM lock table */ + yfs_CB_XStatsVersion = 209, /* YFS get version of extended statistics */ + yfs_CB_GetXStats = 210, /* YFS get contents of extended statistics data */ + yfs_CB_InitCallBackState3 = 213, /* YFS initialise callback state, version 3 */ + yfs_CB_ProbeUuid = 214, /* YFS check the client hasn't rebooted */ + yfs_CB_GetServerPrefs = 215, + yfs_CB_GetCellServDV = 216, + yfs_CB_GetLocalCell = 217, + yfs_CB_GetCacheConfig = 218, + yfs_CB_GetCellByNum = 65537, + yfs_CB_TellMeAboutYourself = 65538, /* get client capabilities */ + yfs_CB_CallBack = 64204, +}; + enum afs_edit_dir_op { afs_edit_dir_create, afs_edit_dir_create_error, @@ -436,6 +464,32 @@ enum afs_cb_break_reason { EM(afs_YFSVL_GetCellName, "YFSVL.GetCellName") \ E_(afs_VL_GetCapabilities, "VL.GetCapabilities") +#define afs_cm_operations \ + EM(afs_CB_CallBack, "CB.CallBack") \ + EM(afs_CB_InitCallBackState, "CB.InitCallBackState") \ + EM(afs_CB_Probe, "CB.Probe") \ + EM(afs_CB_GetLock, "CB.GetLock") \ + EM(afs_CB_GetCE, "CB.GetCE") \ + EM(afs_CB_GetXStatsVersion, "CB.GetXStatsVersion") \ + EM(afs_CB_GetXStats, "CB.GetXStats") \ + EM(afs_CB_InitCallBackState3, "CB.InitCallBackState3") \ + E_(afs_CB_ProbeUuid, "CB.ProbeUuid") + +#define yfs_cm_operations \ + EM(yfs_CB_Probe, "YFSCB.Probe") \ + EM(yfs_CB_GetLock, "YFSCB.GetLock") \ + EM(yfs_CB_XStatsVersion, "YFSCB.XStatsVersion") \ + EM(yfs_CB_GetXStats, "YFSCB.GetXStats") \ + EM(yfs_CB_InitCallBackState3, "YFSCB.InitCallBackState3") \ + EM(yfs_CB_ProbeUuid, "YFSCB.ProbeUuid") \ + EM(yfs_CB_GetServerPrefs, "YFSCB.GetServerPrefs") \ + EM(yfs_CB_GetCellServDV, "YFSCB.GetCellServDV") \ + EM(yfs_CB_GetLocalCell, "YFSCB.GetLocalCell") \ + EM(yfs_CB_GetCacheConfig, "YFSCB.GetCacheConfig") \ + EM(yfs_CB_GetCellByNum, "YFSCB.GetCellByNum") \ + EM(yfs_CB_TellMeAboutYourself, "YFSCB.TellMeAboutYourself") \ + E_(yfs_CB_CallBack, "YFSCB.CallBack") + #define afs_edit_dir_ops \ EM(afs_edit_dir_create, "create") \ EM(afs_edit_dir_create_error, "c_fail") \ @@ -569,6 +623,8 @@ afs_server_traces; afs_cell_traces; afs_fs_operations; afs_vl_operations; +afs_cm_operations; +yfs_cm_operations; afs_edit_dir_ops; afs_edit_dir_reasons; afs_eproto_causes; @@ -649,20 +705,21 @@ TRACE_EVENT(afs_cb_call, TP_STRUCT__entry( __field(unsigned int, call ) - __field(const char *, name ) __field(u32, op ) + __field(u16, service_id ) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->name = call->type->name; __entry->op = call->operation_ID; + __entry->service_id = call->service_id; ), - TP_printk("c=%08x %s o=%u", + TP_printk("c=%08x %s", __entry->call, - __entry->name, - __entry->op) + __entry->service_id == 2501 ? + __print_symbolic(__entry->op, yfs_cm_operations) : + __print_symbolic(__entry->op, afs_cm_operations)) ); TRACE_EVENT(afs_call, From afe6949862f77bcc14fa16ad7938a04e84586d6a Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 30 Apr 2021 08:50:31 -0700 Subject: [PATCH 0708/1469] afs: check function return Static analysis reports this problem write.c:773:29: warning: Assigned value is garbage or undefined mapping->writeback_index = next; ^ ~~~~ The call to afs_writepages_region() can return without setting next. So check the function return before using next. Changes: ver #2: - Need to fix the range_cyclic case also[1]. Fixes: e87b03f5830e ("afs: Prepare for use of THPs") Signed-off-by: Tom Rix Signed-off-by: David Howells Reviewed-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/20210430155031.3287870-1-trix@redhat.com Link: https://lore.kernel.org/r/CAB9dFdvHsLsw7CMnB+4cgciWDSqVjuij4mH3TaXnHQB8sz5rHw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/162609464716.3133237.10354897554363093252.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/162610727640.3408253.8687445613469681311.stgit@warthog.procyon.org.uk/ # v2 --- fs/afs/write.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index 3104b62c2082..1ed62e0ccfe5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -771,13 +771,19 @@ int afs_writepages(struct address_space *mapping, if (wbc->range_cyclic) { start = mapping->writeback_index * PAGE_SIZE; ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX, &next); - if (start > 0 && wbc->nr_to_write > 0 && ret == 0) - ret = afs_writepages_region(mapping, wbc, 0, start, - &next); - mapping->writeback_index = next / PAGE_SIZE; + if (ret == 0) { + mapping->writeback_index = next / PAGE_SIZE; + if (start > 0 && wbc->nr_to_write > 0) { + ret = afs_writepages_region(mapping, wbc, 0, + start, &next); + if (ret == 0) + mapping->writeback_index = + next / PAGE_SIZE; + } + } } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); - if (wbc->nr_to_write > 0) + if (wbc->nr_to_write > 0 && ret == 0) mapping->writeback_index = next; } else { ret = afs_writepages_region(mapping, wbc, From 5a972474cf685bf99ca430979657095bda3a15c8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 12 Jul 2021 17:04:47 +0100 Subject: [PATCH 0709/1469] afs: Fix setting of writeback_index Fix afs_writepages() to always set mapping->writeback_index to a page index and not a byte position[1]. Fixes: 31143d5d515e ("AFS: implement basic file write support") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/CAB9dFdvHsLsw7CMnB+4cgciWDSqVjuij4mH3TaXnHQB8sz5rHw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/162610728339.3408253.4604750166391496546.stgit@warthog.procyon.org.uk/ # v2 (no v1) --- fs/afs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index 1ed62e0ccfe5..c0534697268e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -784,7 +784,7 @@ int afs_writepages(struct address_space *mapping, } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next; + mapping->writeback_index = next / PAGE_SIZE; } else { ret = afs_writepages_region(mapping, wbc, wbc->range_start, wbc->range_end, &next); From b428081282f85db8a0d4ae6206a8c39db9c8341b Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Thu, 29 Apr 2021 18:18:12 +0800 Subject: [PATCH 0710/1469] afs: Remove redundant assignment to ret Variable ret is set to -ENOENT and -ENOMEM but this value is never read as it is overwritten or not used later on, hence it is a redundant assignment and can be removed. Cleans up the following clang-analyzer warning: fs/afs/dir.c:2014:4: warning: Value stored to 'ret' is never read [clang-analyzer-deadcode.DeadStores]. fs/afs/dir.c:659:2: warning: Value stored to 'ret' is never read [clang-analyzer-deadcode.DeadStores]. [DH made the following modifications: - In afs_rename(), -ENOMEM should be placed in op->error instead of ret, rather than the assignment being removed entirely. afs_put_operation() will pick it up from there and return it. - If afs_sillyrename() fails, its error code should be placed in op->error rather than in ret also. ] Fixes: e49c7b2f6de7 ("afs: Build an abstraction around an "operation" concept") Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: David Howells Reviewed-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/1619691492-83866-1-git-send-email-jiapeng.chong@linux.alibaba.com Link: https://lore.kernel.org/r/162609465444.3133237.7562832521724298900.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/162610729052.3408253.17364333638838151299.stgit@warthog.procyon.org.uk/ # v2 --- fs/afs/dir.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 78719f2f567e..ac829e63c570 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -656,7 +656,6 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, return ret; } - ret = -ENOENT; if (!cookie.found) { _leave(" = -ENOENT [not found]"); return -ENOENT; @@ -2020,17 +2019,20 @@ static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, if (d_count(new_dentry) > 2) { /* copy the target dentry's name */ - ret = -ENOMEM; op->rename.tmp = d_alloc(new_dentry->d_parent, &new_dentry->d_name); - if (!op->rename.tmp) + if (!op->rename.tmp) { + op->error = -ENOMEM; goto error; + } ret = afs_sillyrename(new_dvnode, AFS_FS_I(d_inode(new_dentry)), new_dentry, op->key); - if (ret) + if (ret) { + op->error = ret; goto error; + } op->dentry_2 = op->rename.tmp; op->rename.rehash = NULL; From 4afa0c22eed33cfe0c590742387f0d16f32412f3 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 13 Jul 2021 12:34:38 +0300 Subject: [PATCH 0711/1469] driver core: auxiliary bus: Fix memory leak when driver_register() fail If driver_register() returns with error we need to free the memory allocated for auxdrv->driver.name before returning from __auxiliary_driver_register() Fixes: 7de3697e9cbd4 ("Add auxiliary bus support") Reviewed-by: Dan Williams Cc: stable Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210713093438.3173-1-peter.ujfalusi@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/auxiliary.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index adc199dfba3c..6a30264ab2ba 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -231,6 +231,8 @@ EXPORT_SYMBOL_GPL(auxiliary_find_device); int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner, const char *modname) { + int ret; + if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table)) return -EINVAL; @@ -246,7 +248,11 @@ int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, auxdrv->driver.bus = &auxiliary_bus_type; auxdrv->driver.mod_name = modname; - return driver_register(&auxdrv->driver); + ret = driver_register(&auxdrv->driver); + if (ret) + kfree(auxdrv->driver.name); + + return ret; } EXPORT_SYMBOL_GPL(__auxiliary_driver_register); From e9a72f874d5b95cef0765bafc56005a50f72c5fe Mon Sep 17 00:00:00 2001 From: Sayanta Pattanayak Date: Tue, 20 Jul 2021 17:17:40 +0100 Subject: [PATCH 0712/1469] r8169: Avoid duplicate sysfs entry creation error When registering the MDIO bus for a r8169 device, we use the PCI bus/device specifier as a (seemingly) unique device identifier. However the very same BDF number can be used on another PCI segment, which makes the driver fail probing: [ 27.544136] r8169 0002:07:00.0: enabling device (0000 -> 0003) [ 27.559734] sysfs: cannot create duplicate filename '/class/mdio_bus/r8169-700' .... [ 27.684858] libphy: mii_bus r8169-700 failed to register [ 27.695602] r8169: probe of 0002:07:00.0 failed with error -22 Add the segment number to the device name to make it more unique. This fixes operation on ARM N1SDP boards, with two boards connected together to form an SMP system, and all on-board devices showing up twice, just on different PCI segments. A similar issue would occur on large systems with many PCI slots and multiple RTL8169 NICs. Fixes: f1e911d5d0dfd ("r8169: add basic phylib support") Signed-off-by: Sayanta Pattanayak [Andre: expand commit message, use pci_domain_nr()] Signed-off-by: Andre Przywara Acked-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index f744557c33a3..c7af5bc3b8af 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5084,7 +5084,8 @@ static int r8169_mdio_register(struct rtl8169_private *tp) new_bus->priv = tp; new_bus->parent = &pdev->dev; new_bus->irq[0] = PHY_MAC_INTERRUPT; - snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x", pci_dev_id(pdev)); + snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x", + pci_domain_nr(pdev->bus), pci_dev_id(pdev)); new_bus->read = r8169_mdio_read_reg; new_bus->write = r8169_mdio_write_reg; From 0077a50082729c3f9ea2836f59e35d9b7dacfb12 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 21 Jul 2021 12:16:26 +0200 Subject: [PATCH 0713/1469] rbd: resurrect setting of disk->private_data in rbd_init_disk() rbd_open() and rbd_release() expect that disk->private_data is set to rbd_dev. Otherwise we hit a NULL pointer dereference when mapping the image. URL: https://tracker.ceph.com/issues/51759 Fixes: 195b1956b85b ("rbd: use blk_mq_alloc_disk and blk_cleanup_disk") Signed-off-by: Ilya Dryomov Reviewed-by: Christoph Hellwig --- drivers/block/rbd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 784797fa9a53..90b947c96402 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4943,6 +4943,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) disk->minors = RBD_MINORS_PER_MAJOR; } disk->fops = &rbd_bd_ops; + disk->private_data = rbd_dev; blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ From aaeb7bb061be545251606f4d9c82d710ca2a7c8e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jul 2021 10:00:11 +0200 Subject: [PATCH 0714/1469] nvme: set the PRACT bit when using Write Zeroes with T10 PI When using Write Zeroes on a namespace that has protection information enabled they behavior without the PRACT bit counter-intuitive and will generally lead to validation failures when reading the written blocks. Fix this by always setting the PRACT bit that generates matching PI data on the fly. Fixes: 6e02318eaea5 ("nvme: add support for the Write Zeroes command") Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Martin K. Petersen --- drivers/nvme/host/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 17c05a4595f0..dfd9dec0c1f6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -900,7 +900,10 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); - cmnd->write_zeroes.control = 0; + if (nvme_ns_has_pi(ns)) + cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT); + else + cmnd->write_zeroes.control = 0; return BLK_STS_OK; } From e64daad660a0c9ace3acdc57099fffe5ed83f977 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 16 Jul 2021 14:44:07 +0300 Subject: [PATCH 0715/1469] driver core: Prevent warning when removing a device link from unregistered consumer sysfs_remove_link() causes a warning if the parent directory does not exist. That can happen if the device link consumer has not been registered. So do not attempt sysfs_remove_link() in that case. Fixes: 287905e68dd29 ("driver core: Expose device link details in sysfs") Signed-off-by: Adrian Hunter Cc: stable@vger.kernel.org # 5.9+ Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20210716114408.17320-2-adrian.hunter@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index cadcade65825..f6360490a4a3 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -574,8 +574,10 @@ static void devlink_remove_symlinks(struct device *dev, return; } - snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); - sysfs_remove_link(&con->kobj, buf); + if (device_is_registered(con)) { + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); + sysfs_remove_link(&con->kobj, buf); + } snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); From cb7abd1db6e5f99a05f1a00b65be29029a6a152a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:35:44 +0200 Subject: [PATCH 0716/1469] staging: rtl8723bs: select CONFIG_CRYPTO_LIB_ARC4 The other rtlwifi drivers already have this, but r8723bs was converted to the generic implementation without adding the select: ERROR: modpost: "arc4_crypt" [drivers/staging/rtl8723bs/r8723bs.ko] undefined! ERROR: modpost: "arc4_setkey" [drivers/staging/rtl8723bs/r8723bs.ko] undefined! Fixes: 1b11e893eda0 ("staging: rtl8723bs: replace private arc4 encryption with in-kernel one") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210721153550.3624490-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/rtl8723bs/Kconfig b/drivers/staging/rtl8723bs/Kconfig index a88467334dac..7eae820eae3b 100644 --- a/drivers/staging/rtl8723bs/Kconfig +++ b/drivers/staging/rtl8723bs/Kconfig @@ -5,6 +5,7 @@ config RTL8723BS depends on m select WIRELESS_EXT select WEXT_PRIV + select CRYPTO_LIB_ARC4 help This option enables support for RTL8723BS SDIO drivers, such as the wifi found on the 1st gen Intel Compute Stick, the CHIP From 58acd10092268831e49de279446c314727101292 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 20 Jul 2021 16:07:01 -0400 Subject: [PATCH 0717/1469] sctp: update active_key for asoc when old key is being replaced syzbot reported a call trace: BUG: KASAN: use-after-free in sctp_auth_shkey_hold+0x22/0xa0 net/sctp/auth.c:112 Call Trace: sctp_auth_shkey_hold+0x22/0xa0 net/sctp/auth.c:112 sctp_set_owner_w net/sctp/socket.c:131 [inline] sctp_sendmsg_to_asoc+0x152e/0x2180 net/sctp/socket.c:1865 sctp_sendmsg+0x103b/0x1d30 net/sctp/socket.c:2027 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:821 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:723 This is an use-after-free issue caused by not updating asoc->shkey after it was replaced in the key list asoc->endpoint_shared_keys, and the old key was freed. This patch is to fix by also updating active_key for asoc when old key is being replaced with a new one. Note that this issue doesn't exist in sctp_auth_del_key_id(), as it's not allowed to delete the active_key from the asoc. Fixes: 1b1e0bc99474 ("sctp: add refcnt support for sh_key") Reported-by: syzbot+b774577370208727d12b@syzkaller.appspotmail.com Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/auth.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 6f8319b828b0..fe74c5f95630 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -860,6 +860,8 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, if (replace) { list_del_init(&shkey->key_list); sctp_auth_shkey_release(shkey); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber) + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); } list_add(&cur_key->key_list, sh_keys); From 9bfce73c8921c92a9565562e6e7d458d37b7ce80 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Tue, 20 Jul 2021 23:35:28 +0300 Subject: [PATCH 0718/1469] udp: check encap socket in __udp_lib_err Commit d26796ae5894 ("udp: check udp sock encap_type in __udp_lib_err") added checks for encapsulated sockets but it broke cases when there is no implementation of encap_err_lookup for encapsulation, i.e. ESP in UDP encapsulation. Fix it by calling encap_err_lookup only if socket implements this method otherwise treat it as legal socket. Fixes: d26796ae5894 ("udp: check udp sock encap_type in __udp_lib_err") Signed-off-by: Vadim Fedorenko Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/udp.c | 25 +++++++++++++++++++------ net/ipv6/udp.c | 25 +++++++++++++++++++------ 2 files changed, 38 insertions(+), 12 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62cd4cd52e84..1a742b710e54 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, u32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); @@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { - sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb, + sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0cc7ba531b34..c5e15e94bb00 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); @@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, - udptable, skb, + udptable, sk, skb, opt, type, code, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), From 6e0b6528d783b2b87bd9e1bea97cf4dac87540d7 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Tue, 20 Jul 2021 13:21:08 -0500 Subject: [PATCH 0719/1469] drm/i915: Correct the docs for intel_engine_cmd_parser In 93b713304188 ("drm/i915: Revert "drm/i915/gem: Asynchronous cmdparser""), the parameters to intel_engine_cmd_parser() were altered without updating the docs, causing Fi.CI.DOCS to start failing. Fixes: c9d9fdbc108a ("drm/i915: Revert "drm/i915/gem: Asynchronous cmdparser"") Signed-off-by: Jason Ekstrand Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210720182108.2761496-1-jason@jlekstrand.net Signed-off-by: Rodrigo Vivi [Added 'Fixes:' tag and corrected the hash for the ancestor] (cherry picked from commit 15eb083bdb561bb4862cd04cd0523e55483e877e) Signed-off-by: Rodrigo Vivi [Updated Fixes tag to match fixes branch] --- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 00ec618d0159..a3b4d99d64b9 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1416,9 +1416,7 @@ static unsigned long *alloc_whitelist(u32 batch_length) * @batch_offset: byte offset in the batch at which execution starts * @batch_length: length of the commands in batch_obj * @shadow: validated copy of the batch buffer in question - * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist() - * @shadow_map: mapping to @shadow vma - * @batch_map: mapping to @batch vma + * @trampoline: true if we need to trampoline into privileged execution * * Parses the specified batch buffer looking for privilege violations as * described in the overview. From ece1278a9b81bdfc088f087f8372a072b7010956 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Tue, 20 Jul 2021 23:35:29 +0300 Subject: [PATCH 0720/1469] selftests: net: add ESP-in-UDP PMTU test The case of ESP in UDP encapsulation was not covered before. Add cases of local changes of MTU and difference on routed path. Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- tools/testing/selftests/net/nettest.c | 55 ++++++- tools/testing/selftests/net/pmtu.sh | 212 +++++++++++++++++++++++++- 2 files changed, 260 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index 6365c7fd1262..bd6288302094 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -11,9 +11,11 @@ #include #include #include +#include #include #include #include +#include #include #include #include @@ -27,6 +29,10 @@ #include #include +#include +#include +#include + #ifndef IPV6_UNICAST_IF #define IPV6_UNICAST_IF 76 #endif @@ -114,6 +120,9 @@ struct sock_args { struct in_addr in; struct in6_addr in6; } expected_raddr; + + /* ESP in UDP encap test */ + int use_xfrm; }; static int server_mode; @@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args) return 0; } +static int config_xfrm_policy(int sd, struct sock_args *args) +{ + struct xfrm_userpolicy_info policy = {}; + int type = UDP_ENCAP_ESPINUDP; + int xfrm_af = IP_XFRM_POLICY; + int level = SOL_IP; + + if (args->type != SOCK_DGRAM) { + log_error("Invalid socket type. Only DGRAM could be used for XFRM\n"); + return 1; + } + + policy.action = XFRM_POLICY_ALLOW; + policy.sel.family = args->version; + if (args->version == AF_INET6) { + xfrm_af = IPV6_XFRM_POLICY; + level = SOL_IPV6; + } + + policy.dir = XFRM_POLICY_OUT; + if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0) + return 1; + + policy.dir = XFRM_POLICY_IN; + if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0) + return 1; + + if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) { + log_err_errno("Failed to set xfrm encap"); + return 1; + } + + return 0; +} + static int lsock_init(struct sock_args *args) { long flags; @@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args) if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0) log_err_errno("Failed to set close-on-exec flag"); + if (args->use_xfrm && config_xfrm_policy(sd, args)) { + log_err_errno("Failed to set xfrm policy"); + goto err; + } + out: return sd; @@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) return client_status; } -#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq" +#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" static void print_usage(char *prog) { @@ -1795,6 +1844,7 @@ static void print_usage(char *prog) " -D|R datagram (D) / raw (R) socket (default stream)\n" " -l addr local address to bind to in server mode\n" " -c addr local address to bind to in client mode\n" + " -x configure XFRM policy on socket\n" "\n" " -d dev bind socket to given device name\n" " -I dev bind socket to given device name - server mode\n" @@ -1966,6 +2016,9 @@ int main(int argc, char *argv[]) case 'q': quiet = 1; break; + case 'x': + args.use_xfrm = 1; + break; default: print_usage(argv[0]); return 1; diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 64cd2e23c568..543ad7513a8e 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -118,6 +118,16 @@ # below for IPv6 doesn't apply here, because, on IPv4, administrative MTU # changes alone won't affect PMTU # +# - pmtu_vti4_udp_exception +# Same as pmtu_vti4_exception, but using ESP-in-UDP +# +# - pmtu_vti4_udp_routed_exception +# Set up vti tunnel on top of veth connected through routing namespace and +# add xfrm states and policies with ESP-in-UDP encapsulation. Check that +# route exception is not created if link layer MTU is not exceeded, then +# lower MTU on second part of routed environment and check that exception +# is created with the expected PMTU. +# # - pmtu_vti6_exception # Set up vti6 tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is @@ -125,6 +135,13 @@ # decrease and increase MTU of tunnel, checking that route exception PMTU # changes accordingly # +# - pmtu_vti6_udp_exception +# Same as pmtu_vti6_exception, but using ESP-in-UDP +# +# - pmtu_vti6_udp_routed_exception +# Same as pmtu_vti6_udp_routed_exception but with routing between vti +# endpoints +# # - pmtu_vti4_default_mtu # Set up vti4 tunnel on top of veth, in two namespaces with matching # endpoints. Check that MTU assigned to vti interface is the MTU of the @@ -224,6 +241,10 @@ tests=" pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1 pmtu_vti6_exception vti6: PMTU exceptions 0 pmtu_vti4_exception vti4: PMTU exceptions 0 + pmtu_vti6_udp_exception vti6: PMTU exceptions (ESP-in-UDP) 0 + pmtu_vti4_udp_exception vti4: PMTU exceptions (ESP-in-UDP) 0 + pmtu_vti6_udp_routed_exception vti6: PMTU exceptions, routed (ESP-in-UDP) 0 + pmtu_vti4_udp_routed_exception vti4: PMTU exceptions, routed (ESP-in-UDP) 0 pmtu_vti4_default_mtu vti4: default MTU assignment 0 pmtu_vti6_default_mtu vti6: default MTU assignment 0 pmtu_vti4_link_add_mtu vti4: MTU setting on link creation 0 @@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}" ns_c="ip netns exec ${NS_C}" ns_r1="ip netns exec ${NS_R1}" ns_r2="ip netns exec ${NS_R2}" - # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an # identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2). @@ -279,7 +299,6 @@ routes=" A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2 B default ${prefix6}:${b_r1}::2 " - USE_NH="no" # ns family nh id destination gateway nexthops=" @@ -326,6 +345,7 @@ dummy6_mask="64" err_buf= tcpdump_pids= +nettest_pids= err() { err_buf="${err_buf}${1} @@ -548,6 +568,14 @@ setup_vti6() { setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask} } +setup_vti4routed() { + setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask} +} + +setup_vti6routed() { + setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask} +} + setup_vxlan_or_geneve() { type="${1}" a_addr="${2}" @@ -619,18 +647,36 @@ setup_xfrm() { proto=${1} veth_a_addr="${2}" veth_b_addr="${3}" + encap=${4} - run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1 - run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel + run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1 + run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel - run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel - run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel + run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} + run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel } +setup_nettest_xfrm() { + which nettest >/dev/null + if [ $? -ne 0 ]; then + echo "'nettest' command not found; skipping tests" + return 1 + fi + + [ ${1} -eq 6 ] && proto="-6" || proto="" + port=${2} + + run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + nettest_pids="${nettest_pids} $!" + + run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + nettest_pids="${nettest_pids} $!" +} + setup_xfrm4() { setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} } @@ -639,6 +685,26 @@ setup_xfrm6() { setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} } +setup_xfrm4udp() { + setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 4 4500 +} + +setup_xfrm6udp() { + setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 6 4500 +} + +setup_xfrm4udprouted() { + setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 4 4500 +} + +setup_xfrm6udprouted() { + setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 6 4500 +} + setup_routing_old() { for i in ${routes}; do [ "${ns}" = "" ] && ns="${i}" && continue @@ -823,6 +889,11 @@ cleanup() { done tcpdump_pids= + for pid in ${nettest_pids}; do + kill ${pid} + done + nettest_pids= + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done @@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() { return ${fail} } +test_pmtu_vti4_udp_exception() { + setup namespaces veth vti4 xfrm4udp || return $ksft_skip + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti4_a "${ns_b}" vti4_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 20)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 28)) + + mtu "${ns_a}" veth_a ${veth_mtu} + mtu "${ns_b}" veth_b ${veth_mtu} + mtu "${ns_a}" vti4_a ${vti_mtu} + mtu "${ns_b}" vti4_b ${vti_mtu} + + # Send DF packet without exceeding link layer MTU, check that no + # exception is created + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now exceed link layer MTU by one byte, check that exception is created + # with the right PMTU value + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" +} + +test_pmtu_vti6_udp_exception() { + setup namespaces veth vti6 xfrm6udp || return $ksft_skip + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti6_a "${ns_b}" vti6_b + fail=0 + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_a 4000 + mtu "${ns_b}" veth_b 4000 + mtu "${ns_a}" vti6_a 5000 + mtu "${ns_b}" vti6_b 5000 + run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1 + + # Decrease tunnel MTU, check for PMTU decrease in route exception + mtu "${ns_a}" vti6_a 3000 + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1 + + # Increase tunnel MTU, check for PMTU increase in route exception + mtu "${ns_a}" vti6_a 9000 + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1 + + return ${fail} +} + +test_pmtu_vti4_udp_routed_exception() { + setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \ + "${ns_a}" vti4_a "${ns_b}" vti4_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 20)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 28)) + + mtu "${ns_a}" veth_A-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-A ${veth_mtu} + mtu "${ns_b}" veth_B-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-B ${veth_mtu} + + mtu "${ns_a}" vti4_a ${vti_mtu} + mtu "${ns_b}" vti4_b ${vti_mtu} + + # Send DF packet without exceeding link layer MTU, check that no + # exception is created + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now decrease link layer MTU by 8 bytes on R1, check that exception is created + # with the right PMTU value + mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8)) + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))" +} + +test_pmtu_vti6_udp_routed_exception() { + setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \ + "${ns_a}" vti6_a "${ns_b}" vti6_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 40)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 48)) + + mtu "${ns_a}" veth_A-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-A ${veth_mtu} + mtu "${ns_b}" veth_B-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-B ${veth_mtu} + + # mtu "${ns_a}" vti6_a ${vti_mtu} + # mtu "${ns_b}" vti6_b ${vti_mtu} + + run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr} + + # Check that exception was not created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now decrease link layer MTU by 8 bytes on R1, check that exception is created + # with the right PMTU value + mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8)) + run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))" + +} + test_pmtu_vti4_default_mtu() { setup namespaces veth vti4 || return $ksft_skip From f5a11c69b69923a4367d24365ad4dff6d4f3fc42 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 21 Jul 2021 15:55:43 +0000 Subject: [PATCH 0721/1469] Revert "x86/hyperv: fix logical processor creation" This reverts commit 450605c28d571eddca39a65fdbc1338add44c6d9. Signed-off-by: Wei Liu --- arch/x86/kernel/cpu/mshyperv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index cc8f1773deca..c890d67a64ad 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -237,7 +237,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus) for_each_present_cpu(i) { if (i == 0) continue; - ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i); + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); BUG_ON(ret); } From bb55362bd6976631b662ca712779b6532d8de0a6 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Tue, 20 Jul 2021 19:34:39 -0700 Subject: [PATCH 0722/1469] ibmvnic: Remove the proper scrq flush Commit 65d6470d139a ("ibmvnic: clean pending indirect buffs during reset") intended to remove the call to ibmvnic_tx_scrq_flush() when the ->resetting flag is true and was tested that way. But during the final rebase to net-next, the hunk got applied to a block few lines below (which happened to have the same diff context) and the wrong call to ibmvnic_tx_scrq_flush() got removed. Fix that by removing the correct ibmvnic_tx_scrq_flush() and restoring the one that was incorrectly removed. Fixes: 65d6470d139a ("ibmvnic: clean pending indirect buffs during reset") Reported-by: Dany Madden Signed-off-by: Sukadev Bhattiprolu Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ed77191d19f4..a775c69e4fd7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1731,7 +1731,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_send_failed++; tx_dropped++; ret = NETDEV_TX_OK; - ibmvnic_tx_scrq_flush(adapter, tx_scrq); goto out; } @@ -1753,6 +1752,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb_any(skb); tx_send_failed++; tx_dropped++; + ibmvnic_tx_scrq_flush(adapter, tx_scrq); ret = NETDEV_TX_OK; goto out; } From 161dcc02428858fe338b7493158ed6f5fc2a8f26 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:19:32 +0200 Subject: [PATCH 0723/1469] net: ixp46x: fix ptp build failure The rework of the ixp46x cpu detection left the network driver in a half broken state: drivers/net/ethernet/xscale/ptp_ixp46x.c: In function 'ptp_ixp_init': drivers/net/ethernet/xscale/ptp_ixp46x.c:290:51: error: 'IXP4XX_TIMESYNC_BASE_VIRT' undeclared (first use in this function) 290 | (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT; | ^~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/xscale/ptp_ixp46x.c:290:51: note: each undeclared identifier is reported only once for each function it appears in drivers/net/ethernet/xscale/ptp_ixp46x.c: At top level: drivers/net/ethernet/xscale/ptp_ixp46x.c:323:1: error: data definition has no type or storage class [-Werror] 323 | module_init(ptp_ixp_init); I have patches to complete the transition for a future release, but for the moment, add the missing include statements to get it to build again. Fixes: 09aa9aabdcc4 ("soc: ixp4xx: move cpu detection to linux/soc/ixp4xx/cpu.h") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/xscale/ptp_ixp46x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c index 99d4d9439d05..a6fb88fd42f7 100644 --- a/drivers/net/ethernet/xscale/ptp_ixp46x.c +++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include "ixp46x_ts.h" From 1e7107c5ef44431bc1ebbd4c353f1d7c22e5f2ec Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 16 Jun 2021 08:51:57 -0400 Subject: [PATCH 0724/1469] cgroup1: fix leaked context root causing sporadic NULL deref in LTP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Richard reported sporadic (roughly one in 10 or so) null dereferences and other strange behaviour for a set of automated LTP tests. Things like: BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 1516 Comm: umount Not tainted 5.10.0-yocto-standard #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:kernfs_sop_show_path+0x1b/0x60 ...or these others: RIP: 0010:do_mkdirat+0x6a/0xf0 RIP: 0010:d_alloc_parallel+0x98/0x510 RIP: 0010:do_readlinkat+0x86/0x120 There were other less common instances of some kind of a general scribble but the common theme was mount and cgroup and a dubious dentry triggering the NULL dereference. I was only able to reproduce it under qemu by replicating Richard's setup as closely as possible - I never did get it to happen on bare metal, even while keeping everything else the same. In commit 71d883c37e8d ("cgroup_do_mount(): massage calling conventions") we see this as a part of the overall change: -------------- struct cgroup_subsys *ss; - struct dentry *dentry; [...] - dentry = cgroup_do_mount(&cgroup_fs_type, fc->sb_flags, root, - CGROUP_SUPER_MAGIC, ns); [...] - if (percpu_ref_is_dying(&root->cgrp.self.refcnt)) { - struct super_block *sb = dentry->d_sb; - dput(dentry); + ret = cgroup_do_mount(fc, CGROUP_SUPER_MAGIC, ns); + if (!ret && percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + struct super_block *sb = fc->root->d_sb; + dput(fc->root); deactivate_locked_super(sb); msleep(10); return restart_syscall(); } -------------- In changing from the local "*dentry" variable to using fc->root, we now export/leave that dentry pointer in the file context after doing the dput() in the unlikely "is_dying" case. With LTP doing a crazy amount of back to back mount/unmount [testcases/bin/cgroup_regression_5_1.sh] the unlikely becomes slightly likely and then bad things happen. A fix would be to not leave the stale reference in fc->root as follows: --------------                 dput(fc->root); + fc->root = NULL;                 deactivate_locked_super(sb); -------------- ...but then we are just open-coding a duplicate of fc_drop_locked() so we simply use that instead. Cc: Al Viro Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: stable@vger.kernel.org # v5.1+ Reported-by: Richard Purdie Fixes: 71d883c37e8d ("cgroup_do_mount(): massage calling conventions") Signed-off-by: Paul Gortmaker Signed-off-by: Tejun Heo --- fs/internal.h | 1 - include/linux/fs_context.h | 1 + kernel/cgroup/cgroup-v1.c | 4 +--- 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/internal.h b/fs/internal.h index 3ce8edbaa3ca..82e8eb32ff3d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -61,7 +61,6 @@ extern void __init chrdev_init(void); */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); -extern void fc_drop_locked(struct fs_context *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e2bc16300c82..6b54982fc5f3 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -141,6 +141,7 @@ extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); +extern void fc_drop_locked(struct fs_context *fc); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8d6bf56ed77a..de2c432dee20 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { - struct super_block *sb = fc->root->d_sb; - dput(fc->root); - deactivate_locked_super(sb); + fc_drop_locked(fc); ret = 1; } From 83f877a09516bcb82e34df621cc3a794509a11a3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 21 Jul 2021 12:40:10 +0100 Subject: [PATCH 0725/1469] xen/events: remove redundant initialization of variable irq The variable irq is being initialized with a value that is never read, it is being updated later on. The assignment is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20210721114010.108648-1-colin.king@canonical.com Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- drivers/xen/events/events_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index d7e361fb0548..154daddbdcb4 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1009,7 +1009,7 @@ static void __unbind_from_irq(unsigned int irq) int xen_bind_pirq_gsi_to_irq(unsigned gsi, unsigned pirq, int shareable, char *name) { - int irq = -1; + int irq; struct physdev_irq irq_op; int ret; From b42b0bddcbc87b4c66f6497f66fc72d52b712aa7 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 14 Jul 2021 17:19:33 +0800 Subject: [PATCH 0726/1469] workqueue: fix UAF in pwq_unbound_release_workfn() I got a UAF report when doing fuzz test: [ 152.880091][ T8030] ================================================================== [ 152.881240][ T8030] BUG: KASAN: use-after-free in pwq_unbound_release_workfn+0x50/0x190 [ 152.882442][ T8030] Read of size 4 at addr ffff88810d31bd00 by task kworker/3:2/8030 [ 152.883578][ T8030] [ 152.883932][ T8030] CPU: 3 PID: 8030 Comm: kworker/3:2 Not tainted 5.13.0+ #249 [ 152.885014][ T8030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 152.886442][ T8030] Workqueue: events pwq_unbound_release_workfn [ 152.887358][ T8030] Call Trace: [ 152.887837][ T8030] dump_stack_lvl+0x75/0x9b [ 152.888525][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.889371][ T8030] print_address_description.constprop.10+0x48/0x70 [ 152.890326][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.891163][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.891999][ T8030] kasan_report.cold.15+0x82/0xdb [ 152.892740][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.893594][ T8030] __asan_load4+0x69/0x90 [ 152.894243][ T8030] pwq_unbound_release_workfn+0x50/0x190 [ 152.895057][ T8030] process_one_work+0x47b/0x890 [ 152.895778][ T8030] worker_thread+0x5c/0x790 [ 152.896439][ T8030] ? process_one_work+0x890/0x890 [ 152.897163][ T8030] kthread+0x223/0x250 [ 152.897747][ T8030] ? set_kthread_struct+0xb0/0xb0 [ 152.898471][ T8030] ret_from_fork+0x1f/0x30 [ 152.899114][ T8030] [ 152.899446][ T8030] Allocated by task 8884: [ 152.900084][ T8030] kasan_save_stack+0x21/0x50 [ 152.900769][ T8030] __kasan_kmalloc+0x88/0xb0 [ 152.901416][ T8030] __kmalloc+0x29c/0x460 [ 152.902014][ T8030] alloc_workqueue+0x111/0x8e0 [ 152.902690][ T8030] __btrfs_alloc_workqueue+0x11e/0x2a0 [ 152.903459][ T8030] btrfs_alloc_workqueue+0x6d/0x1d0 [ 152.904198][ T8030] scrub_workers_get+0x1e8/0x490 [ 152.904929][ T8030] btrfs_scrub_dev+0x1b9/0x9c0 [ 152.905599][ T8030] btrfs_ioctl+0x122c/0x4e50 [ 152.906247][ T8030] __x64_sys_ioctl+0x137/0x190 [ 152.906916][ T8030] do_syscall_64+0x34/0xb0 [ 152.907535][ T8030] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 152.908365][ T8030] [ 152.908688][ T8030] Freed by task 8884: [ 152.909243][ T8030] kasan_save_stack+0x21/0x50 [ 152.909893][ T8030] kasan_set_track+0x20/0x30 [ 152.910541][ T8030] kasan_set_free_info+0x24/0x40 [ 152.911265][ T8030] __kasan_slab_free+0xf7/0x140 [ 152.911964][ T8030] kfree+0x9e/0x3d0 [ 152.912501][ T8030] alloc_workqueue+0x7d7/0x8e0 [ 152.913182][ T8030] __btrfs_alloc_workqueue+0x11e/0x2a0 [ 152.913949][ T8030] btrfs_alloc_workqueue+0x6d/0x1d0 [ 152.914703][ T8030] scrub_workers_get+0x1e8/0x490 [ 152.915402][ T8030] btrfs_scrub_dev+0x1b9/0x9c0 [ 152.916077][ T8030] btrfs_ioctl+0x122c/0x4e50 [ 152.916729][ T8030] __x64_sys_ioctl+0x137/0x190 [ 152.917414][ T8030] do_syscall_64+0x34/0xb0 [ 152.918034][ T8030] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 152.918872][ T8030] [ 152.919203][ T8030] The buggy address belongs to the object at ffff88810d31bc00 [ 152.919203][ T8030] which belongs to the cache kmalloc-512 of size 512 [ 152.921155][ T8030] The buggy address is located 256 bytes inside of [ 152.921155][ T8030] 512-byte region [ffff88810d31bc00, ffff88810d31be00) [ 152.922993][ T8030] The buggy address belongs to the page: [ 152.923800][ T8030] page:ffffea000434c600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10d318 [ 152.925249][ T8030] head:ffffea000434c600 order:2 compound_mapcount:0 compound_pincount:0 [ 152.926399][ T8030] flags: 0x57ff00000010200(slab|head|node=1|zone=2|lastcpupid=0x7ff) [ 152.927515][ T8030] raw: 057ff00000010200 dead000000000100 dead000000000122 ffff888009c42c80 [ 152.928716][ T8030] raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 [ 152.929890][ T8030] page dumped because: kasan: bad access detected [ 152.930759][ T8030] [ 152.931076][ T8030] Memory state around the buggy address: [ 152.931851][ T8030] ffff88810d31bc00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.932967][ T8030] ffff88810d31bc80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.934068][ T8030] >ffff88810d31bd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.935189][ T8030] ^ [ 152.935763][ T8030] ffff88810d31bd80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.936847][ T8030] ffff88810d31be00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 152.937940][ T8030] ================================================================== If apply_wqattrs_prepare() fails in alloc_workqueue(), it will call put_pwq() which invoke a work queue to call pwq_unbound_release_workfn() and use the 'wq'. The 'wq' allocated in alloc_workqueue() will be freed in error path when apply_wqattrs_prepare() fails. So it will lead a UAF. CPU0 CPU1 alloc_workqueue() alloc_and_link_pwqs() apply_wqattrs_prepare() fails apply_wqattrs_cleanup() schedule_work(&pwq->unbound_release_work) kfree(wq) worker_thread() pwq_unbound_release_workfn() <- trigger uaf here If apply_wqattrs_prepare() fails, the new pwq are not linked, it doesn't hold any reference to the 'wq', 'wq' is invalid to access in the worker, so add check pwq if linked to fix this. Fixes: 2d5f0764b526 ("workqueue: split apply_workqueue_attrs() into 3 stages") Cc: stable@vger.kernel.org # v4.2+ Reported-by: Hulk Robot Suggested-by: Lai Jiangshan Signed-off-by: Yang Yingliang Reviewed-by: Lai Jiangshan Tested-by: Pavel Skripkin Signed-off-by: Tejun Heo --- kernel/workqueue.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 50142fc08902..f148eacda55a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3676,15 +3676,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work) unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false; - if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; - mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); From d6a206e60124a9759dd7f6dfb86b0e1d3b1df82e Mon Sep 17 00:00:00 2001 From: John Keeping Date: Wed, 21 Jul 2021 17:17:45 +0100 Subject: [PATCH 0727/1469] USB: serial: cp210x: add ID for CEL EM3588 USB ZigBee stick Add the USB serial device ID for the CEL ZigBee EM3588 radio stick. Signed-off-by: John Keeping Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index af286240807e..3c80bfbf3bec 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -155,6 +155,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */ { USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ + { USB_DEVICE(0x10C4, 0x8A5B) }, /* CEL EM3588 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */ { USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ From ec3102dc6b36c692104c4a0546d4119de59a3bc1 Mon Sep 17 00:00:00 2001 From: Victor Lu Date: Thu, 24 Jun 2021 11:05:42 -0400 Subject: [PATCH 0728/1469] drm/amd/display: Fix comparison error in dcn21 DML [why] A comparison error made it possible to not iterate through all the specified prefetch modes. [how] Correct "<" to "<=" Reviewed-by: Dmytro Laktyushkin Reviewed-by: Yongqiang Sun Acked-by: Rodrigo Siqueira Signed-off-by: Victor Lu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index c26e742e8137..d25a7d38d21f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -4889,7 +4889,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true) && (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0] - || mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode)); + || mode_lib->vba.NextPrefetchMode <= mode_lib->vba.MaxPrefetchMode)); if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) { mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0]; From 32f1d0cfc3444fb44ff1dba10d28e479690bdd3e Mon Sep 17 00:00:00 2001 From: Eric Yang Date: Wed, 23 Jun 2021 15:48:02 -0400 Subject: [PATCH 0729/1469] drm/amd/display: implement workaround for riommu related hang [Why] During S4/S5/reboot, sometimes riommu invalidation request arrive too early, DCN may be unable to respond to the invalidation request resulting in pstate hang. [How] VBIOS will force allow pstate for riommu invalidation and driver will clear it after powering down display pipes. Acked-by: Rodrigo Siqueira Signed-off-by: Eric Yang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h | 4 +++- .../gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c | 18 ++++++++++++++++++ .../gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h | 1 + .../gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 2 +- .../drm/amd/display/dc/dcn31/dcn31_resource.c | 3 +++ .../amd/display/dc/inc/hw_sequencer_private.h | 1 + 6 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index df6539e4c730..0464a8f3db3c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -636,6 +636,7 @@ struct dce_hwseq_registers { uint32_t ODM_MEM_PWR_CTRL3; uint32_t DMU_MEM_PWR_CNTL; uint32_t MMHUBBUB_MEM_PWR_CNTL; + uint32_t DCHUBBUB_ARB_HOSTVM_CNTL; }; /* set field name */ #define HWS_SF(blk_name, reg_name, field_name, post_fix)\ @@ -1110,7 +1111,8 @@ struct dce_hwseq_registers { type DOMAIN_POWER_FORCEON;\ type DOMAIN_POWER_GATE;\ type DOMAIN_PGFSM_PWR_STATUS;\ - type HPO_HDMISTREAMCLK_G_GATE_DIS; + type HPO_HDMISTREAMCLK_G_GATE_DIS;\ + type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE; struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 836864a5a5dc..6ac6faf0c533 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -47,6 +47,7 @@ #include "dce/dmub_outbox.h" #include "dc_link_dp.h" #include "inc/link_dpcd.h" +#include "dcn10/dcn10_hw_sequencer.h" #define DC_LOGGER_INIT(logger) @@ -594,3 +595,20 @@ bool dcn31_is_abm_supported(struct dc *dc, } return false; } + +static void apply_riommu_invalidation_wa(struct dc *dc) +{ + struct dce_hwseq *hws = dc->hwseq; + + if (!hws->wa.early_riommu_invalidation) + return; + + REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, 0); +} + +void dcn31_init_pipes(struct dc *dc, struct dc_state *context) +{ + dcn10_init_pipes(dc, context); + apply_riommu_invalidation_wa(dc); + +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h index ff72f0fdd5be..40dfebe78fdd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h @@ -52,5 +52,6 @@ void dcn31_reset_hw_ctx_wrap( struct dc_state *context); bool dcn31_is_abm_supported(struct dc *dc, struct dc_state *context, struct dc_stream_state *stream); +void dcn31_init_pipes(struct dc *dc, struct dc_state *context); #endif /* __DC_HWSS_DCN31_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index e3048f8827d2..de74f62f96cd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -104,7 +104,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = { }; static const struct hwseq_private_funcs dcn31_private_funcs = { - .init_pipes = dcn10_init_pipes, + .init_pipes = dcn31_init_pipes, .update_plane_addr = dcn20_update_plane_addr, .plane_atomic_disconnect = dcn10_plane_atomic_disconnect, .update_mpcc = dcn20_update_mpcc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index c67bc9544f5d..3fe0aac4aaa6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -741,6 +741,7 @@ static const struct dccg_mask dccg_mask = { #define HWSEQ_DCN31_REG_LIST()\ SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \ + SR(DCHUBBUB_ARB_HOSTVM_CNTL), \ SR(DIO_MEM_PWR_CTRL), \ SR(ODM_MEM_PWR_CTRL3), \ SR(DMU_MEM_PWR_CNTL), \ @@ -801,6 +802,7 @@ static const struct dce_hwseq_registers hwseq_reg = { #define HWSEQ_DCN31_MASK_SH_LIST(mask_sh)\ HWSEQ_DCN_MASK_SH_LIST(mask_sh), \ HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \ + HWS_SF(, DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, mask_sh), \ HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \ HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, mask_sh), \ HWS_SF(, DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \ @@ -1299,6 +1301,7 @@ static struct dce_hwseq *dcn31_hwseq_create( hws->regs = &hwseq_reg; hws->shifts = &hwseq_shift; hws->masks = &hwseq_mask; + hws->wa.early_riommu_invalidation = true; } return hws; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index f7f7e4fff0c2..082549f75978 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -41,6 +41,7 @@ struct dce_hwseq_wa { bool DEGVIDCN10_254; bool DEGVIDCN21; bool disallow_self_refresh_during_multi_plane_transition; + bool early_riommu_invalidation; }; struct hwseq_wa_state { From d7940911fc0754d99b208f0e3098762d39f403a0 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 7 Jul 2021 13:19:14 -0400 Subject: [PATCH 0730/1469] drm/amd/display: Fix max vstartup calculation for modes with borders [Why] Vertical and horizontal borders in timings are treated as increasing the active area - vblank and hblank actually shrink. Our input into DML does not include these borders so it incorrectly assumes it has more time than available for vstartup and tmdl calculations for some modes with borders. An example of such a timing would be 640x480@72Hz: h_total: 832 h_border_left: 8 h_addressable: 640 h_border_right: 8 h_front_porch: 16 h_sync_width: 40 v_total: 520 v_border_top: 8 v_addressable: 480 v_border_bottom: 8 v_front_porch: 1 v_sync_width: 3 pix_clk_100hz: 315000 [How] Include borders as part of destination vactive/hactive. This change DCN20+ so it has wide impact, but the destination vactive and hactive are only really used for vstartup calculation anyway. Most modes do not have vertical or horizontal borders. Reviewed-by: Dmytro Laktyushkin Acked-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 1b05a37b674d..98d21fb374b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2093,8 +2093,10 @@ int dcn20_populate_dml_pipes_from_context( - timing->v_border_bottom; pipes[pipe_cnt].pipe.dest.htotal = timing->h_total; pipes[pipe_cnt].pipe.dest.vtotal = v_total; - pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable; - pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable; + pipes[pipe_cnt].pipe.dest.hactive = + timing->h_addressable + timing->h_border_left + timing->h_border_right; + pipes[pipe_cnt].pipe.dest.vactive = + timing->v_addressable + timing->v_border_top + timing->v_border_bottom; pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE; pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0; if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING) From f30f55158728b4423cf1caf666dd2e2c1943dc19 Mon Sep 17 00:00:00 2001 From: Bindu Ramamurthy Date: Thu, 27 May 2021 10:11:32 -0400 Subject: [PATCH 0731/1469] drm/amd/display: Populate socclk entries for dcn3.02/3.03 [Why] Initialize socclk entries in bandwidth params for dcn302, dcn303. [How] Fetch the sockclk values from smu for the DPM levels and for the DPM levels where smu returns 0, previous level values are reported. Reviewed-by: Roman Li Acked-by: Rodrigo Siqueira Signed-off-by: Bindu Ramamurthy Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c | 4 ++++ drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c | 7 +++++-- drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c | 7 +++++-- 3 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 513676a6f52b..af7004b770ae 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -190,6 +190,10 @@ void dcn3_init_clocks(struct clk_mgr *clk_mgr_base) &clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz, &num_levels); + /* SOCCLK */ + dcn3_init_single_clock(clk_mgr, PPCLK_SOCCLK, + &clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz, + &num_levels); // DPREFCLK ??? /* DISPCLK */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index 16a75ba0ca82..d65c097333a4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -1399,10 +1399,13 @@ void dcn302_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_02_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; dcn3_02_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[0].dtbclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) + dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz; + else + dcn3_02_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz; /* These clocks cannot come from bw_params, always fill from dcn3_02_soc[1] */ - /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */ + /* FCLK, PHYCLK_D18, DSCCLK */ dcn3_02_soc.clock_limits[i].phyclk_d18_mhz = dcn3_02_soc.clock_limits[0].phyclk_d18_mhz; - dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[0].socclk_mhz; dcn3_02_soc.clock_limits[i].dscclk_mhz = dcn3_02_soc.clock_limits[0].dscclk_mhz; } /* re-init DML with updated bb */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 34b89464ae02..f8b84722a389 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -1327,10 +1327,13 @@ void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[0].dtbclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) + dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz; + else + dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz; /* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */ - /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */ + /* FCLK, PHYCLK_D18, DSCCLK */ dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz; - dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[0].socclk_mhz; dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz; } /* re-init DML with updated bb */ From b0364fa4fc045685f827ea34c0149c953d0240bd Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 7 Jul 2021 16:38:57 -0400 Subject: [PATCH 0732/1469] drm/amd/display: Query VCO frequency from register for DCN3.1 [Why] Hardcoding the VCO frequency isn't correct since we don't own or control the value. In the case where the hardcode is also missing we can't lightup display. [How] Query from the CLK register instead. Update the DFS frequency to be able to compute the VCO frequency. Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- .../display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c | 43 ++++++++++++++- .../display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h | 54 ------------------- 2 files changed, 42 insertions(+), 55 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 7b7d884d58be..d15c628a2ab0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -48,6 +48,21 @@ #include "dc_dmub_srv.h" +#include "yellow_carp_offset.h" + +#define regCLK1_CLK_PLL_REQ 0x0237 +#define regCLK1_CLK_PLL_REQ_BASE_IDX 0 + +#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0 +#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc +#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10 +#define CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL +#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L +#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L + +#define REG(reg_name) \ + (CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name) + #define TO_CLK_MGR_DCN31(clk_mgr)\ container_of(clk_mgr, struct clk_mgr_dcn31, base) @@ -229,7 +244,32 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr) { - return 0; + /* get FbMult value */ + struct fixed31_32 pll_req; + unsigned int fbmult_frac_val = 0; + unsigned int fbmult_int_val = 0; + + /* + * Register value of fbmult is in 8.16 format, we are converting to 31.32 + * to leverage the fix point operations available in driver + */ + + REG_GET(CLK1_CLK_PLL_REQ, FbMult_frac, &fbmult_frac_val); /* 16 bit fractional part*/ + REG_GET(CLK1_CLK_PLL_REQ, FbMult_int, &fbmult_int_val); /* 8 bit integer part */ + + pll_req = dc_fixpt_from_int(fbmult_int_val); + + /* + * since fractional part is only 16 bit in register definition but is 32 bit + * in our fix point definiton, need to shift left by 16 to obtain correct value + */ + pll_req.value |= fbmult_frac_val << 16; + + /* multiply by REFCLK period */ + pll_req = dc_fixpt_mul_int(pll_req, clk_mgr->dfs_ref_freq_khz); + + /* integer part is now VCO frequency in kHz */ + return dc_fixpt_floor(pll_req); } static void dcn31_enable_pme_wa(struct clk_mgr *clk_mgr_base) @@ -592,6 +632,7 @@ void dcn31_clk_mgr_construct( clk_mgr->base.dprefclk_ss_percentage = 0; clk_mgr->base.dprefclk_ss_divider = 1000; clk_mgr->base.ss_on_dprefclk = false; + clk_mgr->base.dfs_ref_freq_khz = 48000; clk_mgr->smu_wm_set.wm_set = (struct dcn31_watermarks *)dm_helpers_allocate_gpu_mem( clk_mgr->base.base.ctx, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h index cc21cf75eafd..f8f100535526 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h @@ -27,60 +27,6 @@ #define __DCN31_CLK_MGR_H__ #include "clk_mgr_internal.h" -//CLK1_CLK_PLL_REQ -#ifndef CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT -#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0 -#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc -#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10 -#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL -#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L -#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L -//CLK1_CLK0_DFS_CNTL -#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER__SHIFT 0x0 -#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER_MASK 0x0000007FL -/*DPREF clock related*/ -#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0 -#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL -#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0 -#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL -#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0 -#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL -#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0 -#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL - -//CLK3_0_CLK3_CLK_PLL_REQ -#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int__SHIFT 0x0 -#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc -#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10 -#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL -#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L -#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L - -#define mmCLK0_CLK3_DFS_CNTL 0x16C60 -#define mmCLK00_CLK0_CLK3_DFS_CNTL 0x16C60 -#define mmCLK01_CLK0_CLK3_DFS_CNTL 0x16E60 -#define mmCLK02_CLK0_CLK3_DFS_CNTL 0x17060 -#define mmCLK03_CLK0_CLK3_DFS_CNTL 0x17260 - -#define mmCLK0_CLK_PLL_REQ 0x16C10 -#define mmCLK00_CLK0_CLK_PLL_REQ 0x16C10 -#define mmCLK01_CLK0_CLK_PLL_REQ 0x16E10 -#define mmCLK02_CLK0_CLK_PLL_REQ 0x17010 -#define mmCLK03_CLK0_CLK_PLL_REQ 0x17210 - -#define mmCLK1_CLK_PLL_REQ 0x1B00D -#define mmCLK10_CLK1_CLK_PLL_REQ 0x1B00D -#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D -#define mmCLK12_CLK1_CLK_PLL_REQ 0x1B40D -#define mmCLK13_CLK1_CLK_PLL_REQ 0x1B60D - -#define mmCLK2_CLK_PLL_REQ 0x17E0D - -/*AMCLK*/ -#define mmCLK11_CLK1_CLK0_DFS_CNTL 0x1B23F -#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D -#endif - struct dcn31_watermarks; struct dcn31_smu_watermark_set { From a8e380fd8d71493623c94511f75e81786cffa223 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Thu, 8 Jul 2021 12:59:59 -0400 Subject: [PATCH 0733/1469] drm/amd/display: Update bounding box for DCN3.1 [Why & How] We're missing a default value for dram_channel_width_bytes in the DCN3.1 SOC bounding box and we don't currently have the interface in place to query the actual value from VBIOS. Put in a hardcoded default until we have the interface in place. Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 3fe0aac4aaa6..38c010afade1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -220,6 +220,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = { .sr_exit_z8_time_us = 402.0, .sr_enter_plus_exit_z8_time_us = 520.0, .writeback_latency_us = 12.0, + .dram_channel_width_bytes = 4, .round_trip_ping_latency_dcfclk_cycles = 106, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, From 2d73eabe2984a435737498ab39bb1500a9ffe9a9 Mon Sep 17 00:00:00 2001 From: Camille Cho Date: Thu, 8 Jul 2021 18:28:37 +0800 Subject: [PATCH 0734/1469] drm/amd/display: Only set default brightness for OLED [Why] We used to unconditionally set backlight path as AUX for panels capable of backlight adjustment via DPCD in set default brightness. [How] This should be limited to OLED panel only since we control backlight via PWM path for SDR mode in LCD HDR panel. Reviewed-by: Krunoslav Kovac Acked-by: Rodrigo Siqueira Signed-off-by: Camille Cho Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 6da226bf11d5..12066f5a53fc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -4914,9 +4914,7 @@ bool dc_link_set_default_brightness_aux(struct dc_link *link) { uint32_t default_backlight; - if (link && - (link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 || - link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) { + if (link && link->dpcd_sink_ext_caps.bits.oled == 1) { if (!dc_link_read_default_bl_aux(link, &default_backlight)) default_backlight = 150000; // if < 5 nits or > 5000, it might be wrong readback From 6580b28e0c734cea2f829e97827005c311293cb7 Mon Sep 17 00:00:00 2001 From: Mikita Lipski Date: Mon, 14 Jun 2021 20:21:42 -0400 Subject: [PATCH 0735/1469] drm/amd/display: Remove MALL function from DCN3.1 [why] DCN31 doesn't have MALL in DMUB so to avoid sending unknown commands to DMUB just remove the function pointer. [how] Remove apply_idle_power_optimizations from function pointers structure for DCN31 Reviewed-by: Nicholas Kazlauskas Acked-by: Rodrigo Siqueira Signed-off-by: Mikita Lipski Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index de74f62f96cd..aaf2dbd095fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -93,7 +93,6 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .set_flip_control_gsl = dcn20_set_flip_control_gsl, .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, - .apply_idle_power_optimizations = dcn30_apply_idle_power_optimizations, .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .set_pipe = dcn21_set_pipe, From 0f984c942cd1703b26dc01351dc47b0c93bc32f3 Mon Sep 17 00:00:00 2001 From: Nevenko Stupar Date: Fri, 9 Jul 2021 13:05:11 -0400 Subject: [PATCH 0736/1469] drm/amd/display: Line Buffer changes DCN 3x increased Line buffer size for DCHUB latency hiding, from 4 lines of 4K resolution lines to 5 lines of 4K resolution lines. All Line Buffer can be used as extended memory for P State change latency hiding. The maximum number of lines is increased to 32 lines. Finally, LB_MEMORY_CONFIG_1 (LB memory piece 1) and LB_MEMORY _CONFIG_2 (LB memory piece 2) are not affected, no change in size, only 3 pieces is affected, i.e., when all 3 pieces are used in both LB_MEMORY_CONFIG_0 and LB_MEMORY_CONFIG_3 (for 4:2:0) modes. Reviewed-by: Jun Lei Acked-by: Rodrigo Siqueira Signed-off-by: Nevenko Stupar Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c | 7 ++++++- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c | 16 ---------------- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h | 3 +-- .../gpu/drm/amd/display/dc/inc/hw/transform.h | 3 +++ 4 files changed, 10 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c index 673b93f4fea5..cb9767ddf93d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c @@ -217,6 +217,8 @@ static void dpp1_dscl_set_lb( const struct line_buffer_params *lb_params, enum lb_memory_config mem_size_config) { + uint32_t max_partitions = 63; /* Currently hardcoded on all ASICs before DCN 3.2 */ + /* LB */ if (dpp->base.caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) { /* DSCL caps: pixel data processed in fixed format */ @@ -239,9 +241,12 @@ static void dpp1_dscl_set_lb( LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */ } + if (dpp->base.caps->max_lb_partitions == 31) + max_partitions = 31; + REG_SET_2(LB_MEMORY_CTRL, 0, MEMORY_CONFIG, mem_size_config, - LB_MAX_PARTITIONS, 63); + LB_MAX_PARTITIONS, max_partitions); } static const uint16_t *dpp1_dscl_get_filter_coeffs_64p(int taps, struct fixed31_32 ratio) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index 2140b75540cf..23a52d47e61c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -383,13 +383,6 @@ bool dpp3_get_optimal_number_of_taps( int min_taps_y, min_taps_c; enum lb_memory_config lb_config; - /* Some ASICs does not support FP16 scaling, so we reject modes require this*/ - if (scl_data->viewport.width != scl_data->h_active && - scl_data->viewport.height != scl_data->v_active && - dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT && - scl_data->format == PIXEL_FORMAT_FP16) - return false; - if (scl_data->viewport.width > scl_data->h_active && dpp->ctx->dc->debug.max_downscale_src_width != 0 && scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) @@ -1440,15 +1433,6 @@ bool dpp3_construct( dpp->tf_shift = tf_shift; dpp->tf_mask = tf_mask; - dpp->lb_pixel_depth_supported = - LB_PIXEL_DEPTH_18BPP | - LB_PIXEL_DEPTH_24BPP | - LB_PIXEL_DEPTH_30BPP | - LB_PIXEL_DEPTH_36BPP; - - dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY; - dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/ - return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h index 3fa86cd090a0..ac644ae6b9f2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h @@ -154,6 +154,7 @@ SRI(COLOR_KEYER_BLUE, CNVC_CFG, id), \ SRI(CURSOR_CONTROL, CURSOR0_, id),\ SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\ + SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \ SRI(DSCL_MEM_PWR_CTRL, DSCL, id) #define DPP_REG_LIST_DCN30(id)\ @@ -163,8 +164,6 @@ SRI(CM_SHAPER_LUT_DATA, CM, id),\ SRI(CM_MEM_PWR_CTRL2, CM, id), \ SRI(CM_MEM_PWR_STATUS2, CM, id), \ - SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \ - SRI(DSCL_MEM_PWR_CTRL, DSCL, id), \ SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_B, CM, id),\ SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_G, CM, id),\ SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_R, CM, id),\ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h index 2a0db2b03047..9ac9d5e8df8b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h @@ -289,6 +289,9 @@ struct dpp_caps { /* DSCL processing pixel data in fixed or float format */ enum dscl_data_processing_format dscl_data_proc_format; + /* max LB partitions */ + unsigned int max_lb_partitions; + /* Calculates the number of partitions in the line buffer. * The implementation of this function is overloaded for * different versions of DSCL LB. From ce350c6e786ef4bc3a4ddb58f8bdf2e48219fdaa Mon Sep 17 00:00:00 2001 From: Bindu Ramamurthy Date: Fri, 9 Jul 2021 10:35:33 -0400 Subject: [PATCH 0737/1469] drm/amd/display: Populate dtbclk entries for dcn3.02/3.03 [Why] Populate dtbclk values from bwparams for dcn302, dcn303. [How] dtbclk values are fetched from bandwidthparams for all DPM levels and for DPM levels where smu returns 0, previous level values are reported. Reviewed-by: Roman Li Acked-by: Rodrigo Siqueira Signed-off-by: Bindu Ramamurthy Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c | 6 +++++- drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index d65c097333a4..7d3ff5d44402 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -1398,7 +1398,11 @@ void dcn302_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_02_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz; dcn3_02_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; dcn3_02_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; - dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[0].dtbclk_mhz; + /* Populate from bw_params for DTBCLK, SOCCLK */ + if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0) + dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[i-1].dtbclk_mhz; + else + dcn3_02_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index f8b84722a389..833ab13fa834 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -1326,7 +1326,11 @@ void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz; dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz; dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz; - dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[0].dtbclk_mhz; + /* Populate from bw_params for DTBCLK, SOCCLK */ + if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0) + dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz; + else + dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0) dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz; else From 93b6bd307a54ea62bfcf89748c80bd25b7bd3205 Mon Sep 17 00:00:00 2001 From: Eric Yang Date: Wed, 30 Jun 2021 18:22:51 -0400 Subject: [PATCH 0738/1469] drm/amd/display: change zstate allow msg condition [Why] PMFW message which previously thought to only control Z9 controls both Z9 and Z10. Also HW design team requested that Z9 must only be supported on eDP due to content protection interop. [How] Change zstate support condition to match updated policy Reviewed-by: Nicholas Kazlauskas Acked-by: Rodrigo Siqueira Signed-off-by: Eric Yang Signed-off-by: Alex Deucher --- .../display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c | 16 +++---- drivers/gpu/drm/amd/display/dc/dc.h | 10 ++--- .../drm/amd/display/dc/dcn20/dcn20_resource.c | 44 ++++++++++++++----- 3 files changed, 45 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index d15c628a2ab0..4a4894e9d9c9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -139,10 +139,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, * also if safe to lower is false, we just go in the higher state */ if (safe_to_lower) { - if (new_clocks->z9_support == DCN_Z9_SUPPORT_ALLOW && - new_clocks->z9_support != clk_mgr_base->clks.z9_support) { + if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_ALLOW && + new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn31_smu_set_Z9_support(clk_mgr, true); - clk_mgr_base->clks.z9_support = new_clocks->z9_support; + clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) { @@ -163,10 +163,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, } } } else { - if (new_clocks->z9_support == DCN_Z9_SUPPORT_DISALLOW && - new_clocks->z9_support != clk_mgr_base->clks.z9_support) { + if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW && + new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn31_smu_set_Z9_support(clk_mgr, false); - clk_mgr_base->clks.z9_support = new_clocks->z9_support; + clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) { @@ -286,7 +286,7 @@ static void dcn31_init_clocks(struct clk_mgr *clk_mgr) clk_mgr->clks.p_state_change_support = true; clk_mgr->clks.prev_p_state_change_support = true; clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN; - clk_mgr->clks.z9_support = DCN_Z9_SUPPORT_UNKNOWN; + clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN; } static bool dcn31_are_clock_states_equal(struct dc_clocks *a, @@ -300,7 +300,7 @@ static bool dcn31_are_clock_states_equal(struct dc_clocks *a, return false; else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz) return false; - else if (a->z9_support != b->z9_support) + else if (a->zstate_support != b->zstate_support) return false; else if (a->dtbclk_en != b->dtbclk_en) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 45640f1c26c4..8dcea8ff5c5a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -354,10 +354,10 @@ enum dcn_pwr_state { }; #if defined(CONFIG_DRM_AMD_DC_DCN) -enum dcn_z9_support_state { - DCN_Z9_SUPPORT_UNKNOWN, - DCN_Z9_SUPPORT_ALLOW, - DCN_Z9_SUPPORT_DISALLOW, +enum dcn_zstate_support_state { + DCN_ZSTATE_SUPPORT_UNKNOWN, + DCN_ZSTATE_SUPPORT_ALLOW, + DCN_ZSTATE_SUPPORT_DISALLOW, }; #endif /* @@ -378,7 +378,7 @@ struct dc_clocks { int dramclk_khz; bool p_state_change_support; #if defined(CONFIG_DRM_AMD_DC_DCN) - enum dcn_z9_support_state z9_support; + enum dcn_zstate_support_state zstate_support; bool dtbclk_en; #endif enum dcn_pwr_state pwr_state; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 98d21fb374b1..b173fa3653b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3081,6 +3081,37 @@ static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) return false; } +static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struct dc_state *context) +{ + int plane_count; + int i; + + plane_count = 0; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].plane_state) + plane_count++; + } + + /* + * Zstate is allowed in following scenarios: + * 1. Single eDP with PSR enabled + * 2. 0 planes (No memory requests) + * 3. Single eDP without PSR but > 5ms stutter period + */ + if (plane_count == 0) + return DCN_ZSTATE_SUPPORT_ALLOW; + else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { + struct dc_link *link = context->streams[0]->sink->link; + + if ((link->link_index == 0 && link->psr_settings.psr_feature_enabled) + || context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + return DCN_ZSTATE_SUPPORT_ALLOW; + else + return DCN_ZSTATE_SUPPORT_DISALLOW; + } else + return DCN_ZSTATE_SUPPORT_DISALLOW; +} + void dcn20_calculate_dlg_params( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, @@ -3088,7 +3119,6 @@ void dcn20_calculate_dlg_params( int vlevel) { int i, pipe_idx; - int plane_count; /* Writeback MCIF_WB arbitration parameters */ dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt); @@ -3104,17 +3134,7 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.z9_support = (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) ? - DCN_Z9_SUPPORT_ALLOW : DCN_Z9_SUPPORT_DISALLOW; - - plane_count = 0; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (context->res_ctx.pipe_ctx[i].plane_state) - plane_count++; - } - - if (plane_count == 0) - context->bw_ctx.bw.dcn.clk.z9_support = DCN_Z9_SUPPORT_ALLOW; + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); From 6588b101ed0a71a60fa7df0a18ed7db07026d109 Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Thu, 15 Jul 2021 14:54:49 +0800 Subject: [PATCH 0739/1469] drm/amd/pm: Support board calibration on aldebaran Add support for board power calibration on Aldebaran. Board calibration is done after DC offset calibration. Signed-off-by: Lijo Lazar Reviewed-by: Kevin Wang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h | 3 +- drivers/gpu/drm/amd/pm/inc/smu_types.h | 3 +- .../drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 46 +++++++++++++++---- 3 files changed, 40 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h index 610266088ff1..35fa0d8e92dd 100644 --- a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h @@ -101,7 +101,8 @@ #define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x41 #define PPSMC_MSG_GfxDriverResetRecovery 0x42 -#define PPSMC_Message_Count 0x43 +#define PPSMC_MSG_BoardPowerCalibration 0x43 +#define PPSMC_Message_Count 0x44 //PPSMC Reset Types #define PPSMC_RESET_TYPE_WARM_RESET 0x00 diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h index 89a16dcd0fff..1d3765b873df 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h @@ -225,7 +225,8 @@ __SMU_DUMMY_MAP(DisableDeterminism), \ __SMU_DUMMY_MAP(SetUclkDpmMode), \ __SMU_DUMMY_MAP(LightSBR), \ - __SMU_DUMMY_MAP(GfxDriverResetRecovery), + __SMU_DUMMY_MAP(GfxDriverResetRecovery), \ + __SMU_DUMMY_MAP(BoardPowerCalibration), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 9316a726195c..cb5485cf243f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -134,6 +134,7 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0), MSG_MAP(SetUclkDpmMode, PPSMC_MSG_SetUclkDpmMode, 0), MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0), + MSG_MAP(BoardPowerCalibration, PPSMC_MSG_BoardPowerCalibration, 0), }; static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = { @@ -440,6 +441,39 @@ static int aldebaran_setup_pptable(struct smu_context *smu) return ret; } +static bool aldebaran_is_primary(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->smuio.funcs && adev->smuio.funcs->get_die_id) + return adev->smuio.funcs->get_die_id(adev) == 0; + + return true; +} + +static int aldebaran_run_board_btc(struct smu_context *smu) +{ + u32 smu_version; + int ret; + + if (!aldebaran_is_primary(smu)) + return 0; + + ret = smu_cmn_get_smc_version(smu, NULL, &smu_version); + if (ret) { + dev_err(smu->adev->dev, "Failed to get smu version!\n"); + return ret; + } + if (smu_version <= 0x00441d00) + return 0; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BoardPowerCalibration, NULL); + if (ret) + dev_err(smu->adev->dev, "Board power calibration failed!\n"); + + return ret; +} + static int aldebaran_run_btc(struct smu_context *smu) { int ret; @@ -447,6 +481,8 @@ static int aldebaran_run_btc(struct smu_context *smu) ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL); if (ret) dev_err(smu->adev->dev, "RunDcBtc failed!\n"); + else + ret = aldebaran_run_board_btc(smu); return ret; } @@ -524,16 +560,6 @@ static int aldebaran_freqs_in_same_level(int32_t frequency1, return (abs(frequency1 - frequency2) <= EPSILON); } -static bool aldebaran_is_primary(struct smu_context *smu) -{ - struct amdgpu_device *adev = smu->adev; - - if (adev->smuio.funcs && adev->smuio.funcs->get_die_id) - return adev->smuio.funcs->get_die_id(adev) == 0; - - return true; -} - static int aldebaran_get_smu_metrics_data(struct smu_context *smu, MetricsMember_t member, uint32_t *value) From ab7a11bd36ca6cd4d4dab2846eaacafaa5963cc1 Mon Sep 17 00:00:00 2001 From: Aaron Liu Date: Wed, 2 Jun 2021 10:32:41 +0800 Subject: [PATCH 0740/1469] drm/amdgpu: update yellow carp external rev_id handling 0x1681 has a different external revision id. Signed-off-by: Aaron Liu Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nv.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index cf73a6923203..f589b8334be6 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -1236,7 +1236,10 @@ static int nv_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; - adev->external_rev_id = adev->rev_id + 0x01; + if (adev->pdev->device == 0x1681) + adev->external_rev_id = adev->rev_id + 0x19; + else + adev->external_rev_id = adev->rev_id + 0x01; break; default: /* FIXME: not supported yet */ From 27f5355f5d9706dfc1c2542253689f421008c969 Mon Sep 17 00:00:00 2001 From: Aaron Liu Date: Wed, 4 Nov 2020 13:04:06 +0800 Subject: [PATCH 0741/1469] drm/amdgpu: add yellow carp pci id (v2) Add Yellow Carp PCI id support. v2: add another DID Signed-off-by: Aaron Liu Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index abb928894eac..361b86b71b56 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1190,6 +1190,10 @@ static const struct pci_device_id pciidlist[] = { /* Van Gogh */ {0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU}, + /* Yellow Carp */ + {0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU}, + {0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU}, + /* Navy_Flounder */ {0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER}, {0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER}, From 6be50f5d83adc9541de3d5be26e968182b5ac150 Mon Sep 17 00:00:00 2001 From: Stylon Wang Date: Wed, 21 Jul 2021 12:25:24 +0800 Subject: [PATCH 0742/1469] drm/amd/display: Fix ASSR regression on embedded panels [Why] Regression found in some embedded panels traces back to the earliest upstreamed ASSR patch. The changed code flow are causing problems with some panels. [How] - Change ASSR enabling code while preserving original code flow as much as possible - Simplify the code on guarding with internal display flag Bug: https://bugzilla.kernel.org/show_bug.cgi?id=213779 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1620 Reviewed-by: Alex Deucher Signed-off-by: Stylon Wang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 12066f5a53fc..9fb8c46dc606 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1820,8 +1820,7 @@ bool perform_link_training_with_retries( */ panel_mode = DP_PANEL_MODE_DEFAULT; } - } else - panel_mode = DP_PANEL_MODE_DEFAULT; + } } #endif @@ -4650,7 +4649,10 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link) } } - if (link->dpcd_caps.panel_mode_edp) { + if (link->dpcd_caps.panel_mode_edp && + (link->connector_signal == SIGNAL_TYPE_EDP || + (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT && + link->is_internal_display))) { return DP_PANEL_MODE_EDP; } From 02dc2ee7c7476dd831df63d2b10cc0a162a531f1 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 21 Jul 2021 14:45:54 -0400 Subject: [PATCH 0743/1469] sctp: do not update transport pathmtu if SPP_PMTUD_ENABLE is not set Currently, in sctp_packet_config(), sctp_transport_pmtu_check() is called to update transport pathmtu with dst's mtu when dst's mtu has been changed by non sctp stack like xfrm. However, this should only happen when SPP_PMTUD_ENABLE is set, no matter where dst's mtu changed. This patch is to fix by checking SPP_PMTUD_ENABLE flag before calling sctp_transport_pmtu_check(). Thanks Jacek for reporting and looking into this issue. v1->v2: - add the missing "{" to fix the build error. Fixes: 69fec325a643 ('Revert "sctp: remove sctp_transport_pmtu_check"') Reported-by: Jacek Szafraniec Tested-by: Jacek Szafraniec Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/output.c b/net/sctp/output.c index 9032ce60d50e..4dfb5ea82b05 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } else if (!sctp_transport_pl_enabled(tp) && - !sctp_transport_pmtu_check(tp)) { - if (asoc->param_flags & SPP_PMTUD_ENABLE) + asoc->param_flags & SPP_PMTUD_ENABLE) { + if (!sctp_transport_pmtu_check(tp)) sctp_assoc_sync_pmtu(asoc); } From d80cded9cc25f841d5250d2e94a7b42be1e81c97 Mon Sep 17 00:00:00 2001 From: Veerabadhran Gopalakrishnan Date: Mon, 19 Jul 2021 19:06:23 +0530 Subject: [PATCH 0744/1469] drm/amdgpu - Corrected the video codecs array name for yellow carp Signed-off-by: Veerabadhran Gopalakrishnan Reviewed-by: James Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index f589b8334be6..94d029dbf30d 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -173,8 +173,8 @@ static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = { }; static const struct amdgpu_video_codecs yc_video_codecs_decode = { - .codec_count = ARRAY_SIZE(bg_video_codecs_decode_array), - .codec_array = bg_video_codecs_decode_array, + .codec_count = ARRAY_SIZE(yc_video_codecs_decode_array), + .codec_array = yc_video_codecs_decode_array, }; static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, From e062233c0ed0a76b6dd4ec785550419a323f9380 Mon Sep 17 00:00:00 2001 From: Frank Wunderlich Date: Mon, 12 Jul 2021 10:07:36 +0200 Subject: [PATCH 0745/1469] drm/mediatek: dpi: Fix NULL dereference in mtk_dpi_bridge_atomic_check bridge->driver_private is not set (NULL) so use bridge_to_dpi(bridge) like it's done in bridge_atomic_get_output_bus_fmts Fixes: ec8747c52434 ("drm/mediatek: dpi: Add bus format negotiation") Signed-off-by: Frank Wunderlich Tested-by: Hsin-Yi Wang Signed-off-by: Chun-Kuang Hu --- drivers/gpu/drm/mediatek/mtk_dpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index bced555648b0..a2eca1f66984 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -605,7 +605,7 @@ static int mtk_dpi_bridge_atomic_check(struct drm_bridge *bridge, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - struct mtk_dpi *dpi = bridge->driver_private; + struct mtk_dpi *dpi = bridge_to_dpi(bridge); unsigned int out_bus_format; out_bus_format = bridge_state->output_bus_cfg.format; From d0e4dae74470fb709fc0ab61862c317938f4cc4d Mon Sep 17 00:00:00 2001 From: Bin Meng Date: Sun, 27 Jun 2021 21:51:17 +0800 Subject: [PATCH 0746/1469] riscv: Fix 32-bit RISC-V boot failure Commit dd2d082b5760 ("riscv: Cleanup setup_bootmem()") adjusted the calling sequence in setup_bootmem(), which invalidates the fix commit de043da0b9e7 ("RISC-V: Fix usage of memblock_enforce_memory_limit") did for 32-bit RISC-V unfortunately. So now 32-bit RISC-V does not boot again when testing booting kernel on QEMU 'virt' with '-m 2G', which was exactly what the original commit de043da0b9e7 ("RISC-V: Fix usage of memblock_enforce_memory_limit") tried to fix. Fixes: dd2d082b5760 ("riscv: Cleanup setup_bootmem()") Signed-off-by: Bin Meng Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 4faf8bd157ea..0fc72603c699 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -123,7 +123,7 @@ void __init setup_bootmem(void) { phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); - phys_addr_t dram_end = memblock_end_of_DRAM(); + phys_addr_t dram_end; phys_addr_t max_mapped_addr = __pa(~(ulong)0); #ifdef CONFIG_XIP_KERNEL @@ -146,6 +146,8 @@ void __init setup_bootmem(void) #endif memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); + dram_end = memblock_end_of_DRAM(); + /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE From 213ad73d06073b197a02476db3a4998e219ddb06 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 21 Jul 2021 10:27:38 -0700 Subject: [PATCH 0747/1469] tcp: disable TFO blackhole logic by default Multiple complaints have been raised from the TFO users on the internet stating that the TFO blackhole logic is too aggressive and gets falsely triggered too often. (e.g. https://blog.apnic.net/2021/07/05/tcp-fast-open-not-so-fast/) Considering that most middleboxes no longer drop TFO packets, we decide to disable the blackhole logic by setting /proc/sys/net/ipv4/tcp_fastopen_blackhole_timeout_set to 0 by default. Fixes: cf1ef3f0719b4 ("net/tcp_fastopen: Disable active side TFO in certain scenarios") Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 2 +- net/ipv4/tcp_fastopen.c | 9 ++++++++- net/ipv4/tcp_ipv4.c | 2 +- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b3fa522e4cd9..316c7dfa9693 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -826,7 +826,7 @@ tcp_fastopen_blackhole_timeout_sec - INTEGER initial value when the blackhole issue goes away. 0 to disable the blackhole detection. - By default, it is set to 1hr. + By default, it is set to 0 (feature is disabled). tcp_fastopen_key - list of comma separated 32-digit hexadecimal INTEGERs The list consists of a primary key and an optional backup key. The diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index b32af76e2132..25fa4c01a17f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -507,6 +507,9 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); + if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + return; + /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); @@ -526,10 +529,14 @@ void tcp_fastopen_active_disable(struct sock *sk) bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; - int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int tfo_da_times; int multiplier; + if (!tfo_bh_timeout) + return false; + + tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); if (!tfo_da_times) return false; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b9dc2d6197be..a692626c19e4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); - net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Reno is always built in */ From e40cba9490bab1414d45c2d62defc0ad4f6e4136 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 21 Jul 2021 15:37:59 +0300 Subject: [PATCH 0748/1469] net: dsa: sja1105: make VID 4095 a bridge VLAN too This simple series of commands: ip link add br0 type bridge vlan_filtering 1 ip link set swp0 master br0 fails on sja1105 with the following error: [ 33.439103] sja1105 spi0.1: vlan-lookup-table needs to have at least the default untagged VLAN [ 33.447710] sja1105 spi0.1: Invalid config, cannot upload Warning: sja1105: Failed to change VLAN Ethertype. For context, sja1105 has 3 operating modes: - SJA1105_VLAN_UNAWARE: the dsa_8021q_vlans are committed to hardware - SJA1105_VLAN_FILTERING_FULL: the bridge_vlans are committed to hardware - SJA1105_VLAN_FILTERING_BEST_EFFORT: both the dsa_8021q_vlans and the bridge_vlans are committed to hardware Swapping out a VLAN list and another in happens in sja1105_build_vlan_table(), which performs a delta update procedure. That function is called from a few places, notably from sja1105_vlan_filtering() which is called from the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING handler. The above set of 2 commands fails when run on a kernel pre-commit 8841f6e63f2c ("net: dsa: sja1105: make devlink property best_effort_vlan_filtering true by default"). So the priv->vlan_state transition that takes place is between VLAN-unaware and full VLAN filtering. So the dsa_8021q_vlans are swapped out and the bridge_vlans are swapped in. So why does it fail? Well, the bridge driver, through nbp_vlan_init(), first sets up the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING attribute, and only then proceeds to call nbp_vlan_add for the default_pvid. So when we swap out the dsa_8021q_vlans and swap in the bridge_vlans in the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING handler, there are no bridge VLANs (yet). So we have wiped the VLAN table clean, and the low-level static config checker complains of an invalid configuration. We _will_ add the bridge VLANs using the dynamic config interface, albeit later, when nbp_vlan_add() calls us. So it is natural that it fails. So why did it ever work? Surprisingly, it looks like I only tested this configuration with 2 things set up in a particular way: - a network manager that brings all ports up - a kernel with CONFIG_VLAN_8021Q=y It is widely known that commit ad1afb003939 ("vlan_dev: VLAN 0 should be treated as "no vlan tag" (802.1p packet)") installs VID 0 to every net device that comes up. DSA treats these VLANs as bridge VLANs, and therefore, in my testing, the list of bridge_vlans was never empty. However, if CONFIG_VLAN_8021Q is not enabled, or the port is not up when it joins a VLAN-aware bridge, the bridge_vlans list will be temporarily empty, and the sja1105_static_config_reload() call from sja1105_vlan_filtering() will fail. To fix this, the simplest thing is to keep VID 4095, the one used for CPU-injected control packets since commit ed040abca4c1 ("net: dsa: sja1105: use 4095 as the private VLAN for untagged traffic"), in the list of bridge VLANs too, not just the list of tag_8021q VLANs. This ensures that the list of bridge VLANs will never be empty. Fixes: ec5ae61076d0 ("net: dsa: sja1105: save/restore VLANs using a delta commit method") Reported-by: Radu Pirea (NXP OSS) Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index ced8c9cb29c2..e2dc997580a8 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -397,6 +397,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) if (dsa_is_cpu_port(ds, port)) v->pvid = true; list_add(&v->list, &priv->dsa_8021q_vlans); + + v = kmemdup(v, sizeof(*v), GFP_KERNEL); + if (!v) + return -ENOMEM; + + list_add(&v->list, &priv->bridge_vlans); } ((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid; From 291d0a2c1fa6ff437c8f1156646fdd2525714c80 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 21 Jul 2021 19:17:21 +0100 Subject: [PATCH 0749/1469] ravb: Fix a typo in comment Fix the typo RX->TX in comment, as the code following the comment process TX and not RX. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Reviewed-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 69c50f81e1cb..805397088850 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -920,7 +920,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) if (ravb_rx(ndev, "a, q)) goto out; - /* Processing RX Descriptor Ring */ + /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); /* Clear TX interrupt */ ravb_write(ndev, ~(mask | TIS_RESERVED), TIS); From 9f061b9acbb0bdf5317b301c1608ca55be522c92 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 21 Jul 2021 19:21:26 +0100 Subject: [PATCH 0750/1469] ravb: Remove extra TAB Align the member description comments for struct ravb_desc by removing the extra TAB. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Reviewed-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 86a1eb0634e8..80e62ca2e3d3 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -864,7 +864,7 @@ enum GECMR_BIT { /* The Ethernet AVB descriptor definitions. */ struct ravb_desc { - __le16 ds; /* Descriptor size */ + __le16 ds; /* Descriptor size */ u8 cc; /* Content control MSBs (reserved) */ u8 die_dt; /* Descriptor interrupt enable and type */ __le32 dptr; /* Descriptor pointer */ From c79e89ecaa246c880292ba68cbe08c9c30db77e3 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Tue, 29 Jun 2021 15:40:18 +0200 Subject: [PATCH 0751/1469] RISC-V: load initrd wherever it fits into memory Requiring that initrd is loaded below RAM start + 256 MiB led to failure to boot SUSE Linux with GRUB on QEMU, cf. https://lists.gnu.org/archive/html/grub-devel/2021-06/msg00037.html Remove the constraint. Reported-by: Andreas Schwab Signed-off-by: Heinrich Schuchardt Reviewed-by: Atish Patra Acked-by: Ard Biesheuvel Fixes: d7071743db31 ("RISC-V: Add EFI stub support.") Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/efi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 6d98cd999680..7b3483ba2e84 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -27,10 +27,10 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) -/* Load initrd at enough distance from DRAM start */ +/* Load initrd anywhere in system RAM */ static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr) { - return image_addr + SZ_256M; + return ULONG_MAX; } #define alloc_screen_info(x...) (&screen_info) From 21cf377a9c40658777ecbd6242be449a19a84e44 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 21 Jul 2021 23:56:41 +0200 Subject: [PATCH 0752/1469] net: dsa: ensure linearized SKBs in case of tail taggers The function skb_put() that is used by tail taggers to make room for the DSA tag must only be called for linearized SKBS. However in case that the slave device inherited features like NETIF_F_HW_SG or NETIF_F_FRAGLIST the SKB passed to the slaves transmit function may not be linearized. Avoid those SKBs by clearing the NETIF_F_HW_SG and NETIF_F_FRAGLIST flags for tail taggers. Furthermore since the tagging protocol can be changed at runtime move the code for setting up the slaves features into dsa_slave_setup_tagger(). Suggested-by: Vladimir Oltean Signed-off-by: Lino Sanfilippo Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ffbba1e71551..532085da8d8f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave) struct dsa_slave_priv *p = netdev_priv(slave); const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; + const struct dsa_switch *ds = dp->ds; slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; @@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave) slave->needed_tailroom += master->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; + + slave->features = master->vlan_features | NETIF_F_HW_TC; + if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) + slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + slave->hw_features |= NETIF_F_HW_TC; + slave->features |= NETIF_F_LLTX; + if (slave->needed_tailroom) + slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); } static struct lock_class_key dsa_slave_netdev_xmit_lock_key; @@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port) if (slave_dev == NULL) return -ENOMEM; - slave_dev->features = master->vlan_features | NETIF_F_HW_TC; - if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) - slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - slave_dev->hw_features |= NETIF_F_HW_TC; - slave_dev->features |= NETIF_F_LLTX; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; if (!is_zero_ether_addr(port->mac)) ether_addr_copy(slave_dev->dev_addr, port->mac); From 37120f23ac8998c250573ea3247ff77426551f69 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 21 Jul 2021 23:56:42 +0200 Subject: [PATCH 0753/1469] net: dsa: tag_ksz: dont let the hardware process the layer 4 checksum If the checksum calculation is offloaded to the network device (e.g due to NETIF_F_HW_CSUM inherited from the DSA master device), the calculated layer 4 checksum is incorrect. This is since the DSA tag which is placed after the layer 4 data is considered as being part of the daa and thus errorneously included into the checksum calculation. To avoid this, always calculate the layer 4 checksum in software. Signed-off-by: Lino Sanfilippo Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/tag_ksz.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 53565f48934c..a201ccf2435d 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, u8 *addr; u16 val; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, u8 *addr; u8 *tag; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); From b0084afde27fe8a504377dee65f55bc6aa776937 Mon Sep 17 00:00:00 2001 From: Alexander Tsoy Date: Thu, 22 Jul 2021 02:56:05 +0300 Subject: [PATCH 0754/1469] ALSA: usb-audio: Add registration quirk for JBL Quantum headsets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These devices has two interfaces, but only the second interface contains the capture endpoint, thus quirk is required to delay the registration until the second interface appears. Tested-by: Jakub Fišer Signed-off-by: Alexander Tsoy Cc: Link: https://lore.kernel.org/r/20210721235605.53741-1-alexander@tsoy.me Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 8b8bee3c3dd6..e7accd87e063 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1897,6 +1897,9 @@ static const struct registration_quirk registration_quirks[] = { REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */ REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */ REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ + REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */ + REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */ + REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */ { 0 } /* terminator */ }; From 98c5b13f3a878066741a907a9d0f1f388556ed5c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 21 Jul 2021 15:33:36 -0700 Subject: [PATCH 0755/1469] net: sparx5: fix unmet dependencies warning WARNING: unmet direct dependencies detected for PHY_SPARX5_SERDES Depends on [n]: (ARCH_SPARX5 || COMPILE_TEST [=n]) && OF [=y] && HAS_IOMEM [=y] Selected by [y]: - SPARX5_SWITCH [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_MICROCHIP [=y] && NET_SWITCHDEV [=y] && HAS_IOMEM [=y] && OF [=y] Signed-off-by: Randy Dunlap Cc: Lars Povlsen Cc: Steen Hegelund Cc: UNGLinuxDriver@microchip.com Cc: "David S. Miller" Cc: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/sparx5/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index ac403d43c74c..7bdbb2d09a14 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -3,6 +3,7 @@ config SPARX5_SWITCH depends on NET_SWITCHDEV depends on HAS_IOMEM depends on OF + depends on ARCH_SPARX5 || COMPILE_TEST select PHYLINK select PHY_SPARX5_SERDES select RESET_CONTROLLER From 9d85a6f44bd5585761947f40f7821c9cd78a1bbe Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Thu, 22 Jul 2021 11:23:43 +0800 Subject: [PATCH 0756/1469] net: sched: cls_api: Fix the the wrong parameter The 4th parameter in tc_chain_notify() should be flags rather than seq. Let's change it back correctly. Fixes: 32a4f5ecd738 ("net: sched: introduce chain object to uapi") Signed-off-by: Yajun Deng Signed-off-by: David S. Miller --- net/sched/cls_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d73b5c5514a9..e3e79e9bd706 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2904,7 +2904,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; From 456a9dace42ecfcec7ce6e17c18d1985d628dcd0 Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Wed, 21 Jul 2021 10:54:29 -0700 Subject: [PATCH 0757/1469] interconnect: Zero initial BW after sync-state The initial BW values may be used by providers to enforce floors. Zero these values after sync-state so that providers know when to stop enforcing them. Fixes: b1d681d8d324 ("interconnect: Add sync state support") Signed-off-by: Mike Tipton Link: https://lore.kernel.org/r/20210721175432.2119-2-mdtipton@codeaurora.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 8a1e70e00876..945121e18b5c 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1106,6 +1106,8 @@ void icc_sync_state(struct device *dev) dev_dbg(p->dev, "interconnect provider is in synced state\n"); list_for_each_entry(n, &p->nodes, node_list) { if (n->init_avg || n->init_peak) { + n->init_avg = 0; + n->init_peak = 0; aggregate_requests(n); p->set(n, n); } From 73606ba9242f8e32023699b500b7922b4cf2993c Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Wed, 21 Jul 2021 10:54:30 -0700 Subject: [PATCH 0758/1469] interconnect: Always call pre_aggregate before aggregate The pre_aggregate callback isn't called in all cases before calling aggregate. Add the missing calls so providers can rely on consistent framework behavior. Fixes: d3703b3e255f ("interconnect: Aggregate before setting initial bandwidth") Signed-off-by: Mike Tipton Link: https://lore.kernel.org/r/20210721175432.2119-3-mdtipton@codeaurora.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 945121e18b5c..1b2c564eaa99 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -973,9 +973,14 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) } node->avg_bw = node->init_avg; node->peak_bw = node->init_peak; + + if (provider->pre_aggregate) + provider->pre_aggregate(node); + if (provider->aggregate) provider->aggregate(node, 0, node->init_avg, node->init_peak, &node->avg_bw, &node->peak_bw); + provider->set(node, node); node->avg_bw = 0; node->peak_bw = 0; From 7bbcb919e32d776ca8ddce08abb391ab92eef6a9 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 20 Jul 2021 15:45:23 +0200 Subject: [PATCH 0759/1469] drm/panel: raspberrypi-touchscreen: Prevent double-free The mipi_dsi_device allocated by mipi_dsi_device_register_full() is already free'd on release. Fixes: 2f733d6194bd ("drm/panel: Add support for the Raspberry Pi 7" Touchscreen.") Signed-off-by: Maxime Ripard Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210720134525.563936-9-maxime@cerno.tech --- drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 2229f1af2ca8..46029c5610c8 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -447,7 +447,6 @@ static int rpi_touchscreen_remove(struct i2c_client *i2c) drm_panel_remove(&ts->base); mipi_dsi_device_unregister(ts->dsi); - kfree(ts->dsi); return 0; } From 69de4421bb4c103ef42a32bafc596e23918c106f Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 21 Jul 2021 10:23:57 -0500 Subject: [PATCH 0760/1469] drm/ttm: Initialize debugfs from ttm_global_init() We create a bunch of debugfs entries as a side-effect of ttm_global_init() and then never clean them up. This isn't usually a problem because we free the whole debugfs directory on module unload. However, if the global reference count ever goes to zero and then ttm_global_init() is called again, we'll re-create those debugfs entries and debugfs will complain in dmesg that we're creating entries that already exist. This patch fixes this problem by changing the lifetime of the whole TTM debugfs directory to match that of the TTM global state. Signed-off-by: Jason Ekstrand Reviewed-by: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210721152358.2893314-6-jason@jlekstrand.net --- drivers/gpu/drm/ttm/ttm_device.c | 12 ++++++++++++ drivers/gpu/drm/ttm/ttm_module.c | 16 ---------------- 2 files changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 519deea8e39b..74e3b460132b 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -44,6 +44,8 @@ static unsigned ttm_glob_use_count; struct ttm_global ttm_glob; EXPORT_SYMBOL(ttm_glob); +struct dentry *ttm_debugfs_root; + static void ttm_global_release(void) { struct ttm_global *glob = &ttm_glob; @@ -53,6 +55,7 @@ static void ttm_global_release(void) goto out; ttm_pool_mgr_fini(); + debugfs_remove(ttm_debugfs_root); __free_page(glob->dummy_read_page); memset(glob, 0, sizeof(*glob)); @@ -73,6 +76,13 @@ static int ttm_global_init(void) si_meminfo(&si); + ttm_debugfs_root = debugfs_create_dir("ttm", NULL); + if (IS_ERR(ttm_debugfs_root)) { + ret = PTR_ERR(ttm_debugfs_root); + ttm_debugfs_root = NULL; + goto out; + } + /* Limit the number of pages in the pool to about 50% of the total * system memory. */ @@ -100,6 +110,8 @@ static int ttm_global_init(void) debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root, &glob->bo_count); out: + if (ret && ttm_debugfs_root) + debugfs_remove(ttm_debugfs_root); if (ret) --ttm_glob_use_count; mutex_unlock(&ttm_global_mutex); diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 997c458f68a9..7fcdef278c74 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -72,22 +72,6 @@ pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp) return tmp; } -struct dentry *ttm_debugfs_root; - -static int __init ttm_init(void) -{ - ttm_debugfs_root = debugfs_create_dir("ttm", NULL); - return 0; -} - -static void __exit ttm_exit(void) -{ - debugfs_remove(ttm_debugfs_root); -} - -module_init(ttm_init); -module_exit(ttm_exit); - MODULE_AUTHOR("Thomas Hellstrom, Jerome Glisse"); MODULE_DESCRIPTION("TTM memory manager subsystem (for DRM device)"); MODULE_LICENSE("GPL and additional rights"); From b9a4b57f423ff8ff9ab9b68a238bdc3e7678f723 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:04:45 +0200 Subject: [PATCH 0761/1469] ASoC: codecs: wcd938x: fix wcd module dependency With SND_SOC_ALL_CODECS=y and SND_SOC_WCD938X_SDW=m, there is a link error from a reverse dependency, since the built-in codec driver calls into the modular soundwire back-end: x86_64-linux-ld: sound/soc/codecs/wcd938x.o: in function `wcd938x_codec_free': wcd938x.c:(.text+0x2c0): undefined reference to `wcd938x_sdw_free' x86_64-linux-ld: sound/soc/codecs/wcd938x.o: in function `wcd938x_codec_hw_params': wcd938x.c:(.text+0x2f6): undefined reference to `wcd938x_sdw_hw_params' x86_64-linux-ld: sound/soc/codecs/wcd938x.o: in function `wcd938x_codec_set_sdw_stream': wcd938x.c:(.text+0x332): undefined reference to `wcd938x_sdw_set_sdw_stream' x86_64-linux-ld: sound/soc/codecs/wcd938x.o: in function `wcd938x_tx_swr_ctrl': wcd938x.c:(.text+0x23de): undefined reference to `wcd938x_swr_get_current_bank' x86_64-linux-ld: sound/soc/codecs/wcd938x.o: in function `wcd938x_bind': wcd938x.c:(.text+0x2579): undefined reference to `wcd938x_sdw_device_get' x86_64-linux-ld: wcd938x.c:(.text+0x25a1): undefined reference to `wcd938x_sdw_device_get' x86_64-linux-ld: wcd938x.c:(.text+0x262a): undefined reference to `__devm_regmap_init_sdw' Work around this using two small hacks: An added Kconfig dependency prevents the main driver from being built-in when soundwire support itself is a loadable module to allow calling devm_regmap_init_sdw(), and a Makefile trick links the wcd938x-sdw backend as built-in if needed to solve the dependency between the two modules. Fixes: 045442228868 ("ASoC: codecs: wcd938x: add audio routing and Kconfig") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210721150510.1837221-1-arnd@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 1 + sound/soc/codecs/Makefile | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 032c87637f63..d24edb01c19b 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1559,6 +1559,7 @@ config SND_SOC_WCD934X config SND_SOC_WCD938X depends on SND_SOC_WCD938X_SDW tristate + depends on SOUNDWIRE || !SOUNDWIRE config SND_SOC_WCD938X_SDW tristate "WCD9380/WCD9385 Codec - SDW" diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile index de8b83dd2c76..7bb38c370842 100644 --- a/sound/soc/codecs/Makefile +++ b/sound/soc/codecs/Makefile @@ -583,7 +583,10 @@ obj-$(CONFIG_SND_SOC_WCD_MBHC) += snd-soc-wcd-mbhc.o obj-$(CONFIG_SND_SOC_WCD9335) += snd-soc-wcd9335.o obj-$(CONFIG_SND_SOC_WCD934X) += snd-soc-wcd934x.o obj-$(CONFIG_SND_SOC_WCD938X) += snd-soc-wcd938x.o -obj-$(CONFIG_SND_SOC_WCD938X_SDW) += snd-soc-wcd938x-sdw.o +ifdef CONFIG_SND_SOC_WCD938X_SDW +# avoid link failure by forcing sdw code built-in when needed +obj-$(CONFIG_SND_SOC_WCD938X) += snd-soc-wcd938x-sdw.o +endif obj-$(CONFIG_SND_SOC_WL1273) += snd-soc-wl1273.o obj-$(CONFIG_SND_SOC_WM0010) += snd-soc-wm0010.o obj-$(CONFIG_SND_SOC_WM1250_EV1) += snd-soc-wm1250-ev1.o From 6d20bf7c020f417fdef1810a22da17c126603472 Mon Sep 17 00:00:00 2001 From: Derek Fang Date: Wed, 21 Jul 2021 21:31:21 +0800 Subject: [PATCH 0762/1469] ASoC: rt5682: Adjust headset volume button threshold Adjust the threshold of headset button volume+ to fix the wrong button detection issue with some brand headsets. Signed-off-by: Derek Fang Link: https://lore.kernel.org/r/20210721133121.12333-1-derek.fang@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5682.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index abcd6f483788..51ecaa2abcd1 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -44,6 +44,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_I2C_CTRL, 0x000f}, {RT5682_PLL2_INTERNAL, 0x8266}, {RT5682_SAR_IL_CMD_3, 0x8365}, + {RT5682_SAR_IL_CMD_6, 0x0180}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) From d00f541a49406afc2c091aac121e29b3b61480a2 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 21 Jul 2021 13:36:03 -0500 Subject: [PATCH 0763/1469] ASoC: amd: renoir: Run hibernation callbacks The registers need to be re-initialized after hibernation or microphone may be non-functional. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213793 Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20210721183603.747-2-mario.limonciello@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/renoir/rn-pci-acp3x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/amd/renoir/rn-pci-acp3x.c b/sound/soc/amd/renoir/rn-pci-acp3x.c index 19438da5dfa5..7b8040e812a1 100644 --- a/sound/soc/amd/renoir/rn-pci-acp3x.c +++ b/sound/soc/amd/renoir/rn-pci-acp3x.c @@ -382,6 +382,8 @@ static const struct dev_pm_ops rn_acp_pm = { .runtime_resume = snd_rn_acp_resume, .suspend = snd_rn_acp_suspend, .resume = snd_rn_acp_resume, + .restore = snd_rn_acp_resume, + .poweroff = snd_rn_acp_suspend, }; static void snd_rn_acp_remove(struct pci_dev *pci) From 090c57da5fd59fb59adc9d9341a77558c93b0abd Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 20 Jul 2021 22:03:48 +0200 Subject: [PATCH 0764/1469] ASoC: tlv320aic32x4: Fix TAS2505/TAS2521 processing block selection The TAS2505/TAS2521 does support only three processing block options, unlike TLV320AIC32x4 which supports 25. This is documented in TI slau472 2.5.1.2 Processing Blocks and Page 0 / Register 60: DAC Instruction Set - 0x00 / 0x3C. Limit the Processing Blocks maximum value to 3 on TAS2505/TAS2521 and select processing block PRB_P1 always, because for the configuration of teh codec implemented in this driver, this is the best quality option. Fixes: b4525b6196cd7 ("ASoC: tlv320aic32x4: add support for TAS2505") Signed-off-by: Marek Vasut Cc: Claudius Heine Cc: Mark Brown Link: https://lore.kernel.org/r/20210720200348.182139-1-marex@denx.de Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic32x4.c | 33 +++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index dcd8aeb45cb3..2e9175b37dc9 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -682,11 +682,20 @@ static int aic32x4_set_dosr(struct snd_soc_component *component, u16 dosr) static int aic32x4_set_processing_blocks(struct snd_soc_component *component, u8 r_block, u8 p_block) { - if (r_block > 18 || p_block > 25) - return -EINVAL; + struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component); - snd_soc_component_write(component, AIC32X4_ADCSPB, r_block); - snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) { + if (r_block || p_block > 3) + return -EINVAL; + + snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + } else { /* AIC32x4 */ + if (r_block > 18 || p_block > 25) + return -EINVAL; + + snd_soc_component_write(component, AIC32X4_ADCSPB, r_block); + snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + } return 0; } @@ -695,6 +704,7 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component, unsigned int sample_rate, unsigned int channels, unsigned int bit_depth) { + struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component); u8 aosr; u16 dosr; u8 adc_resource_class, dac_resource_class; @@ -721,19 +731,28 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component, adc_resource_class = 6; dac_resource_class = 8; dosr_increment = 8; - aic32x4_set_processing_blocks(component, 1, 1); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 1, 1); } else if (sample_rate <= 96000) { aosr = 64; adc_resource_class = 6; dac_resource_class = 8; dosr_increment = 4; - aic32x4_set_processing_blocks(component, 1, 9); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 1, 9); } else if (sample_rate == 192000) { aosr = 32; adc_resource_class = 3; dac_resource_class = 4; dosr_increment = 2; - aic32x4_set_processing_blocks(component, 13, 19); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 13, 19); } else { dev_err(component->dev, "Sampling rate not supported\n"); return -EINVAL; From 1d5ccab95f06675a269f4cb223a1e3f6d1ebef42 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 21 Jul 2021 11:53:21 +0200 Subject: [PATCH 0765/1469] spi: spi-mux: Add module info needed for autoloading MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the spi device table udev can autoload the spi-mux module in the presence of an spi-mux device. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210721095321.2165453-1-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi-mux.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c index 37dfc6e82804..9708b7827ff7 100644 --- a/drivers/spi/spi-mux.c +++ b/drivers/spi/spi-mux.c @@ -167,10 +167,17 @@ err_put_ctlr: return ret; } +static const struct spi_device_id spi_mux_id[] = { + { "spi-mux" }, + { } +}; +MODULE_DEVICE_TABLE(spi, spi_mux_id); + static const struct of_device_id spi_mux_of_match[] = { { .compatible = "spi-mux" }, { } }; +MODULE_DEVICE_TABLE(of, spi_mux_of_match); static struct spi_driver spi_mux_driver = { .probe = spi_mux_probe, @@ -178,6 +185,7 @@ static struct spi_driver spi_mux_driver = { .name = "spi-mux", .of_match_table = spi_mux_of_match, }, + .id_table = spi_mux_id, }; module_spi_driver(spi_mux_driver); From 7aaa0f311e2df2704fa8ddb8ed681a3b5841d0bf Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 22 Jul 2021 15:15:51 +0300 Subject: [PATCH 0766/1469] dpaa2-switch: seed the buffer pool after allocating the swp Any interraction with the buffer pool (seeding a buffer, acquire one) is made through a software portal (SWP, a DPIO object). There are circumstances where the dpaa2-switch driver probes on a DPSW before any DPIO devices have been probed. In this case, seeding of the buffer pool will lead to a panic since no SWPs are initialized. To fix this, seed the buffer pool after making sure that the software portals have been probed and are ready to be used. Fixes: 0b1b71370458 ("staging: dpaa2-switch: handle Rx path on control interface") Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index f3d12d0714fb..68b78642c045 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2770,32 +2770,32 @@ static int dpaa2_switch_ctrl_if_setup(struct ethsw_core *ethsw) if (err) return err; - err = dpaa2_switch_seed_bp(ethsw); - if (err) - goto err_free_dpbp; - err = dpaa2_switch_alloc_rings(ethsw); if (err) - goto err_drain_dpbp; + goto err_free_dpbp; err = dpaa2_switch_setup_dpio(ethsw); if (err) goto err_destroy_rings; + err = dpaa2_switch_seed_bp(ethsw); + if (err) + goto err_deregister_dpio; + err = dpsw_ctrl_if_enable(ethsw->mc_io, 0, ethsw->dpsw_handle); if (err) { dev_err(ethsw->dev, "dpsw_ctrl_if_enable err %d\n", err); - goto err_deregister_dpio; + goto err_drain_dpbp; } return 0; +err_drain_dpbp: + dpaa2_switch_drain_bp(ethsw); err_deregister_dpio: dpaa2_switch_free_dpio(ethsw); err_destroy_rings: dpaa2_switch_destroy_rings(ethsw); -err_drain_dpbp: - dpaa2_switch_drain_bp(ethsw); err_free_dpbp: dpaa2_switch_free_dpbp(ethsw); From 9acc8103ab594f72250788cb45a43427f36d685d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 6 Jul 2021 15:41:15 +0100 Subject: [PATCH 0767/1469] btrfs: fix unpersisted i_size on fsync after expanding truncate If we have an inode that does not have the full sync flag set, was changed in the current transaction, then it is logged while logging some other inode (like its parent directory for example), its i_size is increased by a truncate operation, the log is synced through an fsync of some other inode and then finally we explicitly call fsync on our inode, the new i_size is not persisted. The following example shows how to trigger it, with comments explaining how and why the issue happens: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ touch /mnt/foo $ xfs_io -f -c "pwrite -S 0xab 0 1M" /mnt/bar $ sync # Fsync bar, this will be a noop since the file has not yet been # modified in the current transaction. The goal here is to clear # BTRFS_INODE_NEEDS_FULL_SYNC from the inode's runtime flags. $ xfs_io -c "fsync" /mnt/bar # Now rename both files, without changing their parent directory. $ mv /mnt/bar /mnt/bar2 $ mv /mnt/foo /mnt/foo2 # Increase the size of bar2 with a truncate operation. $ xfs_io -c "truncate 2M" /mnt/bar2 # Now fsync foo2, this results in logging its parent inode (the root # directory), and logging the parent results in logging the inode of # file bar2 (its inode item and the new name). The inode of file bar2 # is logged with an i_size of 0 bytes since it's logged in # LOG_INODE_EXISTS mode, meaning we are only logging its names (and # xattrs if it had any) and the i_size of the inode will not be changed # when the log is replayed. $ xfs_io -c "fsync" /mnt/foo2 # Now explicitly fsync bar2. This resulted in doing nothing, not # logging the inode with the new i_size of 2M and the hole from file # offset 1M to 2M. Because the inode did not have the flag # BTRFS_INODE_NEEDS_FULL_SYNC set, when it was logged through the # fsync of file foo2, its last_log_commit field was updated, # resulting in this explicit of file bar2 not doing anything. $ xfs_io -c "fsync" /mnt/bar2 # File bar2 content and size before a power failure. $ od -A d -t x1 /mnt/bar2 0000000 ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab * 1048576 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 2097152 # Mount the filesystem to replay the log. $ mount /dev/sdc /mnt # Read the file again, should have the same content and size as before # the power failure happened, but it doesn't, i_size is still at 1M. $ od -A d -t x1 /mnt/bar2 0000000 ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab * 1048576 This started to happen after commit 209ecbb8585bf6 ("btrfs: remove stale comment and logic from btrfs_inode_in_log()"), since btrfs_inode_in_log() no longer checks if the inode's list of modified extents is not empty. However, checking that list is not the right way to address this case and the check was added long time ago in commit 125c4cf9f37c98 ("Btrfs: set inode's logged_trans/last_log_commit after ranged fsync") for a different purpose, to address consecutive ranged fsyncs. The reason that checking for the list emptiness makes this test pass is because during an expanding truncate we create an extent map to represent a hole from the old i_size to the new i_size, and add that extent map to the list of modified extents in the inode. However if we are low on available memory and we can not allocate a new extent map, then we don't treat it as an error and just set the full sync flag on the inode, so that the next fsync does not rely on the list of modified extents - so checking for the emptiness of the list to decide if the inode needs to be logged is not reliable, and results in not logging the inode if it was not possible to allocate the extent map for the hole. Fix this by ensuring that if we are only logging that an inode exists (inode item, names/references and xattrs), we don't update the inode's last_log_commit even if it does not have the full sync runtime flag set. A test case for fstests follows soon. CC: stable@vger.kernel.org # 5.13+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index dc6eb088d73e..9fd0348be7f5 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5526,16 +5526,29 @@ log_extents: spin_lock(&inode->lock); inode->logged_trans = trans->transid; /* - * Don't update last_log_commit if we logged that an inode exists - * after it was loaded to memory (full_sync bit set). - * This is to prevent data loss when we do a write to the inode, - * then the inode gets evicted after all delalloc was flushed, - * then we log it exists (due to a rename for example) and then - * fsync it. This last fsync would do nothing (not logging the - * extents previously written). + * Don't update last_log_commit if we logged that an inode exists. + * We do this for two reasons: + * + * 1) We might have had buffered writes to this inode that were + * flushed and had their ordered extents completed in this + * transaction, but we did not previously log the inode with + * LOG_INODE_ALL. Later the inode was evicted and after that + * it was loaded again and this LOG_INODE_EXISTS log operation + * happened. We must make sure that if an explicit fsync against + * the inode is performed later, it logs the new extents, an + * updated inode item, etc, and syncs the log. The same logic + * applies to direct IO writes instead of buffered writes. + * + * 2) When we log the inode with LOG_INODE_EXISTS, its inode item + * is logged with an i_size of 0 or whatever value was logged + * before. If later the i_size of the inode is increased by a + * truncate operation, the log is synced through an fsync of + * some other inode and then finally an explicit fsync against + * this inode is made, we must make sure this fsync logs the + * inode with the new i_size, the hole between old i_size and + * the new i_size, and syncs the log. */ - if (inode_only != LOG_INODE_EXISTS || - !test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) + if (inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); } From 16a200f66ede3f9afa2e51d90ade017aaa18d213 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Sun, 4 Jul 2021 19:14:39 +0800 Subject: [PATCH 0768/1469] btrfs: check for missing device in btrfs_trim_fs A fstrim on a degraded raid1 can trigger the following null pointer dereference: BTRFS info (device loop0): allowing degraded mounts BTRFS info (device loop0): disk space caching is enabled BTRFS info (device loop0): has skinny extents BTRFS warning (device loop0): devid 2 uuid 97ac16f7-e14d-4db1-95bc-3d489b424adb is missing BTRFS warning (device loop0): devid 2 uuid 97ac16f7-e14d-4db1-95bc-3d489b424adb is missing BTRFS info (device loop0): enabling ssd optimizations BUG: kernel NULL pointer dereference, address: 0000000000000620 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 0 PID: 4574 Comm: fstrim Not tainted 5.13.0-rc7+ #31 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 RIP: 0010:btrfs_trim_fs+0x199/0x4a0 [btrfs] RSP: 0018:ffff959541797d28 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff946f84eca508 RCX: a7a67937adff8608 RDX: ffff946e8122d000 RSI: 0000000000000000 RDI: ffffffffc02fdbf0 RBP: ffff946ea4615000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: ffff946e8122d960 R12: 0000000000000000 R13: ffff959541797db8 R14: ffff946e8122d000 R15: ffff959541797db8 FS: 00007f55917a5080(0000) GS:ffff946f9bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000620 CR3: 000000002d2c8001 CR4: 00000000000706f0 Call Trace: btrfs_ioctl_fitrim+0x167/0x260 [btrfs] btrfs_ioctl+0x1c00/0x2fe0 [btrfs] ? selinux_file_ioctl+0x140/0x240 ? syscall_trace_enter.constprop.0+0x188/0x240 ? __x64_sys_ioctl+0x83/0xb0 __x64_sys_ioctl+0x83/0xb0 Reproducer: $ mkfs.btrfs -fq -d raid1 -m raid1 /dev/loop0 /dev/loop1 $ mount /dev/loop0 /btrfs $ umount /btrfs $ btrfs dev scan --forget $ mount -o degraded /dev/loop0 /btrfs $ fstrim /btrfs The reason is we call btrfs_trim_free_extents() for the missing device, which uses device->bdev (NULL for missing device) to find if the device supports discard. Fix is to check if the device is missing before calling btrfs_trim_free_extents(). CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d296483d148f..268ce58d4569 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6019,6 +6019,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) + continue; + ret = btrfs_trim_free_extents(device, &group_trimmed); if (ret) { dev_failed++; From 8949b9a114019b03fbd0d03d65b8647cba4feef3 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 21 Jul 2021 17:31:48 +0100 Subject: [PATCH 0769/1469] btrfs: fix lock inversion problem when doing qgroup extent tracing At btrfs_qgroup_trace_extent_post() we call btrfs_find_all_roots() with a NULL value as the transaction handle argument, which makes that function take the commit_root_sem semaphore, which is necessary when we don't hold a transaction handle or any other mechanism to prevent a transaction commit from wiping out commit roots. However btrfs_qgroup_trace_extent_post() can be called in a context where we are holding a write lock on an extent buffer from a subvolume tree, namely from btrfs_truncate_inode_items(), called either during truncate or unlink operations. In this case we end up with a lock inversion problem because the commit_root_sem is a higher level lock, always supposed to be acquired before locking any extent buffer. Lockdep detects this lock inversion problem since we switched the extent buffer locks from custom locks to semaphores, and when running btrfs/158 from fstests, it reported the following trace: [ 9057.626435] ====================================================== [ 9057.627541] WARNING: possible circular locking dependency detected [ 9057.628334] 5.14.0-rc2-btrfs-next-93 #1 Not tainted [ 9057.628961] ------------------------------------------------------ [ 9057.629867] kworker/u16:4/30781 is trying to acquire lock: [ 9057.630824] ffff8e2590f58760 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.632542] but task is already holding lock: [ 9057.633551] ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs] [ 9057.635255] which lock already depends on the new lock. [ 9057.636292] the existing dependency chain (in reverse order) is: [ 9057.637240] -> #1 (&fs_info->commit_root_sem){++++}-{3:3}: [ 9057.638138] down_read+0x46/0x140 [ 9057.638648] btrfs_find_all_roots+0x41/0x80 [btrfs] [ 9057.639398] btrfs_qgroup_trace_extent_post+0x37/0x70 [btrfs] [ 9057.640283] btrfs_add_delayed_data_ref+0x418/0x490 [btrfs] [ 9057.641114] btrfs_free_extent+0x35/0xb0 [btrfs] [ 9057.641819] btrfs_truncate_inode_items+0x424/0xf70 [btrfs] [ 9057.642643] btrfs_evict_inode+0x454/0x4f0 [btrfs] [ 9057.643418] evict+0xcf/0x1d0 [ 9057.643895] do_unlinkat+0x1e9/0x300 [ 9057.644525] do_syscall_64+0x3b/0xc0 [ 9057.645110] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 9057.645835] -> #0 (btrfs-tree-00){++++}-{3:3}: [ 9057.646600] __lock_acquire+0x130e/0x2210 [ 9057.647248] lock_acquire+0xd7/0x310 [ 9057.647773] down_read_nested+0x4b/0x140 [ 9057.648350] __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.649175] btrfs_read_lock_root_node+0x31/0x40 [btrfs] [ 9057.650010] btrfs_search_slot+0x537/0xc00 [btrfs] [ 9057.650849] scrub_print_warning_inode+0x89/0x370 [btrfs] [ 9057.651733] iterate_extent_inodes+0x1e3/0x280 [btrfs] [ 9057.652501] scrub_print_warning+0x15d/0x2f0 [btrfs] [ 9057.653264] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs] [ 9057.654295] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs] [ 9057.655111] btrfs_work_helper+0xf8/0x400 [btrfs] [ 9057.655831] process_one_work+0x247/0x5a0 [ 9057.656425] worker_thread+0x55/0x3c0 [ 9057.656993] kthread+0x155/0x180 [ 9057.657494] ret_from_fork+0x22/0x30 [ 9057.658030] other info that might help us debug this: [ 9057.659064] Possible unsafe locking scenario: [ 9057.659824] CPU0 CPU1 [ 9057.660402] ---- ---- [ 9057.660988] lock(&fs_info->commit_root_sem); [ 9057.661581] lock(btrfs-tree-00); [ 9057.662348] lock(&fs_info->commit_root_sem); [ 9057.663254] lock(btrfs-tree-00); [ 9057.663690] *** DEADLOCK *** [ 9057.664437] 4 locks held by kworker/u16:4/30781: [ 9057.665023] #0: ffff8e25922a1148 ((wq_completion)btrfs-scrub){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0 [ 9057.666260] #1: ffffabb3451ffe70 ((work_completion)(&work->normal_work)){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0 [ 9057.667639] #2: ffff8e25922da198 (&ret->mutex){+.+.}-{3:3}, at: scrub_handle_errored_block.isra.0+0x5d2/0x1640 [btrfs] [ 9057.669017] #3: ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs] [ 9057.670408] stack backtrace: [ 9057.670976] CPU: 7 PID: 30781 Comm: kworker/u16:4 Not tainted 5.14.0-rc2-btrfs-next-93 #1 [ 9057.672030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 9057.673492] Workqueue: btrfs-scrub btrfs_work_helper [btrfs] [ 9057.674258] Call Trace: [ 9057.674588] dump_stack_lvl+0x57/0x72 [ 9057.675083] check_noncircular+0xf3/0x110 [ 9057.675611] __lock_acquire+0x130e/0x2210 [ 9057.676132] lock_acquire+0xd7/0x310 [ 9057.676605] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.677313] ? lock_is_held_type+0xe8/0x140 [ 9057.677849] down_read_nested+0x4b/0x140 [ 9057.678349] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.679068] __btrfs_tree_read_lock+0x24/0x110 [btrfs] [ 9057.679760] btrfs_read_lock_root_node+0x31/0x40 [btrfs] [ 9057.680458] btrfs_search_slot+0x537/0xc00 [btrfs] [ 9057.681083] ? _raw_spin_unlock+0x29/0x40 [ 9057.681594] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs] [ 9057.682336] scrub_print_warning_inode+0x89/0x370 [btrfs] [ 9057.683058] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs] [ 9057.683834] ? scrub_write_block_to_dev_replace+0xb0/0xb0 [btrfs] [ 9057.684632] iterate_extent_inodes+0x1e3/0x280 [btrfs] [ 9057.685316] scrub_print_warning+0x15d/0x2f0 [btrfs] [ 9057.685977] ? ___ratelimit+0xa4/0x110 [ 9057.686460] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs] [ 9057.687316] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs] [ 9057.688021] btrfs_work_helper+0xf8/0x400 [btrfs] [ 9057.688649] ? lock_is_held_type+0xe8/0x140 [ 9057.689180] process_one_work+0x247/0x5a0 [ 9057.689696] worker_thread+0x55/0x3c0 [ 9057.690175] ? process_one_work+0x5a0/0x5a0 [ 9057.690731] kthread+0x155/0x180 [ 9057.691158] ? set_kthread_struct+0x40/0x40 [ 9057.691697] ret_from_fork+0x22/0x30 Fix this by making btrfs_find_all_roots() never attempt to lock the commit_root_sem when it is called from btrfs_qgroup_trace_extent_post(). We can't just pass a non-NULL transaction handle to btrfs_find_all_roots() from btrfs_qgroup_trace_extent_post(), because that would make backref lookup not use commit roots and acquire read locks on extent buffers, and therefore could deadlock when btrfs_qgroup_trace_extent_post() is called from the btrfs_truncate_inode_items() code path which has acquired a write lock on an extent buffer of the subvolume btree. CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 6 +++--- fs/btrfs/backref.h | 3 ++- fs/btrfs/delayed-ref.c | 4 ++-- fs/btrfs/qgroup.c | 38 +++++++++++++++++++++++++++-------- fs/btrfs/qgroup.h | 2 +- fs/btrfs/tests/qgroup-tests.c | 20 +++++++++--------- 6 files changed, 48 insertions(+), 25 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 7a8a2fc19533..78b202d198b8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1488,15 +1488,15 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, int btrfs_find_all_roots(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 time_seq, struct ulist **roots, - bool ignore_offset) + bool ignore_offset, bool skip_commit_root_sem) { int ret; - if (!trans) + if (!trans && !skip_commit_root_sem) down_read(&fs_info->commit_root_sem); ret = btrfs_find_all_roots_safe(trans, fs_info, bytenr, time_seq, roots, ignore_offset); - if (!trans) + if (!trans && !skip_commit_root_sem) up_read(&fs_info->commit_root_sem); return ret; } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 17abde7f794c..ff5f07f9940b 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -47,7 +47,8 @@ int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, const u64 *extent_item_pos, bool ignore_offset); int btrfs_find_all_roots(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, - u64 time_seq, struct ulist **roots, bool ignore_offset); + u64 time_seq, struct ulist **roots, bool ignore_offset, + bool skip_commit_root_sem); char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, u32 name_len, unsigned long name_off, struct extent_buffer *eb_in, u64 parent, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 06bc842ecdb3..ca848b183474 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -974,7 +974,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref); if (qrecord_inserted) - btrfs_qgroup_trace_extent_post(fs_info, record); + btrfs_qgroup_trace_extent_post(trans, record); return 0; } @@ -1069,7 +1069,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, if (qrecord_inserted) - return btrfs_qgroup_trace_extent_post(fs_info, record); + return btrfs_qgroup_trace_extent_post(trans, record); return 0; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 07ec06d4e972..0fa121171ca1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1704,17 +1704,39 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, return 0; } -int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, +int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans, struct btrfs_qgroup_extent_record *qrecord) { struct ulist *old_root; u64 bytenr = qrecord->bytenr; int ret; - ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false); + /* + * We are always called in a context where we are already holding a + * transaction handle. Often we are called when adding a data delayed + * reference from btrfs_truncate_inode_items() (truncating or unlinking), + * in which case we will be holding a write lock on extent buffer from a + * subvolume tree. In this case we can't allow btrfs_find_all_roots() to + * acquire fs_info->commit_root_sem, because that is a higher level lock + * that must be acquired before locking any extent buffers. + * + * So we want btrfs_find_all_roots() to not acquire the commit_root_sem + * but we can't pass it a non-NULL transaction handle, because otherwise + * it would not use commit roots and would lock extent buffers, causing + * a deadlock if it ends up trying to read lock the same extent buffer + * that was previously write locked at btrfs_truncate_inode_items(). + * + * So pass a NULL transaction handle to btrfs_find_all_roots() and + * explicitly tell it to not acquire the commit_root_sem - if we are + * holding a transaction handle we don't need its protection. + */ + ASSERT(trans != NULL); + + ret = btrfs_find_all_roots(NULL, trans->fs_info, bytenr, 0, &old_root, + false, true); if (ret < 0) { - fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; - btrfs_warn(fs_info, + trans->fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_warn(trans->fs_info, "error accounting new delayed refs extent (err code: %d), quota inconsistent", ret); return 0; @@ -1758,7 +1780,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, kfree(record); return 0; } - return btrfs_qgroup_trace_extent_post(fs_info, record); + return btrfs_qgroup_trace_extent_post(trans, record); } int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, @@ -2629,7 +2651,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) /* Search commit root to find old_roots */ ret = btrfs_find_all_roots(NULL, fs_info, record->bytenr, 0, - &record->old_roots, false); + &record->old_roots, false, false); if (ret < 0) goto cleanup; } @@ -2645,7 +2667,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) * current root. It's safe inside commit_transaction(). */ ret = btrfs_find_all_roots(trans, fs_info, - record->bytenr, BTRFS_SEQ_LAST, &new_roots, false); + record->bytenr, BTRFS_SEQ_LAST, &new_roots, false, false); if (ret < 0) goto cleanup; if (qgroup_to_skip) { @@ -3179,7 +3201,7 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans, num_bytes = found.offset; ret = btrfs_find_all_roots(NULL, fs_info, found.objectid, 0, - &roots, false); + &roots, false, false); if (ret < 0) goto out; /* For rescan, just pass old_roots as NULL */ diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 7283e4f549af..880e9df0dac1 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -298,7 +298,7 @@ int btrfs_qgroup_trace_extent_nolock( * using current root, then we can move all expensive backref walk out of * transaction committing, but not now as qgroup accounting will be wrong again. */ -int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, +int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans, struct btrfs_qgroup_extent_record *qrecord); /* diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index f3137285a9e2..98b5aaba46f1 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -224,7 +224,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root, * quota. */ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, - false); + false, false); if (ret) { ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); @@ -237,7 +237,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return ret; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, - false); + false, false); if (ret) { ulist_free(old_roots); ulist_free(new_roots); @@ -261,7 +261,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root, new_roots = NULL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, - false); + false, false); if (ret) { ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); @@ -273,7 +273,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return -EINVAL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, - false); + false, false); if (ret) { ulist_free(old_roots); ulist_free(new_roots); @@ -325,7 +325,7 @@ static int test_multiple_refs(struct btrfs_root *root, } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, - false); + false, false); if (ret) { ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); @@ -338,7 +338,7 @@ static int test_multiple_refs(struct btrfs_root *root, return ret; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, - false); + false, false); if (ret) { ulist_free(old_roots); ulist_free(new_roots); @@ -360,7 +360,7 @@ static int test_multiple_refs(struct btrfs_root *root, } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, - false); + false, false); if (ret) { ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); @@ -373,7 +373,7 @@ static int test_multiple_refs(struct btrfs_root *root, return ret; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, - false); + false, false); if (ret) { ulist_free(old_roots); ulist_free(new_roots); @@ -401,7 +401,7 @@ static int test_multiple_refs(struct btrfs_root *root, } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, - false); + false, false); if (ret) { ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); @@ -414,7 +414,7 @@ static int test_multiple_refs(struct btrfs_root *root, return ret; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, - false); + false, false); if (ret) { ulist_free(old_roots); ulist_free(new_roots); From c7c3a6dcb1efd52949acc1e640be9aad1206a13a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 22 Jul 2021 09:53:59 +0200 Subject: [PATCH 0770/1469] btrfs: store a block_device in struct btrfs_ordered_extent Store the block device instead of the gendisk in the btrfs_ordered_extent structure instead of acquiring a reference to it later. Note: this is from series removing bdgrab/bdput, btrfs is one of the last users. Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- fs/btrfs/ordered-data.c | 2 -- fs/btrfs/ordered-data.h | 3 +-- fs/btrfs/zoned.c | 12 ++++-------- 4 files changed, 6 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8f60314c36c5..0117d867ecf8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2992,7 +2992,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } - if (ordered_extent->disk) + if (ordered_extent->bdev) btrfs_rewrite_logical_zoned(ordered_extent); btrfs_free_io_failure_record(inode, start, end); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 6eb41b7c0c84..5c0f8481e25e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -190,8 +190,6 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset entry->truncated_len = (u64)-1; entry->qgroup_rsv = ret; entry->physical = (u64)-1; - entry->disk = NULL; - entry->partno = (u8)-1; ASSERT(type == BTRFS_ORDERED_REGULAR || type == BTRFS_ORDERED_NOCOW || diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 566472004edd..b2d88aba8420 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -145,8 +145,7 @@ struct btrfs_ordered_extent { * command in a workqueue context */ u64 physical; - struct gendisk *disk; - u8 partno; + struct block_device *bdev; }; /* diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 297c0b1c0634..907c2cc45c9c 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1349,8 +1349,7 @@ void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, return; ordered->physical = physical; - ordered->disk = bio->bi_bdev->bd_disk; - ordered->partno = bio->bi_bdev->bd_partno; + ordered->bdev = bio->bi_bdev; btrfs_put_ordered_extent(ordered); } @@ -1362,18 +1361,16 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) struct extent_map_tree *em_tree; struct extent_map *em; struct btrfs_ordered_sum *sum; - struct block_device *bdev; u64 orig_logical = ordered->disk_bytenr; u64 *logical = NULL; int nr, stripe_len; /* Zoned devices should not have partitions. So, we can assume it is 0 */ - ASSERT(ordered->partno == 0); - bdev = bdgrab(ordered->disk->part0); - if (WARN_ON(!bdev)) + ASSERT(!bdev_is_partition(ordered->bdev)); + if (WARN_ON(!ordered->bdev)) return; - if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev, + if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, ordered->bdev, ordered->physical, &logical, &nr, &stripe_len))) goto out; @@ -1402,7 +1399,6 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) out: kfree(logical); - bdput(bdev); } bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, From 6b57ba3243c5774e5b2a0984e8ca0d34a126ac6b Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Mon, 12 Jul 2021 17:46:57 +0800 Subject: [PATCH 0771/1469] drm/mediatek: mtk-dpi: Set out_fmt from config if not the last bridge atomic_get_output_bus_fmts() is only called when the bridge is the last element in the bridge chain. If mtk-dpi is not the last bridge, the format of output_bus_cfg is MEDIA_BUS_FMT_FIXED, and mtk_dpi_dual_edge() will fail to write correct value to regs. Fixes: ec8747c52434 ("drm/mediatek: dpi: Add bus format negotiation") Signed-off-by: Hsin-Yi Wang Signed-off-by: Chun-Kuang Hu --- drivers/gpu/drm/mediatek/mtk_dpi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index a2eca1f66984..e94738fe4db8 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -610,6 +610,10 @@ static int mtk_dpi_bridge_atomic_check(struct drm_bridge *bridge, out_bus_format = bridge_state->output_bus_cfg.format; + if (out_bus_format == MEDIA_BUS_FMT_FIXED) + if (dpi->conf->num_output_fmts) + out_bus_format = dpi->conf->output_fmts[0]; + dev_dbg(dpi->dev, "input format 0x%04x, output format 0x%04x\n", bridge_state->input_bus_cfg.format, bridge_state->output_bus_cfg.format); From 1a64a7aff8da352c9419de3d5c34343682916411 Mon Sep 17 00:00:00 2001 From: "jason-jh.lin" Date: Thu, 22 Jul 2021 09:47:43 +0800 Subject: [PATCH 0772/1469] drm/mediatek: Fix cursor plane no update The cursor plane should use the current plane state in atomic_async_update because it would not be the new plane state in the global atomic state since _swap_state happened when those hook are run. Fix cursor plane issue by below modification: 1. Remove plane_helper_funcs->atomic_update(plane, state) in mtk_drm_crtc_async_update. 2. Add mtk_drm_update_new_state in to mtk_plane_atomic_async_update to update the cursor plane by current plane state hook and update others plane by the new_state. Fixes: 37418bf14c13 ("drm: Use state helper instead of the plane state pointer") Signed-off-by: jason-jh.lin Tested-by: Enric Balletbo i Serra Signed-off-by: Chun-Kuang Hu --- drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 3 -- drivers/gpu/drm/mediatek/mtk_drm_plane.c | 60 ++++++++++++++---------- 2 files changed, 34 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 474efb844249..735efe79f075 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -532,13 +532,10 @@ void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *state) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - const struct drm_plane_helper_funcs *plane_helper_funcs = - plane->helper_private; if (!mtk_crtc->enabled) return; - plane_helper_funcs->atomic_update(plane, state); mtk_drm_crtc_update_config(mtk_crtc, false); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index b5582dcf564c..e6dcb34d3052 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -110,6 +110,35 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane, true, true); } +static void mtk_plane_update_new_state(struct drm_plane_state *new_state, + struct mtk_plane_state *mtk_plane_state) +{ + struct drm_framebuffer *fb = new_state->fb; + struct drm_gem_object *gem; + struct mtk_drm_gem_obj *mtk_gem; + unsigned int pitch, format; + dma_addr_t addr; + + gem = fb->obj[0]; + mtk_gem = to_mtk_gem_obj(gem); + addr = mtk_gem->dma_addr; + pitch = fb->pitches[0]; + format = fb->format->format; + + addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; + addr += (new_state->src.y1 >> 16) * pitch; + + mtk_plane_state->pending.enable = true; + mtk_plane_state->pending.pitch = pitch; + mtk_plane_state->pending.format = format; + mtk_plane_state->pending.addr = addr; + mtk_plane_state->pending.x = new_state->dst.x1; + mtk_plane_state->pending.y = new_state->dst.y1; + mtk_plane_state->pending.width = drm_rect_width(&new_state->dst); + mtk_plane_state->pending.height = drm_rect_height(&new_state->dst); + mtk_plane_state->pending.rotation = new_state->rotation; +} + static void mtk_plane_atomic_async_update(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -126,8 +155,10 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_h = new_state->src_h; plane->state->src_w = new_state->src_w; swap(plane->state->fb, new_state->fb); - new_plane_state->pending.async_dirty = true; + mtk_plane_update_new_state(new_state, new_plane_state); + wmb(); /* Make sure the above parameters are set before update */ + new_plane_state->pending.async_dirty = true; mtk_drm_crtc_async_update(new_state->crtc, plane, state); } @@ -189,14 +220,8 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(new_state); - struct drm_crtc *crtc = new_state->crtc; - struct drm_framebuffer *fb = new_state->fb; - struct drm_gem_object *gem; - struct mtk_drm_gem_obj *mtk_gem; - unsigned int pitch, format; - dma_addr_t addr; - if (!crtc || WARN_ON(!fb)) + if (!new_state->crtc || WARN_ON(!new_state->fb)) return; if (!new_state->visible) { @@ -204,24 +229,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, return; } - gem = fb->obj[0]; - mtk_gem = to_mtk_gem_obj(gem); - addr = mtk_gem->dma_addr; - pitch = fb->pitches[0]; - format = fb->format->format; - - addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; - addr += (new_state->src.y1 >> 16) * pitch; - - mtk_plane_state->pending.enable = true; - mtk_plane_state->pending.pitch = pitch; - mtk_plane_state->pending.format = format; - mtk_plane_state->pending.addr = addr; - mtk_plane_state->pending.x = new_state->dst.x1; - mtk_plane_state->pending.y = new_state->dst.y1; - mtk_plane_state->pending.width = drm_rect_width(&new_state->dst); - mtk_plane_state->pending.height = drm_rect_height(&new_state->dst); - mtk_plane_state->pending.rotation = new_state->rotation; + mtk_plane_update_new_state(new_state, mtk_plane_state); wmb(); /* Make sure the above parameters are set before update */ mtk_plane_state->pending.dirty = true; } From 5434d0dc56bce4510109a431a7eb71ec5131ef0f Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Thu, 22 Jul 2021 18:33:15 +0530 Subject: [PATCH 0773/1469] ASoC: amd: enable stop_dma_first flag for cz_dai_7219_98357 dai link DMA driver stop sequence should be invoked first before invoking I2S controller driver stop sequence for Stoneyridge platform. Enable stop_dma_first flag for cz_dai_7219_98357 dai link structure. Signed-off-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20210722130328.23796-1-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- sound/soc/amd/acp-da7219-max98357a.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c index 9449fb40a956..3c60c5f96dcb 100644 --- a/sound/soc/amd/acp-da7219-max98357a.c +++ b/sound/soc/amd/acp-da7219-max98357a.c @@ -525,6 +525,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { | SND_SOC_DAIFMT_CBM_CFM, .init = cz_da7219_init, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_da7219_play_ops, SND_SOC_DAILINK_REG(designware1, dlgs, platform), }, @@ -534,6 +535,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_da7219_cap_ops, SND_SOC_DAILINK_REG(designware2, dlgs, platform), }, @@ -543,6 +545,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_max_play_ops, SND_SOC_DAILINK_REG(designware3, mx, platform), }, @@ -553,6 +556,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_dmic0_cap_ops, SND_SOC_DAILINK_REG(designware3, adau, platform), }, @@ -563,6 +567,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_dmic1_cap_ops, SND_SOC_DAILINK_REG(designware2, adau, platform), }, From 8311ee2164c5cd1b63a601ea366f540eae89f10e Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Tue, 20 Jul 2021 18:01:16 +0800 Subject: [PATCH 0774/1469] spi: meson-spicc: fix memory leak in meson_spicc_remove In meson_spicc_probe, the error handling code needs to clean up master by calling spi_master_put, but the remove function does not have this function call. This will lead to memory leak of spicc->master. Reported-by: Dongliang Mu Fixes: 454fa271bc4e("spi: Add Meson SPICC driver") Signed-off-by: Dongliang Mu Link: https://lore.kernel.org/r/20210720100116.1438974-1-mudongliangabcd@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-meson-spicc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index b2c4621db34d..c208efeadd18 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -785,6 +785,8 @@ static int meson_spicc_remove(struct platform_device *pdev) clk_disable_unprepare(spicc->core); clk_disable_unprepare(spicc->pclk); + spi_master_put(spicc->master); + return 0; } From e09f2ab8eecc6dcbd7013a1303cbe56b00dc9fb0 Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Thu, 22 Jul 2021 15:48:45 +0200 Subject: [PATCH 0775/1469] spi: update modalias_show after of_device_uevent_modalias support Commit 3ce6c9e2617e ("spi: add of_device_uevent_modalias support") is incomplete, as it didn't update the modalias_show function to generate the of: modalias string if available. Fixes: 3ce6c9e2617e ("spi: add of_device_uevent_modalias support") Signed-off-by: Andreas Schwab Link: https://lore.kernel.org/r/mvmwnpi4fya.fsf@suse.de Signed-off-by: Mark Brown --- drivers/spi/spi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 35928d0843d9..397dd2959bfd 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -58,6 +58,10 @@ modalias_show(struct device *dev, struct device_attribute *a, char *buf) const struct spi_device *spi = to_spi_device(dev); int len; + len = of_device_modalias(dev, buf, PAGE_SIZE); + if (len != -ENODEV) + return len; + len = acpi_device_modalias(dev, buf, PAGE_SIZE - 1); if (len != -ENODEV) return len; From 67f0d6d9883c13174669f88adac4f0ee656cc16a Mon Sep 17 00:00:00 2001 From: Haoran Luo Date: Wed, 21 Jul 2021 14:12:07 +0000 Subject: [PATCH 0776/1469] tracing: Fix bug in rb_per_cpu_empty() that might cause deadloop. The "rb_per_cpu_empty()" misinterpret the condition (as not-empty) when "head_page" and "commit_page" of "struct ring_buffer_per_cpu" points to the same buffer page, whose "buffer_data_page" is empty and "read" field is non-zero. An error scenario could be constructed as followed (kernel perspective): 1. All pages in the buffer has been accessed by reader(s) so that all of them will have non-zero "read" field. 2. Read and clear all buffer pages so that "rb_num_of_entries()" will return 0 rendering there's no more data to read. It is also required that the "read_page", "commit_page" and "tail_page" points to the same page, while "head_page" is the next page of them. 3. Invoke "ring_buffer_lock_reserve()" with large enough "length" so that it shot pass the end of current tail buffer page. Now the "head_page", "commit_page" and "tail_page" points to the same page. 4. Discard current event with "ring_buffer_discard_commit()", so that "head_page", "commit_page" and "tail_page" points to a page whose buffer data page is now empty. When the error scenario has been constructed, "tracing_read_pipe" will be trapped inside a deadloop: "trace_empty()" returns 0 since "rb_per_cpu_empty()" returns 0 when it hits the CPU containing such constructed ring buffer. Then "trace_find_next_entry_inc()" always return NULL since "rb_num_of_entries()" reports there's no more entry to read. Finally "trace_seq_to_user()" returns "-EBUSY" spanking "tracing_read_pipe" back to the start of the "waitagain" loop. I've also written a proof-of-concept script to construct the scenario and trigger the bug automatically, you can use it to trace and validate my reasoning above: https://github.com/aegistudio/RingBufferDetonator.git Tests has been carried out on linux kernel 5.14-rc2 (2734d6c1b1a089fb593ef6a23d4b70903526fe0c), my fixed version of kernel (for testing whether my update fixes the bug) and some older kernels (for range of affected kernels). Test result is also attached to the proof-of-concept repository. Link: https://lore.kernel.org/linux-trace-devel/YPaNxsIlb2yjSi5Y@aegistudio/ Link: https://lore.kernel.org/linux-trace-devel/YPgrN85WL9VyrZ55@aegistudio Cc: stable@vger.kernel.org Fixes: bf41a158cacba ("ring-buffer: make reentrant") Suggested-by: Linus Torvalds Signed-off-by: Haoran Luo Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d1463eac11a3..e592d1df6f88 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3880,10 +3880,30 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) if (unlikely(!head)) return true; - return reader->read == rb_page_commit(reader) && - (commit == reader || - (commit == head && - head->read == rb_page_commit(commit))); + /* Reader should exhaust content in reader page */ + if (reader->read != rb_page_commit(reader)) + return false; + + /* + * If writers are committing on the reader page, knowing all + * committed content has been read, the ring buffer is empty. + */ + if (commit == reader) + return true; + + /* + * If writers are committing on a page other than reader page + * and head page, there should always be content to read. + */ + if (commit != head) + return false; + + /* + * Writers are committing on the head page, we just need + * to care about there're committed data, and the reader will + * swap reader page with head page when it is to read data. + */ + return rb_page_commit(commit) == 0; } /** From 2485bd7557a7edb4520b4072af464f0a08c8efe0 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Thu, 22 Jul 2021 14:53:32 +1000 Subject: [PATCH 0777/1469] cifs: only write 64kb at a time when fallocating a small region of a file We only allow sending single credit writes through the SMB2_write() synchronous api so split this into smaller chunks. Fixes: 966a3cb7c7db ("cifs: improve fallocate emulation") Signed-off-by: Ronnie Sahlberg Reported-by: Namjae Jeon Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index ba3c58e1f725..5cefb5972396 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3617,7 +3617,7 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, char *buf) { struct cifs_io_parms io_parms = {0}; - int nbytes; + int rc, nbytes; struct kvec iov[2]; io_parms.netfid = cfile->fid.netfid; @@ -3625,13 +3625,25 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, io_parms.tcon = tcon; io_parms.persistent_fid = cfile->fid.persistent_fid; io_parms.volatile_fid = cfile->fid.volatile_fid; - io_parms.offset = off; - io_parms.length = len; - /* iov[0] is reserved for smb header */ - iov[1].iov_base = buf; - iov[1].iov_len = io_parms.length; - return SMB2_write(xid, &io_parms, &nbytes, iov, 1); + while (len) { + io_parms.offset = off; + io_parms.length = len; + if (io_parms.length > SMB2_MAX_BUFFER_SIZE) + io_parms.length = SMB2_MAX_BUFFER_SIZE; + /* iov[0] is reserved for smb header */ + iov[1].iov_base = buf; + iov[1].iov_len = io_parms.length; + rc = SMB2_write(xid, &io_parms, &nbytes, iov, 1); + if (rc) + break; + if (nbytes > len) + return -EINVAL; + buf += nbytes; + off += nbytes; + len -= nbytes; + } + return rc; } static int smb3_simple_fallocate_range(unsigned int xid, From b62366181a5e9473e9c10e98f400049491c55876 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 16 Jul 2021 03:26:41 -0300 Subject: [PATCH 0778/1469] cifs: support share failover when remounting When remouting a DFS share, force a new DFS referral of the path and if the currently cached targets do not match any of the new targets or there was no cached targets, then mark it for reconnect. For example: $ mount //dom/dfs/link /mnt -o username=foo,password=bar $ ls /mnt oldfile.txt change target share of 'link' in server settings $ mount /mnt -o remount,username=foo,password=bar $ ls /mnt newfile.txt Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/connect.c | 4 +- fs/cifs/dfs_cache.c | 229 ++++++++++++++++++++++++++++++++++++------- fs/cifs/dfs_cache.h | 3 + fs/cifs/fs_context.c | 7 ++ 4 files changed, 203 insertions(+), 40 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1b04d6ec14dd..3781eee9360a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -220,7 +220,7 @@ cifs_reconnect(struct TCP_Server_Info *server) #ifdef CONFIG_CIFS_DFS_UPCALL struct super_block *sb = NULL; struct cifs_sb_info *cifs_sb = NULL; - struct dfs_cache_tgt_list tgt_list = {0}; + struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); struct dfs_cache_tgt_iterator *tgt_it = NULL; #endif @@ -3130,7 +3130,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ { int rc; char *npath = NULL; - struct dfs_cache_tgt_list tgt_list = {0}; + struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); struct dfs_cache_tgt_iterator *tgt_it = NULL; struct smb3_fs_context tmp_ctx = {NULL}; diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 7c1769714609..283745592844 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -19,6 +19,7 @@ #include "cifs_debug.h" #include "cifs_unicode.h" #include "smb2glob.h" +#include "dns_resolve.h" #include "dfs_cache.h" @@ -911,6 +912,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl) err_free_it: list_for_each_entry_safe(it, nit, head, it_list) { + list_del(&it->it_list); kfree(it->it_name); kfree(it); } @@ -1293,6 +1295,194 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, return 0; } +static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, const char *s2) +{ + char unc[sizeof("\\\\") + SERVER_NAME_LENGTH] = {0}; + const char *host; + size_t hostlen; + char *ip = NULL; + struct sockaddr sa; + bool match; + int rc; + + if (strcasecmp(s1, s2)) + return false; + + /* + * Resolve share's hostname and check if server address matches. Otherwise just ignore it + * as we could not have upcall to resolve hostname or failed to convert ip address. + */ + match = true; + extract_unc_hostname(s1, &host, &hostlen); + scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host); + + rc = dns_resolve_server_name_to_ip(unc, &ip, NULL); + if (rc < 0) { + cifs_dbg(FYI, "%s: could not resolve %.*s. assuming server address matches.\n", + __func__, (int)hostlen, host); + return true; + } + + if (!cifs_convert_address(&sa, ip, strlen(ip))) { + cifs_dbg(VFS, "%s: failed to convert address \'%s\'. skip address matching.\n", + __func__, ip); + } else { + mutex_lock(&server->srv_mutex); + match = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, &sa); + mutex_unlock(&server->srv_mutex); + } + + kfree(ip); + return match; +} + +/* + * Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new + * target shares in @refs. + */ +static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl, + const struct dfs_info3_param *refs, int numrefs) +{ + struct dfs_cache_tgt_iterator *it; + int i; + + for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) { + for (i = 0; i < numrefs; i++) { + if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it), + refs[i].node_name)) + return; + } + } + + cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__); + for (i = 0; i < tcon->ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (tcon->ses->chans[i].server->tcpStatus != CifsExiting) + tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } +} + +/* Refresh dfs referral of tcon and mark it for reconnect if needed */ +static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh) +{ + const char *path = tcon->dfs_path + 1; + struct cifs_ses *ses; + struct cache_entry *ce; + struct dfs_info3_param *refs = NULL; + int numrefs = 0; + bool needs_refresh = false; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + int rc = 0; + unsigned int xid; + + ses = find_ipc_from_server_path(sessions, path); + if (IS_ERR(ses)) { + cifs_dbg(FYI, "%s: could not find ipc session\n", __func__); + return PTR_ERR(ses); + } + + down_read(&htable_rw_lock); + ce = lookup_cache_entry(path); + needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); + if (!IS_ERR(ce)) { + rc = get_targets(ce, &tl); + if (rc) + cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc); + } + up_read(&htable_rw_lock); + + if (!needs_refresh) { + rc = 0; + goto out; + } + + xid = get_xid(); + rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); + free_xid(xid); + + /* Create or update a cache entry with the new referral */ + if (!rc) { + dump_refs(refs, numrefs); + + down_write(&htable_rw_lock); + ce = lookup_cache_entry(path); + if (IS_ERR(ce)) + add_cache_entry_locked(refs, numrefs); + else if (force_refresh || cache_entry_expired(ce)) + update_cache_entry_locked(ce, refs, numrefs); + up_write(&htable_rw_lock); + + mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs); + } + +out: + dfs_cache_free_tgts(&tl); + free_dfs_info_array(refs, numrefs); + return rc; +} + +/** + * dfs_cache_remount_fs - remount a DFS share + * + * Reconfigure dfs mount by forcing a new DFS referral and if the currently cached targets do not + * match any of the new targets, mark it for reconnect. + * + * @cifs_sb: cifs superblock. + * + * Return zero if remounted, otherwise non-zero. + */ +int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) +{ + struct cifs_tcon *tcon; + struct mount_group *mg; + struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL}; + int rc; + + if (!cifs_sb || !cifs_sb->master_tlink) + return -EINVAL; + + tcon = cifs_sb_master_tcon(cifs_sb); + if (!tcon->dfs_path) { + cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__); + return 0; + } + + if (uuid_is_null(&cifs_sb->dfs_mount_id)) { + cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__); + return -EINVAL; + } + + mutex_lock(&mount_group_list_lock); + mg = find_mount_group_locked(&cifs_sb->dfs_mount_id); + if (IS_ERR(mg)) { + mutex_unlock(&mount_group_list_lock); + cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__); + return PTR_ERR(mg); + } + kref_get(&mg->refcount); + mutex_unlock(&mount_group_list_lock); + + spin_lock(&mg->lock); + memcpy(&sessions, mg->sessions, mg->num_sessions * sizeof(mg->sessions[0])); + spin_unlock(&mg->lock); + + /* + * After reconnecting to a different server, unique ids won't match anymore, so we disable + * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). + */ + cifs_autodisable_serverino(cifs_sb); + /* + * Force the use of prefix path to support failover on DFS paths that resolve to targets + * that have different prefix paths. + */ + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + rc = refresh_tcon(sessions, tcon, true); + + kref_put(&mg->refcount, mount_group_release); + return rc; +} + /* * Refresh all active dfs mounts regardless of whether they are in cache or not. * (cache can be cleared) @@ -1303,7 +1493,6 @@ static void refresh_mounts(struct cifs_ses **sessions) struct cifs_ses *ses; struct cifs_tcon *tcon, *ntcon; struct list_head tcons; - unsigned int xid; INIT_LIST_HEAD(&tcons); @@ -1321,44 +1510,8 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { - const char *path = tcon->dfs_path + 1; - struct cache_entry *ce; - struct dfs_info3_param *refs = NULL; - int numrefs = 0; - bool needs_refresh = false; - int rc = 0; - list_del_init(&tcon->ulist); - - ses = find_ipc_from_server_path(sessions, path); - if (IS_ERR(ses)) - goto next_tcon; - - down_read(&htable_rw_lock); - ce = lookup_cache_entry(path); - needs_refresh = IS_ERR(ce) || cache_entry_expired(ce); - up_read(&htable_rw_lock); - - if (!needs_refresh) - goto next_tcon; - - xid = get_xid(); - rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); - free_xid(xid); - - /* Create or update a cache entry with the new referral */ - if (!rc) { - down_write(&htable_rw_lock); - ce = lookup_cache_entry(path); - if (IS_ERR(ce)) - add_cache_entry_locked(refs, numrefs); - else if (cache_entry_expired(ce)) - update_cache_entry_locked(ce, refs, numrefs); - up_write(&htable_rw_lock); - } - -next_tcon: - free_dfs_info_array(refs, numrefs); + refresh_tcon(sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index b29d3ae64829..52070d1df189 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -13,6 +13,8 @@ #include #include "cifsglob.h" +#define DFS_CACHE_TGT_LIST_INIT(var) { .tl_numtgts = 0, .tl_list = LIST_HEAD_INIT((var).tl_list), } + struct dfs_cache_tgt_list { int tl_numtgts; struct list_head tl_list; @@ -44,6 +46,7 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id); void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses); char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap); +int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb); static inline struct dfs_cache_tgt_iterator * dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl, diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 553adfbcc22a..9a59d7ff9a11 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -13,6 +13,9 @@ #include #include #include +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif */ #include @@ -779,6 +782,10 @@ static int smb3_reconfigure(struct fs_context *fc) smb3_cleanup_fs_context_contents(cifs_sb->ctx); rc = smb3_fs_context_dup(cifs_sb->ctx, ctx); smb3_update_mnt_flags(cifs_sb); +#ifdef CONFIG_CIFS_DFS_UPCALL + if (!rc) + rc = dfs_cache_remount_fs(cifs_sb); +#endif return rc; } From 21a64910997e0c1d268bebf9b1217ba5804d592d Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 22 Jul 2021 13:50:41 -0500 Subject: [PATCH 0779/1469] CIFS: Clarify SMB1 code for POSIX Create Coverity also complains about the way we calculate the offset (starting from the address of a 4 byte array within the header structure rather than from the beginning of the struct plus 4 bytes) for SMB1 CIFSPOSIXCreate. This changeset doesn't change the address but makes it slightly clearer. Addresses-Coverity: 711518 ("Out of bounds write") Signed-off-by: Steve French --- fs/cifs/cifssmb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index f72e3b3dca69..d4144c182604 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1081,7 +1081,8 @@ PsxCreat: param_offset = offsetof(struct smb_com_transaction2_spi_req, InformationLevel) - 4; offset = param_offset + params; - pdata = (OPEN_PSX_REQ *)(((char *)&pSMB->hdr.Protocol) + offset); + /* SMB offsets are from the beginning of SMB which is 4 bytes in, after RFC1001 field */ + pdata = (OPEN_PSX_REQ *)((char *)(pSMB) + offset + 4); pdata->Level = cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC); pdata->Permissions = cpu_to_le64(mode); pdata->PosixOpenFlags = cpu_to_le32(posix_flags); From 7b09d4e0be94968b7c6c117e34ca90cea9c6d986 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 22 Jul 2021 14:35:15 -0500 Subject: [PATCH 0780/1469] CIFS: Clarify SMB1 code for POSIX delete file Coverity also complains about the way we calculate the offset (starting from the address of a 4 byte array within the header structure rather than from the beginning of the struct plus 4 bytes) for SMB1 CIFSPOSIXDelFile. This changeset doesn't change the address but makes it slightly clearer. Addresses-Coverity: 711519 ("Out of bounds write") Signed-off-by: Steve French --- fs/cifs/cifssmb.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index d4144c182604..65d1a65bfc37 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -873,8 +873,11 @@ PsxDelete: InformationLevel) - 4; offset = param_offset + params; - /* Setup pointer to Request Data (inode type) */ - pRqD = (struct unlink_psx_rq *)(((char *)&pSMB->hdr.Protocol) + offset); + /* Setup pointer to Request Data (inode type). + * Note that SMB offsets are from the beginning of SMB which is 4 bytes + * in, after RFC1001 field + */ + pRqD = (struct unlink_psx_rq *)((char *)(pSMB) + offset + 4); pRqD->type = cpu_to_le16(type); pSMB->ParameterOffset = cpu_to_le16(param_offset); pSMB->DataOffset = cpu_to_le16(offset); From 0cc936f74bcacb039b7533aeac0a887dfc896bf6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Jul 2021 17:08:07 -0600 Subject: [PATCH 0781/1469] io_uring: fix early fdput() of file A previous commit shuffled some code around, and inadvertently used struct file after fdput() had been called on it. As we can't touch the file post fdput() dropping our reference, move the fdput() to after that has been done. Cc: Pavel Begunkov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/io-uring/YPnqM0fY3nM5RdRI@zeniv-ca.linux.org.uk/ Fixes: f2a48dd09b8e ("io_uring: refactor io_sq_offload_create()") Reported-by: Al Viro Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index fe3d948658ad..f2fe4eca150b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7991,9 +7991,11 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, f = fdget(p->wq_fd); if (!f.file) return -ENXIO; - fdput(f); - if (f.file->f_op != &io_uring_fops) + if (f.file->f_op != &io_uring_fops) { + fdput(f); return -EINVAL; + } + fdput(f); } if (ctx->flags & IORING_SETUP_SQPOLL) { struct task_struct *tsk; From 488968a8945c119859d91bb6a8dc13bf50002f15 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Fri, 23 Jul 2021 11:21:24 +1000 Subject: [PATCH 0782/1469] cifs: fix fallocate when trying to allocate a hole. Remove the conditional checking for out_data_len and skipping the fallocate if it is 0. This is wrong will actually change any legitimate the fallocate where the entire region is unallocated into a no-op. Additionally, before allocating the range, if FALLOC_FL_KEEP_SIZE is set then we need to clamp the length of the fallocate region as to not extend the size of the file. Fixes: 966a3cb7c7db ("cifs: improve fallocate emulation") Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 5cefb5972396..23d6f4d71649 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3667,11 +3667,6 @@ static int smb3_simple_fallocate_range(unsigned int xid, (char **)&out_data, &out_data_len); if (rc) goto out; - /* - * It is already all allocated - */ - if (out_data_len == 0) - goto out; buf = kzalloc(1024 * 1024, GFP_KERNEL); if (buf == NULL) { @@ -3794,6 +3789,24 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, goto out; } + if (keep_size == true) { + /* + * We can not preallocate pages beyond the end of the file + * in SMB2 + */ + if (off >= i_size_read(inode)) { + rc = 0; + goto out; + } + /* + * For fallocates that are partially beyond the end of file, + * clamp len so we only fallocate up to the end of file. + */ + if (off + len > i_size_read(inode)) { + len = i_size_read(inode) - off; + } + } + if ((keep_size == true) || (i_size_read(inode) >= off + len)) { /* * At this point, we are trying to fallocate an internal From 29f6a20c21b5bdc7eb623a712bbf7b99612ee746 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 2 Jul 2021 21:49:14 +0200 Subject: [PATCH 0783/1469] arm64: dts: ls1028: sl28: fix networking for variant 2 The PHY configuration for the variant 2 is still missing the flag for in-band signalling between PHY and MAC. Both sides - MAC and PHY - have to match the setting. For now, Linux only supports setting the MAC side and thus it has to match the setting the bootloader is configuring. Enable in-band signalling to make ethernet work. Fixes: ab43f0307449 ("arm64: dts: ls1028a: sl28: add support for variant 2") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts index dd764b720fb0..f6a79c8080d1 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts @@ -54,6 +54,7 @@ &mscc_felix_port0 { label = "swp0"; + managed = "in-band-status"; phy-handle = <&phy0>; phy-mode = "sgmii"; status = "okay"; @@ -61,6 +62,7 @@ &mscc_felix_port1 { label = "swp1"; + managed = "in-band-status"; phy-handle = <&phy1>; phy-mode = "sgmii"; status = "okay"; From 828db68f4ff1ab6982a36a56522b585160dc8c8e Mon Sep 17 00:00:00 2001 From: Oleksandr Suvorov Date: Tue, 13 Jul 2021 23:21:07 +0300 Subject: [PATCH 0784/1469] ARM: dts: colibri-imx6ull: limit SDIO clock to 25MHz NXP and AzureWave don't recommend using SDIO bus mode 3.3V@50MHz due to noise affecting the wireless throughput. Colibri iMX6ULL uses only 3.3V signaling for Wi-Fi module AW-CM276NF. Limit the SDIO Clock on Colibri iMX6ULL to 25MHz. Fixes: c2e4987e0e02 ("ARM: dts: imx6ull: add Toradex Colibri iMX6ULL support") Signed-off-by: Oleksandr Suvorov Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi b/arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi index a0545431b3dc..9f1e38282bee 100644 --- a/arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri-wifi.dtsi @@ -43,6 +43,7 @@ assigned-clock-rates = <0>, <198000000>; cap-power-off-card; keep-power-in-suspend; + max-frequency = <25000000>; mmc-pwrseq = <&wifi_pwrseq>; no-1-8-v; non-removable; From c09dc9e1cd3c205f66b2505d742e819735c0eb6f Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 29 Jun 2021 11:13:46 +0200 Subject: [PATCH 0785/1469] riscv: Fix memory_limit for 64-bit kernel As described in Documentation/riscv/vm-layout.rst, the end of the virtual address space for 64-bit kernel is occupied by the modules/BPF/ kernel mappings so this actually reduces the amount of memory we are able to map and then use in the linear mapping. So make sure this limit is correctly set. Signed-off-by: Alexandre Ghiti Fixes: 2bfc6cd81bd1 ("riscv: Move kernel mapping outside of linear mapping") Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ac48742fa6fc..e4356d65fdce 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -127,10 +127,17 @@ void __init mem_init(void) } /* - * The default maximal physical memory size is -PAGE_OFFSET, - * limit the memory size via mem. + * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel, + * whereas for 64-bit kernel, the end of the virtual address space is occupied + * by the modules/BPF/kernel mappings which reduces the available size of the + * linear mapping. + * Limit the memory size via mem. */ +#ifdef CONFIG_64BIT +static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G; +#else static phys_addr_t memory_limit = -PAGE_OFFSET; +#endif static int __init early_mem(char *p) { From c99127c452484ac89c75af39c3c865174ce2de99 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 29 Jun 2021 11:13:47 +0200 Subject: [PATCH 0786/1469] riscv: Make sure the linear mapping does not use the kernel mapping For 64-bit kernel, the end of the address space is occupied by the kernel mapping and currently, the functions to populate the kernel page tables (i.e. create_p*d_mapping) do not override existing mapping so we must make sure the linear mapping does not map memory in the kernel mapping by clipping the memory above the memory limit. Signed-off-by: Alexandre Ghiti Fixes: c9811e379b21 ("riscv: Add mem kernel parameter support") Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index e4356d65fdce..644a34b0d77d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -717,6 +717,8 @@ static void __init setup_vm_final(void) if (start <= __pa(PAGE_OFFSET) && __pa(PAGE_OFFSET) < end) start = __pa(PAGE_OFFSET); + if (end >= __pa(PAGE_OFFSET) + memory_limit) + end = __pa(PAGE_OFFSET) + memory_limit; map_size = best_map_size(start, end - start); for (pa = start; pa < end; pa += map_size) { From db6b84a368b495cb7e41be9cb9e73d4d0537d027 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 29 Jun 2021 11:13:48 +0200 Subject: [PATCH 0787/1469] riscv: Make sure the kernel mapping does not overlap with IS_ERR_VALUE The check that is done in setup_bootmem currently only works for 32-bit kernel since the kernel mapping has been moved outside of the linear mapping for 64-bit kernel. So make sure that for 64-bit kernel, the kernel mapping does not overlap with the last 4K of the addressable memory. Signed-off-by: Alexandre Ghiti Fixes: 2bfc6cd81bd1 ("riscv: Move kernel mapping outside of linear mapping") Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 644a34b0d77d..a14bf3910eec 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -159,7 +159,7 @@ static void __init setup_bootmem(void) { phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); - phys_addr_t max_mapped_addr = __pa(~(ulong)0); + phys_addr_t __maybe_unused max_mapped_addr; phys_addr_t dram_end; #ifdef CONFIG_XIP_KERNEL @@ -183,14 +183,20 @@ static void __init setup_bootmem(void) dram_end = memblock_end_of_DRAM(); +#ifndef CONFIG_64BIT /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. + * if end of dram is equal to maximum addressable memory. For 64-bit + * kernel, this problem can't happen here as the end of the virtual + * address space is occupied by the kernel mapping then this check must + * be done in create_kernel_page_table. */ + max_mapped_addr = __pa(~(ulong)0); if (max_mapped_addr == (dram_end - 1)) memblock_set_current_limit(max_mapped_addr - 4096); +#endif min_low_pfn = PFN_UP(memblock_start_of_DRAM()); max_low_pfn = max_pfn = PFN_DOWN(dram_end); @@ -578,6 +584,14 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0); BUG_ON((kernel_map.phys_addr % map_size) != 0); +#ifdef CONFIG_64BIT + /* + * The last 4K bytes of the addressable memory can not be mapped because + * of IS_ERR_VALUE macro. + */ + BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K); +#endif + pt_ops.alloc_pte = alloc_pte_early; pt_ops.get_pte_virt = get_pte_virt_early; #ifndef __PAGETABLE_PMD_FOLDED From e39cdacf2f664b09029e7c1eb354c91a20c367af Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Tue, 22 Jun 2021 07:11:31 +0000 Subject: [PATCH 0788/1469] pcmcia: i82092: fix a null pointer dereference bug During the driver loading process, the 'dev' field was not assigned, but the 'dev' field was referenced in the subsequent 'i82092aa_set_mem_map' function. Signed-off-by: Zheyu Ma CC: [linux@dominikbrodowski.net: shorten commit message, add Cc to stable] Signed-off-by: Dominik Brodowski --- drivers/pcmcia/i82092.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c index 85887d885b5f..192c9049d654 100644 --- a/drivers/pcmcia/i82092.c +++ b/drivers/pcmcia/i82092.c @@ -112,6 +112,7 @@ static int i82092aa_pci_probe(struct pci_dev *dev, for (i = 0; i < socket_count; i++) { sockets[i].card_state = 1; /* 1 = present but empty */ sockets[i].io_base = pci_resource_start(dev, 0); + sockets[i].dev = dev; sockets[i].socket.features |= SS_CAP_PCCARD; sockets[i].socket.map_size = 0x1000; sockets[i].socket.irq_mask = 0; From f62f3c20647ebd5fb6ecb8f0b477b9281c44c10a Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 20 Jul 2021 20:43:09 +1000 Subject: [PATCH 0789/1469] KVM: PPC: Book3S: Fix H_RTAS rets buffer overflow The kvmppc_rtas_hcall() sets the host rtas_args.rets pointer based on the rtas_args.nargs that was provided by the guest. That guest nargs value is not range checked, so the guest can cause the host rets pointer to be pointed outside the args array. The individual rtas function handlers check the nargs and nrets values to ensure they are correct, but if they are not, the handlers store a -3 (0xfffffffd) failure indication in rets[0] which corrupts host memory. Fix this by testing up front whether the guest supplied nargs and nret would exceed the array size, and fail the hcall directly without storing a failure indication to rets[0]. Also expand on a comment about why we kill the guest and try not to return errors directly if we have a valid rets[0] pointer. Fixes: 8e591cb72047 ("KVM: PPC: Book3S: Add infrastructure to implement kernel-side RTAS calls") Cc: stable@vger.kernel.org # v3.10+ Reported-by: Alexey Kardashevskiy Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kvm/book3s_rtas.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index c5e677508d3b..0f847f1e5ddd 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -242,6 +242,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) * value so we can restore it on the way out. */ orig_rets = args.rets; + if (be32_to_cpu(args.nargs) >= ARRAY_SIZE(args.args)) { + /* + * Don't overflow our args array: ensure there is room for + * at least rets[0] (even if the call specifies 0 nret). + * + * Each handler must then check for the correct nargs and nret + * values, but they may always return failure in rets[0]. + */ + rc = -EINVAL; + goto fail; + } args.rets = &args.args[be32_to_cpu(args.nargs)]; mutex_lock(&vcpu->kvm->arch.rtas_token_lock); @@ -269,9 +280,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) fail: /* * We only get here if the guest has called RTAS with a bogus - * args pointer. That means we can't get to the args, and so we - * can't fail the RTAS call. So fail right out to userspace, - * which should kill the guest. + * args pointer or nargs/nret values that would overflow the + * array. That means we can't get to the args, and so we can't + * fail the RTAS call. So fail right out to userspace, which + * should kill the guest. + * + * SLOF should actually pass the hcall return value from the + * rtas handler call in r3, so enter_rtas could be modified to + * return a failure indication in r3 and we could return such + * errors to the guest rather than failing to host userspace. + * However old guests that don't test for failure could then + * continue silently after errors, so for now we won't do this. */ return rc; } From d9c57d3ed52a92536f5fa59dc5ccdd58b4875076 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 8 Jul 2021 21:26:22 +1000 Subject: [PATCH 0790/1469] KVM: PPC: Book3S HV Nested: Sanitise H_ENTER_NESTED TM state The H_ENTER_NESTED hypercall is handled by the L0, and it is a request by the L1 to switch the context of the vCPU over to that of its L2 guest, and return with an interrupt indication. The L1 is responsible for switching some registers to guest context, and the L0 switches others (including all the hypervisor privileged state). If the L2 MSR has TM active, then the L1 is responsible for recheckpointing the L2 TM state. Then the L1 exits to L0 via the H_ENTER_NESTED hcall, and the L0 saves the TM state as part of the exit, and then it recheckpoints the TM state as part of the nested entry and finally HRFIDs into the L2 with TM active MSR. Not efficient, but about the simplest approach for something that's horrendously complicated. Problems arise if the L1 exits to the L0 with a TM state which does not match the L2 TM state being requested. For example if the L1 is transactional but the L2 MSR is non-transactional, or vice versa. The L0's HRFID can take a TM Bad Thing interrupt and crash. Fix this by disallowing H_ENTER_NESTED in TM[T] state entirely, and then ensuring that if the L1 is suspended then the L2 must have TM active, and if the L1 is not suspended then the L2 must not have TM active. Fixes: 360cae313702 ("KVM: PPC: Book3S HV: Nested guest entry via hypercall") Cc: stable@vger.kernel.org # v4.20+ Reported-by: Alexey Kardashevskiy Acked-by: Michael Neuling Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kvm/book3s_hv_nested.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 8543ad538b0c..898f942eb198 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -302,6 +302,9 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.l1_ptcr == 0) return H_NOT_AVAILABLE; + if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr)) + return H_BAD_MODE; + /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); regs_ptr = kvmppc_get_gpr(vcpu, 5); @@ -322,6 +325,23 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (l2_hv.vcpu_token >= NR_CPUS) return H_PARAMETER; + /* + * L1 must have set up a suspended state to enter the L2 in a + * transactional state, and only in that case. These have to be + * filtered out here to prevent causing a TM Bad Thing in the + * host HRFID. We could synthesize a TM Bad Thing back to the L1 + * here but there doesn't seem like much point. + */ + if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr)) { + if (!MSR_TM_ACTIVE(l2_regs.msr)) + return H_BAD_MODE; + } else { + if (l2_regs.msr & MSR_TS_MASK) + return H_BAD_MODE; + if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_TS_MASK)) + return H_BAD_MODE; + } + /* translate lpid */ l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true); if (!l2) From 20fb73911fec01f06592de1cdbca00b66602ebd7 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 15 Jul 2021 14:23:21 +0100 Subject: [PATCH 0791/1469] ARM: imx: fix missing 3rd argument in macro imx_mmdc_perf_init The function imx_mmdc_perf_init recently had a 3rd argument added to it but the equivalent macro was not updated and is still the older 2 argument version. Fix this by adding in the missing 3rd argumement mmdc_ipg_clk. Fixes: f07ec8536580 ("ARM: imx: add missing clk_disable_unprepare()") Signed-off-by: Colin Ian King Signed-off-by: Shawn Guo --- arch/arm/mach-imx/mmdc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 4a6f1359e1e9..af12668d0bf5 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -534,7 +534,7 @@ pmu_free: #else #define imx_mmdc_remove NULL -#define imx_mmdc_perf_init(pdev, mmdc_base) 0 +#define imx_mmdc_perf_init(pdev, mmdc_base, mmdc_ipg_clk) 0 #endif static int imx_mmdc_probe(struct platform_device *pdev) From 3d9e30a52047f2d464efdfd1d561ae1f707a0286 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 18 Jul 2021 23:43:02 +0200 Subject: [PATCH 0792/1469] ARM: dts: imx: Swap M53Menlo pinctrl_power_button/pinctrl_power_out pins The pinctrl_power_button/pinctrl_power_out each define single GPIO pinmux, except it is exactly the other one than the matching gpio-keys and gpio-poweroff DT nodes use for that functionality. Swap the two GPIOs to correct this error. Fixes: 50d29fdb765d ("ARM: dts: imx53: Add power GPIOs on M53Menlo") Signed-off-by: Marek Vasut Cc: Shawn Guo Cc: Fabio Estevam Cc: NXP Linux Team Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx53-m53menlo.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx53-m53menlo.dts b/arch/arm/boot/dts/imx53-m53menlo.dts index f98691ae4415..d3082b9774e4 100644 --- a/arch/arm/boot/dts/imx53-m53menlo.dts +++ b/arch/arm/boot/dts/imx53-m53menlo.dts @@ -388,13 +388,13 @@ pinctrl_power_button: powerbutgrp { fsl,pins = < - MX53_PAD_SD2_DATA2__GPIO1_13 0x1e4 + MX53_PAD_SD2_DATA0__GPIO1_15 0x1e4 >; }; pinctrl_power_out: poweroutgrp { fsl,pins = < - MX53_PAD_SD2_DATA0__GPIO1_15 0x1e4 + MX53_PAD_SD2_DATA2__GPIO1_13 0x1e4 >; }; From ec61cd49bf566401306cfc4855bda8c08bbaa46c Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Mon, 28 Jun 2021 14:37:13 +0200 Subject: [PATCH 0793/1469] mac80211: Do not strip skb headroom on monitor frames When a monitor interface is present together with other interfaces, a received skb is copied and received on the monitor netdev. Before, the copied skb was allocated with exactly the amount of space needed for the radiotap header, resulting in an skb without any headroom at all being received on the monitor netdev. With the introduction of eBPF and XDP in the kernel, skbs may be processed by custom eBPF programs. However, since the skb cannot be reallocated in the eBPF program, no more data or headers can be pushed. The old code made sure the final headroom was zero regardless of the value of NET_SKB_PAD, so increasing that constant would have no effect. Now we allocate monitor skb copies with a headroom of NET_SKB_PAD bytes before the radiotap header. Monitor interfaces now behave in the same way as other netdev interfaces that honor the NET_SKB_PAD constant. Signed-off-by: Johan Almbladh Link: https://lore.kernel.org/r/20210628123713.2070753-1-johan.almbladh@anyfinetworks.com Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 771921c057e8..2563473b5cf1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -730,7 +730,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, * Need to make a copy and possibly remove radiotap header * and FCS from the original. */ - skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC); + skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD, + 0, GFP_ATOMIC); if (!skb) return NULL; From 1a7915501ca94a1f10288defe333cd5ade210b63 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 29 Jun 2021 13:28:53 +0200 Subject: [PATCH 0794/1469] mac80211: fix starting aggregation sessions on mesh interfaces The logic for starting aggregation sessions was recently moved from minstrel_ht to mac80211, into the subif tx handler just after the sta lookup. Unfortunately this didn't work for mesh interfaces, since the sta lookup is deferred until a much later point in time on those. Fix this by also calling the aggregation check right after the deferred sta lookup. Fixes: 08a46c642001 ("mac80211: move A-MPDU session check from minstrel_ht to mac80211") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20210629112853.29785-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 57 ++++++++++++++++++++++++++--------------------- 1 file changed, 32 insertions(+), 25 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e96981144358..8509778ff31f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, return queued; } +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + /* * initialises @tx * pass %NULL for the station if unknown, a valid pointer if known @@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + bool aggr_check = false; int tid; memset(tx, 0, sizeof(*tx)); @@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, } else if (tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } - if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) + if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) { tx->sta = sta_info_get(sdata, hdr->addr1); + aggr_check = true; + } } if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && @@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx; tid = ieee80211_get_tid(hdr); - tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx && aggr_check) { + ieee80211_aggr_check(sdata, tx->sta, skb); + tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + } + if (tid_tx) { bool queued; @@ -4120,29 +4150,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) } EXPORT_SYMBOL(ieee80211_txq_schedule_start); -static void -ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, - struct sk_buff *skb) -{ - struct rate_control_ref *ref = sdata->local->rate_ctrl; - u16 tid; - - if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) - return; - - if (!sta || !sta->sta.ht_cap.ht_supported || - !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || - skb->protocol == sdata->control_port_protocol) - return; - - tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(&sta->sta, tid, 0); -} - void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, From a5d3cbdb09ff1f52cbe040932e06c8b9915c6dad Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 2 Jul 2021 07:01:11 +0200 Subject: [PATCH 0795/1469] mac80211: fix enabling 4-address mode on a sta vif after assoc Notify the driver about the 4-address mode change and also send a nulldata packet to the AP to notify it about the change Fixes: 1ff4e8f2dec8 ("mac80211: notify the driver when a sta uses 4-address mode") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20210702050111.47546-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 19 +++++++++++++++++++ net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/mlme.c | 4 ++-- 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 84cc7733ea66..4e6f11e63df3 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; int ret; ret = ieee80211_if_change_type(sdata, type); @@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy, RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (params->use_4addr == ifmgd->use_4addr) + return 0; + sdata->u.mgd.use_4addr = params->use_4addr; + if (!ifmgd->associated) + return 0; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get(sdata, ifmgd->bssid); + if (sta) + drv_sta_set_4addr(local, sdata, &sta->sta, + params->use_4addr); + mutex_unlock(&local->sta_mtx); + + if (params->use_4addr) + ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 22549b95d1aa..30ce6d2ec7ce 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2201,6 +2201,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t); void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, bool powersave); +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a00f11a33699..c0ea3b1aa9e1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, ieee80211_tx_skb(sdata, skb); } -static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { struct sk_buff *skb; struct ieee80211_hdr *nullfunc; From 17109e9783799be2a063b2bd861a508194b0a487 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Tue, 6 Jul 2021 17:44:23 +0200 Subject: [PATCH 0796/1469] virt_wifi: fix error on connect When connecting without first doing a scan, the BSS list is empty and __cfg80211_connect_result() generates this warning: $ iw dev wlan0 connect -w VirtWifi [ 15.371989] ------------[ cut here ]------------ [ 15.372179] WARNING: CPU: 0 PID: 92 at net/wireless/sme.c:756 __cfg80211_connect_result+0x402/0x440 [ 15.372383] CPU: 0 PID: 92 Comm: kworker/u2:2 Not tainted 5.13.0-kvm #444 [ 15.372512] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-3.fc34 04/01/2014 [ 15.372597] Workqueue: cfg80211 cfg80211_event_work [ 15.372756] RIP: 0010:__cfg80211_connect_result+0x402/0x440 [ 15.372818] Code: 48 2b 04 25 28 00 00 00 75 59 48 8b 3b 48 8b 76 10 48 8d 65 e0 5b 41 5c 41 5d 41 5e 5d 49 8d 65 f0 41 5d e9 d0 d4 fd ff 0f 0b <0f> 0b e9 f6 fd ff ff e8 f2 4a b4 ff e9 ec fd ff ff 0f 0b e9 19 fd [ 15.372966] RSP: 0018:ffffc900005cbdc0 EFLAGS: 00010246 [ 15.373022] RAX: 0000000000000000 RBX: ffff8880028e2400 RCX: ffff8880028e2472 [ 15.373088] RDX: 0000000000000002 RSI: 00000000fffffe01 RDI: ffffffff815335ba [ 15.373149] RBP: ffffc900005cbe00 R08: 0000000000000008 R09: ffff888002bdf8b8 [ 15.373209] R10: ffff88803ec208f0 R11: ffffffffffffe9ae R12: ffff88801d687d98 [ 15.373280] R13: ffff88801b5fe000 R14: ffffc900005cbdc0 R15: dead000000000100 [ 15.373330] FS: 0000000000000000(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 [ 15.373382] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 15.373425] CR2: 000056421c468958 CR3: 000000001b458001 CR4: 0000000000170eb0 [ 15.373478] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 15.373529] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 15.373580] Call Trace: [ 15.373611] ? cfg80211_process_wdev_events+0x10e/0x170 [ 15.373743] cfg80211_process_wdev_events+0x10e/0x170 [ 15.373783] cfg80211_process_rdev_events+0x21/0x40 [ 15.373846] cfg80211_event_work+0x20/0x30 [ 15.373892] process_one_work+0x1e9/0x340 [ 15.373956] worker_thread+0x4b/0x3f0 [ 15.374017] ? process_one_work+0x340/0x340 [ 15.374053] kthread+0x11f/0x140 [ 15.374089] ? set_kthread_struct+0x30/0x30 [ 15.374153] ret_from_fork+0x1f/0x30 [ 15.374187] ---[ end trace 321ef0cb7e9c0be1 ]--- wlan0 (phy #0): connected to 00:00:00:00:00:00 Add the fake bss just before the connect so that cfg80211_get_bss() finds the virtual network. As some code was duplicated, move it in a common function. Signed-off-by: Matteo Croce Link: https://lore.kernel.org/r/20210706154423.11065-1-mcroce@linux.microsoft.com Signed-off-by: Johannes Berg --- drivers/net/wireless/virt_wifi.c | 52 ++++++++++++++++++++------------ 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 1df959532c7d..514f2c1124b6 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -136,6 +136,29 @@ static struct ieee80211_supported_band band_5ghz = { /* Assigned at module init. Guaranteed locally-administered and unicast. */ static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {}; +static void virt_wifi_inform_bss(struct wiphy *wiphy) +{ + u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); + struct cfg80211_bss *informed_bss; + static const struct { + u8 tag; + u8 len; + u8 ssid[8]; + } __packed ssid = { + .tag = WLAN_EID_SSID, + .len = 8, + .ssid = "VirtWifi", + }; + + informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, + CFG80211_BSS_FTYPE_PRESP, + fake_router_bssid, tsf, + WLAN_CAPABILITY_ESS, 0, + (void *)&ssid, sizeof(ssid), + DBM_TO_MBM(-50), GFP_KERNEL); + cfg80211_put_bss(wiphy, informed_bss); +} + /* Called with the rtnl lock held. */ static int virt_wifi_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request) @@ -156,28 +179,13 @@ static int virt_wifi_scan(struct wiphy *wiphy, /* Acquires and releases the rdev BSS lock. */ static void virt_wifi_scan_result(struct work_struct *work) { - struct { - u8 tag; - u8 len; - u8 ssid[8]; - } __packed ssid = { - .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi", - }; - struct cfg80211_bss *informed_bss; struct virt_wifi_wiphy_priv *priv = container_of(work, struct virt_wifi_wiphy_priv, scan_result.work); struct wiphy *wiphy = priv_to_wiphy(priv); struct cfg80211_scan_info scan_info = { .aborted = false }; - u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); - informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, - CFG80211_BSS_FTYPE_PRESP, - fake_router_bssid, tsf, - WLAN_CAPABILITY_ESS, 0, - (void *)&ssid, sizeof(ssid), - DBM_TO_MBM(-50), GFP_KERNEL); - cfg80211_put_bss(wiphy, informed_bss); + virt_wifi_inform_bss(wiphy); /* Schedules work which acquires and releases the rtnl lock. */ cfg80211_scan_done(priv->scan_request, &scan_info); @@ -225,10 +233,12 @@ static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev, if (!could_schedule) return -EBUSY; - if (sme->bssid) + if (sme->bssid) { ether_addr_copy(priv->connect_requested_bss, sme->bssid); - else + } else { + virt_wifi_inform_bss(wiphy); eth_zero_addr(priv->connect_requested_bss); + } wiphy_debug(wiphy, "connect\n"); @@ -241,11 +251,13 @@ static void virt_wifi_connect_complete(struct work_struct *work) struct virt_wifi_netdev_priv *priv = container_of(work, struct virt_wifi_netdev_priv, connect.work); u8 *requested_bss = priv->connect_requested_bss; - bool has_addr = !is_zero_ether_addr(requested_bss); bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid); u16 status = WLAN_STATUS_SUCCESS; - if (!priv->is_up || (has_addr && !right_addr)) + if (is_zero_ether_addr(requested_bss)) + requested_bss = NULL; + + if (!priv->is_up || (requested_bss && !right_addr)) status = WLAN_STATUS_UNSPECIFIED_FAILURE; else priv->is_connected = true; From 0d059964504a1605d84938c0b5b38f6573121c4a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 12 Jul 2021 21:53:30 +0200 Subject: [PATCH 0797/1469] nl80211: limit band information in non-split data In non-split data, we shouldn't be adding S1G and 6 GHz data (or future bands) since we're really close to the 4k message size limit. Remove those bands, any modern userspace that can use S1G or 6 GHz should already be using split dumps, and if not then it needs to update. Link: https://lore.kernel.org/r/20210712215329.31444162a2c2.I5555312e4a074c84f8b4e7ad79dc4d1fbfc5126c@changeid Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 50eb405b0690..16c88beea48b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2351,7 +2351,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; for (band = state->band_start; - band < NUM_NL80211_BANDS; band++) { + band < (state->split ? + NUM_NL80211_BANDS : + NL80211_BAND_60GHZ + 1); + band++) { struct ieee80211_supported_band *sband; /* omit higher bands for ancient software */ From f9a5c358c8d26fed0cc45f2afc64633d4ba21dff Mon Sep 17 00:00:00 2001 From: Nguyen Dinh Phi Date: Mon, 28 Jun 2021 21:23:34 +0800 Subject: [PATCH 0798/1469] cfg80211: Fix possible memory leak in function cfg80211_bss_update When we exceed the limit of BSS entries, this function will free the new entry, however, at this time, it is the last door to access the inputed ies, so these ies will be unreferenced objects and cause memory leak. Therefore we should free its ies before deallocating the new entry, beside of dropping it from hidden_list. Signed-off-by: Nguyen Dinh Phi Link: https://lore.kernel.org/r/20210628132334.851095-1-phind.uet@gmail.com Signed-off-by: Johannes Berg --- net/wireless/scan.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index f03c7ac8e184..7897b1478c3c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1754,16 +1754,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; } From 32ec3960175e58a914fc242b66dfe33e9059568f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 23 Jul 2021 11:13:52 +0200 Subject: [PATCH 0799/1469] pinctrl: qcom: fix GPIOLIB dependencies Enabling the PINCTRL_SM8350 symbol without GPIOLIB or SCM causes a build failure: WARNING: unmet direct dependencies detected for PINCTRL_MSM Depends on [m]: PINCTRL [=y] && (ARCH_QCOM [=y] || COMPILE_TEST [=y]) && GPIOLIB [=y] && (QCOM_SCM [=m] || !QCOM_SCM [=m]) Selected by [y]: - PINCTRL_SM8350 [=y] && PINCTRL [=y] && (ARCH_QCOM [=y] || COMPILE_TEST [=y]) && GPIOLIB [=y] && OF [=y] aarch64-linux-ld: drivers/pinctrl/qcom/pinctrl-msm.o: in function `msm_gpio_irq_set_type': pinctrl-msm.c:(.text.msm_gpio_irq_set_type+0x1c8): undefined reference to `qcom_scm_io_readl' The main problem here is the 'select PINCTRL_MSM', which needs to be a 'depends on' as it is for all the other front-ends. As the GPIOLIB dependency is now implied by that, symbol, remove the duplicate dependencies in the process. Fixes: d5d348a3271f ("pinctrl: qcom: Add SM8350 pinctrl driver") Fixes: 376f9e34c10f ("drivers: pinctrl: qcom: fix Kconfig dependency on GPIOLIB") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210723091400.1669716-1-arnd@kernel.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/Kconfig | 63 ++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 32 deletions(-) diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 2f51b4f99393..cad4e60df618 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -13,7 +13,7 @@ config PINCTRL_MSM config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -21,7 +21,7 @@ config PINCTRL_APQ8064 config PINCTRL_APQ8084 tristate "Qualcomm APQ8084 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -29,7 +29,7 @@ config PINCTRL_APQ8084 config PINCTRL_IPQ4019 tristate "Qualcomm IPQ4019 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -37,7 +37,7 @@ config PINCTRL_IPQ4019 config PINCTRL_IPQ8064 tristate "Qualcomm IPQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -45,7 +45,7 @@ config PINCTRL_IPQ8064 config PINCTRL_IPQ8074 tristate "Qualcomm Technologies, Inc. IPQ8074 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -55,7 +55,7 @@ config PINCTRL_IPQ8074 config PINCTRL_IPQ6018 tristate "Qualcomm Technologies, Inc. IPQ6018 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -65,7 +65,7 @@ config PINCTRL_IPQ6018 config PINCTRL_MSM8226 tristate "Qualcomm 8226 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -74,7 +74,7 @@ config PINCTRL_MSM8226 config PINCTRL_MSM8660 tristate "Qualcomm 8660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -82,7 +82,7 @@ config PINCTRL_MSM8660 config PINCTRL_MSM8960 tristate "Qualcomm 8960 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -90,7 +90,7 @@ config PINCTRL_MSM8960 config PINCTRL_MDM9615 tristate "Qualcomm 9615 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -98,7 +98,7 @@ config PINCTRL_MDM9615 config PINCTRL_MSM8X74 tristate "Qualcomm 8x74 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -106,7 +106,7 @@ config PINCTRL_MSM8X74 config PINCTRL_MSM8916 tristate "Qualcomm 8916 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -114,7 +114,7 @@ config PINCTRL_MSM8916 config PINCTRL_MSM8953 tristate "Qualcomm 8953 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -124,7 +124,7 @@ config PINCTRL_MSM8953 config PINCTRL_MSM8976 tristate "Qualcomm 8976 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -134,7 +134,7 @@ config PINCTRL_MSM8976 config PINCTRL_MSM8994 tristate "Qualcomm 8994 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -143,7 +143,7 @@ config PINCTRL_MSM8994 config PINCTRL_MSM8996 tristate "Qualcomm MSM8996 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -151,7 +151,7 @@ config PINCTRL_MSM8996 config PINCTRL_MSM8998 tristate "Qualcomm MSM8998 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -159,7 +159,7 @@ config PINCTRL_MSM8998 config PINCTRL_QCS404 tristate "Qualcomm QCS404 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -167,7 +167,7 @@ config PINCTRL_QCS404 config PINCTRL_QDF2XXX tristate "Qualcomm Technologies QDF2xxx pin controller driver" - depends on GPIOLIB && ACPI + depends on ACPI depends on PINCTRL_MSM help This is the GPIO driver for the TLMM block found on the @@ -175,7 +175,7 @@ config PINCTRL_QDF2XXX config PINCTRL_QCOM_SPMI_PMIC tristate "Qualcomm SPMI PMIC pin controller driver" - depends on GPIOLIB && OF && SPMI + depends on OF && SPMI select REGMAP_SPMI select PINMUX select PINCONF @@ -190,7 +190,7 @@ config PINCTRL_QCOM_SPMI_PMIC config PINCTRL_QCOM_SSBI_PMIC tristate "Qualcomm SSBI PMIC pin controller driver" - depends on GPIOLIB && OF + depends on OF select PINMUX select PINCONF select GENERIC_PINCONF @@ -204,7 +204,7 @@ config PINCTRL_QCOM_SSBI_PMIC config PINCTRL_SC7180 tristate "Qualcomm Technologies Inc SC7180 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -213,7 +213,7 @@ config PINCTRL_SC7180 config PINCTRL_SC7280 tristate "Qualcomm Technologies Inc SC7280 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -222,7 +222,7 @@ config PINCTRL_SC7280 config PINCTRL_SC8180X tristate "Qualcomm Technologies Inc SC8180x pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -231,7 +231,7 @@ config PINCTRL_SC8180X config PINCTRL_SDM660 tristate "Qualcomm Technologies Inc SDM660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -240,7 +240,7 @@ config PINCTRL_SDM660 config PINCTRL_SDM845 tristate "Qualcomm Technologies Inc SDM845 pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -249,7 +249,7 @@ config PINCTRL_SDM845 config PINCTRL_SDX55 tristate "Qualcomm Technologies Inc SDX55 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -258,7 +258,7 @@ config PINCTRL_SDX55 config PINCTRL_SM6125 tristate "Qualcomm Technologies Inc SM6125 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -267,7 +267,7 @@ config PINCTRL_SM6125 config PINCTRL_SM8150 tristate "Qualcomm Technologies Inc SM8150 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -276,7 +276,7 @@ config PINCTRL_SM8150 config PINCTRL_SM8250 tristate "Qualcomm Technologies Inc SM8250 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -285,8 +285,7 @@ config PINCTRL_SM8250 config PINCTRL_SM8350 tristate "Qualcomm Technologies Inc SM8350 pin controller driver" - depends on GPIOLIB && OF - select PINCTRL_MSM + depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc TLMM block found on the Qualcomm From 923f98929182dfd04e9149be839160b63a3db145 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 22 Jul 2021 13:11:34 +0300 Subject: [PATCH 0800/1469] arm64: dts: armada-3720-turris-mox: fixed indices for the SDHC controllers Since drivers/mmc/host/sdhci-xenon.c declares the PROBE_PREFER_ASYNCHRONOUS probe type, it is not guaranteed whether /dev/mmcblk0 will belong to sdhci0 or sdhci1. In turn, this will break booting by: root=/dev/mmcblk0p1 Fix the issue by adding aliases so that the old MMC controller indices are preserved. Fixes: 7320915c8861 ("mmc: Set PROBE_PREFER_ASYNCHRONOUS for drivers that existed in v4.14") Signed-off-by: Vladimir Oltean Signed-off-by: Gregory CLEMENT --- arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index ce2bcddf396f..f2d7d6f071bc 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -19,6 +19,8 @@ aliases { spi0 = &spi0; ethernet1 = ð1; + mmc0 = &sdhci0; + mmc1 = &sdhci1; }; chosen { From b66541422824cf6cf20e9a35112e9cb5d82cdf62 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 13 Jul 2021 10:27:28 +0800 Subject: [PATCH 0801/1469] ext4: fix potential uninitialized access to retval in kmmpd if (!ext4_has_feature_mmp(sb)) then retval can be unitialized before we jump to the wait_to_exit label. Fixes: 61bb4a1c417e ("ext4: fix possible UAF when remounting r/o a mmp-protected file system") Signed-off-by: Ye Bin Link: https://lore.kernel.org/r/20210713022728.2533770-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index bc364c119af6..cebea4270817 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -138,7 +138,7 @@ static int kmmpd(void *data) unsigned mmp_check_interval; unsigned long last_update_time; unsigned long diff; - int retval; + int retval = 0; mmp_block = le64_to_cpu(es->s_mmp_block); mmp = (struct mmp_struct *)(bh->b_data); From 73dc707161a83c24a9e6804b2d60e6f4a4d6be74 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Wed, 14 Jul 2021 13:59:40 +0800 Subject: [PATCH 0802/1469] ext4: remove conflicting comment from __ext4_forget We do a bforget and return for no journal case, so let's remove this conflict comment. Reviewed-by: Jan Kara Signed-off-by: Guoqing Jiang Link: https://lore.kernel.org/r/20210714055940.1553705-1-guoqing.jiang@linux.dev Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index b96ecba91899..b60f0152ea57 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -244,9 +244,6 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, * "bh" may be NULL: a metadata block may have been freed from memory * but there may still be a record of it in the journal, and that record * still needs to be revoked. - * - * If the handle isn't valid we're not journaling, but we still need to - * call into ext4_journal_revoke() to put the buffer head. */ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, From 32c3973d808301e7a980f80fee8818fdf7c82b09 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 17 Jul 2021 10:10:29 +0200 Subject: [PATCH 0803/1469] netfilter: flowtable: avoid possible false sharing The flowtable follows the same timeout approach as conntrack, use the same idiom as in cc16921351d8 ("netfilter: conntrack: avoid same-timeout update") but also include the fix provided by e37542ba111f ("netfilter: conntrack: avoid possible false sharing"). Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1e50908b1b7e..551976e4284c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -331,7 +331,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + u32 timeout; + + timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + if (READ_ONCE(flow->timeout) != timeout) + WRITE_ONCE(flow->timeout, timeout); if (likely(!nf_flowtable_hw_offload(flow_table))) return; From 32953df7a6eb56bd9b8f18a13034d55f9fc96cfa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 17 Jul 2021 10:20:08 +0200 Subject: [PATCH 0804/1469] netfilter: nft_last: avoid possible false sharing Use the idiom described in: https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve-performance Moreover, prevent a compiler optimization. Fixes: 836382dc2471 ("netfilter: nf_tables: add last expression") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_last.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 8088b99f2ee3..304e33cbed9b 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -48,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); - priv->last_jiffies = jiffies; - priv->last_set = 1; + if (READ_ONCE(priv->last_jiffies) != jiffies) + WRITE_ONCE(priv->last_jiffies, jiffies); + if (READ_ONCE(priv->last_set) == 0) + WRITE_ONCE(priv->last_set, 1); } static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_last_priv *priv = nft_expr_priv(expr); + unsigned long last_jiffies = READ_ONCE(priv->last_jiffies); + u32 last_set = READ_ONCE(priv->last_set); __be64 msecs; - if (time_before(jiffies, priv->last_jiffies)) - priv->last_set = 0; + if (time_before(jiffies, last_jiffies)) { + WRITE_ONCE(priv->last_set, 0); + last_set = 0; + } - if (priv->last_set) - msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + if (last_set) + msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies); else msecs = 0; - if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) || nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) goto nla_put_failure; From 30a56a2b881821625f79837d4d968c679852444e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 18 Jul 2021 18:36:00 +0200 Subject: [PATCH 0805/1469] netfilter: conntrack: adjust stop timestamp to real expiry value In case the entry is evicted via garbage collection there is delay between the timeout value and the eviction event. This adjusts the stop value based on how much time has passed. Fixes: b87a2f9199ea82 ("netfilter: conntrack: add gc worker to remove timed-out entries") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 83c52df85870..5c03e5106751 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -670,8 +670,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { From a33f387ecd5aafae514095c2c4a8c24f7aea7e8b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 20 Jul 2021 18:22:50 +0200 Subject: [PATCH 0806/1469] netfilter: nft_nat: allow to specify layer 4 protocol NAT only nft_nat reports a bogus EAFNOSUPPORT if no layer 3 information is specified. Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_nat.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 0840c635b752..be1595d6979d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; From ee7ab3f263f8131722cff3871b9618b1e7478f07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Mon, 28 Jun 2021 17:12:29 +0200 Subject: [PATCH 0807/1469] arm64: dts: armada-3720-turris-mox: remove mrvl,i2c-fast-mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some SFP modules are not detected when i2c-fast-mode is enabled even when clock-frequency is already set to 100000. The I2C bus violates the timing specifications when run in fast mode. So disable fast mode on Turris Mox. Same change was already applied for uDPU (also Armada 3720 board with SFP) in commit fe3ec631a77d ("arm64: dts: uDPU: remove i2c-fast-mode"). Fixes: 7109d817db2e ("arm64: dts: marvell: add DTS for Turris Mox") Signed-off-by: Pali Rohár Reviewed-by: Marek Behún Acked-by: Russell King (Oracle) Signed-off-by: Gregory CLEMENT --- arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index f2d7d6f071bc..a05b1ab2dd12 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -121,6 +121,7 @@ pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; clock-frequency = <100000>; + /delete-property/ mrvl,i2c-fast-mode; status = "okay"; rtc@6f { From 3b13911a2fd0dd0146c9777a254840c5466cf120 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 21 Jul 2021 19:10:08 -0400 Subject: [PATCH 0808/1469] tracing: Synthetic event field_pos is an index not a boolean Performing the following: ># echo 'wakeup_lat s32 pid; u64 delta; char wake_comm[]' > synthetic_events ># echo 'hist:keys=pid:__arg__1=common_timestamp.usecs' > events/sched/sched_waking/trigger ># echo 'hist:keys=next_pid:pid=next_pid,delta=common_timestamp.usecs-$__arg__1:onmatch(sched.sched_waking).trace(wakeup_lat,$pid,$delta,prev_comm)'\ > events/sched/sched_switch/trigger ># echo 1 > events/synthetic/enable Crashed the kernel: BUG: kernel NULL pointer dereference, address: 000000000000001b #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP CPU: 7 PID: 0 Comm: swapper/7 Not tainted 5.13.0-rc5-test+ #104 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 RIP: 0010:strlen+0x0/0x20 Code: f6 82 80 2b 0b bc 20 74 11 0f b6 50 01 48 83 c0 01 f6 82 80 2b 0b bc 20 75 ef c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 9 f8 c3 31 RSP: 0018:ffffaa75000d79d0 EFLAGS: 00010046 RAX: 0000000000000002 RBX: ffff9cdb55575270 RCX: 0000000000000000 RDX: ffff9cdb58c7a320 RSI: ffffaa75000d7b40 RDI: 000000000000001b RBP: ffffaa75000d7b40 R08: ffff9cdb40a4f010 R09: ffffaa75000d7ab8 R10: ffff9cdb4398c700 R11: 0000000000000008 R12: ffff9cdb58c7a320 R13: ffff9cdb55575270 R14: ffff9cdb58c7a000 R15: 0000000000000018 FS: 0000000000000000(0000) GS:ffff9cdb5aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001b CR3: 00000000c0612006 CR4: 00000000001706e0 Call Trace: trace_event_raw_event_synth+0x90/0x1d0 action_trace+0x5b/0x70 event_hist_trigger+0x4bd/0x4e0 ? cpumask_next_and+0x20/0x30 ? update_sd_lb_stats.constprop.0+0xf6/0x840 ? __lock_acquire.constprop.0+0x125/0x550 ? find_held_lock+0x32/0x90 ? sched_clock_cpu+0xe/0xd0 ? lock_release+0x155/0x440 ? update_load_avg+0x8c/0x6f0 ? enqueue_entity+0x18a/0x920 ? __rb_reserve_next+0xe5/0x460 ? ring_buffer_lock_reserve+0x12a/0x3f0 event_triggers_call+0x52/0xe0 trace_event_buffer_commit+0x1ae/0x240 trace_event_raw_event_sched_switch+0x114/0x170 __traceiter_sched_switch+0x39/0x50 __schedule+0x431/0xb00 schedule_idle+0x28/0x40 do_idle+0x198/0x2e0 cpu_startup_entry+0x19/0x20 secondary_startup_64_no_verify+0xc2/0xcb The reason is that the dynamic events array keeps track of the field position of the fields array, via the field_pos variable in the synth_field structure. Unfortunately, that field is a boolean for some reason, which means any field_pos greater than 1 will be a bug (in this case it was 2). Link: https://lkml.kernel.org/r/20210721191008.638bce34@oasis.local.home Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Ingo Molnar Cc: Andrew Morton Cc: stable@vger.kernel.org Fixes: bd82631d7ccdc ("tracing: Add support for dynamic strings to synthetic events") Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_synth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h index 6e146b959dcd..4007fe95cf42 100644 --- a/kernel/trace/trace_synth.h +++ b/kernel/trace/trace_synth.h @@ -14,10 +14,10 @@ struct synth_field { char *name; size_t size; unsigned int offset; + unsigned int field_pos; bool is_signed; bool is_string; bool is_dynamic; - bool field_pos; }; struct synth_event { From 1e3bac71c5053c99d438771fc9fa5082ae5d90aa Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 21 Jul 2021 11:00:53 -0400 Subject: [PATCH 0809/1469] tracing/histogram: Rename "cpu" to "common_cpu" Currently the histogram logic allows the user to write "cpu" in as an event field, and it will record the CPU that the event happened on. The problem with this is that there's a lot of events that have "cpu" as a real field, and using "cpu" as the CPU it ran on, makes it impossible to run histograms on the "cpu" field of events. For example, if I want to have a histogram on the count of the workqueue_queue_work event on its cpu field, running: ># echo 'hist:keys=cpu' > events/workqueue/workqueue_queue_work/trigger Gives a misleading and wrong result. Change the command to "common_cpu" as no event should have "common_*" fields as that's a reserved name for fields used by all events. And this makes sense here as common_cpu would be a field used by all events. Now we can even do: ># echo 'hist:keys=common_cpu,cpu if cpu < 100' > events/workqueue/workqueue_queue_work/trigger ># cat events/workqueue/workqueue_queue_work/hist # event histogram # # trigger info: hist:keys=common_cpu,cpu:vals=hitcount:sort=hitcount:size=2048 if cpu < 100 [active] # { common_cpu: 0, cpu: 2 } hitcount: 1 { common_cpu: 0, cpu: 4 } hitcount: 1 { common_cpu: 7, cpu: 7 } hitcount: 1 { common_cpu: 0, cpu: 7 } hitcount: 1 { common_cpu: 0, cpu: 1 } hitcount: 1 { common_cpu: 0, cpu: 6 } hitcount: 2 { common_cpu: 0, cpu: 5 } hitcount: 2 { common_cpu: 1, cpu: 1 } hitcount: 4 { common_cpu: 6, cpu: 6 } hitcount: 4 { common_cpu: 5, cpu: 5 } hitcount: 14 { common_cpu: 4, cpu: 4 } hitcount: 26 { common_cpu: 0, cpu: 0 } hitcount: 39 { common_cpu: 2, cpu: 2 } hitcount: 184 Now for backward compatibility, I added a trick. If "cpu" is used, and the field is not found, it will fall back to "common_cpu" and work as it did before. This way, it will still work for old programs that use "cpu" to get the actual CPU, but if the event has a "cpu" as a field, it will get that event's "cpu" field, which is probably what it wants anyway. I updated the tracefs/README to include documentation about both the common_timestamp and the common_cpu. This way, if that text is present in the README, then an application can know that common_cpu is supported over just plain "cpu". Link: https://lkml.kernel.org/r/20210721110053.26b4f641@oasis.local.home Cc: Namhyung Kim Cc: Ingo Molnar Cc: Andrew Morton Cc: stable@vger.kernel.org Fixes: 8b7622bf94a44 ("tracing: Add cpu field for hist triggers") Reviewed-by: Tom Zanussi Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- Documentation/trace/histogram.rst | 2 +- kernel/trace/trace.c | 4 ++++ kernel/trace/trace_events_hist.c | 22 ++++++++++++++++------ 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index b71e09f745c3..f99be8062bc8 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -191,7 +191,7 @@ Documentation written by Tom Zanussi with the event, in nanoseconds. May be modified by .usecs to have timestamps interpreted as microseconds. - cpu int the cpu on which the event occurred. + common_cpu int the cpu on which the event occurred. ====================== ==== ======================================= Extended error information diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f8b80b5bab71..c59dd35a6da5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5609,6 +5609,10 @@ static const char readme_msg[] = "\t [:name=histname1]\n" "\t [:.]\n" "\t [if ]\n\n" + "\t Note, special fields can be used as well:\n" + "\t common_timestamp - to record current timestamp\n" + "\t common_cpu - to record the CPU the event happened on\n" + "\n" "\t When a matching event is hit, an entry is added to a hash\n" "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 16a9dfc9fffc..34325f41ebc0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1111,7 +1111,7 @@ static const char *hist_field_name(struct hist_field *field, field->flags & HIST_FIELD_FL_ALIAS) field_name = hist_field_name(field->operands[0], ++level); else if (field->flags & HIST_FIELD_FL_CPU) - field_name = "cpu"; + field_name = "common_cpu"; else if (field->flags & HIST_FIELD_FL_EXPR || field->flags & HIST_FIELD_FL_VAR_REF) { if (field->system) { @@ -1991,14 +1991,24 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "cpu") == 0) + } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; else { field = trace_find_event_field(file->event_call, field_name); if (!field || !field->size) { - hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); - field = ERR_PTR(-EINVAL); - goto out; + /* + * For backward compatibility, if field_name + * was "cpu", then we treat this the same as + * common_cpu. + */ + if (strcmp(field_name, "cpu") == 0) { + *flags |= HIST_FIELD_FL_CPU; + } else { + hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, + errpos(field_name)); + field = ERR_PTR(-EINVAL); + goto out; + } } } out: @@ -5085,7 +5095,7 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) seq_printf(m, "%s=", hist_field->var.name); if (hist_field->flags & HIST_FIELD_FL_CPU) - seq_puts(m, "cpu"); + seq_puts(m, "common_cpu"); else if (field_name) { if (hist_field->flags & HIST_FIELD_FL_VAR_REF || hist_field->flags & HIST_FIELD_FL_ALIAS) From 217e26bd87b2930856726b48a4e71c768b8c9bf5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:22:32 +0200 Subject: [PATCH 0810/1469] netfilter: nfnl_hook: fix unused variable warning The only user of this variable is in an #ifdef: net/netfilter/nfnetlink_hook.c: In function 'nfnl_hook_entries_head': net/netfilter/nfnetlink_hook.c:177:28: error: unused variable 'netdev' [-Werror=unused-variable] Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Arnd Bergmann Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_hook.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 50b4e3c9347a..202f57d17bab 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -174,7 +174,9 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; +#ifdef CONFIG_NETFILTER_INGRESS struct net_device *netdev; +#endif switch (pf) { case NFPROTO_IPV4: From 9528c19507dc9bc3d6cd96f4611d7cb80c5afcde Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 21 Jul 2021 19:53:41 -0400 Subject: [PATCH 0811/1469] tracing: Clean up alloc_synth_event() alloc_synth_event() currently has the following code to initialize the event fields and dynamic_fields: for (i = 0, j = 0; i < n_fields; i++) { event->fields[i] = fields[i]; if (fields[i]->is_dynamic) { event->dynamic_fields[j] = fields[i]; event->dynamic_fields[j]->field_pos = i; event->dynamic_fields[j++] = fields[i]; event->n_dynamic_fields++; } } 1) It would make more sense to have all fields keep track of their field_pos. 2) event->dynmaic_fields[j] is assigned twice for no reason. 3) We can move updating event->n_dynamic_fields outside the loop, and just assign it to j. This combination makes the code much cleaner. Link: https://lkml.kernel.org/r/20210721195341.29bb0f77@oasis.local.home Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_synth.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 2ac75eb6aa86..9315fc03e303 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -893,15 +893,13 @@ static struct synth_event *alloc_synth_event(const char *name, int n_fields, dyn_event_init(&event->devent, &synth_event_ops); for (i = 0, j = 0; i < n_fields; i++) { + fields[i]->field_pos = i; event->fields[i] = fields[i]; - if (fields[i]->is_dynamic) { - event->dynamic_fields[j] = fields[i]; - event->dynamic_fields[j]->field_pos = i; + if (fields[i]->is_dynamic) event->dynamic_fields[j++] = fields[i]; - event->n_dynamic_fields++; - } } + event->n_dynamic_fields = j; event->n_fields = n_fields; out: return event; From 68e83498cb4fad31963b5c76a71e80b824bc316e Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Wed, 21 Jul 2021 13:47:26 +0200 Subject: [PATCH 0812/1469] ftrace: Avoid synchronize_rcu_tasks_rude() call when not necessary synchronize_rcu_tasks_rude() triggers IPIs and forces rescheduling on all CPUs. It is a costly operation and, when targeting nohz_full CPUs, very disrupting (hence the name). So avoid calling it when 'old_hash' doesn't need to be freed. Link: https://lkml.kernel.org/r/20210721114726.1545103-1-nsaenzju@redhat.com Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e6fb3e6e1ffc..4fbcf560dd03 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5985,7 +5985,8 @@ ftrace_graph_release(struct inode *inode, struct file *file) * infrastructure to do the synchronization, thus we must do it * ourselves. */ - synchronize_rcu_tasks_rude(); + if (old_hash != EMPTY_HASH) + synchronize_rcu_tasks_rude(); free_ftrace_hash(old_hash); } From 3b1a8f457fcf105924c72e99f1191834837c978d Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 21 Jul 2021 13:09:15 +0100 Subject: [PATCH 0813/1469] ftrace: Remove redundant initialization of variable ret The variable ret is being initialized with a value that is never read, it is being updated later on. The assignment is redundant and can be removed. Link: https://lkml.kernel.org/r/20210721120915.122278-1-colin.king@canonical.com Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4fbcf560dd03..7b180f61e6d3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7545,7 +7545,7 @@ int ftrace_is_dead(void) */ int register_ftrace_function(struct ftrace_ops *ops) { - int ret = -1; + int ret; ftrace_ops_init(ops); From 352384d5c84ebe40fa77098cc234fe173247d8ef Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 22 Jul 2021 21:52:18 -0400 Subject: [PATCH 0814/1469] tracepoints: Update static_call before tp_funcs when adding a tracepoint Because of the significant overhead that retpolines pose on indirect calls, the tracepoint code was updated to use the new "static_calls" that can modify the running code to directly call a function instead of using an indirect caller, and this function can be changed at runtime. In the tracepoint code that calls all the registered callbacks that are attached to a tracepoint, the following is done: it_func_ptr = rcu_dereference_raw((&__tracepoint_##name)->funcs); if (it_func_ptr) { __data = (it_func_ptr)->data; static_call(tp_func_##name)(__data, args); } If there's just a single callback, the static_call is updated to just call that callback directly. Once another handler is added, then the static caller is updated to call the iterator, that simply loops over all the funcs in the array and calls each of the callbacks like the old method using indirect calling. The issue was discovered with a race between updating the funcs array and updating the static_call. The funcs array was updated first and then the static_call was updated. This is not an issue as long as the first element in the old array is the same as the first element in the new array. But that assumption is incorrect, because callbacks also have a priority field, and if there's a callback added that has a higher priority than the callback on the old array, then it will become the first callback in the new array. This means that it is possible to call the old callback with the new callback data element, which can cause a kernel panic. static_call = callback1() funcs[] = {callback1,data1}; callback2 has higher priority than callback1 CPU 1 CPU 2 ----- ----- new_funcs = {callback2,data2}, {callback1,data1} rcu_assign_pointer(tp->funcs, new_funcs); /* * Now tp->funcs has the new array * but the static_call still calls callback1 */ it_func_ptr = tp->funcs [ new_funcs ] data = it_func_ptr->data [ data2 ] static_call(callback1, data); /* Now callback1 is called with * callback2's data */ [ KERNEL PANIC ] update_static_call(iterator); To prevent this from happening, always switch the static_call to the iterator before assigning the tp->funcs to the new array. The iterator will always properly match the callback with its data. To trigger this bug: In one terminal: while :; do hackbench 50; done In another terminal echo 1 > /sys/kernel/tracing/events/sched/sched_waking/enable while :; do echo 1 > /sys/kernel/tracing/set_event_pid; sleep 0.5 echo 0 > /sys/kernel/tracing/set_event_pid; sleep 0.5 done And it doesn't take long to crash. This is because the set_event_pid adds a callback to the sched_waking tracepoint with a high priority, which will be called before the sched_waking trace event callback is called. Note, the removal to a single callback updates the array first, before changing the static_call to single callback, which is the proper order as the first element in the array is the same as what the static_call is being changed to. Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/ Cc: stable@vger.kernel.org Fixes: d25e37d89dd2f ("tracepoint: Optimize using static_call()") Reported-by: Stefan Metzmacher tested-by: Stefan Metzmacher Signed-off-by: Steven Rostedt (VMware) --- kernel/tracepoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 976bf8ce8039..fc32821f8240 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -299,8 +299,8 @@ static int tracepoint_add_func(struct tracepoint *tp, * a pointer to it. This array is referenced by __DO_TRACE from * include/linux/tracepoint.h using rcu_dereference_sched(). */ - rcu_assign_pointer(tp->funcs, tp_funcs); tracepoint_update_call(tp, tp_funcs, false); + rcu_assign_pointer(tp->funcs, tp_funcs); static_key_enable(&tp->key); release_probes(old); From 65662a8dcdd01342b71ee44234bcfd0162e195af Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Thu, 29 Apr 2021 19:49:47 +0200 Subject: [PATCH 0815/1469] i40e: Fix logic of disabling queues Correct the message flow between driver and firmware when disabling queues. Previously in case of PF reset (due to required reinit after reconfig), the error like: "VSI seid 397 Tx ring 60 disable timeout" could show up occasionally. The error was not a real issue of hardware or firmware, it was caused by wrong sequence of messages invoked by the driver. Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Aleksandr Loktionov Signed-off-by: Arkadiusz Kubalewski Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 58 ++++++++++++--------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 861e59a350bd..5297e6c59083 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4454,11 +4454,10 @@ int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, } /** - * i40e_vsi_control_tx - Start or stop a VSI's rings + * i40e_vsi_enable_tx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_tx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; @@ -4467,7 +4466,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q, - false /*is xdp*/, enable); + false /*is xdp*/, true); if (ret) break; @@ -4476,7 +4475,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q + vsi->alloc_queue_pairs, - true /*is xdp*/, enable); + true /*is xdp*/, true); if (ret) break; } @@ -4574,32 +4573,25 @@ int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable) } /** - * i40e_vsi_control_rx - Start or stop a VSI's rings + * i40e_vsi_enable_rx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_rx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - ret = i40e_control_wait_rx_q(pf, pf_q, enable); + ret = i40e_control_wait_rx_q(pf, pf_q, true); if (ret) { dev_info(&pf->pdev->dev, - "VSI seid %d Rx ring %d %sable timeout\n", - vsi->seid, pf_q, (enable ? "en" : "dis")); + "VSI seid %d Rx ring %d enable timeout\n", + vsi->seid, pf_q); break; } } - /* Due to HW errata, on Rx disable only, the register can indicate done - * before it really is. Needs 50ms to be sure - */ - if (!enable) - mdelay(50); - return ret; } @@ -4612,29 +4604,47 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) int ret = 0; /* do rx first for enable and last for disable */ - ret = i40e_vsi_control_rx(vsi, true); + ret = i40e_vsi_enable_rx(vsi); if (ret) return ret; - ret = i40e_vsi_control_tx(vsi, true); + ret = i40e_vsi_enable_tx(vsi); return ret; } +#define I40E_DISABLE_TX_GAP_MSEC 50 + /** * i40e_vsi_stop_rings - Stop a VSI's rings * @vsi: the VSI being configured **/ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { + struct i40e_pf *pf = vsi->back; + int pf_q, err, q_end; + /* When port TX is suspended, don't wait */ if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) return i40e_vsi_stop_rings_no_wait(vsi); - /* do rx first for enable and last for disable - * Ignore return value, we need to shutdown whatever we can - */ - i40e_vsi_control_tx(vsi, false); - i40e_vsi_control_rx(vsi, false); + q_end = vsi->base_queue + vsi->num_queue_pairs; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false); + + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) { + err = i40e_control_wait_rx_q(pf, pf_q, false); + if (err) + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d dissable timeout\n", + vsi->seid, pf_q); + } + + msleep(I40E_DISABLE_TX_GAP_MSEC); + pf_q = vsi->base_queue; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0); + + i40e_vsi_wait_queues_disabled(vsi); } /** From 71d6fdba4b2d82fdd883fec31dee77fbcf59773a Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Fri, 21 May 2021 18:41:26 +0200 Subject: [PATCH 0816/1469] i40e: Fix firmware LLDP agent related warning Make warning meaningful for the user. Previously the trace: "Starting FW LLDP agent failed: error: I40E_ERR_ADMIN_QUEUE_ERROR, I40E_AQ_RC_EAGAIN" was produced when user tried to start Firmware LLDP agent, just after it was stopped with sequence: ethtool --set-priv-flags disable-fw-lldp on ethtool --set-priv-flags disable-fw-lldp off (without any delay between the commands) At that point the firmware is still processing stop command, the behavior is expected. Fixes: c1041d070437 ("i40e: Missing response checks in driver when starting/stopping FW LLDP") Signed-off-by: Aleksandr Loktionov Signed-off-by: Arkadiusz Kubalewski Tested-by: Imam Hassan Reza Biswas Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 3e822bad4851..d9e26f9713a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5294,6 +5294,10 @@ flags_complete: dev_warn(&pf->pdev->dev, "Device configuration forbids SW from starting the LLDP agent.\n"); return -EINVAL; + case I40E_AQ_RC_EAGAIN: + dev_warn(&pf->pdev->dev, + "Stop FW LLDP agent command is still being processed, please try again in a second.\n"); + return -EBUSY; default: dev_warn(&pf->pdev->dev, "Starting FW LLDP agent failed: error: %s, %s\n", From dc614c46178b0b89bde86ac54fc687a28580d2b7 Mon Sep 17 00:00:00 2001 From: Lukasz Cieplicki Date: Mon, 31 May 2021 16:55:49 +0000 Subject: [PATCH 0817/1469] i40e: Add additional info to PHY type error In case of PHY type error occurs, the message was too generic. Add additional info to PHY type error indicating that it can be wrong cable connected. Fixes: 124ed15bf126 ("i40e: Add dual speed module support") Signed-off-by: Lukasz Cieplicki Signed-off-by: Michal Maloszewski Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d9e26f9713a5..2c9e4eeb7270 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -980,7 +980,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, default: /* if we got here and link is up something bad is afoot */ netdev_info(netdev, - "WARNING: Link is up but PHY type 0x%x is not recognized.\n", + "WARNING: Link is up but PHY type 0x%x is not recognized, or incorrect cable is in use\n", hw_link_info->phy_type); } From 89ec1f0886c127c7e41ac61a6b6d539f4fb2510b Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Wed, 2 Jun 2021 00:47:03 +0000 Subject: [PATCH 0818/1469] i40e: Fix queue-to-TC mapping on Tx In SW DCB mode the packets sent receive incorrect UP tags. They are constructed correctly and put into tx_ring, but UP is later remapped by HW on the basis of TCTUPR register contents according to Tx queue selected, and BW used is consistent with the new UP values. This is caused by Tx queue selection in kernel not taking into account DCB configuration. This patch fixes the issue by implementing the ndo_select_queue NDO callback. Fixes: fd0a05ce74ef ("i40e: transmit, receive, and NAPI") Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Jedrzej Jagielski Tested-by: Imam Hassan Reza Biswas Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 50 +++++++++++++++++++++ drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 + 3 files changed, 53 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5297e6c59083..278077208f37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13271,6 +13271,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_poll_controller = i40e_netpoll, #endif .ndo_setup_tc = __i40e_setup_tc, + .ndo_select_queue = i40e_lan_select_queue, .ndo_set_features = i40e_set_features, .ndo_set_vf_mac = i40e_ndo_set_vf_mac, .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 38eb8151ee9a..3f25bd8c4924 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3631,6 +3631,56 @@ dma_error: return -1; } +static u16 i40e_swdcb_skb_tx_hash(struct net_device *dev, + const struct sk_buff *skb, + u16 num_tx_queues) +{ + u32 jhash_initval_salt = 0xd631614b; + u32 hash; + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16)skb->protocol ^ skb->hash; + + hash = jhash_1word(hash, jhash_initval_salt); + + return (u16)(((u64)hash * num_tx_queues) >> 32); +} + +u16 i40e_lan_select_queue(struct net_device *netdev, + struct sk_buff *skb, + struct net_device __always_unused *sb_dev) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_hw *hw; + u16 qoffset; + u16 qcount; + u8 tclass; + u16 hash; + u8 prio; + + /* is DCB enabled at all? */ + if (vsi->tc_config.numtc == 1) + return i40e_swdcb_skb_tx_hash(netdev, skb, + netdev->real_num_tx_queues); + + prio = skb->priority; + hw = &vsi->back->hw; + tclass = hw->local_dcbx_config.etscfg.prioritytable[prio]; + /* sanity check */ + if (unlikely(!(vsi->tc_config.enabled_tc & BIT(tclass)))) + tclass = 0; + + /* select a queue assigned for the given TC */ + qcount = vsi->tc_config.tc_info[tclass].qcount; + hash = i40e_swdcb_skb_tx_hash(netdev, skb, qcount); + + qoffset = vsi->tc_config.tc_info[tclass].qoffset; + return qoffset + hash; +} + /** * i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring * @xdpf: data to transmit diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 86fed05b4f19..bfc2845c99d1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -451,6 +451,8 @@ static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +u16 i40e_lan_select_queue(struct net_device *netdev, struct sk_buff *skb, + struct net_device *sb_dev); void i40e_clean_tx_ring(struct i40e_ring *tx_ring); void i40e_clean_rx_ring(struct i40e_ring *rx_ring); int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring); From ea52faae1d17cd3048681d86d2e8641f44de484d Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Fri, 18 Jun 2021 08:49:49 +0000 Subject: [PATCH 0819/1469] i40e: Fix log TC creation failure when max num of queues is exceeded Fix missing failed message if driver does not have enough queues to complete TC command. Without this fix no message is displayed in dmesg. Fixes: a9ce82f744dc ("i40e: Enable 'channel' mode in mqprio for TC configs") Signed-off-by: Grzegorz Szczurek Signed-off-by: Jedrzej Jagielski Tested-by: Imam Hassan Reza Biswas Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 278077208f37..1d1f52756a93 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7290,6 +7290,8 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, } if (vsi->num_queue_pairs < (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + dev_err(&vsi->back->pdev->dev, + "Failed to create traffic channel, insufficient number of queues.\n"); return -EINVAL; } if (sum_max_rate > i40e_get_link_speed(vsi)) { From d72e91efcae12f2f24ced984d00d60517c677857 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Thu, 22 Jul 2021 18:15:51 +0530 Subject: [PATCH 0820/1469] octeontx2-af: Remove unnecessary devm_kfree Remove devm_kfree of memory where VLAN entry to RVU PF mapping info is saved. This will be freed anyway at driver exit. Having this could result in warning from devm_kfree() if the memory is not allocated due to errors in rvu_nix_block_init() before nix_setup_txvlan(). Fixes: 9a946def264d ("octeontx2-af: Modify nix_vtag_cfg mailbox to support TX VTAG entries") Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0933699a0d2d..0d2cd5169018 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3842,7 +3842,6 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr, vlan = &nix_hw->txvlan; kfree(vlan->rsrc.bmap); mutex_destroy(&vlan->rsrc_lock); - devm_kfree(rvu->dev, vlan->entry2pfvf_map); mcast = &nix_hw->mcast; qmem_free(rvu->dev, mcast->mce_ctx); From f8dd60de194817c86bf812700980762bb5a8d9a4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 22 Jul 2021 12:05:41 -0400 Subject: [PATCH 0821/1469] tipc: fix implicit-connect for SYN+ For implicit-connect, when it's either SYN- or SYN+, an ACK should be sent back to the client immediately. It's not appropriate for the client to enter established state only after receiving data from the server. On client side, after the SYN is sent out, tipc_wait_for_connect() should be called to wait for the ACK if timeout is set. This patch also restricts __tipc_sendstream() to call __sendmsg() only when it's in TIPC_OPEN state, so that the client can program in a single loop doing both connecting and data sending like: for (...) sendmsg(dest, buf); This makes the implicit-connect more implicit. Fixes: b97bf3fd8f6a ("[TIPC] Initial merge") Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/socket.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 34a97ea36cc8..ebd300c26a44 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk); static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz); static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack); +static int tipc_wait_for_connect(struct socket *sock, long *timeo_p); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = 0; } - if (unlikely(syn && !rc)) + if (unlikely(syn && !rc)) { tipc_set_sk_state(sk, TIPC_CONNECTING); + if (timeout) { + timeout = msecs_to_jiffies(timeout); + tipc_wait_for_connect(sock, &timeout); + } + } return rc ? rc : dlen; } @@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) return -EMSGSIZE; /* Handle implicit connection setup */ - if (unlikely(dest)) { + if (unlikely(dest && sk->sk_state == TIPC_OPEN)) { rc = __tipc_sendmsg(sock, m, dlen); if (dlen && dlen == rc) { tsk->peer_caps = tipc_node_get_capabilities(net, dnode); @@ -2689,9 +2695,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, bool kern) { struct sock *new_sk, *sk = sock->sk; - struct sk_buff *buf; struct tipc_sock *new_tsock; + struct msghdr m = {NULL,}; struct tipc_msg *msg; + struct sk_buff *buf; long timeo; int res; @@ -2737,19 +2744,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, } /* - * Respond to 'SYN-' by discarding it & returning 'ACK'-. - * Respond to 'SYN+' by queuing it on new socket. + * Respond to 'SYN-' by discarding it & returning 'ACK'. + * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'. */ if (!msg_data_sz(msg)) { - struct msghdr m = {NULL,}; - tsk_advance_rx_queue(sk); - __tipc_sendstream(new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } + __tipc_sendstream(new_sock, &m, 0); release_sock(new_sk); exit: release_sock(sk); From d237a7f11719ff9320721be5818352e48071aab6 Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Fri, 23 Jul 2021 09:25:34 +0700 Subject: [PATCH 0822/1469] tipc: fix sleeping in tipc accept routine The release_sock() is blocking function, it would change the state after sleeping. In order to evaluate the stated condition outside the socket lock context, switch to use wait_woken() instead. Fixes: 6398e23cdb1d8 ("tipc: standardize accept routine") Acked-by: Jon Maloy Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/socket.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ebd300c26a44..75b99b7eda22 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2652,7 +2652,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -2661,12 +2661,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2678,7 +2678,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } From 227adfb2b1dfbc53dfc53b9dd7a93a6298ff7c56 Mon Sep 17 00:00:00 2001 From: Gilad Naaman Date: Thu, 22 Jul 2021 20:01:28 +0300 Subject: [PATCH 0823/1469] net: Set true network header for ECN decapsulation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In cases where the header straight after the tunnel header was another ethernet header (TEB), instead of the network header, the ECN decapsulation code would treat the ethernet header as if it was an IP header, resulting in mishandling and possible wrong drops or corruption of the IP header. In this case, ECT(1) is sent, so IP_ECN_decapsulate tries to copy it to the inner IPv4 header, and correct its checksum. The offset of the ECT bits in an IPv4 header corresponds to the lower 2 bits of the second octet of the destination MAC address in the ethernet header. The IPv4 checksum corresponds to end of the source address. In order to reproduce: $ ip netns add A $ ip netns add B $ ip -n A link add _v0 type veth peer name _v1 netns B $ ip -n A link set _v0 up $ ip -n A addr add dev _v0 10.254.3.1/24 $ ip -n A route add default dev _v0 scope global $ ip -n B link set _v1 up $ ip -n B addr add dev _v1 10.254.1.6/24 $ ip -n B route add default dev _v1 scope global $ ip -n B link add gre1 type gretap local 10.254.1.6 remote 10.254.3.1 key 0x49000000 $ ip -n B link set gre1 up # Now send an IPv4/GRE/Eth/IPv4 frame where the outer header has ECT(1), # and the inner header has no ECT bits set: $ cat send_pkt.py #!/usr/bin/env python3 from scapy.all import * pkt = IP(b'E\x01\x00\xa7\x00\x00\x00\x00@/`%\n\xfe\x03\x01\n\xfe\x01\x06 \x00eXI\x00' b'\x00\x00\x18\xbe\x92\xa0\xee&\x18\xb0\x92\xa0l&\x08\x00E\x00\x00}\x8b\x85' b'@\x00\x01\x01\xe4\xf2\x82\x82\x82\x01\x82\x82\x82\x02\x08\x00d\x11\xa6\xeb' b'3\x1e\x1e\\xf3\\xf7`\x00\x00\x00\x00ZN\x00\x00\x00\x00\x00\x00\x10\x11\x12' b'\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./01234' b'56789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ') send(pkt) $ sudo ip netns exec B tcpdump -neqlllvi gre1 icmp & ; sleep 1 $ sudo ip netns exec A python3 send_pkt.py In the original packet, the source/destinatio MAC addresses are dst=18:be:92:a0:ee:26 src=18:b0:92:a0:6c:26 In the received packet, they are dst=18:bd:92:a0:ee:26 src=18:b0:92:a0:6c:27 Thanks to Lahav Schlesinger and Isaac Garzon for helping me pinpoint the origin. Fixes: b723748750ec ("tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040") Cc: David S. Miller Cc: Hideaki YOSHIFUJI Cc: David Ahern Cc: Jakub Kicinski Cc: Toke Høiland-Jørgensen Signed-off-by: Gilad Naaman Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0dca00745ac3..be75b409445c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } - skb_reset_network_header(skb); + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { From 46c7655f0b56b1ac864115441064cde9ed124f4a Mon Sep 17 00:00:00 2001 From: Kangmin Park Date: Fri, 23 Jul 2021 02:44:43 +0900 Subject: [PATCH 0824/1469] ipv6: decrease hop limit counter in ip6_forward() Decrease hop limit counter when deliver skb to ndp proxy. Signed-off-by: Kangmin Park Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e1b9f7ac8bad..8e6ca9ad6812 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -549,9 +549,10 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); - if (proxied > 0) + if (proxied > 0) { + hdr->hop_limit--; return ip6_input(skb); - else if (proxied < 0) { + } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } From 798a315fc359aa6dbe48e09d802aa59b7e158ffc Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Thu, 1 Jul 2021 16:09:55 +0800 Subject: [PATCH 0825/1469] pinctrl: mediatek: Fix fallback behavior for bias_set_combo Some pin doesn't support PUPD register, if it fails and fallbacks with bias_set_combo case, it will call mtk_pinconf_bias_set_pupd_r1_r0() to modify the PUPD pin again. Since the general bias set are either PU/PD or PULLSEL/PULLEN, try bias_set or bias_set_rev1 for the other fallback case. If the pin doesn't support neither PU/PD nor PULLSEL/PULLEN, it will return -ENOTSUPP. Fixes: 81bd1579b43e ("pinctrl: mediatek: Fix fallback call path") Signed-off-by: Hsin-Yi Wang Reviewed-by: Chen-Yu Tsai Reviewed-by: Zhiyong Tao Link: https://lore.kernel.org/r/20210701080955.2660294-1-hsinyi@chromium.org Signed-off-by: Linus Walleij --- drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 5b3b048725cc..45ebdeba985a 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -925,12 +925,10 @@ int mtk_pinconf_adv_pull_set(struct mtk_pinctrl *hw, err = hw->soc->bias_set(hw, desc, pullup); if (err) return err; - } else if (hw->soc->bias_set_combo) { - err = hw->soc->bias_set_combo(hw, desc, pullup, arg); - if (err) - return err; } else { - return -ENOTSUPP; + err = mtk_pinconf_bias_set_rev1(hw, desc, pullup); + if (err) + err = mtk_pinconf_bias_set(hw, desc, pullup); } } From c92c74131a84b508aa8f079a25d7bbe10748449e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 22 Jul 2021 16:05:51 +0300 Subject: [PATCH 0826/1469] net: dsa: mv88e6xxx: silently accept the deletion of VID 0 too The blamed commit modified the driver to accept the addition of VID 0 without doing anything, but deleting that VID still fails: [ 32.080780] mv88e6085 d0032004.mdio-mii:10 lan8: failed to kill vid 0081/0 Modify mv88e6xxx_port_vlan_leave() to do the same thing as the addition. Fixes: b8b79c414eca ("net: dsa: mv88e6xxx: Fix adding vlan 0") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index beb41572d04e..272b0535d946 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2155,7 +2155,7 @@ static int mv88e6xxx_port_vlan_leave(struct mv88e6xxx_chip *chip, int i, err; if (!vid) - return -EOPNOTSUPP; + return 0; err = mv88e6xxx_vtu_get(chip, vid, &vlan); if (err) From 68d1f1d4af188c290087958c75c7b89a816e1137 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Thu, 22 Jul 2021 20:21:05 +0200 Subject: [PATCH 0827/1469] wwan: core: Fix missing RTM_NEWLINK event for default link A wwan link created via the wwan_create_default_link procedure is never notified to the user (RTM_NEWLINK), causing issues with user tools relying on such event to track network links (NetworkManager). This is because the procedure misses a call to rtnl_configure_link(), which sets the link as initialized and notifies the new link (cf proper usage in __rtnl_newlink()). Cc: stable@vger.kernel.org Fixes: ca374290aaad ("wwan: core: support default netdev creation") Suggested-by: Sergey Ryazanov Signed-off-by: Loic Poulain Acked-by: Sergey Ryazanov Signed-off-by: David S. Miller --- drivers/net/wwan/wwan_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 3e16c318e705..674a81d79db3 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -984,6 +984,8 @@ static void wwan_create_default_link(struct wwan_device *wwandev, goto unlock; } + rtnl_configure_link(dev, NULL); /* Link initialized, notify new link */ + unlock: rtnl_unlock(); From 3ce6e1f662a910970880188ea7bfd00542bd3934 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 6 Jul 2021 23:40:34 +0900 Subject: [PATCH 0828/1469] loop: reintroduce global lock for safe loop_validate_file() traversal Commit 6cc8e7430801fa23 ("loop: scale loop device by introducing per device lock") re-opened a race window for NULL pointer dereference at loop_validate_file() where commit 310ca162d779efee ("block/loop: Use global lock for ioctl() operation.") has closed. Although we need to guarantee that other loop devices will not change during traversal, we can't take remote "struct loop_device"->lo_mutex inside loop_validate_file() in order to avoid AB-BA deadlock. Therefore, introduce a global lock dedicated for loop_validate_file() which is conditionally taken before local "struct loop_device"->lo_mutex is taken. Signed-off-by: Tetsuo Handa Fixes: 6cc8e7430801fa23 ("loop: scale loop device by introducing per device lock") Signed-off-by: Jens Axboe --- drivers/block/loop.c | 128 ++++++++++++++++++++++++++++++++----------- 1 file changed, 97 insertions(+), 31 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f37b9e3d833c..f0cdff0c5fbf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -88,6 +88,47 @@ static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); +static DEFINE_MUTEX(loop_validate_mutex); + +/** + * loop_global_lock_killable() - take locks for safe loop_validate_file() test + * + * @lo: struct loop_device + * @global: true if @lo is about to bind another "struct loop_device", false otherwise + * + * Returns 0 on success, -EINTR otherwise. + * + * Since loop_validate_file() traverses on other "struct loop_device" if + * is_loop_device() is true, we need a global lock for serializing concurrent + * loop_configure()/loop_change_fd()/__loop_clr_fd() calls. + */ +static int loop_global_lock_killable(struct loop_device *lo, bool global) +{ + int err; + + if (global) { + err = mutex_lock_killable(&loop_validate_mutex); + if (err) + return err; + } + err = mutex_lock_killable(&lo->lo_mutex); + if (err && global) + mutex_unlock(&loop_validate_mutex); + return err; +} + +/** + * loop_global_unlock() - release locks taken by loop_global_lock_killable() + * + * @lo: struct loop_device + * @global: true if @lo was about to bind another "struct loop_device", false otherwise + */ +static void loop_global_unlock(struct loop_device *lo, bool global) +{ + mutex_unlock(&lo->lo_mutex); + if (global) + mutex_unlock(&loop_validate_mutex); +} static int max_part; static int part_shift; @@ -672,13 +713,15 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) while (is_loop_device(f)) { struct loop_device *l; + lockdep_assert_held(&loop_validate_mutex); if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; - if (l->lo_state != Lo_bound) { + if (l->lo_state != Lo_bound) return -EINVAL; - } + /* Order wrt setting lo->lo_backing_file in loop_configure(). */ + rmb(); f = l->lo_backing_file; } if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) @@ -697,13 +740,18 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { - struct file *file = NULL, *old_file; - int error; - bool partscan; + struct file *file = fget(arg); + struct file *old_file; + int error; + bool partscan; + bool is_loop; - error = mutex_lock_killable(&lo->lo_mutex); + if (!file) + return -EBADF; + is_loop = is_loop_device(file); + error = loop_global_lock_killable(lo, is_loop); if (error) - return error; + goto out_putf; error = -ENXIO; if (lo->lo_state != Lo_bound) goto out_err; @@ -713,11 +761,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out_err; - error = -EBADF; - file = fget(arg); - if (!file) - goto out_err; - error = loop_validate_file(file, bdev); if (error) goto out_err; @@ -740,7 +783,16 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); + + /* + * Flush loop_validate_file() before fput(), for l->lo_backing_file + * might be pointing at old_file which might be the last reference. + */ + if (!is_loop) { + mutex_lock(&loop_validate_mutex); + mutex_unlock(&loop_validate_mutex); + } /* * We must drop file reference outside of lo_mutex as dropping * the file ref can take open_mutex which creates circular locking @@ -752,9 +804,9 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, return 0; out_err: - mutex_unlock(&lo->lo_mutex); - if (file) - fput(file); + loop_global_unlock(lo, is_loop); +out_putf: + fput(file); return error; } @@ -1136,22 +1188,22 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, struct block_device *bdev, const struct loop_config *config) { - struct file *file; - struct inode *inode; + struct file *file = fget(config->fd); + struct inode *inode; struct address_space *mapping; - int error; - loff_t size; - bool partscan; - unsigned short bsize; + int error; + loff_t size; + bool partscan; + unsigned short bsize; + bool is_loop; + + if (!file) + return -EBADF; + is_loop = is_loop_device(file); /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); - error = -EBADF; - file = fget(config->fd); - if (!file) - goto out; - /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1162,7 +1214,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, goto out_putf; } - error = mutex_lock_killable(&lo->lo_mutex); + error = loop_global_lock_killable(lo, is_loop); if (error) goto out_bdev; @@ -1242,6 +1294,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, size = get_loop_size(lo, file); loop_set_size(lo, size); + /* Order wrt reading lo_state in loop_validate_file(). */ + wmb(); + lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; @@ -1253,7 +1308,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); if (partscan) loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) @@ -1261,13 +1316,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, return 0; out_unlock: - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, is_loop); out_bdev: if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); -out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; @@ -1283,6 +1337,18 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) int lo_number; struct loop_worker *pos, *worker; + /* + * Flush loop_configure() and loop_change_fd(). It is acceptable for + * loop_validate_file() to succeed, for actual clear operation has not + * started yet. + */ + mutex_lock(&loop_validate_mutex); + mutex_unlock(&loop_validate_mutex); + /* + * loop_validate_file() now fails because l->lo_state != Lo_bound + * became visible. + */ + mutex_lock(&lo->lo_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { err = -ENXIO; From 9986066d94c971edf19464ed7bf5b26a91520e97 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Fri, 23 Jul 2021 13:36:18 +0530 Subject: [PATCH 0829/1469] octeontx2-af: Fix uninitialized variables in rvu_switch Get the number of VFs of a PF correctly by calling rvu_get_pf_numvfs in rvu_switch_disable function. Also hwvf is not required hence remove it. Fixes: 23109f8dd06d ("octeontx2-af: Introduce internal packet switching") Reported-by: kernel test robot Reported-by: Colin Ian King Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 6 ++++-- .../net/ethernet/marvell/octeontx2/af/rvu_switch.c | 11 ++++++----- 2 files changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 017163fb3cd5..5fe277e354f7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -391,8 +391,10 @@ void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf) /* Get numVFs attached to this PF and first HWVF */ cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf)); - *numvfs = (cfg >> 12) & 0xFF; - *hwvf = cfg & 0xFFF; + if (numvfs) + *numvfs = (cfg >> 12) & 0xFF; + if (hwvf) + *hwvf = cfg & 0xFFF; } static int rvu_get_hwvf(struct rvu *rvu, int pcifunc) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c index 2e5379710aa5..820adf390b8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c @@ -71,8 +71,8 @@ static int rvu_switch_install_rules(struct rvu *rvu) struct rvu_switch *rswitch = &rvu->rswitch; u16 start = rswitch->start_entry; struct rvu_hwinfo *hw = rvu->hw; - int pf, vf, numvfs, hwvf; u16 pcifunc, entry = 0; + int pf, vf, numvfs; int err; for (pf = 1; pf < hw->total_pfs; pf++) { @@ -110,8 +110,8 @@ static int rvu_switch_install_rules(struct rvu *rvu) rswitch->entry2pcifunc[entry++] = pcifunc; - rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf); - for (vf = 0; vf < numvfs; vf++, hwvf++) { + rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); + for (vf = 0; vf < numvfs; vf++) { pcifunc = pf << 10 | ((vf + 1) & 0x3FF); rvu_get_nix_blkaddr(rvu, pcifunc); @@ -198,7 +198,7 @@ void rvu_switch_disable(struct rvu *rvu) struct npc_mcam_free_entry_req free_req = { 0 }; struct rvu_switch *rswitch = &rvu->rswitch; struct rvu_hwinfo *hw = rvu->hw; - int pf, vf, numvfs, hwvf; + int pf, vf, numvfs; struct msg_rsp rsp; u16 pcifunc; int err; @@ -217,7 +217,8 @@ void rvu_switch_disable(struct rvu *rvu) "Reverting RX rule for PF%d failed(%d)\n", pf, err); - for (vf = 0; vf < numvfs; vf++, hwvf++) { + rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); + for (vf = 0; vf < numvfs; vf++) { pcifunc = pf << 10 | ((vf + 1) & 0x3FF); err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); if (err) From 52f3456a96c06760b9bfae460e39596fec7af22e Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 23 Jul 2021 18:31:32 +0300 Subject: [PATCH 0830/1469] net: qrtr: fix memory leaks Syzbot reported memory leak in qrtr. The problem was in unputted struct sock. qrtr_local_enqueue() function calls qrtr_port_lookup() which takes sock reference if port was found. Then there is the following check: if (!ipc || &ipc->sk == skb->sk) { ... return -ENODEV; } Since we should drop the reference before returning from this function and ipc can be non-NULL inside this if, we should add qrtr_port_put() inside this if. The similar corner case is in qrtr_endpoint_post() as Manivannan reported. In case of sock_queue_rcv_skb() failure we need to put port reference to avoid leaking struct sock pointer. Fixes: e04df98adf7d ("net: qrtr: Remove receive worker") Fixes: bdabad3e363d ("net: Add Qualcomm IPC router") Reported-and-tested-by: syzbot+35a511c72ea7356cdcf3@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Reviewed-by: Manivannan Sadhasivam Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e6f4a6202f82..171b7f3be6ef 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -518,8 +518,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!ipc) goto err; - if (sock_queue_rcv_skb(&ipc->sk, skb)) + if (sock_queue_rcv_skb(&ipc->sk, skb)) { + qrtr_port_put(ipc); goto err; + } qrtr_port_put(ipc); } @@ -839,6 +841,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ + if (ipc) + qrtr_port_put(ipc); kfree_skb(skb); return -ENODEV; } From 15bbf8bb4d4ab87108ecf5f4155ec8ffa3c141d6 Mon Sep 17 00:00:00 2001 From: Paul Jakma Date: Fri, 23 Jul 2021 16:13:04 +0100 Subject: [PATCH 0831/1469] NIU: fix incorrect error return, missed in previous revert Commit 7930742d6, reverting 26fd962, missed out on reverting an incorrect change to a return value. The niu_pci_vpd_scan_props(..) == 1 case appears to be a normal path - treating it as an error and return -EINVAL was breaking VPD_SCAN and causing the driver to fail to load. Fix, so my Neptune card works again. Cc: Kangjie Lu Cc: Shannon Nelson Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: stable Fixes: 7930742d ('Revert "niu: fix missing checks of niu_pci_eeprom_read"') Signed-off-by: Paul Jakma Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/niu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 74e748662ec0..860644d182ab 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8191,8 +8191,9 @@ static int niu_pci_vpd_fetch(struct niu *np, u32 start) err = niu_pci_vpd_scan_props(np, here, end); if (err < 0) return err; + /* ret == 1 is not an error */ if (err == 1) - return -EINVAL; + return 0; } return 0; } From 5ba03936c05584b6f6f79be5ebe7e5036c1dd252 Mon Sep 17 00:00:00 2001 From: Wei Shuyu Date: Mon, 28 Jun 2021 15:15:08 +0800 Subject: [PATCH 0832/1469] md/raid10: properly indicate failure when ending a failed write request Similar to [1], this patch fixes the same bug in raid10. Also cleanup the comments. [1] commit 2417b9869b81 ("md/raid1: properly indicate failure when ending a failed write request") Cc: stable@vger.kernel.org Fixes: 7cee6d4e6035 ("md/raid10: end bio when the device faulty") Signed-off-by: Wei Shuyu Acked-by: Guoqing Jiang Signed-off-by: Song Liu --- drivers/md/raid1.c | 2 -- drivers/md/raid10.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ced076ba560e..753822ca9613 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -472,8 +472,6 @@ static void raid1_end_write_request(struct bio *bio) /* * When the device is faulty, it is not necessary to * handle write error. - * For failfast, this is the only remaining device, - * We need to retry the write without FailFast. */ if (!test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_WriteError, &r1_bio->state); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 13f5e6b2a73d..40e845fb9717 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -469,12 +469,12 @@ static void raid10_end_write_request(struct bio *bio) /* * When the device is faulty, it is not necessary to * handle write error. - * For failfast, this is the only remaining device, - * We need to retry the write without FailFast. */ if (!test_bit(Faulty, &rdev->flags)) set_bit(R10BIO_WriteError, &r10_bio->state); else { + /* Fail the request */ + set_bit(R10BIO_Degraded, &r10_bio->state); r10_bio->devs[slot].bio = NULL; to_put = bio; dec_rdev = 1; From 6840e17b8ea992453e2d6f460d403cb05d194e76 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 23 Jul 2021 11:02:45 -0700 Subject: [PATCH 0833/1469] ionic: make all rx_mode work threadsafe Move the bulk of the code from ionic_set_rx_mode(), which can be called from atomic context, into ionic_lif_rx_mode() which is a safe context. A call from the stack will get pushed off into a work thread, but it is also possible to simultaneously have a call driven by a queue reconfig request from an ethtool command or fw recovery event. We add a mutex around the rx_mode work to be sure they don't collide. Fixes: 81dbc24147f9 ("ionic: change set_rx_mode from_ndo to can_sleep") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- .../net/ethernet/pensando/ionic/ionic_lif.c | 205 ++++++++---------- .../net/ethernet/pensando/ionic/ionic_lif.h | 4 +- 2 files changed, 96 insertions(+), 113 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index af3a5368529c..7815e9034fb8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -29,7 +29,7 @@ static const u8 ionic_qtype_versions[IONIC_QTYPE_MAX] = { */ }; -static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode); +static void ionic_lif_rx_mode(struct ionic_lif *lif); static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr); static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr); static void ionic_link_status_check(struct ionic_lif *lif); @@ -77,7 +77,7 @@ static void ionic_lif_deferred_work(struct work_struct *work) switch (w->type) { case IONIC_DW_TYPE_RX_MODE: - ionic_lif_rx_mode(lif, w->rx_mode); + ionic_lif_rx_mode(lif); break; case IONIC_DW_TYPE_RX_ADDR_ADD: ionic_lif_addr_add(lif, w->addr); @@ -1301,10 +1301,8 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) return 0; } -static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add, - bool can_sleep) +static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add) { - struct ionic_deferred_work *work; unsigned int nmfilters; unsigned int nufilters; @@ -1330,63 +1328,77 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add, lif->nucast--; } - if (!can_sleep) { - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) - return -ENOMEM; - work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD : - IONIC_DW_TYPE_RX_ADDR_DEL; - memcpy(work->addr, addr, ETH_ALEN); - netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n", - add ? "add" : "del", addr); - ionic_lif_deferred_enqueue(&lif->deferred, work); - } else { - netdev_dbg(lif->netdev, "rx_filter %s %pM\n", - add ? "add" : "del", addr); - if (add) - return ionic_lif_addr_add(lif, addr); - else - return ionic_lif_addr_del(lif, addr); - } + netdev_dbg(lif->netdev, "rx_filter %s %pM\n", + add ? "add" : "del", addr); + if (add) + return ionic_lif_addr_add(lif, addr); + else + return ionic_lif_addr_del(lif, addr); return 0; } static int ionic_addr_add(struct net_device *netdev, const u8 *addr) { - return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_SLEEP); -} - -static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr) -{ - return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_NOT_SLEEP); + return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR); } static int ionic_addr_del(struct net_device *netdev, const u8 *addr) { - return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_SLEEP); + return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR); } -static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr) +static void ionic_lif_rx_mode(struct ionic_lif *lif) { - return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_NOT_SLEEP); -} - -static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_mode_set = { - .opcode = IONIC_CMD_RX_MODE_SET, - .lif_index = cpu_to_le16(lif->index), - .rx_mode = cpu_to_le16(rx_mode), - }, - }; + struct net_device *netdev = lif->netdev; + unsigned int nfilters; + unsigned int nd_flags; char buf[128]; - int err; + u16 rx_mode; int i; #define REMAIN(__x) (sizeof(buf) - (__x)) + mutex_lock(&lif->config_lock); + + /* grab the flags once for local use */ + nd_flags = netdev->flags; + + rx_mode = IONIC_RX_MODE_F_UNICAST; + rx_mode |= (nd_flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; + rx_mode |= (nd_flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; + rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; + rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; + + /* sync unicast addresses + * next check to see if we're in an overflow state + * if so, we track that we overflowed and enable NIC PROMISC + * else if the overflow is set and not needed + * we remove our overflow flag and check the netdev flags + * to see if we can disable NIC PROMISC + */ + __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); + if (netdev_uc_count(netdev) + 1 > nfilters) { + rx_mode |= IONIC_RX_MODE_F_PROMISC; + lif->uc_overflow = true; + } else if (lif->uc_overflow) { + lif->uc_overflow = false; + if (!(nd_flags & IFF_PROMISC)) + rx_mode &= ~IONIC_RX_MODE_F_PROMISC; + } + + /* same for multicast */ + __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters); + if (netdev_mc_count(netdev) > nfilters) { + rx_mode |= IONIC_RX_MODE_F_ALLMULTI; + lif->mc_overflow = true; + } else if (lif->mc_overflow) { + lif->mc_overflow = false; + if (!(nd_flags & IFF_ALLMULTI)) + rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI; + } + i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:", lif->rx_mode, rx_mode); if (rx_mode & IONIC_RX_MODE_F_UNICAST) @@ -1399,79 +1411,48 @@ static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC"); if (rx_mode & IONIC_RX_MODE_F_ALLMULTI) i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI"); - netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf); + if (rx_mode & IONIC_RX_MODE_F_RDMA_SNIFFER) + i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_RDMA_SNIFFER"); + netdev_dbg(netdev, "lif%d %s\n", lif->index, buf); - err = ionic_adminq_post_wait(lif, &ctx); - if (err) - netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n", - rx_mode, err); - else - lif->rx_mode = rx_mode; + if (lif->rx_mode != rx_mode) { + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_mode_set = { + .opcode = IONIC_CMD_RX_MODE_SET, + .lif_index = cpu_to_le16(lif->index), + }, + }; + int err; + + ctx.cmd.rx_mode_set.rx_mode = cpu_to_le16(rx_mode); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + netdev_warn(netdev, "set rx_mode 0x%04x failed: %d\n", + rx_mode, err); + else + lif->rx_mode = rx_mode; + } + + mutex_unlock(&lif->config_lock); } static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep) { struct ionic_lif *lif = netdev_priv(netdev); struct ionic_deferred_work *work; - unsigned int nfilters; - unsigned int rx_mode; - rx_mode = IONIC_RX_MODE_F_UNICAST; - rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; - rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; - rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; - rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; - - /* sync unicast addresses - * next check to see if we're in an overflow state - * if so, we track that we overflowed and enable NIC PROMISC - * else if the overflow is set and not needed - * we remove our overflow flag and check the netdev flags - * to see if we can disable NIC PROMISC - */ - if (can_sleep) - __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); - else - __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del); - nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); - if (netdev_uc_count(netdev) + 1 > nfilters) { - rx_mode |= IONIC_RX_MODE_F_PROMISC; - lif->uc_overflow = true; - } else if (lif->uc_overflow) { - lif->uc_overflow = false; - if (!(netdev->flags & IFF_PROMISC)) - rx_mode &= ~IONIC_RX_MODE_F_PROMISC; - } - - /* same for multicast */ - if (can_sleep) - __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); - else - __dev_mc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del); - nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters); - if (netdev_mc_count(netdev) > nfilters) { - rx_mode |= IONIC_RX_MODE_F_ALLMULTI; - lif->mc_overflow = true; - } else if (lif->mc_overflow) { - lif->mc_overflow = false; - if (!(netdev->flags & IFF_ALLMULTI)) - rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI; - } - - if (lif->rx_mode != rx_mode) { - if (!can_sleep) { - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - netdev_err(lif->netdev, "rxmode change dropped\n"); - return; - } - work->type = IONIC_DW_TYPE_RX_MODE; - work->rx_mode = rx_mode; - netdev_dbg(lif->netdev, "deferred: rx_mode\n"); - ionic_lif_deferred_enqueue(&lif->deferred, work); - } else { - ionic_lif_rx_mode(lif, rx_mode); + if (!can_sleep) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "rxmode change dropped\n"); + return; } + work->type = IONIC_DW_TYPE_RX_MODE; + netdev_dbg(lif->netdev, "deferred: rx_mode\n"); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_lif_rx_mode(lif); } } @@ -3058,6 +3039,7 @@ void ionic_lif_deinit(struct ionic_lif *lif) ionic_lif_qcq_deinit(lif, lif->notifyqcq); ionic_lif_qcq_deinit(lif, lif->adminqcq); + mutex_destroy(&lif->config_lock); mutex_destroy(&lif->queue_lock); ionic_lif_reset(lif); } @@ -3185,7 +3167,7 @@ static int ionic_station_set(struct ionic_lif *lif) */ if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) - ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP); + ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR); } else { /* Update the netdev mac with the device's mac */ memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); @@ -3202,7 +3184,7 @@ static int ionic_station_set(struct ionic_lif *lif) netdev_dbg(lif->netdev, "adding station MAC addr %pM\n", netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP); + ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR); return 0; } @@ -3225,6 +3207,7 @@ int ionic_lif_init(struct ionic_lif *lif) lif->hw_index = le16_to_cpu(comp.hw_index); mutex_init(&lif->queue_lock); + mutex_init(&lif->config_lock); /* now that we have the hw_index we can figure out our doorbell page */ lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 346506f01715..af291303bd7a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -108,7 +108,6 @@ struct ionic_deferred_work { struct list_head list; enum ionic_deferred_work_type type; union { - unsigned int rx_mode; u8 addr[ETH_ALEN]; u8 fw_status; }; @@ -179,6 +178,7 @@ struct ionic_lif { unsigned int index; unsigned int hw_index; struct mutex queue_lock; /* lock for queue structures */ + struct mutex config_lock; /* lock for config actions */ spinlock_t adminq_lock; /* lock for AdminQ operations */ struct ionic_qcq *adminqcq; struct ionic_qcq *notifyqcq; @@ -199,7 +199,7 @@ struct ionic_lif { unsigned int nrxq_descs; u32 rx_copybreak; u64 rxq_features; - unsigned int rx_mode; + u16 rx_mode; u64 hw_features; bool registered; bool mc_overflow; From f79eef711eb57d56874b08ea11db69221de54a6d Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 23 Jul 2021 11:02:46 -0700 Subject: [PATCH 0834/1469] ionic: catch no ptp support earlier If PTP configuration is attempted on ports that don't support it, such as VF ports, the driver will return an error status -95, or EOPNOSUPP and print an error message enp98s0: hwstamp set failed: -95 Because some daemons can retry every few seconds, this can end up filling the dmesg log and pushing out other more useful messages. We can catch this issue earlier in our handling and return the error without a log message. Fixes: 829600ce5e4e ("ionic: add ts_config replay") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_lif.h | 7 ++----- drivers/net/ethernet/pensando/ionic/ionic_phc.c | 10 +++++++--- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index af291303bd7a..69ab59fedb6c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -302,7 +302,7 @@ int ionic_lif_identify(struct ionic *ionic, u8 lif_type, int ionic_lif_size(struct ionic *ionic); #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) -int ionic_lif_hwstamp_replay(struct ionic_lif *lif); +void ionic_lif_hwstamp_replay(struct ionic_lif *lif); int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr); int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr); ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter); @@ -311,10 +311,7 @@ void ionic_lif_unregister_phc(struct ionic_lif *lif); void ionic_lif_alloc_phc(struct ionic_lif *lif); void ionic_lif_free_phc(struct ionic_lif *lif); #else -static inline int ionic_lif_hwstamp_replay(struct ionic_lif *lif) -{ - return -EOPNOTSUPP; -} +static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {} static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c index a87c87e86aef..6e2403c71608 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c @@ -188,6 +188,9 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) struct hwtstamp_config config; int err; + if (!lif->phc || !lif->phc->ptp) + return -EOPNOTSUPP; + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; @@ -203,15 +206,16 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) return 0; } -int ionic_lif_hwstamp_replay(struct ionic_lif *lif) +void ionic_lif_hwstamp_replay(struct ionic_lif *lif) { int err; + if (!lif->phc || !lif->phc->ptp) + return; + err = ionic_lif_hwstamp_set_ts_config(lif, NULL); if (err) netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err); - - return err; } int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr) From a6ff85e0a2d9d074a4b4c291ba9ec1e5b0aba22b Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 23 Jul 2021 11:02:47 -0700 Subject: [PATCH 0835/1469] ionic: remove intr coalesce update from napi Move the interrupt coalesce value update out of the napi thread and into the dim_work thread and set it only when it has actually changed. Fixes: 04a834592bf5 ("ionic: dynamic interrupt moderation") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 14 +++++++++++++- drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 4 ---- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 7815e9034fb8..e795fa63ca12 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -53,7 +53,19 @@ static void ionic_dim_work(struct work_struct *work) cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); qcq = container_of(dim, struct ionic_qcq, dim); new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec); - qcq->intr.dim_coal_hw = new_coal ? new_coal : 1; + new_coal = new_coal ? new_coal : 1; + + if (qcq->intr.dim_coal_hw != new_coal) { + unsigned int qi = qcq->cq.bound_q->index; + struct ionic_lif *lif = qcq->q.lif; + + qcq->intr.dim_coal_hw = new_coal; + + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[qi]->intr.index, + qcq->intr.dim_coal_hw); + } + dim->state = DIM_START_MEASURE; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 08934888575c..9d3a04110685 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -463,10 +463,6 @@ static void ionic_dim_update(struct ionic_qcq *qcq) lif = qcq->q.lif; qi = qcq->cq.bound_q->index; - ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[qi]->intr.index, - qcq->intr.dim_coal_hw); - dim_update_sample(qcq->cq.bound_intr->rearm_count, lif->txqstats[qi].pkts, lif->txqstats[qi].bytes, From 76ed8a4a00b484dcccef819ef2618bcf8e46f560 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 23 Jul 2021 11:02:48 -0700 Subject: [PATCH 0836/1469] ionic: fix up dim accounting for tx and rx We need to count the correct Tx and/or Rx packets for dynamic interrupt moderation, depending on which we're processing on the queue interrupt. Fixes: 04a834592bf5 ("ionic: dynamic interrupt moderation") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- .../net/ethernet/pensando/ionic/ionic_txrx.c | 28 ++++++++++++++----- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 9d3a04110685..1c6e2b9fc96b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -451,11 +451,12 @@ void ionic_rx_empty(struct ionic_queue *q) q->tail_idx = 0; } -static void ionic_dim_update(struct ionic_qcq *qcq) +static void ionic_dim_update(struct ionic_qcq *qcq, int napi_mode) { struct dim_sample dim_sample; struct ionic_lif *lif; unsigned int qi; + u64 pkts, bytes; if (!qcq->intr.dim_coal_hw) return; @@ -463,10 +464,23 @@ static void ionic_dim_update(struct ionic_qcq *qcq) lif = qcq->q.lif; qi = qcq->cq.bound_q->index; + switch (napi_mode) { + case IONIC_LIF_F_TX_DIM_INTR: + pkts = lif->txqstats[qi].pkts; + bytes = lif->txqstats[qi].bytes; + break; + case IONIC_LIF_F_RX_DIM_INTR: + pkts = lif->rxqstats[qi].pkts; + bytes = lif->rxqstats[qi].bytes; + break; + default: + pkts = lif->txqstats[qi].pkts + lif->rxqstats[qi].pkts; + bytes = lif->txqstats[qi].bytes + lif->rxqstats[qi].bytes; + break; + } + dim_update_sample(qcq->cq.bound_intr->rearm_count, - lif->txqstats[qi].pkts, - lif->txqstats[qi].bytes, - &dim_sample); + pkts, bytes, &dim_sample); net_dim(&qcq->dim, dim_sample); } @@ -487,7 +501,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) ionic_tx_service, NULL, NULL); if (work_done < budget && napi_complete_done(napi, work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR); flags |= IONIC_INTR_CRED_UNMASK; cq->bound_intr->rearm_count++; } @@ -526,7 +540,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(cq->bound_q); if (work_done < budget && napi_complete_done(napi, work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR); flags |= IONIC_INTR_CRED_UNMASK; cq->bound_intr->rearm_count++; } @@ -572,7 +586,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq); + ionic_dim_update(qcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } From f07f9815b7046e25cc32bf8542c9c0bbc5eb6e0e Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 23 Jul 2021 11:02:49 -0700 Subject: [PATCH 0837/1469] ionic: count csum_none when offload enabled Be sure to count the csum_none cases when csum offload is enabled. Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 1c6e2b9fc96b..08870190e4d2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -274,12 +274,11 @@ static void ionic_rx_clean(struct ionic_queue *q, } } - if (likely(netdev->features & NETIF_F_RXCSUM)) { - if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) { - skb->ip_summed = CHECKSUM_COMPLETE; - skb->csum = (__force __wsum)le16_to_cpu(comp->csum); - stats->csum_complete++; - } + if (likely(netdev->features & NETIF_F_RXCSUM) && + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC)) { + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum = (__force __wsum)le16_to_cpu(comp->csum); + stats->csum_complete++; } else { stats->csum_none++; } From 3c30ef0f78cfb36fdb13753794b0384cf7e37cc9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jul 2021 11:49:29 -0600 Subject: [PATCH 0838/1469] io_uring: never attempt iopoll reissue from release path There are two reasons why this shouldn't be done: 1) Ring is exiting, and we're canceling requests anyway. Any request should be canceled anyway. In theory, this could iterate for a number of times if someone else is also driving the target block queue into request starvation, however the likelihood of this happening is miniscule. 2) If the original task decided to pass the ring to another task, then we don't want to be reissuing from this context as it may be an unrelated task or context. No assumptions should be made about the context in which ->release() is run. This can only happen for pure read/write, and we'll get -EFAULT on them anyway. Link: https://lore.kernel.org/io-uring/YPr4OaHv0iv0KTOc@zeniv-ca.linux.org.uk/ Reported-by: Al Viro Signed-off-by: Jens Axboe --- fs/io_uring.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index f2fe4eca150b..117dc32eb8a8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2205,7 +2205,7 @@ static inline bool io_run_task_work(void) * Find and free completed poll iocbs */ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, - struct list_head *done) + struct list_head *done, bool resubmit) { struct req_batch rb; struct io_kiocb *req; @@ -2220,7 +2220,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - if (READ_ONCE(req->result) == -EAGAIN && + if (READ_ONCE(req->result) == -EAGAIN && resubmit && !(req->flags & REQ_F_DONT_REISSUE)) { req->iopoll_completed = 0; req_ref_get(req); @@ -2244,7 +2244,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, - long min) + long min, bool resubmit) { struct io_kiocb *req, *tmp; LIST_HEAD(done); @@ -2287,7 +2287,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, } if (!list_empty(&done)) - io_iopoll_complete(ctx, nr_events, &done); + io_iopoll_complete(ctx, nr_events, &done, resubmit); return ret; } @@ -2305,7 +2305,7 @@ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) while (!list_empty(&ctx->iopoll_list)) { unsigned int nr_events = 0; - io_do_iopoll(ctx, &nr_events, 0); + io_do_iopoll(ctx, &nr_events, 0, false); /* let it sleep and repeat later if can't complete a request */ if (nr_events == 0) @@ -2367,7 +2367,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) list_empty(&ctx->iopoll_list)) break; } - ret = io_do_iopoll(ctx, &nr_events, min); + ret = io_do_iopoll(ctx, &nr_events, min, true); } while (!ret && nr_events < min && !need_resched()); out: mutex_unlock(&ctx->uring_lock); @@ -6798,7 +6798,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) mutex_lock(&ctx->uring_lock); if (!list_empty(&ctx->iopoll_list)) - io_do_iopoll(ctx, &nr_events, 0); + io_do_iopoll(ctx, &nr_events, 0, true); /* * Don't submit if refs are dying, good for io_uring_register(), From 991468dcf198bb87f24da330676724a704912b47 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jul 2021 11:53:54 -0600 Subject: [PATCH 0839/1469] io_uring: explicitly catch any illegal async queue attempt Catch an illegal case to queue async from an unrelated task that got the ring fd passed to it. This should not be possible to hit, but better be proactive and catch it explicitly. io-wq is extended to check for early IO_WQ_WORK_CANCEL being set on a work item as well, so it can run the request through the normal cancelation path. Signed-off-by: Jens Axboe --- fs/io-wq.c | 7 ++++++- fs/io_uring.c | 11 +++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 843d4a7bcd6e..cf086b01c6c6 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -731,7 +731,12 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) int work_flags; unsigned long flags; - if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) { + /* + * If io-wq is exiting for this task, or if the request has explicitly + * been marked as one that should not get executed, cancel it here. + */ + if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) || + (work->flags & IO_WQ_WORK_CANCEL)) { io_run_cancel(work, wqe); return; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 117dc32eb8a8..5a0fd6bcd318 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1294,6 +1294,17 @@ static void io_queue_async_work(struct io_kiocb *req) /* init ->work of the whole link before punting */ io_prep_async_link(req); + + /* + * Not expected to happen, but if we do have a bug where this _can_ + * happen, catch it here and ensure the request is marked as + * canceled. That will make io-wq go through the usual work cancel + * procedure rather than attempt to run this request (or create a new + * worker for it). + */ + if (WARN_ON_ONCE(!same_thread_group(req->task, current))) + req->work.flags |= IO_WQ_WORK_CANCEL; + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, &req->work, req->flags); io_wq_enqueue(tctx->io_wq, &req->work); From 76f5dfacfb42b75e5782c017827877cfcee20474 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 23 Jul 2021 08:22:26 +0800 Subject: [PATCH 0840/1469] riscv: stacktrace: pin the task's stack in get_wchan Pin the task's stack before calling walk_stackframe() in get_wchan(). This can fix the panic as reported by Andreas when CONFIG_VMAP_STACK=y: [ 65.609696] Unable to handle kernel paging request at virtual address ffffffd0003bbde8 [ 65.610460] Oops [#1] [ 65.610626] Modules linked in: virtio_blk virtio_mmio rtc_goldfish btrfs blake2b_generic libcrc32c xor raid6_pq sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua efivarfs [ 65.611670] CPU: 2 PID: 1 Comm: systemd Not tainted 5.14.0-rc1-1.g34fe32a-default #1 openSUSE Tumbleweed (unreleased) c62f7109153e5a0897ee58ba52393ad99b070fd2 [ 65.612334] Hardware name: riscv-virtio,qemu (DT) [ 65.613008] epc : get_wchan+0x5c/0x88 [ 65.613334] ra : get_wchan+0x42/0x88 [ 65.613625] epc : ffffffff800048a4 ra : ffffffff8000488a sp : ffffffd00021bb90 [ 65.614008] gp : ffffffff817709f8 tp : ffffffe07fe91b80 t0 : 00000000000001f8 [ 65.614411] t1 : 0000000000020000 t2 : 0000000000000000 s0 : ffffffd00021bbd0 [ 65.614818] s1 : ffffffd0003bbdf0 a0 : 0000000000000001 a1 : 0000000000000002 [ 65.615237] a2 : ffffffff81618008 a3 : 0000000000000000 a4 : 0000000000000000 [ 65.615637] a5 : ffffffd0003bc000 a6 : 0000000000000002 a7 : ffffffe27d370000 [ 65.616022] s2 : ffffffd0003bbd90 s3 : ffffffff8071a81e s4 : 0000000000003fff [ 65.616407] s5 : ffffffffffffc000 s6 : 0000000000000000 s7 : ffffffff81618008 [ 65.616845] s8 : 0000000000000001 s9 : 0000000180000040 s10: 0000000000000000 [ 65.617248] s11: 000000000000016b t3 : 000000ff00000000 t4 : 0c6aec92de5e3fd7 [ 65.617672] t5 : fff78f60608fcfff t6 : 0000000000000078 [ 65.618088] status: 0000000000000120 badaddr: ffffffd0003bbde8 cause: 000000000000000d [ 65.618621] [] get_wchan+0x5c/0x88 [ 65.619008] [] do_task_stat+0x7a2/0xa46 [ 65.619325] [] proc_tgid_stat+0xe/0x16 [ 65.619637] [] proc_single_show+0x46/0x96 [ 65.619979] [] seq_read_iter+0x190/0x31e [ 65.620341] [] seq_read+0xc4/0x104 [ 65.620633] [] vfs_read+0x6a/0x112 [ 65.620922] [] ksys_read+0x54/0xbe [ 65.621206] [] sys_read+0xe/0x16 [ 65.621474] [] ret_from_syscall+0x0/0x2 [ 65.622169] ---[ end trace f24856ed2b8789c5 ]--- [ 65.622832] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Signed-off-by: Jisheng Zhang Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/stacktrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index ff467b98c3e3..ac7593607fa6 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -132,8 +132,12 @@ unsigned long get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && !task_is_running(task))) + if (likely(task && task != current && !task_is_running(task))) { + if (!try_get_task_stack(task)) + return 0; walk_stackframe(task, NULL, save_wchan, &pc); + put_task_stack(task); + } return pc; } From e71e2ace5721a8b921dca18b045069e7bb411277 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 23 Jul 2021 15:50:01 -0700 Subject: [PATCH 0841/1469] userfaultfd: do not untag user pointers Patch series "userfaultfd: do not untag user pointers", v5. If a user program uses userfaultfd on ranges of heap memory, it may end up passing a tagged pointer to the kernel in the range.start field of the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable allocator, or on Android if using the Tagged Pointers feature for MTE readiness [1]. When a fault subsequently occurs, the tag is stripped from the fault address returned to the application in the fault.address field of struct uffd_msg. However, from the application's perspective, the tagged address *is* the memory address, so if the application is unaware of memory tags, it may get confused by receiving an address that is, from its point of view, outside of the bounds of the allocation. We observed this behavior in the kselftest for userfaultfd [2] but other applications could have the same problem. Address this by not untagging pointers passed to the userfaultfd ioctls. Instead, let the system call fail. Also change the kselftest to use mmap so that it doesn't encounter this problem. [1] https://source.android.com/devices/tech/debug/tagged-pointers [2] tools/testing/selftests/vm/userfaultfd.c This patch (of 2): Do not untag pointers passed to the userfaultfd ioctls. Instead, let the system call fail. This will provide an early indication of problems with tag-unaware userspace code instead of letting the code get confused later, and is consistent with how we decided to handle brk/mmap/mremap in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in brk()/mmap()/mremap()"), as well as being consistent with the existing tagged address ABI documentation relating to how ioctl arguments are handled. The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag user pointers") plus some fixups to some additional calls to validate_range that have appeared since then. [1] https://source.android.com/devices/tech/debug/tagged-pointers [2] tools/testing/selftests/vm/userfaultfd.c Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI") Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Reviewed-by: Catalin Marinas Cc: Alistair Delva Cc: Andrea Arcangeli Cc: Dave Martin Cc: Evgenii Stepanov Cc: Lokesh Gidra Cc: Mitch Phillips Cc: Vincenzo Frascino Cc: Will Deacon Cc: William McVicker Cc: [5.4] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/arm64/tagged-address-abi.rst | 24 ++++++++++++++------ fs/userfaultfd.c | 26 ++++++++++------------ 2 files changed, 29 insertions(+), 21 deletions(-) diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst index 459e6b66ff68..0c9120ec58ae 100644 --- a/Documentation/arm64/tagged-address-abi.rst +++ b/Documentation/arm64/tagged-address-abi.rst @@ -45,14 +45,24 @@ how the user addresses are used by the kernel: 1. User addresses not accessed by the kernel but used for address space management (e.g. ``mprotect()``, ``madvise()``). The use of valid - tagged pointers in this context is allowed with the exception of - ``brk()``, ``mmap()`` and the ``new_address`` argument to - ``mremap()`` as these have the potential to alias with existing - user addresses. + tagged pointers in this context is allowed with these exceptions: - NOTE: This behaviour changed in v5.6 and so some earlier kernels may - incorrectly accept valid tagged pointers for the ``brk()``, - ``mmap()`` and ``mremap()`` system calls. + - ``brk()``, ``mmap()`` and the ``new_address`` argument to + ``mremap()`` as these have the potential to alias with existing + user addresses. + + NOTE: This behaviour changed in v5.6 and so some earlier kernels may + incorrectly accept valid tagged pointers for the ``brk()``, + ``mmap()`` and ``mremap()`` system calls. + + - The ``range.start``, ``start`` and ``dst`` arguments to the + ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from + ``userfaultfd()``, as fault addresses subsequently obtained by reading + the file descriptor will be untagged, which may otherwise confuse + tag-unaware programs. + + NOTE: This behaviour changed in v5.14 and so some earlier kernels may + incorrectly accept valid tagged pointers for this system call. 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI relaxation is disabled by default and the application thread needs to diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f6e0f0c0d0e5..5c2d806e6ae5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1236,23 +1236,21 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, } static __always_inline int validate_range(struct mm_struct *mm, - __u64 *start, __u64 len) + __u64 start, __u64 len) { __u64 task_size = mm->task_size; - *start = untagged_addr(*start); - - if (*start & ~PAGE_MASK) + if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; - if (*start < mmap_min_addr) + if (start < mmap_min_addr) return -EINVAL; - if (*start >= task_size) + if (start >= task_size) return -EINVAL; - if (len > task_size - *start) + if (len > task_size - start) return -EINVAL; return 0; } @@ -1316,7 +1314,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vm_flags |= VM_UFFD_MINOR; } - ret = validate_range(mm, &uffdio_register.range.start, + ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; @@ -1522,7 +1520,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; - ret = validate_range(mm, &uffdio_unregister.start, + ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; @@ -1671,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; - ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len); + ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; @@ -1711,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, sizeof(uffdio_copy)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len); + ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* @@ -1768,7 +1766,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_zeropage.range.start, + ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; @@ -1818,7 +1816,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, sizeof(struct uffdio_writeprotect))) return -EFAULT; - ret = validate_range(ctx->mm, &uffdio_wp.range.start, + ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; @@ -1866,7 +1864,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; - ret = validate_range(ctx->mm, &uffdio_continue.range.start, + ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; From 0db282ba2c12c1515d490d14a1ff696643ab0f1b Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 23 Jul 2021 15:50:04 -0700 Subject: [PATCH 0842/1469] selftest: use mmap instead of posix_memalign to allocate memory This test passes pointers obtained from anon_allocate_area to the userfaultfd and mremap APIs. This causes a problem if the system allocator returns tagged pointers because with the tagged address ABI the kernel rejects tagged addresses passed to these APIs, which would end up causing the test to fail. To make this test compatible with such system allocators, stop using the system allocator to allocate memory in anon_allocate_area, and instead just use mmap. Link: https://lkml.kernel.org/r/20210714195437.118982-3-pcc@google.com Link: https://linux-review.googlesource.com/id/Icac91064fcd923f77a83e8e133f8631c5b8fc241 Fixes: c47174fc362a ("userfaultfd: selftest") Co-developed-by: Lokesh Gidra Signed-off-by: Lokesh Gidra Signed-off-by: Peter Collingbourne Reviewed-by: Catalin Marinas Cc: Vincenzo Frascino Cc: Dave Martin Cc: Will Deacon Cc: Andrea Arcangeli Cc: Alistair Delva Cc: William McVicker Cc: Evgenii Stepanov Cc: Mitch Phillips Cc: Andrey Konovalov Cc: [5.4] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index e363bdaff59d..2ea438e6b8b1 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area) static void anon_allocate_area(void **alloc_area) { - if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) - err("posix_memalign() failed"); + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (*alloc_area == MAP_FAILED) + err("mmap of anonymous memory failed"); } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) From 32ae8a0669392248a92d7545a7363004543f3932 Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Fri, 23 Jul 2021 15:50:08 -0700 Subject: [PATCH 0843/1469] kfence: defer kfence_test_init to ensure that kunit debugfs is created kfence_test_init and kunit_init both use the same level late_initcall, which means if kfence_test_init linked ahead of kunit_init, kfence_test_init will get a NULL debugfs_rootdir as parent dentry, then kfence_test_init and kfence_debugfs_init both create a debugfs node named "kfence" under debugfs_mount->mnt_root, and it will throw out "debugfs: Directory 'kfence' with parent '/' already present!" with EEXIST. So kfence_test_init should be deferred. Link: https://lkml.kernel.org/r/20210714113140.2949995-1-o451686892@gmail.com Signed-off-by: Weizhao Ouyang Tested-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/kfence_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 7f24b9bcb2ec..942cbc16ad26 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -852,7 +852,7 @@ static void kfence_test_exit(void) tracepoint_synchronize_unregister(); } -late_initcall(kfence_test_init); +late_initcall_sync(kfence_test_init); module_exit(kfence_test_exit); MODULE_LICENSE("GPL v2"); From 235a85cb32bb123854ad31de46fdbf04c1d57cda Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 23 Jul 2021 15:50:11 -0700 Subject: [PATCH 0844/1469] kfence: move the size check to the beginning of __kfence_alloc() Check the allocation size before toggling kfence_allocation_gate. This way allocations that can't be served by KFENCE will not result in waiting for another CONFIG_KFENCE_SAMPLE_INTERVAL without allocating anything. Link: https://lkml.kernel.org/r/20210714092222.1890268-1-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Marco Elver Reviewed-by: Marco Elver Cc: Dmitry Vyukov Cc: Marco Elver Cc: Greg Kroah-Hartman Cc: [5.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index d7666ace9d2e..2623ff401a10 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -733,6 +733,13 @@ void kfence_shutdown_cache(struct kmem_cache *s) void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { + /* + * Perform size check before switching kfence_allocation_gate, so that + * we don't disable KFENCE without making an allocation. + */ + if (size > PAGE_SIZE) + return NULL; + /* * allocation_gate only needs to become non-zero, so it doesn't make * sense to continue writing to it and pay the associated contention @@ -757,9 +764,6 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (!READ_ONCE(kfence_enabled)) return NULL; - if (size > PAGE_SIZE) - return NULL; - return kfence_guarded_alloc(s, size, flags); } From 236e9f1538523d3d380dda1cc99571d587058f37 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 23 Jul 2021 15:50:14 -0700 Subject: [PATCH 0845/1469] kfence: skip all GFP_ZONEMASK allocations Allocation requests outside ZONE_NORMAL (MOVABLE, HIGHMEM or DMA) cannot be fulfilled by KFENCE, because KFENCE memory pool is located in a zone different from the requested one. Because callers of kmem_cache_alloc() may actually rely on the allocation to reside in the requested zone (e.g. memory allocations done with __GFP_DMA must be DMAable), skip all allocations done with GFP_ZONEMASK and/or respective SLAB flags (SLAB_CACHE_DMA and SLAB_CACHE_DMA32). Link: https://lkml.kernel.org/r/20210714092222.1890268-2-glider@google.com Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Acked-by: Souptick Joarder Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Souptick Joarder Cc: [5.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 2623ff401a10..575c685aa642 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -740,6 +740,15 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (size > PAGE_SIZE) return NULL; + /* + * Skip allocations from non-default zones, including DMA. We cannot + * guarantee that pages in the KFENCE pool will have the requested + * properties (e.g. reside in DMAable memory). + */ + if ((flags & GFP_ZONEMASK) || + (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) + return NULL; + /* * allocation_gate only needs to become non-zero, so it doesn't make * sense to continue writing to it and pay the associated contention From 8dad53a11f8d94dceb540a5f8f153484f42be84b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Jul 2021 15:50:17 -0700 Subject: [PATCH 0846/1469] mm: call flush_dcache_page() in memcpy_to_page() and memzero_page() memcpy_to_page and memzero_page can write to arbitrary pages, which could be in the page cache or in high memory, so call flush_kernel_dcache_pages to flush the dcache. This is a problem when using these helpers on dcache challeneged architectures. Right now there are just a few users, chances are no one used the PC floppy driver, the aha1542 driver for an ISA SCSI HBA, and a few advanced and optional btrfs and ext4 features on those platforms yet since the conversion. Link: https://lkml.kernel.org/r/20210713055231.137602-2-hch@lst.de Fixes: bb90d4bc7b6a ("mm/highmem: Lift memcpy_[to|from]_page to core") Fixes: 28961998f858 ("iov_iter: lift memzero_page() to highmem.h") Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Cc: Chaitanya Kulkarni Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8c6e8e996c87..8e7e50a53a12 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -318,6 +318,7 @@ static inline void memcpy_to_page(struct page *page, size_t offset, VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); + flush_dcache_page(page); kunmap_local(to); } @@ -325,6 +326,7 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_atomic(page); memset(addr + offset, 0, len); + flush_dcache_page(page); kunmap_atomic(addr); } From d9a42b53bdf7b0329dc09a59fc1b092640b6da19 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Jul 2021 15:50:20 -0700 Subject: [PATCH 0847/1469] mm: use kmap_local_page in memzero_page The commit message introducing the global memzero_page explicitly mentions switching to kmap_local_page in the commit log but doesn't actually do that. Link: https://lkml.kernel.org/r/20210713055231.137602-3-hch@lst.de Fixes: 28961998f858 ("iov_iter: lift memzero_page() to highmem.h") Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ira Weiny Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8e7e50a53a12..d9a606a9fc64 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -324,10 +324,10 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { - char *addr = kmap_atomic(page); + char *addr = kmap_local_page(page); memset(addr + offset, 0, len); flush_dcache_page(page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif /* _LINUX_HIGHMEM_H */ From 69e5d322a2fb86173fde8bad26e8eb38cad1b1e9 Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Fri, 23 Jul 2021 15:50:23 -0700 Subject: [PATCH 0848/1469] mm: page_alloc: fix page_poison=1 / INIT_ON_ALLOC_DEFAULT_ON interaction To reproduce the failure we need the following system: - kernel command: page_poison=1 init_on_free=0 init_on_alloc=0 - kernel config: * CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y * CONFIG_INIT_ON_FREE_DEFAULT_ON=y * CONFIG_PAGE_POISONING=y Resulting in: 0000000085629bdd: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 0000000022861832: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000000c597f5b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ CPU: 11 PID: 15195 Comm: bash Kdump: loaded Tainted: G U O 5.13.1-gentoo-x86_64 #1 Hardware name: System manufacturer System Product Name/PRIME Z370-A, BIOS 2801 01/13/2021 Call Trace: dump_stack+0x64/0x7c __kernel_unpoison_pages.cold+0x48/0x84 post_alloc_hook+0x60/0xa0 get_page_from_freelist+0xdb8/0x1000 __alloc_pages+0x163/0x2b0 __get_free_pages+0xc/0x30 pgd_alloc+0x2e/0x1a0 mm_init+0x185/0x270 dup_mm+0x6b/0x4f0 copy_process+0x190d/0x1b10 kernel_clone+0xba/0x3b0 __do_sys_clone+0x8f/0xb0 do_syscall_64+0x68/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Before commit 51cba1ebc60d ("init_on_alloc: Optimize static branches") init_on_alloc never enabled static branch by default. It could only be enabed explicitly by init_mem_debugging_and_hardening(). But after commit 51cba1ebc60d, a static branch could already be enabled by default. There was no code to ever disable it. That caused page_poison=1 / init_on_free=1 conflict. This change extends init_mem_debugging_and_hardening() to also disable static branch disabling. Link: https://lkml.kernel.org/r/20210714031935.4094114-1-keescook@chromium.org Link: https://lore.kernel.org/r/20210712215816.1512739-1-slyfox@gentoo.org Fixes: 51cba1ebc60d ("init_on_alloc: Optimize static branches") Signed-off-by: Sergei Trofimovich Signed-off-by: Kees Cook Co-developed-by: Kees Cook Reported-by: Mikhail Morfikov Reported-by: Tested-by: Reviewed-by: David Hildenbrand Cc: Alexander Potapenko Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3e97e68aef7a..856b175c15a4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -840,21 +840,24 @@ void init_mem_debugging_and_hardening(void) } #endif - if (_init_on_alloc_enabled_early) { - if (page_poisoning_requested) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc\n"); - else - static_branch_enable(&init_on_alloc); - } - if (_init_on_free_enabled_early) { - if (page_poisoning_requested) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_free\n"); - else - static_branch_enable(&init_on_free); + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && + page_poisoning_requested) { + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " + "will take precedence over init_on_alloc and init_on_free\n"); + _init_on_alloc_enabled_early = false; + _init_on_free_enabled_early = false; } + if (_init_on_alloc_enabled_early) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); + + if (_init_on_free_enabled_early) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); + #ifdef CONFIG_DEBUG_PAGEALLOC if (!debug_pagealloc_enabled()) return; From 79e482e9c3ae86e849c701c846592e72baddda5a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 23 Jul 2021 15:50:26 -0700 Subject: [PATCH 0849/1469] memblock: make for_each_mem_range() traverse MEMBLOCK_HOTPLUG regions Commit b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") didn't take into account that when there is movable_node parameter in the kernel command line, for_each_mem_range() would skip ranges marked with MEMBLOCK_HOTPLUG. The page table setup code in POWER uses for_each_mem_range() to create the linear mapping of the physical memory and since the regions marked as MEMORY_HOTPLUG are skipped, they never make it to the linear map. A later access to the memory in those ranges will fail: BUG: Unable to handle kernel data access on write at 0xc000000400000000 Faulting instruction address: 0xc00000000008a3c0 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 53 Comm: kworker/u2:0 Not tainted 5.13.0 #7 NIP: c00000000008a3c0 LR: c0000000003c1ed8 CTR: 0000000000000040 REGS: c000000008a57770 TRAP: 0300 Not tainted (5.13.0) MSR: 8000000002009033 CR: 84222202 XER: 20040000 CFAR: c0000000003c1ed4 DAR: c000000400000000 DSISR: 42000000 IRQMASK: 0 GPR00: c0000000003c1ed8 c000000008a57a10 c0000000019da700 c000000400000000 GPR04: 0000000000000280 0000000000000180 0000000000000400 0000000000000200 GPR08: 0000000000000100 0000000000000080 0000000000000040 0000000000000300 GPR12: 0000000000000380 c000000001bc0000 c0000000001660c8 c000000006337e00 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000040000000 0000000020000000 c000000001a81990 c000000008c30000 GPR24: c000000008c20000 c000000001a81998 000fffffffff0000 c000000001a819a0 GPR28: c000000001a81908 c00c000001000000 c000000008c40000 c000000008a64680 NIP clear_user_page+0x50/0x80 LR __handle_mm_fault+0xc88/0x1910 Call Trace: __handle_mm_fault+0xc44/0x1910 (unreliable) handle_mm_fault+0x130/0x2a0 __get_user_pages+0x248/0x610 __get_user_pages_remote+0x12c/0x3e0 get_arg_page+0x54/0xf0 copy_string_kernel+0x11c/0x210 kernel_execve+0x16c/0x220 call_usermodehelper_exec_async+0x1b0/0x2f0 ret_from_kernel_thread+0x5c/0x70 Instruction dump: 79280fa4 79271764 79261f24 794ae8e2 7ca94214 7d683a14 7c893a14 7d893050 7d4903a6 60000000 60000000 60000000 <7c001fec> 7c091fec 7c081fec 7c051fec ---[ end trace 490b8c67e6075e09 ]--- Making for_each_mem_range() include MEMBLOCK_HOTPLUG regions in the traversal fixes this issue. Link: https://bugzilla.redhat.com/show_bug.cgi?id=1976100 Link: https://lkml.kernel.org/r/20210712071132.20902-1-rppt@kernel.org Fixes: b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") Signed-off-by: Mike Rapoport Tested-by: Greg Kurz Reviewed-by: David Hildenbrand Cc: [5.10+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- mm/memblock.c | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index cbf46f56d105..4a53c3ca86bd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -209,7 +209,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_NONE, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -220,7 +220,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_NONE, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas diff --git a/mm/memblock.c b/mm/memblock.c index 0041ff62c584..de7b553baa50 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -947,7 +947,8 @@ static bool should_skip_region(struct memblock_type *type, return true; /* skip hotpluggable memory regions if needed */ - if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) + if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && + !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ From b43a9e76b4cc78cdaa8c809dd31cd452797b7661 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 23 Jul 2021 15:50:29 -0700 Subject: [PATCH 0850/1469] writeback, cgroup: remove wb from offline list before releasing refcnt Boyang reported that the commit c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") causes the kernel to crash while running xfstests generic/256 on ext4 on aarch64 and ppc64le. run fstests generic/256 at 2021-07-12 05:41:40 EXT4-fs (vda3): mounted filesystem with ordered data mode. Opts: . Quota mode: none. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x96000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 64k pages, 48-bit VAs, pgdp=00000000b0502000 [0000000000000000] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: dm_flakey dm_snapshot dm_bufio dm_zero dm_mod loop tls rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs rfkill sunrpc ext4 vfat fat mbcache jbd2 drm fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 sha1_ce virtio_blk virtio_net net_failover virtio_console failover virtio_mmio aes_neon_bs [last unloaded: scsi_debug] CPU: 0 PID: 408468 Comm: kworker/u8:5 Tainted: G X --------- --- 5.14.0-0.rc1.15.bx.el9.aarch64 #1 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Workqueue: events_unbound cleanup_offline_cgwbs_workfn pstate: 004000c5 (nzcv daIF +PAN -UAO -TCO BTYPE=--) pc : cleanup_offline_cgwbs_workfn+0x320/0x394 lr : cleanup_offline_cgwbs_workfn+0xe0/0x394 sp : ffff80001554fd10 x29: ffff80001554fd10 x28: 0000000000000000 x27: 0000000000000001 x26: 0000000000000000 x25: 00000000000000e0 x24: ffffd2a2fbe671a8 x23: ffff80001554fd88 x22: ffffd2a2fbe67198 x21: ffffd2a2fc25a730 x20: ffff210412bc3000 x19: ffff210412bc3280 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000030 x12: 0000000000000040 x11: ffff210481572238 x10: ffff21048157223a x9 : ffffd2a2fa276c60 x8 : ffff210484106b60 x7 : 0000000000000000 x6 : 000000000007d18a x5 : ffff210416a86400 x4 : ffff210412bc0280 x3 : 0000000000000000 x2 : ffff80001554fd88 x1 : ffff210412bc0280 x0 : 0000000000000003 Call trace: cleanup_offline_cgwbs_workfn+0x320/0x394 process_one_work+0x1f4/0x4b0 worker_thread+0x184/0x540 kthread+0x114/0x120 ret_from_fork+0x10/0x18 Code: d63f0020 97f99963 17ffffa6 f8588263 (f9400061) ---[ end trace e250fe289272792a ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs SMP: failed to stop secondary CPUs 0-2 Kernel Offset: 0x52a2e9fa0000 from 0xffff800010000000 PHYS_OFFSET: 0xfff0defca0000000 CPU features: 0x00200251,23200840 Memory Limit: none ---[ end Kernel panic - not syncing: Oops: Fatal exception ]--- The problem happens when cgwb_release_workfn() races with cleanup_offline_cgwbs_workfn(): wb_tryget() in cleanup_offline_cgwbs_workfn() can be called after percpu_ref_exit() is cgwb_release_workfn(), which is basically a use-after-free error. Fix the problem by making removing the writeback structure from the offline list before releasing the percpu reference counter. It will guarantee that cleanup_offline_cgwbs_workfn() will not see and not access writeback structures which are about to be released. Link: https://lkml.kernel.org/r/20210716201039.3762203-1-guro@fb.com Fixes: c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") Signed-off-by: Roman Gushchin Reported-by: Boyang Xue Suggested-by: Jan Kara Tested-by: Darrick J. Wong Cc: Will Deacon Cc: Dave Chinner Cc: Murphy Zhou Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/backing-dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 271f2ca862c8..f5561ea7d90a 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -398,12 +398,12 @@ static void cgwb_release_workfn(struct work_struct *work) blkcg_unpin_online(blkcg); fprop_local_destroy_percpu(&wb->memcg_completions); - percpu_ref_exit(&wb->refcnt); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); + percpu_ref_exit(&wb->refcnt); wb_exit(wb); WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); From 593311e85b26ecc6e4d45b6fb81b942b6672df09 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 23 Jul 2021 15:50:32 -0700 Subject: [PATCH 0851/1469] writeback, cgroup: do not reparent dax inodes The inode switching code is not suited for dax inodes. An attempt to switch a dax inode to a parent writeback structure (as a part of a writeback cleanup procedure) results in a panic like this: run fstests generic/270 at 2021-07-15 05:54:02 XFS (pmem0p2): EXPERIMENTAL big timestamp feature in use. Use at your own risk! XFS (pmem0p2): DAX enabled. Warning: EXPERIMENTAL, use at your own risk XFS (pmem0p2): EXPERIMENTAL inode btree counters feature in use. Use at your own risk! XFS (pmem0p2): Mounting V5 Filesystem XFS (pmem0p2): Ending clean mount XFS (pmem0p2): Quotacheck needed: Please wait. XFS (pmem0p2): Quotacheck: Done. XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) BUG: unable to handle page fault for address: 0000000005b0f669 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 13 PID: 10479 Comm: kworker/13:16 Not tainted 5.14.0-rc1-master-8096acd7442e+ #8 Hardware name: HP ProLiant DL360 Gen9/ProLiant DL360 Gen9, BIOS P89 09/13/2016 Workqueue: inode_switch_wbs inode_switch_wbs_work_fn RIP: 0010:inode_do_switch_wbs+0xaf/0x470 Code: 00 30 0f 85 c1 03 00 00 0f 1f 44 00 00 31 d2 48 c7 c6 ff ff ff ff 48 8d 7c 24 08 e8 eb 49 1a 00 48 85 c0 74 4a bb ff ff ff ff <48> 8b 50 08 48 8d 4a ff 83 e2 01 48 0f 45 c1 48 8b 00 a8 08 0f 85 RSP: 0018:ffff9c66691abdc8 EFLAGS: 00010002 RAX: 0000000005b0f661 RBX: 00000000ffffffff RCX: ffff89e6a21382b0 RDX: 0000000000000001 RSI: ffff89e350230248 RDI: ffffffffffffffff RBP: ffff89e681d19400 R08: 0000000000000000 R09: 0000000000000228 R10: ffffffffffffffff R11: ffffffffffffffc0 R12: ffff89e6a2138130 R13: ffff89e316af7400 R14: ffff89e316af6e78 R15: ffff89e6a21382b0 FS: 0000000000000000(0000) GS:ffff89ee5fb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005b0f669 CR3: 0000000cb2410004 CR4: 00000000001706e0 Call Trace: inode_switch_wbs_work_fn+0xb6/0x2a0 process_one_work+0x1e6/0x380 worker_thread+0x53/0x3d0 kthread+0x10f/0x130 ret_from_fork+0x22/0x30 Modules linked in: xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nft_counter nf_tables nfnetlink bridge stp llc rfkill sunrpc intel_rapl_msr intel_rapl_common sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ipmi_ssif kvm mgag200 i2c_algo_bit iTCO_wdt irqbypass drm_kms_helper iTCO_vendor_support acpi_ipmi rapl syscopyarea sysfillrect intel_cstate ipmi_si sysimgblt ioatdma dax_pmem_compat fb_sys_fops ipmi_devintf device_dax i2c_i801 pcspkr intel_uncore hpilo nd_pmem cec dax_pmem_core dca i2c_smbus acpi_tad lpc_ich ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sd_mod t10_pi crct10dif_pclmul crc32_pclmul crc32c_intel tg3 ghash_clmulni_intel serio_raw hpsa hpwdt scsi_transport_sas wmi dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000005b0f669 ---[ end trace ed2105faff8384f3 ]--- RIP: 0010:inode_do_switch_wbs+0xaf/0x470 Code: 00 30 0f 85 c1 03 00 00 0f 1f 44 00 00 31 d2 48 c7 c6 ff ff ff ff 48 8d 7c 24 08 e8 eb 49 1a 00 48 85 c0 74 4a bb ff ff ff ff <48> 8b 50 08 48 8d 4a ff 83 e2 01 48 0f 45 c1 48 8b 00 a8 08 0f 85 RSP: 0018:ffff9c66691abdc8 EFLAGS: 00010002 RAX: 0000000005b0f661 RBX: 00000000ffffffff RCX: ffff89e6a21382b0 RDX: 0000000000000001 RSI: ffff89e350230248 RDI: ffffffffffffffff RBP: ffff89e681d19400 R08: 0000000000000000 R09: 0000000000000228 R10: ffffffffffffffff R11: ffffffffffffffc0 R12: ffff89e6a2138130 R13: ffff89e316af7400 R14: ffff89e316af6e78 R15: ffff89e6a21382b0 FS: 0000000000000000(0000) GS:ffff89ee5fb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005b0f669 CR3: 0000000cb2410004 CR4: 00000000001706e0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x15200000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- The crash happens on an attempt to iterate over attached pagecache pages and check the dirty flag: a dax inode's xarray contains pfn's instead of generic struct page pointers. This happens for DAX and not for other kinds of non-page entries in the inodes because it's a tagged iteration, and shadow/swap entries are never tagged; only DAX entries get tagged. Fix the problem by bailing out (with the false return value) of inode_prepare_sbs_switch() if a dax inode is passed. [willy@infradead.org: changelog addition] Link: https://lkml.kernel.org/r/20210719171350.3876830-1-guro@fb.com Fixes: c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") Signed-off-by: Roman Gushchin Reported-by: Murphy Zhou Reported-by: Darrick J. Wong Tested-by: Darrick J. Wong Tested-by: Murphy Zhou Acked-by: Matthew Wilcox (Oracle) Cc: Jan Kara Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 06d04a74ab6c..4c3370548982 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -521,6 +521,9 @@ static bool inode_prepare_wbs_switch(struct inode *inode, */ smp_mb(); + if (IS_DAX(inode)) + return false; + /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || From af64237461910f4c7365d367291d1c4f20c18769 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 23 Jul 2021 15:50:35 -0700 Subject: [PATCH 0852/1469] mm/secretmem: wire up ->set_page_dirty Make secretmem up to date with the changes done in commit 0af573780b0b ("mm: require ->set_page_dirty to be explicitly wired up") so that unconditional call to this method won't cause crashes. Link: https://lkml.kernel.org/r/20210716063933.31633-1-rppt@kernel.org Fixes: 0af573780b0b ("mm: require ->set_page_dirty to be explicitly wired up") Signed-off-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/secretmem.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/secretmem.c b/mm/secretmem.c index f77d25467a14..030f02ddc7c1 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -152,6 +152,7 @@ static void secretmem_freepage(struct page *page) } const struct address_space_operations secretmem_aops = { + .set_page_dirty = __set_page_dirty_no_writeback, .freepage = secretmem_freepage, .migratepage = secretmem_migratepage, .isolate_page = secretmem_isolate_page, From e904c2ccf9b5cb356eec754ffea05c08984f6535 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 23 Jul 2021 15:50:38 -0700 Subject: [PATCH 0853/1469] mm: mmap_lock: fix disabling preemption directly Commit 832b50725373 ("mm: mmap_lock: use local locks instead of disabling preemption") fixed a bug by using local locks. But commit d01079f3d0c0 ("mm/mmap_lock: remove dead code for !CONFIG_TRACING configurations") changed those lines back to the original version. I guess it was introduced by fixing conflicts. Link: https://lkml.kernel.org/r/20210720074228.76342-1-songmuchun@bytedance.com Fixes: d01079f3d0c0 ("mm/mmap_lock: remove dead code for !CONFIG_TRACING configurations") Signed-off-by: Muchun Song Acked-by: Mel Gorman Reviewed-by: Yang Shi Reviewed-by: Pankaj Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap_lock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index f5852a058ce0..1854850b4b89 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -156,14 +156,14 @@ static inline void put_memcg_path_buf(void) #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ do { \ const char *memcg_path; \ - preempt_disable(); \ + local_lock(&memcg_paths.lock); \ memcg_path = get_mm_memcg_path(mm); \ trace_mmap_lock_##type(mm, \ memcg_path != NULL ? memcg_path : "", \ ##__VA_ARGS__); \ if (likely(memcg_path != NULL)) \ put_memcg_path_buf(); \ - preempt_enable(); \ + local_unlock(&memcg_paths.lock); \ } while (0) #else /* !CONFIG_MEMCG */ From e4dc3489143f84f7ed30be58b886bb6772f229b9 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Fri, 23 Jul 2021 15:50:41 -0700 Subject: [PATCH 0854/1469] mm: fix the deadlock in finish_fault() Commit 63f3655f9501 ("mm, memcg: fix reclaim deadlock with writeback") fix the following ABBA deadlock by pre-allocating the pte page table without holding the page lock. lock_page(A) SetPageWriteback(A) unlock_page(A) lock_page(B) lock_page(B) pte_alloc_one shrink_page_list wait_on_page_writeback(A) SetPageWriteback(B) unlock_page(B) # flush A, B to clear the writeback Commit f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") reworked the relevant code but ignored this race. This will cause the deadlock above to appear again, so fix it. Link: https://lkml.kernel.org/r/20210721074849.57004-1-zhengqi.arch@bytedance.com Fixes: f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") Signed-off-by: Qi Zheng Acked-by: Kirill A. Shutemov Cc: Thomas Gleixner Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Muchun Song Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 747a01d495f2..25fc46e87214 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4026,8 +4026,17 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return ret; } - if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) + if (vmf->prealloc_pte) { + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (likely(pmd_none(*vmf->pmd))) { + mm_inc_nr_ptes(vma->vm_mm); + pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); + vmf->prealloc_pte = NULL; + } + spin_unlock(vmf->ptl); + } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; + } } /* See comment in handle_pte_fault() */ From e0f7e2b2f7e7864238a4eea05cc77ae1be2bf784 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 23 Jul 2021 15:50:44 -0700 Subject: [PATCH 0855/1469] hugetlbfs: fix mount mode command line processing In commit 32021982a324 ("hugetlbfs: Convert to fs_context") processing of the mount mode string was changed from match_octal() to fsparam_u32. This changed existing behavior as match_octal does not require octal values to have a '0' prefix, but fsparam_u32 does. Use fsparam_u32oct which provides the same behavior as match_octal. Link: https://lkml.kernel.org/r/20210721183326.102716-1-mike.kravetz@oracle.com Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context") Signed-off-by: Mike Kravetz Reported-by: Dennis Camera Reviewed-by: Matthew Wilcox (Oracle) Cc: David Howells Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 926eeb9bf4eb..cdfb1ae78a3f 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -77,7 +77,7 @@ enum hugetlb_param { static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), - fsparam_u32 ("mode", Opt_mode), + fsparam_u32oct("mode", Opt_mode), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("pagesize", Opt_pagesize), fsparam_string("size", Opt_size), From 6010d300f9f7e16d1bf327b4730bcd0c0886d9e6 Mon Sep 17 00:00:00 2001 From: Akira Tsukamoto Date: Tue, 20 Jul 2021 17:50:52 +0900 Subject: [PATCH 0856/1469] riscv: __asm_copy_to-from_user: Fix: overrun copy There were two causes for the overrun memory access. The threshold size was too small. The aligning dst require one SZREG and unrolling word copy requires 8*SZREG, total have to be at least 9*SZREG. Inside the unrolling copy, the subtracting -(8*SZREG-1) would make iteration happening one extra loop. Proper value is -(8*SZREG). Signed-off-by: Akira Tsukamoto Fixes: ca6eaaa210de ("riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall") Signed-off-by: Palmer Dabbelt --- arch/riscv/lib/uaccess.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index bceb0629e440..8bbeca89a93f 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -35,7 +35,7 @@ ENTRY(__asm_copy_from_user) /* * Use byte copy only if too small. */ - li a3, 8*SZREG /* size must be larger than size in word_copy */ + li a3, 9*SZREG /* size must be larger than size in word_copy */ bltu a2, a3, .Lbyte_copy_tail /* @@ -75,7 +75,7 @@ ENTRY(__asm_copy_from_user) * a3 - a1 & mask:(SZREG-1) * t0 - end of aligned dst */ - addi t0, t0, -(8*SZREG-1) /* not to over run */ + addi t0, t0, -(8*SZREG) /* not to over run */ 2: fixup REG_L a4, 0(a1), 10f fixup REG_L a5, SZREG(a1), 10f @@ -97,7 +97,7 @@ ENTRY(__asm_copy_from_user) addi a1, a1, 8*SZREG bltu a0, t0, 2b - addi t0, t0, 8*SZREG-1 /* revert to original value */ + addi t0, t0, 8*SZREG /* revert to original value */ j .Lbyte_copy_tail .Lshift_copy: From 22b5f16ffeff38938ad7420a2bfa3c281c36fd17 Mon Sep 17 00:00:00 2001 From: Akira Tsukamoto Date: Tue, 20 Jul 2021 17:51:45 +0900 Subject: [PATCH 0857/1469] riscv: __asm_copy_to-from_user: Fix: fail on RV32 Had a bug when converting bytes to bits when the cpu was rv32. The a3 contains the number of bytes and multiple of 8 would be the bits. The LGREG is holding 2 for RV32 and 3 for RV32, so to achieve multiple of 8 it must always be constant 3. The 2 was mistakenly used for rv32. Signed-off-by: Akira Tsukamoto Fixes: ca6eaaa210de ("riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall") Signed-off-by: Palmer Dabbelt --- arch/riscv/lib/uaccess.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 8bbeca89a93f..279876821969 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -125,7 +125,7 @@ ENTRY(__asm_copy_from_user) * t3 - prev shift * t4 - current shift */ - slli t3, a3, LGREG + slli t3, a3, 3 /* converting bytes in a3 to bits */ li a5, SZREG*8 sub t4, a5, t3 From d4b3e0105e3c2411af666a50b1bf2d25656a5e83 Mon Sep 17 00:00:00 2001 From: Akira Tsukamoto Date: Tue, 20 Jul 2021 17:52:36 +0900 Subject: [PATCH 0858/1469] riscv: __asm_copy_to-from_user: Remove unnecessary size check Clean up: The size of 0 will be evaluated in the next step. Not required here. Signed-off-by: Akira Tsukamoto Fixes: ca6eaaa210de ("riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall") Signed-off-by: Palmer Dabbelt --- arch/riscv/lib/uaccess.S | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 279876821969..54d497a03164 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -30,7 +30,6 @@ ENTRY(__asm_copy_from_user) * t0 - end of uncopied dst */ add t0, a0, a2 - bgtu a0, t0, 5f /* * Use byte copy only if too small. From ea196c548c0ac407afd31d142712b6da8bd00244 Mon Sep 17 00:00:00 2001 From: Akira Tsukamoto Date: Tue, 20 Jul 2021 17:53:23 +0900 Subject: [PATCH 0859/1469] riscv: __asm_copy_to-from_user: Fix: Typos in comments Fixing typos and grammar mistakes and using more intuitive label name. Signed-off-by: Akira Tsukamoto Fixes: ca6eaaa210de ("riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall") Signed-off-by: Palmer Dabbelt --- arch/riscv/lib/uaccess.S | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 54d497a03164..63bc691cff91 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -33,19 +33,20 @@ ENTRY(__asm_copy_from_user) /* * Use byte copy only if too small. + * SZREG holds 4 for RV32 and 8 for RV64 */ li a3, 9*SZREG /* size must be larger than size in word_copy */ bltu a2, a3, .Lbyte_copy_tail /* - * Copy first bytes until dst is align to word boundary. + * Copy first bytes until dst is aligned to word boundary. * a0 - start of dst * t1 - start of aligned dst */ addi t1, a0, SZREG-1 andi t1, t1, ~(SZREG-1) /* dst is already aligned, skip */ - beq a0, t1, .Lskip_first_bytes + beq a0, t1, .Lskip_align_dst 1: /* a5 - one byte for copying data */ fixup lb a5, 0(a1), 10f @@ -54,7 +55,7 @@ ENTRY(__asm_copy_from_user) addi a0, a0, 1 /* dst */ bltu a0, t1, 1b /* t1 - start of aligned dst */ -.Lskip_first_bytes: +.Lskip_align_dst: /* * Now dst is aligned. * Use shift-copy if src is misaligned. @@ -71,7 +72,6 @@ ENTRY(__asm_copy_from_user) * * a0 - start of aligned dst * a1 - start of aligned src - * a3 - a1 & mask:(SZREG-1) * t0 - end of aligned dst */ addi t0, t0, -(8*SZREG) /* not to over run */ @@ -106,7 +106,7 @@ ENTRY(__asm_copy_from_user) * For misaligned copy we still perform aligned word copy, but * we need to use the value fetched from the previous iteration and * do some shifts. - * This is safe because reading less than a word size. + * This is safe because reading is less than a word size. * * a0 - start of aligned dst * a1 - start of src @@ -116,7 +116,7 @@ ENTRY(__asm_copy_from_user) */ /* calculating aligned word boundary for dst */ andi t1, t0, ~(SZREG-1) - /* Converting unaligned src to aligned arc */ + /* Converting unaligned src to aligned src */ andi a1, a1, ~(SZREG-1) /* @@ -128,7 +128,7 @@ ENTRY(__asm_copy_from_user) li a5, SZREG*8 sub t4, a5, t3 - /* Load the first word to combine with seceond word */ + /* Load the first word to combine with second word */ fixup REG_L a5, 0(a1), 10f 3: @@ -160,7 +160,7 @@ ENTRY(__asm_copy_from_user) * a1 - start of remaining src * t0 - end of remaining dst */ - bgeu a0, t0, 5f + bgeu a0, t0, .Lout_copy_user /* check if end of copy */ 4: fixup lb a5, 0(a1), 10f addi a1, a1, 1 /* src */ @@ -168,7 +168,7 @@ ENTRY(__asm_copy_from_user) addi a0, a0, 1 /* dst */ bltu a0, t0, 4b /* t0 - end of dst */ -5: +.Lout_copy_user: /* Disable access to user memory */ csrc CSR_STATUS, t6 li a0, 0 From cdf72837cda89b2d38bd18fbe6cc591c1d5f2416 Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Fri, 23 Jul 2021 05:41:53 +0930 Subject: [PATCH 0860/1469] ALSA: scarlett2: Fix Mute/Dim/MSD Mode control names Append "Playback Switch" to the names of "Mute" and "Dim" controls, and append "Switch" to the "MSD Mode" control as per Documentation/sound/designs/control-names.rst. Signed-off-by: Geoffrey D. Bennett Link: https://lore.kernel.org/r/77f1000652c37e3217fb8dad8e156bc6392abc0b.1626959758.git.g@b4.vu Signed-off-by: Takashi Iwai --- sound/usb/mixer_scarlett_gen2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index f9d698a37153..347995ea39e4 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -228,7 +228,7 @@ enum { }; static const char *const scarlett2_dim_mute_names[SCARLETT2_DIM_MUTE_COUNT] = { - "Mute", "Dim" + "Mute Playback Switch", "Dim Playback Switch" }; /* Description of each hardware port type: @@ -3455,7 +3455,7 @@ static int scarlett2_add_msd_ctl(struct usb_mixer_interface *mixer) /* Add MSD control */ return scarlett2_add_new_ctl(mixer, &scarlett2_msd_ctl, - 0, 1, "MSD Mode", NULL); + 0, 1, "MSD Mode Switch", NULL); } /*** Cleanup/Suspend Callbacks ***/ From d3a4f784d20c696b134b916f57956f12a37ecd47 Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Fri, 23 Jul 2021 05:42:08 +0930 Subject: [PATCH 0861/1469] ALSA: scarlett2: Fix Direct Monitor control name for 2i2 The Direct Monitor control for the 2i2 is an enumerated value, not a boolean. Fix the control name to say "Playback Enum" instead of "Playback Switch" in this case. Signed-off-by: Geoffrey D. Bennett Link: https://lore.kernel.org/r/faf5de1d2100038e7d07520d770fda4a1adc276a.1626959758.git.g@b4.vu Signed-off-by: Takashi Iwai --- sound/usb/mixer_scarlett_gen2.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 347995ea39e4..fa604b61066f 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -2530,14 +2530,18 @@ static int scarlett2_add_direct_monitor_ctl(struct usb_mixer_interface *mixer) { struct scarlett2_data *private = mixer->private_data; const struct scarlett2_device_info *info = private->info; + const char *s; if (!info->direct_monitor) return 0; + s = info->direct_monitor == 1 + ? "Direct Monitor Playback Switch" + : "Direct Monitor Playback Enum"; + return scarlett2_add_new_ctl( mixer, &scarlett2_direct_monitor_ctl[info->direct_monitor - 1], - 0, 1, "Direct Monitor Playback Switch", - &private->direct_monitor_ctl); + 0, 1, s, &private->direct_monitor_ctl); } /*** Speaker Switching Control ***/ From 9ee0fc8366ddce380547878640708f1bd7dd2ead Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Fri, 23 Jul 2021 05:42:48 +0930 Subject: [PATCH 0862/1469] ALSA: scarlett2: Correct channel mute status after mute button pressed After the hardware mute button is pressed, private->vol_updated is set so that the mute status is invalidated. As the channel mute values may be affected by the global mute value, update scarlett2_mute_ctl_get() to call scarlett2_update_volumes() if private->vol_updated is set. Signed-off-by: Geoffrey D. Bennett Link: https://lore.kernel.org/r/aa18ddbf8d8bd7f31832ab1b6b6057c00b931202.1626959758.git.g@b4.vu Signed-off-by: Takashi Iwai --- sound/usb/mixer_scarlett_gen2.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index fa604b61066f..3457fbc8108f 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -1856,9 +1856,15 @@ static int scarlett2_mute_ctl_get(struct snd_kcontrol *kctl, struct snd_ctl_elem_value *ucontrol) { struct usb_mixer_elem_info *elem = kctl->private_data; - struct scarlett2_data *private = elem->head.mixer->private_data; + struct usb_mixer_interface *mixer = elem->head.mixer; + struct scarlett2_data *private = mixer->private_data; int index = line_out_remap(private, elem->control); + mutex_lock(&private->data_mutex); + if (private->vol_updated) + scarlett2_update_volumes(mixer); + mutex_unlock(&private->data_mutex); + ucontrol->value.integer.value[0] = private->mute_switch[index]; return 0; } From 2b8b12be9b9752c36efda38b7dd5d83d790d01d8 Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Fri, 23 Jul 2021 05:43:26 +0930 Subject: [PATCH 0863/1469] ALSA: scarlett2: Fix line out/speaker switching notifications The values of the line output controls can change when the SW/HW switches are set to HW, and also when speaker switching is enabled. These notifications were sent with a mask of only SNDRV_CTL_EVENT_MASK_INFO. Change the notifications to set the SNDRV_CTL_EVENT_MASK_VALUE mask bit as well. When the mute control is updated, the notification was sent with a mask of SNDRV_CTL_EVENT_MASK_INFO. Change the mask to the correct value of SNDRV_CTL_EVENT_MASK_VALUE. Signed-off-by: Geoffrey D. Bennett Link: https://lore.kernel.org/r/8192e15ba62fa4bc90425c005f265c0de530be20.1626959758.git.g@b4.vu Signed-off-by: Takashi Iwai --- sound/usb/mixer_scarlett_gen2.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 3457fbc8108f..3d5848d5481b 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -1961,10 +1961,12 @@ static void scarlett2_vol_ctl_set_writable(struct usb_mixer_interface *mixer, ~SNDRV_CTL_ELEM_ACCESS_WRITE; } - /* Notify of write bit change */ - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO, + /* Notify of write bit and possible value change */ + snd_ctl_notify(card, + SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO, &private->vol_ctls[index]->id); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO, + snd_ctl_notify(card, + SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO, &private->mute_ctls[index]->id); } @@ -2599,7 +2601,9 @@ static int scarlett2_speaker_switch_enable(struct usb_mixer_interface *mixer) /* disable the line out SW/HW switch */ scarlett2_sw_hw_ctl_ro(private, i); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO, + snd_ctl_notify(card, + SNDRV_CTL_EVENT_MASK_VALUE | + SNDRV_CTL_EVENT_MASK_INFO, &private->sw_hw_ctls[i]->id); } @@ -2923,7 +2927,7 @@ static int scarlett2_dim_mute_ctl_put(struct snd_kcontrol *kctl, if (private->vol_sw_hw_switch[line_index]) { private->mute_switch[line_index] = val; snd_ctl_notify(mixer->chip->card, - SNDRV_CTL_EVENT_MASK_INFO, + SNDRV_CTL_EVENT_MASK_VALUE, &private->mute_ctls[i]->id); } } From 4511781f95da0a3b2bad34f3f5e3967e80cd2d18 Mon Sep 17 00:00:00 2001 From: "chihhao.chen" Date: Sat, 24 Jul 2021 12:23:41 +0800 Subject: [PATCH 0864/1469] ALSA: usb-audio: fix incorrect clock source setting The following scenario describes an echo test for Samsung USBC Headset (AKG) with VID/PID (0x04e8/0xa051). We first start a capture stream(USB IN transfer) in 96Khz/24bit/1ch mode. In clock find source function, we get value 0x2 for clock selector and 0x1 for clock source. Kernel-4.14 behavior Since clock source is valid so clock selector was not set again. We pass through this function and start a playback stream(USB OUT transfer) in 48Khz/32bit/2ch mode. This time we get value 0x1 for clock selector and 0x1 for clock source. Finally clock id with this setting is 0x9. Kernel-5.10 behavior Clock selector was always set one more time even it is valid. When we start a playback stream, we will get 0x2 for clock selector and 0x1 for clock source. In this case clock id becomes 0xA. This is an incorrect clock source setting and results in severe noises. We see wrong data rate in USB IN transfer. (From 288 bytes/ms becomes 144 bytes/ms) It should keep in 288 bytes/ms. This earphone works fine on older kernel version load because this is a newly-added behavior. Fixes: d2e8f641257d ("ALSA: usb-audio: Explicitly set up the clock selector") Signed-off-by: chihhao.chen Link: https://lore.kernel.org/r/1627100621-19225-1-git-send-email-chihhao.chen@mediatek.com Signed-off-by: Takashi Iwai --- sound/usb/clock.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 52de52288e10..14456f61539e 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -324,6 +324,12 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, sources[ret - 1], visited, validate); if (ret > 0) { + /* + * For Samsung USBC Headset (AKG), setting clock selector again + * will result in incorrect default clock setting problems + */ + if (chip->usb_id == USB_ID(0x04e8, 0xa051)) + return ret; err = uac_clock_selector_set_val(chip, entity_id, cur); if (err < 0) return err; From 9f9decdb64c5cc05b66f7a6ede226dd90684570b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:13:20 +0200 Subject: [PATCH 0865/1469] iio: accel: fxls8962af: fix i2c dependency With CONFIG_SPI=y and CONFIG_I2C=m, building fxls8962af into vmlinux causes a link error against the I2C module: aarch64-linux-ld: drivers/iio/accel/fxls8962af-core.o: in function `fxls8962af_fifo_flush': fxls8962af-core.c:(.text+0x3a0): undefined reference to `i2c_verify_client' Work around it by adding a Kconfig dependency that forces the SPI driver to be a loadable module whenever I2C is a module. Fixes: af959b7b96b8 ("iio: accel: fxls8962af: fix errata bug E3 - I2C burst reads") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210721151330.2176653-1-arnd@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/accel/Kconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 0e56ace61103..8d8b1ba42ff8 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -231,6 +231,7 @@ config DMARD10 config FXLS8962AF tristate + depends on I2C || !I2C # cannot be built-in for modular I2C config FXLS8962AF_I2C tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer I2C Driver" @@ -247,6 +248,7 @@ config FXLS8962AF_I2C config FXLS8962AF_SPI tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer SPI Driver" depends on SPI + depends on I2C || !I2C select FXLS8962AF select REGMAP_SPI help From 14a30238ecb8dcf52a9e2be514414e3ec443b536 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 21 Jul 2021 16:03:45 +0200 Subject: [PATCH 0866/1469] dt-bindings: iio: st: Remove wrong items length check The original bindings was listing the length of the interrupts as either 1 or 2, depending on the setup. This is also what is enforced by the top level schema. However, that is further constrained with an if clause that require exactly two interrupts, even though it might not make sense on those devices or in some setups. Let's remove the clause entirely. Cc: Denis Ciocca Cc: Lars-Peter Clausen Fixes: 0cd71145803d ("iio: st-sensors: Update ST Sensor bindings") Signed-off-by: Maxime Ripard Reviewed-by: Rob Herring Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210721140424.725744-16-maxime@cerno.tech Signed-off-by: Jonathan Cameron --- .../bindings/iio/st,st-sensors.yaml | 41 ------------------- 1 file changed, 41 deletions(-) diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index b2a1e42c56fa..71de5631ebae 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -152,47 +152,6 @@ allOf: maxItems: 1 st,drdy-int-pin: false - - if: - properties: - compatible: - enum: - # Two intertial interrupts i.e. accelerometer/gyro interrupts - - st,h3lis331dl-accel - - st,l3g4200d-gyro - - st,l3g4is-gyro - - st,l3gd20-gyro - - st,l3gd20h-gyro - - st,lis2de12 - - st,lis2dw12 - - st,lis2hh12 - - st,lis2dh12-accel - - st,lis331dl-accel - - st,lis331dlh-accel - - st,lis3de - - st,lis3dh-accel - - st,lis3dhh - - st,lis3mdl-magn - - st,lng2dm-accel - - st,lps331ap-press - - st,lsm303agr-accel - - st,lsm303dlh-accel - - st,lsm303dlhc-accel - - st,lsm303dlm-accel - - st,lsm330-accel - - st,lsm330-gyro - - st,lsm330d-accel - - st,lsm330d-gyro - - st,lsm330dl-accel - - st,lsm330dl-gyro - - st,lsm330dlc-accel - - st,lsm330dlc-gyro - - st,lsm9ds0-gyro - - st,lsm9ds1-magn - then: - properties: - interrupts: - maxItems: 2 - required: - compatible - reg From f5d156c7bfab7d728b2fd35bc63eab12eda18125 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Mon, 19 Jul 2021 15:34:37 +0800 Subject: [PATCH 0867/1469] arm64: dts: imx8mp: remove fallback compatible string for FlexCAN FlexCAN on i.MX8MP is not derived from i.MX6Q, instead reuses from i.MX8QM with extra ECC added and default is enabled, so that the FlexCAN would be put into freeze mode without FLEXCAN_QUIRK_DISABLE_MECR quirk. This patch removes "fsl,imx6q-flexcan" fallback compatible string since it's not compatible with the i.MX6Q. Link: https://lore.kernel.org/r/20210719073437.32078-1-qiangqing.zhang@nxp.com Signed-off-by: Joakim Zhang Reviewed-by: Fabio Estevam Signed-off-by: Marc Kleine-Budde --- arch/arm64/boot/dts/freescale/imx8mp.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index ca38d0d6c3c4..f4eaab3ecf03 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -579,7 +579,7 @@ }; flexcan1: can@308c0000 { - compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan"; + compatible = "fsl,imx8mp-flexcan"; reg = <0x308c0000 0x10000>; interrupts = ; clocks = <&clk IMX8MP_CLK_IPG_ROOT>, @@ -594,7 +594,7 @@ }; flexcan2: can@308d0000 { - compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan"; + compatible = "fsl,imx8mp-flexcan"; reg = <0x308d0000 0x10000>; interrupts = ; clocks = <&clk IMX8MP_CLK_IPG_ROOT>, From 54f93336d000229f72c26d8a3f69dd256b744528 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Thu, 22 Jul 2021 15:08:19 +0800 Subject: [PATCH 0868/1469] can: raw: raw_setsockopt(): fix raw_rcv panic for sock UAF We get a bug during ltp can_filter test as following. =========================================== [60919.264984] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 [60919.265223] PGD 8000003dda726067 P4D 8000003dda726067 PUD 3dda727067 PMD 0 [60919.265443] Oops: 0000 [#1] SMP PTI [60919.265550] CPU: 30 PID: 3638365 Comm: can_filter Kdump: loaded Tainted: G W 4.19.90+ #1 [60919.266068] RIP: 0010:selinux_socket_sock_rcv_skb+0x3e/0x200 [60919.293289] RSP: 0018:ffff8d53bfc03cf8 EFLAGS: 00010246 [60919.307140] RAX: 0000000000000000 RBX: 000000000000001d RCX: 0000000000000007 [60919.320756] RDX: 0000000000000001 RSI: ffff8d5104a8ed00 RDI: ffff8d53bfc03d30 [60919.334319] RBP: ffff8d9338056800 R08: ffff8d53bfc29d80 R09: 0000000000000001 [60919.347969] R10: ffff8d53bfc03ec0 R11: ffffb8526ef47c98 R12: ffff8d53bfc03d30 [60919.350320] perf: interrupt took too long (3063 > 2500), lowering kernel.perf_event_max_sample_rate to 65000 [60919.361148] R13: 0000000000000001 R14: ffff8d53bcf90000 R15: 0000000000000000 [60919.361151] FS: 00007fb78b6b3600(0000) GS:ffff8d53bfc00000(0000) knlGS:0000000000000000 [60919.400812] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [60919.413730] CR2: 0000000000000010 CR3: 0000003e3f784006 CR4: 00000000007606e0 [60919.426479] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [60919.439339] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [60919.451608] PKRU: 55555554 [60919.463622] Call Trace: [60919.475617] [60919.487122] ? update_load_avg+0x89/0x5d0 [60919.498478] ? update_load_avg+0x89/0x5d0 [60919.509822] ? account_entity_enqueue+0xc5/0xf0 [60919.520709] security_sock_rcv_skb+0x2a/0x40 [60919.531413] sk_filter_trim_cap+0x47/0x1b0 [60919.542178] ? kmem_cache_alloc+0x38/0x1b0 [60919.552444] sock_queue_rcv_skb+0x17/0x30 [60919.562477] raw_rcv+0x110/0x190 [can_raw] [60919.572539] can_rcv_filter+0xbc/0x1b0 [can] [60919.582173] can_receive+0x6b/0xb0 [can] [60919.591595] can_rcv+0x31/0x70 [can] [60919.600783] __netif_receive_skb_one_core+0x5a/0x80 [60919.609864] process_backlog+0x9b/0x150 [60919.618691] net_rx_action+0x156/0x400 [60919.627310] ? sched_clock_cpu+0xc/0xa0 [60919.635714] __do_softirq+0xe8/0x2e9 [60919.644161] do_softirq_own_stack+0x2a/0x40 [60919.652154] [60919.659899] do_softirq.part.17+0x4f/0x60 [60919.667475] __local_bh_enable_ip+0x60/0x70 [60919.675089] __dev_queue_xmit+0x539/0x920 [60919.682267] ? finish_wait+0x80/0x80 [60919.689218] ? finish_wait+0x80/0x80 [60919.695886] ? sock_alloc_send_pskb+0x211/0x230 [60919.702395] ? can_send+0xe5/0x1f0 [can] [60919.708882] can_send+0xe5/0x1f0 [can] [60919.715037] raw_sendmsg+0x16d/0x268 [can_raw] It's because raw_setsockopt() concurrently with unregister_netdevice_many(). Concurrent scenario as following. cpu0 cpu1 raw_bind raw_setsockopt unregister_netdevice_many unlist_netdevice dev_get_by_index raw_notifier raw_enable_filters ...... can_rx_register can_rcv_list_find(..., net->can.rx_alldev_list) ...... sock_close raw_release(sock_a) ...... can_receive can_rcv_filter(net->can.rx_alldev_list, ...) raw_rcv(skb, sock_a) BUG After unlist_netdevice(), dev_get_by_index() return NULL in raw_setsockopt(). Function raw_enable_filters() will add sock and can_filter to net->can.rx_alldev_list. Then the sock is closed. Followed by, we sock_sendmsg() to a new vcan device use the same can_filter. Protocol stack match the old receiver whose sock has been released on net->can.rx_alldev_list in can_rcv_filter(). Function raw_rcv() uses the freed sock. UAF BUG is triggered. We can find that the key issue is that net_device has not been protected in raw_setsockopt(). Use rtnl_lock to protect net_device in raw_setsockopt(). Fixes: c18ce101f2e4 ("[CAN]: Add raw protocol") Link: https://lore.kernel.org/r/20210722070819.1048263-1-william.xuanziyang@huawei.com Cc: linux-stable Signed-off-by: Ziyang Xuan Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- net/can/raw.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/net/can/raw.c b/net/can/raw.c index ed4fcb7ab0c3..cd5a49380116 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + } if (ro->bound) { /* (try to) register the new filters */ @@ -588,6 +596,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -600,10 +609,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + } /* remove current error mask */ if (ro->bound) { @@ -627,6 +642,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; From 0c71437dd50dd687c15d8ca80b3b68f10bb21d63 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 14 Jul 2021 13:16:02 +0200 Subject: [PATCH 0869/1469] can: j1939: j1939_session_deactivate(): clarify lifetime of session object The j1939_session_deactivate() is decrementing the session ref-count and potentially can free() the session. This would cause use-after-free situation. However, the code calling j1939_session_deactivate() does always hold another reference to the session, so that it would not be free()ed in this code path. This patch adds a comment to make this clear and a WARN_ON, to ensure that future changes will not violate this requirement. Further this patch avoids dereferencing the session pointer as a precaution to avoid use-after-free if the session is actually free()ed. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/r/20210714111602.24021-1-o.rempel@pengutronix.de Reported-by: Xiaochen Zou Signed-off-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- net/can/j1939/transport.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index c3946c355882..bb1092c3e7e3 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1075,11 +1075,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session) static bool j1939_session_deactivate(struct j1939_session *session) { + struct j1939_priv *priv = session->priv; bool active; - j1939_session_list_lock(session->priv); + j1939_session_list_lock(priv); + /* This function should be called with a session ref-count of at + * least 2. + */ + WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); - j1939_session_list_unlock(session->priv); + j1939_session_list_unlock(priv); return active; } From c6eea1c8bda56737752465a298dc6ce07d6b8ce3 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 6 Jul 2021 19:00:08 +0800 Subject: [PATCH 0870/1469] can: j1939: j1939_xtp_rx_dat_one(): fix rxtimer value between consecutive TP.DT to 750ms For receive side, the max time interval between two consecutive TP.DT should be 750ms. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/r/1625569210-47506-1-git-send-email-zhangchangzhong@huawei.com Cc: linux-stable Signed-off-by: Zhang Changzhong Acked-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- net/can/j1939/transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index bb1092c3e7e3..bdc95bd7a851 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1874,7 +1874,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, if (!session->transmission) j1939_tp_schedule_txtimer(session, 0); } else { - j1939_tp_set_rxtimeout(session, 250); + j1939_tp_set_rxtimeout(session, 750); } session->last_cmd = 0xff; consume_skb(se_skb); From 590eb2b7d8cfafb27e8108d52d4bf4850626d31d Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Fri, 25 Jun 2021 15:09:29 +0200 Subject: [PATCH 0871/1469] can: peak_usb: pcan_usb_handle_bus_evt(): fix reading rxerr/txerr values This patch fixes an incorrect way of reading error counters in messages received for this purpose from the PCAN-USB interface. These messages inform about the increase or decrease of the error counters, whose values are placed in bytes 1 and 2 of the message data (not 0 and 1). Fixes: ea8b33bde76c ("can: pcan_usb: add support of rxerr/txerr counters") Link: https://lore.kernel.org/r/20210625130931.27438-4-s.grosjean@peak-system.com Cc: linux-stable Signed-off-by: Stephane Grosjean Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 1d6f77252f01..899a3d21b77f 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -117,7 +117,8 @@ #define PCAN_USB_BERR_MASK (PCAN_USB_ERR_RXERR | PCAN_USB_ERR_TXERR) /* identify bus event packets with rx/tx error counters */ -#define PCAN_USB_ERR_CNT 0x80 +#define PCAN_USB_ERR_CNT_DEC 0x00 /* counters are decreasing */ +#define PCAN_USB_ERR_CNT_INC 0x80 /* counters are increasing */ /* private to PCAN-USB adapter */ struct pcan_usb { @@ -608,11 +609,12 @@ static int pcan_usb_handle_bus_evt(struct pcan_usb_msg_context *mc, u8 ir) /* acccording to the content of the packet */ switch (ir) { - case PCAN_USB_ERR_CNT: + case PCAN_USB_ERR_CNT_DEC: + case PCAN_USB_ERR_CNT_INC: /* save rx/tx error counters from in the device context */ - pdev->bec.rxerr = mc->ptr[0]; - pdev->bec.txerr = mc->ptr[1]; + pdev->bec.rxerr = mc->ptr[1]; + pdev->bec.txerr = mc->ptr[2]; break; default: From ef68a717960658e6a1e5f08adb0574326e9a12c2 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Sat, 24 Apr 2021 16:20:39 +0200 Subject: [PATCH 0872/1469] can: mcp251xfd: mcp251xfd_irq(): stop timestamping worker in case error in IRQ In case an error occurred in the IRQ handler, the chip status is dumped via devcoredump and all IRQs are disabled, but the chip stays powered for further analysis. The chip is in an undefined state and will not receive any CAN frames, so shut down the timestamping worker, which reads the TBC register regularly, too. This avoids any CRC read error messages if there is a communication problem with the chip. Fixes: efd8d98dfb90 ("can: mcp251xfd: add HW timestamp infrastructure") Link: https://lore.kernel.org/r/20210724155131.471303-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 47c3f408a799..9ae48072b6c6 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2300,6 +2300,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id) err, priv->regs_status.intf); mcp251xfd_dump(priv); mcp251xfd_chip_interrupts_disable(priv); + mcp251xfd_timestamp_stop(priv); return handled; } From 84edec86f449adea9ee0b4912a79ab8d9d65abb7 Mon Sep 17 00:00:00 2001 From: Chris Lesiak Date: Mon, 14 Jun 2021 09:18:20 -0500 Subject: [PATCH 0873/1469] iio: humidity: hdc100x: Add margin to the conversion time The datasheets have the following note for the conversion time specification: "This parameter is specified by design and/or characterization and it is not tested in production." Parts have been seen that require more time to do 14-bit conversions for the relative humidity channel. The result is ENXIO due to the address phase of a transfer not getting an ACK. Delay an additional 1 ms per conversion to allow for additional margin. Fixes: 4839367d99e3 ("iio: humidity: add HDC100x support") Signed-off-by: Chris Lesiak Acked-by: Matt Ranostay Link: https://lore.kernel.org/r/20210614141820.2034827-1-chris.lesiak@licor.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/humidity/hdc100x.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index 2a957f19048e..9e0fce917ce4 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -25,6 +25,8 @@ #include #include +#include + #define HDC100X_REG_TEMP 0x00 #define HDC100X_REG_HUMIDITY 0x01 @@ -166,7 +168,7 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, struct iio_chan_spec const *chan) { struct i2c_client *client = data->client; - int delay = data->adc_int_us[chan->address]; + int delay = data->adc_int_us[chan->address] + 1*USEC_PER_MSEC; int ret; __be16 val; @@ -316,7 +318,7 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct hdc100x_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - int delay = data->adc_int_us[0] + data->adc_int_us[1]; + int delay = data->adc_int_us[0] + data->adc_int_us[1] + 2*USEC_PER_MSEC; int ret; /* dual read starts at temp register */ From 3cf4375a090473d240281a0d2b04a3a5aaeac34b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 23 Jul 2021 18:46:01 -0400 Subject: [PATCH 0874/1469] tipc: do not write skb_shinfo frags when doing decrytion One skb's skb_shinfo frags are not writable, and they can be shared with other skbs' like by pskb_copy(). To write the frags may cause other skb's data crash. So before doing en/decryption, skb_cow_data() should always be called for a cloned or nonlinear skb if req dst is using the same sg as req src. While at it, the likely branch can be removed, as it will be covered by skb_cow_data(). Note that esp_input() has the same issue, and I will fix it in another patch. tipc_aead_encrypt() doesn't have this issue, as it only processes linear data in the unlikely branch. Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication") Reported-by: Shuang Li Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/crypto.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index e5c43d4d5a75..c9391d38de85 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, if (unlikely(!aead)) return -ENOKEY; - /* Cow skb data if needed */ - if (likely(!skb_cloned(skb) && - (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) { - nsg = 1 + skb_shinfo(skb)->nr_frags; - } else { - nsg = skb_cow_data(skb, 0, &unused); - if (unlikely(nsg < 0)) { - pr_err("RX: skb_cow_data() returned %d\n", nsg); - return nsg; - } + nsg = skb_cow_data(skb, 0, &unused); + if (unlikely(nsg < 0)) { + pr_err("RX: skb_cow_data() returned %d\n", nsg); + return nsg; } /* Allocate memory for the AEAD operation */ From 89bc7f456cd40e0be7b94f4fdae9186f22b76a05 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 23 Jul 2021 17:53:48 -0400 Subject: [PATCH 0875/1469] bnxt_en: Add missing periodic PHC overflow check We use the timecounter APIs for the 48-bit PHC and packet timestamps. We must periodically update the timecounter at roughly half the overflow interval. The overflow interval is about 78 hours, so update it every 19 hours (1/4 interval) for some extra margins. Fixes: 390862f45c85 ("bnxt_en: Get the full 48-bit hardware timestamp periodically") Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 7 +++++++ drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h | 4 ++++ 2 files changed, 11 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 9089e7f3fbd4..ec381c2423b8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -353,6 +353,12 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info) bnxt_ptp_get_current_time(bp); ptp->next_period = now + HZ; + if (time_after_eq(now, ptp->next_overflow_check)) { + spin_lock_bh(&ptp->ptp_lock); + timecounter_read(&ptp->tc); + spin_unlock_bh(&ptp->ptp_lock); + ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD; + } return HZ; } @@ -423,6 +429,7 @@ int bnxt_ptp_init(struct bnxt *bp) ptp->cc.shift = 0; ptp->cc.mult = 1; + ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); ptp->ptp_info = bnxt_ptp_caps; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 4135ea3ec788..254ba7bc0f99 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -32,6 +32,10 @@ struct bnxt_ptp_cfg { u64 current_time; u64 old_time; unsigned long next_period; + unsigned long next_overflow_check; + /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */ + #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) + u16 tx_seqid; struct bnxt *bp; atomic_t tx_avail; From 78d9d8005e4556448f398d876f29d0ca7ab8e398 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 16 Jul 2021 21:40:51 +0800 Subject: [PATCH 0876/1469] riscv: stacktrace: Fix NULL pointer dereference When CONFIG_FRAME_POINTER=y, calling dump_stack() can always trigger NULL pointer dereference panic similar as below: [ 0.396060] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-rc5+ #47 [ 0.396692] Hardware name: riscv-virtio,qemu (DT) [ 0.397176] Call Trace: [ 0.398191] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000960 [ 0.399487] Oops [#1] [ 0.399739] Modules linked in: [ 0.400135] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-rc5+ #47 [ 0.400570] Hardware name: riscv-virtio,qemu (DT) [ 0.400926] epc : walk_stackframe+0xc4/0xdc [ 0.401291] ra : dump_backtrace+0x30/0x38 [ 0.401630] epc : ffffffff80004922 ra : ffffffff8000496a sp : ffffffe000f3bd00 [ 0.402115] gp : ffffffff80cfdcb8 tp : ffffffe000f30000 t0 : ffffffff80d0b0cf [ 0.402602] t1 : ffffffff80d0b0c0 t2 : 0000000000000000 s0 : ffffffe000f3bd60 [ 0.403071] s1 : ffffffff808bc2e8 a0 : 0000000000001000 a1 : 0000000000000000 [ 0.403448] a2 : ffffffff803d7088 a3 : ffffffff808bc2e8 a4 : 6131725dbc24d400 [ 0.403820] a5 : 0000000000001000 a6 : 0000000000000002 a7 : ffffffffffffffff [ 0.404226] s2 : 0000000000000000 s3 : 0000000000000000 s4 : 0000000000000000 [ 0.404634] s5 : ffffffff803d7088 s6 : ffffffff808bc2e8 s7 : ffffffff80630650 [ 0.405085] s8 : ffffffff80912a80 s9 : 0000000000000008 s10: ffffffff804000fc [ 0.405388] s11: 0000000000000000 t3 : 0000000000000043 t4 : ffffffffffffffff [ 0.405616] t5 : 000000000000003d t6 : ffffffe000f3baa8 [ 0.405793] status: 0000000000000100 badaddr: 0000000000000960 cause: 000000000000000d [ 0.406135] [] walk_stackframe+0xc4/0xdc [ 0.407032] [] dump_backtrace+0x30/0x38 [ 0.407797] [] show_stack+0x40/0x4c [ 0.408234] [] dump_stack+0x90/0xb6 [ 0.409019] [] ptdump_init+0x20/0xc4 [ 0.409681] [] do_one_initcall+0x4c/0x226 [ 0.410110] [] kernel_init_freeable+0x1f4/0x258 [ 0.410562] [] kernel_init+0x22/0x148 [ 0.410959] [] ret_from_exception+0x0/0x14 [ 0.412241] ---[ end trace b2ab92c901b96251 ]--- [ 0.413099] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b The reason is the task is NULL when we finally call walk_stackframe() the NULL is passed from __dump_stack(): |static void __dump_stack(void) |{ | dump_stack_print_info(KERN_DEFAULT); | show_stack(NULL, NULL, KERN_DEFAULT); |} Fix this issue by checking "task == NULL" case in walk_stackframe(). Fixes: eac2f3059e02 ("riscv: stacktrace: fix the riscv stacktrace when CONFIG_FRAME_POINTER enabled") Signed-off-by: Jisheng Zhang Reviewed-by: Atish Patra Tested-by: Wende Tan Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/stacktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index ac7593607fa6..315db3d0229b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -27,7 +27,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); - } else if (task == current) { + } else if (task == NULL || task == current) { fp = (unsigned long)__builtin_frame_address(1); sp = (unsigned long)__builtin_frame_address(0); pc = (unsigned long)__builtin_return_address(0); From fc68f42aa737dc15e7665a4101d4168aadb8e4c4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 24 Jul 2021 15:25:54 -0700 Subject: [PATCH 0877/1469] ACPI: fix NULL pointer dereference Commit 71f642833284 ("ACPI: utils: Fix reference counting in for_each_acpi_dev_match()") started doing "acpi_dev_put()" on a pointer that was possibly NULL. That fails miserably, because that helper inline function is not set up to handle that case. Just make acpi_dev_put() silently accept a NULL pointer, rather than calling down to put_device() with an invalid offset off that NULL pointer. Link: https://lore.kernel.org/lkml/a607c149-6bf6-0fd0-0e31-100378504da2@kernel.dk/ Reported-and-tested-by: Jens Axboe Tested-by: Daniel Scally Cc: Andy Shevchenko Signed-off-by: Linus Torvalds --- include/acpi/acpi_bus.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index b9d434a93632..13d93371790e 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -720,7 +720,8 @@ static inline struct acpi_device *acpi_dev_get(struct acpi_device *adev) static inline void acpi_dev_put(struct acpi_device *adev) { - put_device(&adev->dev); + if (adev) + put_device(&adev->dev); } struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle); From ac059d16442f30e6a9a95d41655153e01247e710 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Sun, 25 Jul 2021 13:28:24 +0530 Subject: [PATCH 0878/1469] octeontx2-af: Fix PKIND overlap between LBK and LMAC interfaces Currently PKINDs are not assigned to LBK channels. The default value of LBK_CHX_PKIND (channel to PKIND mapping) register is zero, which is resulting in a overlap of pkind between LBK and CGX LMACs. When KPU1 parser config is modified when PTP timestamping is enabled on the CGX LMAC interface it is impacting traffic on LBK interfaces as well. This patch fixes the issue by reserving the PKIND#0 for LBK devices. CGX mapped PF pkind starts from 1 and also fixes the max pkind available. Fixes: 421572175ba5 ("octeontx2-af: Support to enable/disable HW timestamping") Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/npc.h | 3 +++ drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 1 + drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 11 +++++++---- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 19bad9a59c8f..243cf8070e77 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -151,7 +151,10 @@ enum npc_kpu_lh_ltype { * Software assigns pkind for each incoming port such as CGX * Ethernet interfaces, LBK interfaces, etc. */ +#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_VLAN_EXDSA_PKIND + enum npc_pkind_type { + NPC_RX_LBK_PKIND = 0ULL, NPC_RX_VLAN_EXDSA_PKIND = 56ULL, NPC_RX_CHLEN24B_PKIND = 57ULL, NPC_RX_CPT_HDR_PKIND, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0d2cd5169018..30067668eda7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -298,6 +298,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) rvu_nix_chan_lbk(rvu, lbkid, vf + 1); pfvf->rx_chan_cnt = 1; pfvf->tx_chan_cnt = 1; + rvu_npc_set_pkind(rvu, NPC_RX_LBK_PKIND, pfvf); rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, pfvf->rx_chan_cnt); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 1097291aaa45..52b255426c22 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1721,7 +1721,6 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr) { struct rvu_hwinfo *hw = rvu->hw; int num_pkinds, num_kpus, idx; - struct npc_pkind *pkind; /* Disable all KPUs and their entries */ for (idx = 0; idx < hw->npc_kpus; idx++) { @@ -1739,9 +1738,8 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr) * Check HW max count to avoid configuring junk or * writing to unsupported CSR addresses. */ - pkind = &hw->pkind; num_pkinds = rvu->kpu.pkinds; - num_pkinds = min_t(int, pkind->rsrc.max, num_pkinds); + num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds); for (idx = 0; idx < num_pkinds; idx++) npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true); @@ -1891,7 +1889,8 @@ static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr) if (npc_const1 & BIT_ULL(63)) npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2); - pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL; + pkind->rsrc.max = NPC_UNRESERVED_PKIND_COUNT; + hw->npc_pkinds = (npc_const1 >> 12) & 0xFFULL; hw->npc_kpu_entries = npc_const1 & 0xFFFULL; hw->npc_kpus = (npc_const >> 8) & 0x1FULL; hw->npc_intfs = npc_const & 0xFULL; @@ -2002,6 +2001,10 @@ int rvu_npc_init(struct rvu *rvu) err = rvu_alloc_bitmap(&pkind->rsrc); if (err) return err; + /* Reserve PKIND#0 for LBKs. Power reset value of LBK_CH_PKIND is '0', + * no need to configure PKIND for all LBKs separately. + */ + rvu_alloc_rsrc(&pkind->rsrc); /* Allocate mem for pkind to PF and channel mapping info */ pkind->pfchan_map = devm_kcalloc(rvu->dev, pkind->rsrc.max, From 69f0aeb13bb548e2d5710a350116e03f0273302e Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Sun, 25 Jul 2021 13:29:03 +0530 Subject: [PATCH 0879/1469] octeontx2-pf: Fix interface down flag on error In the existing code while changing the number of TX/RX queues using ethtool the PF/VF interface resources are freed and reallocated (otx2_stop and otx2_open is called) if the device is in running state. If any resource allocation fails in otx2_open, driver free already allocated resources and return. But again, when the number of queues changes as the device state still running oxt2_stop is called. In which we try to free already freed resources leading to driver crash. This patch fixes the issue by setting the INTF_DOWN flag on error and free the resources in otx2_stop only if the flag is not set. Fixes: 50fe6c02e5ad ("octeontx2-pf: Register and handle link notifications") Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 7 +++---- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 5 +++++ 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 8df748e0677b..b906a0eb6e0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -298,15 +298,14 @@ static int otx2_set_channels(struct net_device *dev, err = otx2_set_real_num_queues(dev, channel->tx_count, channel->rx_count); if (err) - goto fail; + return err; pfvf->hw.rx_queues = channel->rx_count; pfvf->hw.tx_queues = channel->tx_count; pfvf->qset.cq_cnt = pfvf->hw.tx_queues + pfvf->hw.rx_queues; -fail: if (if_up) - dev->netdev_ops->ndo_open(dev); + err = dev->netdev_ops->ndo_open(dev); netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n", pfvf->hw.tx_queues, pfvf->hw.rx_queues); @@ -410,7 +409,7 @@ static int otx2_set_ringparam(struct net_device *netdev, qs->rqe_cnt = rx_count; if (if_up) - netdev->netdev_ops->ndo_open(netdev); + return netdev->netdev_ops->ndo_open(netdev); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f300b807a85b..2c24944a4dba 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1662,6 +1662,7 @@ int otx2_open(struct net_device *netdev) err_tx_stop_queues: netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); + pf->flags |= OTX2_FLAG_INTF_DOWN; err_free_cints: otx2_free_cints(pf, qidx); vec = pci_irq_vector(pf->pdev, @@ -1689,6 +1690,10 @@ int otx2_stop(struct net_device *netdev) struct otx2_rss_info *rss; int qidx, vec, wrk; + /* If the DOWN flag is set resources are already freed */ + if (pf->flags & OTX2_FLAG_INTF_DOWN) + return 0; + netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); From 4c85e57575fb9e6405d02d55aef8025c60abb824 Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Sun, 25 Jul 2021 13:29:37 +0530 Subject: [PATCH 0880/1469] octeontx2-pf: Dont enable backpressure on LBK links Avoid configure backpressure for LBK links as they don't support it and enable lmacs before configuration pause frames. Fixes: 75f36270990c ("octeontx2-pf: Support to enable/disable pause frames via ethtool") Signed-off-by: Geetha sowjanya Signed-off-by: Hariprasad Kelam Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 2 +- .../ethernet/marvell/octeontx2/nic/otx2_common.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 9169849881bf..544c96c8fe1d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1504,8 +1504,8 @@ static int cgx_lmac_init(struct cgx *cgx) /* Add reference */ cgx->lmac_idmap[lmac->lmac_id] = lmac; - cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true); set_bit(lmac->lmac_id, &cgx->lmac_bmap); + cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true); } return cgx_lmac_verify_fwi_version(cgx); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 7cccd802c4ed..70fcc1fd962f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -924,12 +924,14 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) aq->cq.drop = RQ_DROP_LVL_CQ(pfvf->hw.rq_skid, cq->cqe_cnt); aq->cq.drop_ena = 1; - /* Enable receive CQ backpressure */ - aq->cq.bp_ena = 1; - aq->cq.bpid = pfvf->bpid[0]; + if (!is_otx2_lbkvf(pfvf->pdev)) { + /* Enable receive CQ backpressure */ + aq->cq.bp_ena = 1; + aq->cq.bpid = pfvf->bpid[0]; - /* Set backpressure level is same as cq pass level */ - aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt); + /* Set backpressure level is same as cq pass level */ + aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt); + } } /* Fill AQ info */ @@ -1186,7 +1188,7 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, aq->aura.fc_hyst_bits = 0; /* Store count on all updates */ /* Enable backpressure for RQ aura */ - if (aura_id < pfvf->hw.rqpool_cnt) { + if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) { aq->aura.bp_ena = 0; aq->aura.nix0_bpid = pfvf->bpid[0]; /* Set backpressure level for RQ's Aura */ From 149ea30fdd5c28b89a3bfdecfc75cdab1deddb14 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 23 Jul 2021 17:56:00 +0300 Subject: [PATCH 0881/1469] devlink: Fix phys_port_name of virtual port and merge error Merge commit cited in fixes tag was incorrect. Due to it phys_port_name of the virtual port resulted in incorrect name. Also the phys_port_name of the physical port was written twice due to the merge error. Fix it by removing the old code and inserting back the misplaced code. Related commits of interest in net and net-next branches that resulted in merge conflict are: in net-next branch: commit f285f37cb1e6 ("devlink: append split port number to the port name") in net branch: commit b28d8f0c25a9 ("devlink: Correct VIRTUAL port to not have phys_port attributes") Fixes: 126285651b7 ("Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net") Signed-off-by: Parav Pandit Reported-by: Niklas Schnelle Tested-by: Niklas Schnelle Signed-off-by: David S. Miller --- net/core/devlink.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index 8fdd04f00fd7..85032626de24 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9328,18 +9328,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: n = snprintf(name, len, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); - if (!attrs->split) - n = snprintf(name, len, "p%u", attrs->phys.port_number); - else - n = snprintf(name, len, "p%us%u", - attrs->phys.port_number, - attrs->phys.split_subport_number); - break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -9381,6 +9373,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; } if (n >= len) From ad4e1e48a6291f7fb53fbef38ca264966ffd65c9 Mon Sep 17 00:00:00 2001 From: Kevin Lo Date: Fri, 23 Jul 2021 21:59:27 +0800 Subject: [PATCH 0882/1469] net: phy: broadcom: re-add check for PHY_BRCM_DIS_TXCRXC_NOENRGY on the BCM54811 PHY Restore PHY_ID_BCM54811 accidently removed by commit 5d4358ede8eb. Fixes: 5d4358ede8eb ("net: phy: broadcom: Allow BCM54210E to configure APD") Signed-off-by: Kevin Lo Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 7bf3011b8e77..83aea5c5cd03 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -288,7 +288,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) { if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E || BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810 || - BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E) + BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54811) val |= BCM54XX_SHD_SCR3_RXCTXC_DIS; else val |= BCM54XX_SHD_SCR3_TRDDAPD; From 7e4960b3d66d7248b23de3251118147812b42da2 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 23 Jul 2021 18:36:09 +0800 Subject: [PATCH 0883/1469] mlx4: Fix missing error code in mlx4_load_one() The error code is missing in this code scenario, add the error code '-EINVAL' to the return value 'err'. Eliminate the follow smatch warning: drivers/net/ethernet/mellanox/mlx4/main.c:3538 mlx4_load_one() warn: missing error code 'err'. Reported-by: Abaci Robot Fixes: 7ae0e400cd93 ("net/mlx4_core: Flexible (asymmetric) allocation of EQs and MSI-X vectors for PF/VFs") Signed-off-by: Jiapeng Chong Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 00c84656b2e7..28ac4693da3c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3535,6 +3535,7 @@ slave_start: if (!SRIOV_VALID_STATE(dev->flags)) { mlx4_err(dev, "Invalid SRIOV state\n"); + err = -EINVAL; goto err_close; } } From a1833a54033e4ca760ad58fa2a6469ad59b3fa1a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 25 Jul 2021 11:06:37 -0700 Subject: [PATCH 0884/1469] smpboot: fix duplicate and misplaced inlining directive gcc doesn't care, but clang quite reasonably pointed out that the recent commit e9ba16e68cce ("smpboot: Mark idle_init() as __always_inlined to work around aggressive compiler un-inlining") did some really odd things: kernel/smpboot.c:50:20: warning: duplicate 'inline' declaration specifier [-Wduplicate-decl-specifier] static inline void __always_inline idle_init(unsigned int cpu) ^ which not only has that duplicate inlining specifier, but the new __always_inline was put in the wrong place of the function definition. We put the storage class specifiers (ie things like "static" and "extern") first, and the type information after that. And while the compiler may not care, we put the inline specifier before the types. So it should be just static __always_inline void idle_init(unsigned int cpu) instead. Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Linus Torvalds --- kernel/smpboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 21b7953f8242..cf6acab78538 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -47,7 +47,7 @@ void __init idle_thread_set_boot_cpu(void) * * Creates the thread if it does not exist. */ -static inline void __always_inline idle_init(unsigned int cpu) +static __always_inline void idle_init(unsigned int cpu) { struct task_struct *tsk = per_cpu(idle_threads, cpu); From 44379b986424b02acfa6e8c85ec5d68d89d3ccc4 Mon Sep 17 00:00:00 2001 From: Jagan Teki Date: Sun, 25 Jul 2021 23:17:37 +0530 Subject: [PATCH 0885/1469] drm/panel: panel-simple: Fix proper bpc for ytc700tlag_05_201c ytc700tlag_05_201c panel support 8 bpc not 6 bpc as per recent testing in i.MX8MM platform. Fix it. Fixes: 7a1f4fa4a629 ("drm/panel: simple: Add YTC700TLAG-05-201C") Signed-off-by: Jagan Teki Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210725174737.891106-1-jagan@amarulasolutions.com --- drivers/gpu/drm/panel/panel-simple.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 21939d4352cf..1b80290c2b53 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -4166,7 +4166,7 @@ static const struct drm_display_mode yes_optoelectronics_ytc700tlag_05_201c_mode static const struct panel_desc yes_optoelectronics_ytc700tlag_05_201c = { .modes = &yes_optoelectronics_ytc700tlag_05_201c_mode, .num_modes = 1, - .bpc = 6, + .bpc = 8, .size = { .width = 154, .height = 90, From 795e3d2ea68e489ee7039ac29e98bfea0e34a96c Mon Sep 17 00:00:00 2001 From: Harshvardhan Jha Date: Sun, 25 Jul 2021 23:28:04 +0530 Subject: [PATCH 0886/1469] net: qede: Fix end of loop tests for list_for_each_entry The list_for_each_entry() iterator, "vlan" in this code, can never be NULL so the warning will never be printed. Signed-off-by: Harshvardhan Jha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qede/qede_filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index c59b72c90293..a2e4dfb5cb44 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -831,7 +831,7 @@ int qede_configure_vlan_filters(struct qede_dev *edev) int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct qede_dev *edev = netdev_priv(dev); - struct qede_vlan *vlan = NULL; + struct qede_vlan *vlan; int rc = 0; DP_VERBOSE(edev, NETIF_MSG_IFDOWN, "Removing vlan 0x%04x\n", vid); @@ -842,7 +842,7 @@ int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) if (vlan->vid == vid) break; - if (!vlan || (vlan->vid != vid)) { + if (list_entry_is_head(vlan, &edev->vlan_list, list)) { DP_VERBOSE(edev, (NETIF_MSG_IFUP | NETIF_MSG_IFDOWN), "Vlan isn't configured\n"); goto out; From 058e6e0ed0eace43401c945082dec1d669b5b231 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 25 Jul 2021 13:42:50 -0400 Subject: [PATCH 0887/1469] sctp: improve the code for pmtu probe send and recv update This patch does 3 things: - make sctp_transport_pl_send() and sctp_transport_pl_recv() return bool type to decide if more probe is needed to send. - pr_debug() only when probe is really needed to send. - count pl.raise_count in sctp_transport_pl_send() instead of sctp_transport_pl_recv(), and it's only incremented for the 1st probe for the same size. These are preparations for the next patch to make probes happen only when there's packet loss in Search Complete state. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++-- net/sctp/sm_statefuns.c | 15 +++++++------- net/sctp/transport.c | 41 +++++++++++++++++++++----------------- 3 files changed, 32 insertions(+), 28 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 32fc4a309df5..f3d414ed208e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1024,8 +1024,8 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); -void sctp_transport_pl_send(struct sctp_transport *t); -void sctp_transport_pl_recv(struct sctp_transport *t); +bool sctp_transport_pl_send(struct sctp_transport *t); +bool sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 09a8f23ec709..32df65f68c12 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net, if (!sctp_transport_pl_enabled(transport)) return SCTP_DISPOSITION_CONSUME; - sctp_transport_pl_send(transport); - - reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); - if (!reply) - return SCTP_DISPOSITION_NOMEM; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + if (sctp_transport_pl_send(transport)) { + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + } sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, !sctp_transport_pl_enabled(link)) return SCTP_DISPOSITION_DISCARD; - sctp_transport_pl_recv(link); - if (link->pl.state == SCTP_PL_COMPLETE) + if (sctp_transport_pl_recv(link)) return SCTP_DISPOSITION_CONSUME; return sctp_sf_send_probe(net, ep, asoc, type, link, commands); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 397a6244dd97..23e7bd3e3bd4 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -258,16 +258,12 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) sctp_transport_pl_update(transport); } -void sctp_transport_pl_send(struct sctp_transport *t) +bool sctp_transport_pl_send(struct sctp_transport *t) { - pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", - __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); - - if (t->pl.probe_count < SCTP_MAX_PROBES) { - t->pl.probe_count++; - return; - } + if (t->pl.probe_count < SCTP_MAX_PROBES) + goto out; + t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ @@ -299,10 +295,20 @@ void sctp_transport_pl_send(struct sctp_transport *t) sctp_assoc_sync_pmtu(t->asoc); } } - t->pl.probe_count = 1; + +out: + if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 && + !t->pl.probe_count) + t->pl.raise_count++; + + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.probe_count++; + return true; } -void sctp_transport_pl_recv(struct sctp_transport *t) +bool sctp_transport_pl_recv(struct sctp_transport *t) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); @@ -323,7 +329,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t) if (!t->pl.probe_high) { t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, SCTP_MAX_PLPMTU); - return; + return false; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -335,14 +341,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE) { - t->pl.raise_count++; - if (t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; - } + } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; } + + return t->pl.state == SCTP_PL_COMPLETE; } static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) From eacf078cf4c7aa23e9591738511f142cc39b5186 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 25 Jul 2021 13:42:51 -0400 Subject: [PATCH 0888/1469] sctp: send pmtu probe only if packet loss in Search Complete state This patch is to introduce last_rtx_chunks into sctp_transport to detect if there's any packet retransmission/loss happened by checking against asoc's rtx_data_chunks in sctp_transport_pl_send(). If there is, namely, transport->last_rtx_chunks != asoc->rtx_data_chunks, the pmtu probe will be sent out. Otherwise, increment the pl.raise_count and return when it's in Search Complete state. With this patch, if in Search Complete state, which is a long period, it doesn't need to keep probing the current pmtu unless there's data packet loss. This will save quite some traffic. v1->v2: - add the missing Fixes tag. Fixes: 0dac127c0557 ("sctp: do black hole detection in search complete state") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + net/sctp/transport.c | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f3d414ed208e..651bba654d77 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -984,6 +984,7 @@ struct sctp_transport { } cacc; struct { + __u32 last_rtx_chunks; __u16 pmtu; __u16 probe_size; __u16 probe_high; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 23e7bd3e3bd4..a3d3ca6dd63d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,6 +263,7 @@ bool sctp_transport_pl_send(struct sctp_transport *t) if (t->pl.probe_count < SCTP_MAX_PROBES) goto out; + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ @@ -298,8 +299,10 @@ bool sctp_transport_pl_send(struct sctp_transport *t) out: if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 && - !t->pl.probe_count) + !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) { t->pl.raise_count++; + return false; + } pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); @@ -313,6 +316,7 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; t->pl.pmtu = t->pl.probe_size; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { From ff1176468d368232b684f75e82563369208bc371 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 25 Jul 2021 15:35:14 -0700 Subject: [PATCH 0889/1469] Linux 5.14-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e4f5895badb5..6b555f64df06 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Opossums on Parade # *DOCUMENTATION* From 9f66861181e64dc192bea136da6c91528910002e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 4 Jul 2021 16:01:37 -0700 Subject: [PATCH 0890/1469] m68k/coldfire: change pll var. to clk_pll DEFINE_CLK() makes the variable name be clk_xyz, so variable 'pll' should instead be 'clk_pll'. In file included from ../arch/m68k/coldfire/m525x.c:12: ../arch/m68k/coldfire/m525x.c:29:30: error: 'pll' undeclared here (not in a function) 29 | CLKDEV_INIT(NULL, "pll.0", &pll), | ^~~ ../include/linux/clkdev.h:30:10: note: in definition of macro 'CLKDEV_INIT' 30 | .clk = c, \ | ^ In file included from ../arch/m68k/coldfire/m525x.c:21: ../arch/m68k/include/asm/mcfclk.h:43:27: warning: 'clk_pll' defined but not used [-Wunused-variable] 43 | static struct clk clk_##clk_ref = { \ | ^~~~ ../arch/m68k/coldfire/m525x.c:25:1: note: in expansion of macro 'DEFINE_CLK' 25 | DEFINE_CLK(pll, "pll.0", MCF_CLK); | ^~~~~~~~~~ Fixes: 63aadb77669a ("m68k: coldfire: use clkdev_lookup on most coldfire") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Cc: Greg Ungerer Cc: linux-m68k@lists.linux-m68k.org Cc: uclinux-dev@uclinux.org Cc: Arnd Bergmann Signed-off-by: Greg Ungerer --- arch/m68k/coldfire/m525x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/m68k/coldfire/m525x.c b/arch/m68k/coldfire/m525x.c index 2c4d2ca2f20d..485375112e28 100644 --- a/arch/m68k/coldfire/m525x.c +++ b/arch/m68k/coldfire/m525x.c @@ -26,7 +26,7 @@ DEFINE_CLK(pll, "pll.0", MCF_CLK); DEFINE_CLK(sys, "sys.0", MCF_BUSCLK); static struct clk_lookup m525x_clk_lookup[] = { - CLKDEV_INIT(NULL, "pll.0", &pll), + CLKDEV_INIT(NULL, "pll.0", &clk_pll), CLKDEV_INIT(NULL, "sys.0", &clk_sys), CLKDEV_INIT("mcftmr.0", NULL, &clk_sys), CLKDEV_INIT("mcftmr.1", NULL, &clk_sys), From e4b016f4b44176807e545fd437cd519b6380e86f Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Fri, 8 Nov 2019 15:36:08 +0000 Subject: [PATCH 0891/1469] alpha: __udiv_qrnnd should be exported When building an alpha kernel with mpi set as module, I hit this build error: ERROR: "__udiv_qrnnd" [lib/mpi/mpi.ko] undefined! make[2]: *** [scripts/Makefile.modpost:92: __modpost] Error 1 make[1]: *** [Makefile:1266: modules] Error 2 This is due to __udiv_qrnnd not exported. Signed-off-by: Corentin Labbe Signed-off-by: Matt Turner --- arch/alpha/math-emu/math.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c index d568cd9a3e43..5617ac0889b8 100644 --- a/arch/alpha/math-emu/math.c +++ b/arch/alpha/math-emu/math.c @@ -401,3 +401,5 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask) egress: return si_code; } + +EXPORT_SYMBOL(__udiv_qrnnd); From a09c33cbf3db545d44eab16eb528acf834310690 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Mon, 13 Jul 2020 11:43:41 +0200 Subject: [PATCH 0892/1469] alpha: Kconfig: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: Matt Turner --- arch/alpha/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 77d3280dc678..f4ffad76e8b1 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -532,7 +532,7 @@ config SMP will run faster if you say N here. See also the SMP-HOWTO available at - . + . If you don't know what to do here, say N. From 5e3c3a0ae5d194f0a464aaaa71d764d96f2e7245 Mon Sep 17 00:00:00 2001 From: Chen Li Date: Tue, 13 Oct 2020 14:31:52 +0800 Subject: [PATCH 0893/1469] alpha: remove undef inline in compiler.h since 889b3c1245de48ed0cacf7aebb25c489d3e4a3e9, CONFIG_OPTIMIZE_INLINING is removed entirely and inline is always defined to `inline __gnu_inline __inline_maybe_unused notrace` in compiler_types.h Besides, undef inline here also means it never use __attribute__((__gnu_inline__)), so `extern inline` function can never be defined header files, otherwise multiple definition errors will happen, e.g. if multiple translation units use alpha/include/asm/pal.h will report multiple definitions, because there are many extern inline function definitions in this header. ``` c extern inline TYPE NAME(void) \ { \ register TYPE __r0 __asm__("$0"); \ __asm__ __volatile__( \ ... ``` Ofc, it is also ok to remove `extern` in `extern inline` here, then all of iso c99 and gnuc99/89 are ok, but there are also other alpha headers have such function definitions. Signed-off-by: chenli Signed-off-by: Matt Turner --- arch/alpha/include/asm/compiler.h | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/arch/alpha/include/asm/compiler.h b/arch/alpha/include/asm/compiler.h index 5159ba259d65..ae645959018a 100644 --- a/arch/alpha/include/asm/compiler.h +++ b/arch/alpha/include/asm/compiler.h @@ -4,15 +4,4 @@ #include -/* Some idiots over in thought inline should imply - always_inline. This breaks stuff. We'll include this file whenever - we run into such problems. */ - -#include -#undef inline -#undef __inline__ -#undef __inline -#undef __always_inline -#define __always_inline inline __attribute__((always_inline)) - #endif /* __ALPHA_COMPILER_H */ From f0443da1d8560f4c664ab0f9a900ed69e9aaeb14 Mon Sep 17 00:00:00 2001 From: Zheng Yongjun Date: Wed, 16 Dec 2020 21:12:41 +0800 Subject: [PATCH 0894/1469] alpha: convert comma to semicolon Replace a comma between expression statements by a semicolon. Fixes: cba1ec7e88a0 ("alpha: switch to generic kernel_thread()") Signed-off-by: Zheng Yongjun Signed-off-by: Matt Turner --- arch/alpha/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index ef0c08ed0481..a5123ea426ce 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -256,7 +256,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childstack->r26 = (unsigned long) ret_from_kernel_thread; childstack->r9 = usp; /* function */ childstack->r10 = kthread_arg; - childregs->hae = alpha_mv.hae_cache, + childregs->hae = alpha_mv.hae_cache; childti->pcb.usp = 0; return 0; } From caace6ca4e06f09413fb8f8a63319594cfb7d47d Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Tue, 5 Jan 2021 10:16:27 -0500 Subject: [PATCH 0895/1469] alpha: Send stop IPI to send to online CPUs This issue was noticed while debugging a shutdown issue where some secondary CPUs are not being shutdown correctly. A fix for that [1] requires that secondary cpus be offlined using the cpu_online_mask so that the stop operation is a no-op if CPU HOTPLUG is disabled. I, like the author in [1] looked at the architectures and found that alpha is one of two architectures that executes smp_send_stop() on all possible CPUs. On alpha, smp_send_stop() sends an IPI to all possible CPUs but only needs to send them to online CPUs. Send the stop IPI to only the online CPUs. [1] https://lkml.org/lkml/2020/1/10/250 Signed-off-by: Prarit Bhargava Cc: Richard Henderson Cc: Ivan Kokshaysky Signed-off-by: Matt Turner --- arch/alpha/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 4b2575f936d4..cb64e4797d2a 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -582,7 +582,7 @@ void smp_send_stop(void) { cpumask_t to_whom; - cpumask_copy(&to_whom, cpu_possible_mask); + cpumask_copy(&to_whom, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &to_whom); #ifdef DEBUG_IPI_MSG if (hard_smp_processor_id() != boot_cpu_id) From bfd736e3ffcc9dfc23c0a619fcc131eefd91d7ca Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Mon, 18 Jan 2021 11:20:29 +0000 Subject: [PATCH 0896/1469] alpha: defconfig: add necessary configs for boot testing Gentoo's KernelCI will soon boot test alpha kernel and we need CONFIG_DEVTMPFS=y to be set for that. Note that CONFIG_DEVTMPFS=y is already necessary for lot of other distribution/tools like recent udev/systemd. Signed-off-by: Corentin Labbe Signed-off-by: Matt Turner --- arch/alpha/configs/defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/alpha/configs/defconfig b/arch/alpha/configs/defconfig index dd2dd9f0861f..7f1ca30b115b 100644 --- a/arch/alpha/configs/defconfig +++ b/arch/alpha/configs/defconfig @@ -70,3 +70,4 @@ CONFIG_DEBUG_INFO=y CONFIG_ALPHA_LEGACY_START_ADDRESS=y CONFIG_MATHEMU=y CONFIG_CRYPTO_HMAC=y +CONFIG_DEVTMPFS=y From 8f34ed9d959786e2f2a643a1237f69f0171911cf Mon Sep 17 00:00:00 2001 From: tangchunyou Date: Wed, 20 Jan 2021 21:34:10 +0800 Subject: [PATCH 0897/1469] alpha: fix typos in a comment "kerne" -> "kernel" Signed-off-by: tangchunyou Signed-off-by: Matt Turner --- arch/alpha/boot/bootpz.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/boot/bootpz.c b/arch/alpha/boot/bootpz.c index 43af71835adf..90a2b341e9c0 100644 --- a/arch/alpha/boot/bootpz.c +++ b/arch/alpha/boot/bootpz.c @@ -200,7 +200,7 @@ extern char _end; START_ADDR KSEG address of the entry point of kernel code. ZERO_PGE KSEG address of page full of zeroes, but - upon entry to kerne cvan be expected + upon entry to kernel, it can be expected to hold the parameter list and possible INTRD information. From 6208721f1399912a0a53c77ed86dcc25d3e20efb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 20 Apr 2021 19:56:31 +0200 Subject: [PATCH 0898/1469] binfmt: remove support for em86 (alpha only) We have a fairly specific alpha binary loader in Linux: running x86 (i386, i486) binaries via the em86 [1] emulator. As noted in the Kconfig option, the same behavior can be achieved via binfmt_misc, for example, more nowadays used for running qemu-user. An example on how to get binfmt_misc running with em86 can be found in Documentation/admin-guide/binfmt-misc.rst The defconfig does not have CONFIG_BINFMT_EM86=y set. And doing a make defconfig && make olddefconfig results in # CONFIG_BINFMT_EM86 is not set ... as we don't seem to have any supported Linux distirbution for alpha anymore, there isn't really any "default" user of that feature anymore. Searching for "CONFIG_BINFMT_EM86=y" reveals mostly discussions from around 20 years ago, like [2] describing how to get netscape via em86 running via em86, or [3] discussing that running wine or installing Win 3.11 through em86 would be a nice feature. The latest binaries available for em86 are from 2000, version 2.2.1 [4] -- which translates to "unsupported"; further, em86 doesn't even work with glibc-2.x but only with glibc-2.0 [4, 5]. These are clear signs that there might not be too many em86 users out there, especially users relying on modern Linux kernels. Even though the code footprint is relatively small, let's just get rid of this blast from the past that's effectively unused. [1] http://ftp.dreamtime.org/pub/linux/Linux-Alpha/em86/v0.4/docs/em86.html [2] https://static.lwn.net/1998/1119/a/alpha-netscape.html [3] https://groups.google.com/g/linux.debian.alpha/c/AkGuQHeCe0Y [4] http://zeniv.linux.org.uk/pub/linux/alpha/em86/v2.2-1/relnotes.2.2.1.html [5] https://forum.teamspeak.com/archive/index.php/t-1477.html Cc: Alexander Viro Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: Jonathan Corbet Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: linux-alpha@vger.kernel.org Signed-off-by: David Hildenbrand Signed-off-by: Matt Turner --- fs/Kconfig.binfmt | 15 ------- fs/Makefile | 1 - fs/binfmt_em86.c | 110 ---------------------------------------------- 3 files changed, 126 deletions(-) delete mode 100644 fs/binfmt_em86.c diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 06fb7a93a1bd..4d5ae61580aa 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -168,21 +168,6 @@ config OSF4_COMPAT with v4 shared libraries freely available from Compaq. If you're going to use shared libraries from Tru64 version 5.0 or later, say N. -config BINFMT_EM86 - tristate "Kernel support for Linux/Intel ELF binaries" - depends on ALPHA - help - Say Y here if you want to be able to execute Linux/Intel ELF - binaries just like native Alpha binaries on your Alpha machine. For - this to work, you need to have the emulator /usr/bin/em86 in place. - - You can get the same functionality by saying N here and saying Y to - "Kernel support for MISC binaries". - - You may answer M to compile the emulation support as a module and - later load the module when you want to use a Linux/Intel binary. The - module will be called binfmt_em86. If unsure, say Y. - config BINFMT_MISC tristate "Kernel support for MISC binaries" help diff --git a/fs/Makefile b/fs/Makefile index 9c708e1fbe8f..f98f3e691c37 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ obj-$(CONFIG_FILE_LOCKING) += locks.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o -obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c deleted file mode 100644 index 06b9b9fddf70..000000000000 --- a/fs/binfmt_em86.c +++ /dev/null @@ -1,110 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/fs/binfmt_em86.c - * - * Based on linux/fs/binfmt_script.c - * Copyright (C) 1996 Martin von Löwis - * original #!-checking implemented by tytso. - * - * em86 changes Copyright (C) 1997 Jim Paradis - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - - -#define EM86_INTERP "/usr/bin/em86" -#define EM86_I_NAME "em86" - -static int load_em86(struct linux_binprm *bprm) -{ - const char *i_name, *i_arg; - char *interp; - struct file * file; - int retval; - struct elfhdr elf_ex; - - /* Make sure this is a Linux/Intel ELF executable... */ - elf_ex = *((struct elfhdr *)bprm->buf); - - if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0) - return -ENOEXEC; - - /* First of all, some simple consistency checks */ - if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) || - (!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) || - !bprm->file->f_op->mmap) { - return -ENOEXEC; - } - - /* Need to be able to load the file after exec */ - if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; - - /* Unlike in the script case, we don't have to do any hairy - * parsing to find our interpreter... it's hardcoded! - */ - interp = EM86_INTERP; - i_name = EM86_I_NAME; - i_arg = NULL; /* We reserve the right to add an arg later */ - - /* - * Splice in (1) the interpreter's name for argv[0] - * (2) (optional) argument to interpreter - * (3) filename of emulated file (replace argv[0]) - * - * This is done in reverse order, because of how the - * user environment and arguments are stored. - */ - remove_arg_zero(bprm); - retval = copy_string_kernel(bprm->filename, bprm); - if (retval < 0) return retval; - bprm->argc++; - if (i_arg) { - retval = copy_string_kernel(i_arg, bprm); - if (retval < 0) return retval; - bprm->argc++; - } - retval = copy_string_kernel(i_name, bprm); - if (retval < 0) return retval; - bprm->argc++; - - /* - * OK, now restart the process with the interpreter's inode. - * Note that we use open_exec() as the name is now in kernel - * space, and we don't need to copy it. - */ - file = open_exec(interp); - if (IS_ERR(file)) - return PTR_ERR(file); - - bprm->interpreter = file; - return 0; -} - -static struct linux_binfmt em86_format = { - .module = THIS_MODULE, - .load_binary = load_em86, -}; - -static int __init init_em86_binfmt(void) -{ - register_binfmt(&em86_format); - return 0; -} - -static void __exit exit_em86_binfmt(void) -{ - unregister_binfmt(&em86_format); -} - -core_initcall(init_em86_binfmt); -module_exit(exit_em86_binfmt); -MODULE_LICENSE("GPL"); From 15b9e384030cf34de33deed70d670a8dc0fc784a Mon Sep 17 00:00:00 2001 From: He Zhe Date: Mon, 26 Apr 2021 17:16:29 +0800 Subject: [PATCH 0899/1469] alpha: Add syscall_get_return_value() audit now requires syscall_get_return_value instead of regs_return_value to retrieve syscall return code . Other architectures that support audit have already define this function. Signed-off-by: He Zhe Signed-off-by: Matt Turner --- arch/alpha/include/asm/syscall.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h index 11c688c1d7ec..f21babaeed85 100644 --- a/arch/alpha/include/asm/syscall.h +++ b/arch/alpha/include/asm/syscall.h @@ -9,4 +9,10 @@ static inline int syscall_get_arch(struct task_struct *task) return AUDIT_ARCH_ALPHA; } +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->r0; +} + #endif /* _ASM_ALPHA_SYSCALL_H */ From ee3e9fa29e8b2553097009dac270cbed0f03f6d2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 May 2021 23:37:20 +0200 Subject: [PATCH 0900/1469] alpha: fp_emul: avoid init/cleanup_module names This is one of the last modules using the old calling conventions for module init/exit functions. Change it over to the style used everywhere else. Signed-off-by: Arnd Bergmann Signed-off-by: Matt Turner --- arch/alpha/math-emu/math.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c index 5617ac0889b8..f7cef66af88d 100644 --- a/arch/alpha/math-emu/math.c +++ b/arch/alpha/math-emu/math.c @@ -65,7 +65,7 @@ static long (*save_emul) (unsigned long pc); long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long); long do_alpha_fp_emul(unsigned long); -int init_module(void) +static int alpha_fp_emul_init_module(void) { save_emul_imprecise = alpha_fp_emul_imprecise; save_emul = alpha_fp_emul; @@ -73,12 +73,14 @@ int init_module(void) alpha_fp_emul = do_alpha_fp_emul; return 0; } +module_init(alpha_fp_emul_init_module); -void cleanup_module(void) +static void alpha_fp_emul_cleanup_module(void) { alpha_fp_emul_imprecise = save_emul_imprecise; alpha_fp_emul = save_emul; } +module_exit(alpha_fp_emul_cleanup_module); #undef alpha_fp_emul_imprecise #define alpha_fp_emul_imprecise do_alpha_fp_emul_imprecise From 3e0c6d15adeafa2afcb4c95c892bb5980c1430e6 Mon Sep 17 00:00:00 2001 From: gushengxian Date: Tue, 25 May 2021 20:16:10 -0700 Subject: [PATCH 0901/1469] alpha: Remove space between * and parameter name 'struct pcb_struct * pcb_va' should be 'struct pcb_struct *pcb_va'. Signed-off-by: gushengxian Signed-off-by: Matt Turner --- arch/alpha/boot/bootp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/boot/bootp.c b/arch/alpha/boot/bootp.c index 00266e6e1b71..b4faba2432d5 100644 --- a/arch/alpha/boot/bootp.c +++ b/arch/alpha/boot/bootp.c @@ -23,7 +23,7 @@ #include "ksize.h" extern unsigned long switch_to_osf_pal(unsigned long nr, - struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa, + struct pcb_struct *pcb_va, struct pcb_struct *pcb_pa, unsigned long *vptb); extern void move_stack(unsigned long new_stack); From fc520525c18ac2207792eb2067c6b626326a87ad Mon Sep 17 00:00:00 2001 From: gushengxian Date: Fri, 2 Jul 2021 05:48:12 -0700 Subject: [PATCH 0902/1469] alpha: fix spelling mistakes Fix some spelling mistakes in comments: delarations ==> declarations softare ==> software suffiently ==> sufficiently requred ==> required unaliged ==> unaligned Signed-off-by: gushengxian Signed-off-by: Matt Turner --- arch/alpha/boot/misc.c | 2 +- arch/alpha/kernel/osf_sys.c | 4 ++-- arch/alpha/kernel/perf_event.c | 2 +- arch/alpha/kernel/sys_nautilus.c | 2 +- arch/alpha/kernel/traps.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/alpha/boot/misc.c b/arch/alpha/boot/misc.c index d65192202703..325d4dd4f904 100644 --- a/arch/alpha/boot/misc.c +++ b/arch/alpha/boot/misc.c @@ -30,7 +30,7 @@ extern long srm_printk(const char *, ...) __attribute__ ((format (printf, 1, 2))); /* - * gzip delarations + * gzip declarations */ #define OF(args) args #define STATIC static diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index d5367a1c6300..d31167e3269c 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -834,7 +834,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, return -EFAULT; state = ¤t_thread_info()->ieee_state; - /* Update softare trap enable bits. */ + /* Update software trap enable bits. */ *state = (*state & ~IEEE_SW_MASK) | (swcr & IEEE_SW_MASK); /* Update the real fpcr. */ @@ -854,7 +854,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, state = ¤t_thread_info()->ieee_state; exc &= IEEE_STATUS_MASK; - /* Update softare trap enable bits. */ + /* Update software trap enable bits. */ swcr = (*state & IEEE_SW_MASK) | exc; *state |= exc; diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index e7a59d927d78..efcf7321701b 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -574,7 +574,7 @@ static void alpha_pmu_start(struct perf_event *event, int flags) * Check that CPU performance counters are supported. * - currently support EV67 and later CPUs. * - actually some later revisions of the EV6 have the same PMC model as the - * EV67 but we don't do suffiently deep CPU detection to detect them. + * EV67 but we don't do sufficiently deep CPU detection to detect them. * Bad luck to the very few people who might have one, I guess. */ static int supported_cpu(void) diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 53adf43dcd44..96fd6ff3fe81 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -212,7 +212,7 @@ nautilus_init_pci(void) /* Use default IO. */ pci_add_resource(&bridge->windows, &ioport_resource); - /* Irongate PCI memory aperture, calculate requred size before + /* Irongate PCI memory aperture, calculate required size before setting it up. */ pci_add_resource(&bridge->windows, &irongate_mem); diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 921d4b6e4d95..5398f982bdd1 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -730,7 +730,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, long error; /* Check the UAC bits to decide what the user wants us to do - with the unaliged access. */ + with the unaligned access. */ if (!(current_thread_info()->status & TS_UAC_NOPRINT)) { if (__ratelimit(&ratelimit)) { From d7f237df53457cf0cbdb9943b9b7c93a05e2fdb6 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Fri, 23 Jul 2021 05:52:25 -0400 Subject: [PATCH 0903/1469] drm/i915/bios: Fix ports mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PORT_A to PORT_F are regular integers defined in the enum port, while for_each_port_masked requires a bit mask for the ports. Current given mask: 0b111 Desired mask: 0b111111 I noticed this while Christoph was reporting a bug found on headless GVT configuration which bisect blamed commit 3ae04c0c7e63 ("drm/i915/bios: limit default outputs to ports A through F") v2: Avoid unnecessary line continuations as pointed by CI and Christoph Cc: Christoph Hellwig Fixes: 3ae04c0c7e63 ("drm/i915/bios: limit default outputs to ports A through F") Cc: Lucas De Marchi Cc: Ville Syrjälä Cc: Jani Nikula Signed-off-by: Rodrigo Vivi Reviewed-by: José Roberto de Souza Reviewed-by: Lucas De Marchi Tested-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210723095225.562913-1-rodrigo.vivi@intel.com (cherry picked from commit 9b52aa720168859526bf90d77fa210fc0336f170) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_bios.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 5b6922e28ef2..aa667fa71158 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -2166,7 +2166,8 @@ static void init_vbt_missing_defaults(struct drm_i915_private *i915) { enum port port; - int ports = PORT_A | PORT_B | PORT_C | PORT_D | PORT_E | PORT_F; + int ports = BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_C) | + BIT(PORT_D) | BIT(PORT_E) | BIT(PORT_F); if (!HAS_DDI(i915) && !IS_CHERRYVIEW(i915)) return; From 5d3a618f356595f132ee85c63a1b5f007a71f23c Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Fri, 23 Jul 2021 16:43:52 -0700 Subject: [PATCH 0904/1469] drm/i915: fix not reading DSC disable fuse in GLK We were using GRAPHICS_VER() to handle SKL_DFSM register, which means we were not handling GLK correctly since that has GRAPHICS_VER == 9, but DISPLAY_VER == 10. Switch the entire branch to check DISPLAY_VER which makes it more in line with Bspec. Even though the Bspec has an exception for RKL in TGL_DFSM_PIPE_D_DISABLE, we don't have to do anything as the bit has disable semantic and RKL doesn't have pipe D. Bspec: 50075, 7548 Fixes: 2b5a4562edd0 ("drm/i915/display: Simplify GLK display version tests") Cc: Matt Roper Signed-off-by: Lucas De Marchi Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210723234352.214459-1-lucas.demarchi@intel.com (cherry picked from commit 4fd177288a4ee046bd8590355a64de855dcf77e2) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_device_info.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 7eaa92fee421..e0a10f36acc1 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -325,7 +325,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - } else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) { + } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) { u32 dfsm = intel_de_read(dev_priv, SKL_DFSM); if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { @@ -340,7 +340,8 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - if (GRAPHICS_VER(dev_priv) >= 12 && + + if (DISPLAY_VER(dev_priv) >= 12 && (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { info->pipe_mask &= ~BIT(PIPE_D); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); @@ -352,10 +353,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE) info->display.has_fbc = 0; - if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) + if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) info->display.has_dmc = 0; - if (GRAPHICS_VER(dev_priv) >= 10 && + if (DISPLAY_VER(dev_priv) >= 10 && (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE)) info->display.has_dsc = 0; } From b4bde5554f70fb04ff07989fdc1356ab84d6f482 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Thu, 22 Jul 2021 16:29:22 -0700 Subject: [PATCH 0905/1469] drm/i915/display: split DISPLAY_VER 9 and 10 in intel_setup_outputs() Commit 5a9d38b20a5a ("drm/i915/display: hide workaround for broken vbt in intel_bios.c") moved the workaround for broken or missing VBT to intel_bios.c. However is_port_valid() only protects the handling of different skus of the same display version. Since in intel_setup_outputs() we share the code path with version 9, this would also create port F for SKL/KBL, which does not exist. Missing VBT can be reproduced when starting a headless QEMU with no opregion available. Avoid the issue by splitting versions 9 and 10 in intel_setup_outputs(), which also makes it more clear what code path it's taking for each version. v2: move generic display version after Geminilake since that one has a different set of outputs Fixes: 5a9d38b20a5a ("drm/i915/display: hide workaround for broken vbt in intel_bios.c") Cc: Jani Nikula Cc: Rodrigo Vivi Reported-by: Christoph Hellwig Signed-off-by: Lucas De Marchi Reviewed-by: Rodrigo Vivi Reviewed-by: Matt Roper Tested-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210722232922.3796835-1-lucas.demarchi@intel.com (cherry picked from commit ec387b8ff8d757561369be9a280cf63f23bbb926) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_display.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3bad4e00f7be..2d5d21740c25 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11361,13 +11361,19 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) intel_ddi_init(dev_priv, PORT_B); intel_ddi_init(dev_priv, PORT_C); vlv_dsi_init(dev_priv); - } else if (DISPLAY_VER(dev_priv) >= 9) { + } else if (DISPLAY_VER(dev_priv) == 10) { intel_ddi_init(dev_priv, PORT_A); intel_ddi_init(dev_priv, PORT_B); intel_ddi_init(dev_priv, PORT_C); intel_ddi_init(dev_priv, PORT_D); intel_ddi_init(dev_priv, PORT_E); intel_ddi_init(dev_priv, PORT_F); + } else if (DISPLAY_VER(dev_priv) >= 9) { + intel_ddi_init(dev_priv, PORT_A); + intel_ddi_init(dev_priv, PORT_B); + intel_ddi_init(dev_priv, PORT_C); + intel_ddi_init(dev_priv, PORT_D); + intel_ddi_init(dev_priv, PORT_E); } else if (HAS_DDI(dev_priv)) { u32 found; From 480e93e12aa04d857f7cc2e6fcec181c0d690404 Mon Sep 17 00:00:00 2001 From: Harshvardhan Jha Date: Sun, 25 Jul 2021 23:23:55 +0530 Subject: [PATCH 0906/1469] net: xfrm: Fix end of loop tests for list_for_each_entry The list_for_each_entry() iterator, "pos" in this code, can never be NULL so the warning will never be printed. Signed-off-by: Harshvardhan Jha Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_ipcomp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2e8afe078d61..cb40ff0ff28d 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -241,7 +241,7 @@ static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms) break; } - WARN_ON(!pos); + WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list)); if (--pos->users) return; From f0c6225531e4a9e43e51c5f7b02089bdd725c734 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Sat, 17 Jul 2021 23:11:38 -0500 Subject: [PATCH 0907/1469] ACPI: PM: Add support for upcoming AMD uPEP HID AMDI007 AMD systems with uPEP HID AMDI007 should be using revision 2 and the AMD method. Fixes: 8fbd6c15ea0a ("ACPI: PM: Adjust behavior for field problems on AMD systems") Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/s2idle.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 1c507804fb10..fbdbef0ab552 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -378,19 +378,25 @@ static int lps0_device_attach(struct acpi_device *adev, * AMDI0006: * - should use rev_id 0x0 * - function mask = 0x3: Should use Microsoft method + * AMDI0007: + * - Should use rev_id 0x2 + * - Should only use AMD method */ const char *hid = acpi_device_hid(adev); - rev_id = 0; + rev_id = strcmp(hid, "AMDI0007") ? 0 : 2; lps0_dsm_func_mask = validate_dsm(adev->handle, ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid); lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle, - ACPI_LPS0_DSM_UUID_MICROSOFT, rev_id, + ACPI_LPS0_DSM_UUID_MICROSOFT, 0, &lps0_dsm_guid_microsoft); if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") || !strcmp(hid, "AMDI0005"))) { lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1; acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n", ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask); + } else if (lps0_dsm_func_mask_microsoft > 0 && !strcmp(hid, "AMDI0007")) { + lps0_dsm_func_mask_microsoft = -EINVAL; + acpi_handle_debug(adev->handle, "_DSM Using AMD method\n"); } } else { rev_id = 1; From 94cbe7db7d757c2d481c3617ab5579a28cfc2175 Mon Sep 17 00:00:00 2001 From: Mohammad Athari Bin Ismail Date: Mon, 26 Jul 2021 10:20:20 +0800 Subject: [PATCH 0908/1469] net: stmmac: add est_irq_status callback function for GMAC 4.10 and 5.10 Assign dwmac5_est_irq_status to est_irq_status callback function for GMAC 4.10 and 5.10. With this, EST related interrupts could be handled properly. Fixes: e49aa315cb01 ("net: stmmac: EST interrupts handling and error reporting") Cc: # 5.13.x Signed-off-by: Mohammad Athari Bin Ismail Acked-by: Wong Vee Khee Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 67ba083eb90c..b21745368983 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1249,6 +1249,7 @@ const struct stmmac_ops dwmac410_ops = { .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, .est_configure = dwmac5_est_configure, + .est_irq_status = dwmac5_est_irq_status, .fpe_configure = dwmac5_fpe_configure, .fpe_send_mpacket = dwmac5_fpe_send_mpacket, .fpe_irq_status = dwmac5_fpe_irq_status, @@ -1300,6 +1301,7 @@ const struct stmmac_ops dwmac510_ops = { .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, .est_configure = dwmac5_est_configure, + .est_irq_status = dwmac5_est_irq_status, .fpe_configure = dwmac5_fpe_configure, .fpe_send_mpacket = dwmac5_fpe_send_mpacket, .fpe_irq_status = dwmac5_fpe_irq_status, From 2ebda027148315581b89a2ed2fef84ad53b2aedd Mon Sep 17 00:00:00 2001 From: Chen Shen Date: Mon, 26 Jul 2021 13:47:34 +0800 Subject: [PATCH 0909/1469] sctp: delete addr based on sin6_scope_id sctp_inet6addr_event deletes 'addr' from 'local_addr_list' when setting netdev down, but it is possible to delete the incorrect entry (match the first one with the same ipaddr, but the different 'ifindex'), if there are some netdevs with the same 'local-link' ipaddr added already. It should delete the entry depending on 'sin6_addr' and 'sin6_scope_id' both. otherwise, the endpoint will call 'sctp_sf_ootb' if it can't find the according association when receives 'heartbeat', and finally will reply 'abort'. For example: 1.when linux startup the entries in local_addr_list: ifindex:35 addr:fe80::40:43ff:fe80:0 (eths0.201) ifindex:36 addr:fe80::40:43ff:fe80:0 (eths0.209) ifindex:37 addr:fe80::40:43ff:fe80:0 (eths0.210) the route table: local fe80::40:43ff:fe80:0 dev eths0.201 local fe80::40:43ff:fe80:0 dev eths0.209 local fe80::40:43ff:fe80:0 dev eths0.210 2.after 'ifconfig eths0.209 down' the entries in local_addr_list: ifindex:36 addr:fe80::40:43ff:fe80:0 (eths0.209) ifindex:37 addr:fe80::40:43ff:fe80:0 (eths0.210) the route table: local fe80::40:43ff:fe80:0 dev eths0.201 local fe80::40:43ff:fe80:0 dev eths0.210 3.asoc not found for src:[fe80::40:43ff:fe80:0]:37381 dst:[:1]:53335 ::1->fe80::40:43ff:fe80:0 HEARTBEAT fe80::40:43ff:fe80:0->::1 ABORT Signed-off-by: Chen Shen Signed-off-by: David S. Miller --- net/sctp/ipv6.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e48dd909dee5..470dbdc27d58 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET6 && - ipv6_addr_equal(&addr->a.v6.sin6_addr, - &ifa->addr)) { + ipv6_addr_equal(&addr->a.v6.sin6_addr, + &ifa->addr) && + addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; From 2c39ca6885a2ec03e5c9e7c12a4da2aa8926605a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 23 Jul 2021 19:02:00 +0100 Subject: [PATCH 0910/1469] ASoC: tlv320aic31xx: Fix jack detection after suspend The tlv320aic31xx driver relies on regcache_sync() to restore the register contents after going to _BIAS_OFF, for example during system suspend. This does not work for the jack detection configuration since that is configured via the same register that status is read back from so the register is volatile and not cached. This can also cause issues during init if the jack detection ends up getting set up before the CODEC is initially brought out of _BIAS_OFF, we will reset the CODEC and resync the cache as part of that process. Fix this by explicitly reapplying the jack detection configuration after resyncing the register cache during power on. This issue was found by an engineer working off-list on a product kernel, I just wrote up the upstream fix. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210723180200.25105-1-broonie@kernel.org Cc: stable@vger.kernel.org --- sound/soc/codecs/tlv320aic31xx.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c index b504d63385b3..52d2c968b5c0 100644 --- a/sound/soc/codecs/tlv320aic31xx.c +++ b/sound/soc/codecs/tlv320aic31xx.c @@ -35,6 +35,9 @@ #include "tlv320aic31xx.h" +static int aic31xx_set_jack(struct snd_soc_component *component, + struct snd_soc_jack *jack, void *data); + static const struct reg_default aic31xx_reg_defaults[] = { { AIC31XX_CLKMUX, 0x00 }, { AIC31XX_PLLPR, 0x11 }, @@ -1256,6 +1259,13 @@ static int aic31xx_power_on(struct snd_soc_component *component) return ret; } + /* + * The jack detection configuration is in the same register + * that is used to report jack detect status so is volatile + * and not covered by the cache sync, restore it separately. + */ + aic31xx_set_jack(component, aic31xx->jack, NULL); + return 0; } From 9a9e74819bb0e4694279fb437e136fe485878d25 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 16 Jul 2021 16:41:04 +0200 Subject: [PATCH 0911/1469] KVM: nSVM: Rename nested_svm_vmloadsave() to svm_copy_vmloadsave_state() To match svm_copy_vmrun_state(), rename nested_svm_vmloadsave() to svm_copy_vmloadsave_state(). Opportunistically add missing braces to 'else' branch in vmload_vmsave_interception(). No functional change intended. Suggested-by: Paolo Bonzini Signed-off-by: Vitaly Kuznetsov Message-Id: <20210716144104.465269-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 2 +- arch/x86/kvm/svm/svm.c | 7 ++++--- arch/x86/kvm/svm/svm.h | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 3bd09c50c98b..8493592b63b4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -722,7 +722,7 @@ void svm_copy_vmrun_state(struct vmcb_save_area *from_save, to_save->cpl = 0; } -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +void svm_copy_vmloadsave_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; to_vmcb->save.gs = from_vmcb->save.gs; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 664d20f0689c..cfe165d74093 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2147,11 +2147,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) ret = kvm_skip_emulated_instruction(vcpu); if (vmload) { - nested_svm_vmloadsave(vmcb12, svm->vmcb); + svm_copy_vmloadsave_state(vmcb12, svm->vmcb); svm->sysenter_eip_hi = 0; svm->sysenter_esp_hi = 0; - } else - nested_svm_vmloadsave(svm->vmcb, vmcb12); + } else { + svm_copy_vmloadsave_state(svm->vmcb, vmcb12); + } kvm_vcpu_unmap(vcpu, &map, true); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 7e2090752d8f..1b65ee3a9569 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -466,7 +466,7 @@ int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); void svm_copy_vmrun_state(struct vmcb_save_area *from_save, struct vmcb_save_area *to_save); -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +void svm_copy_vmloadsave_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) From 2bb16bea5feaa582fbbdbfd84ecaa1ab61bbb34c Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 19 Jul 2021 11:03:22 +0200 Subject: [PATCH 0912/1469] KVM: nSVM: Swap the parameter order for svm_copy_vmrun_state()/svm_copy_vmloadsave_state() Make svm_copy_vmrun_state()/svm_copy_vmloadsave_state() interface match 'memcpy(dest, src)' to avoid any confusion. No functional change intended. Suggested-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20210719090322.625277-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 8 ++++---- arch/x86/kvm/svm/svm.c | 12 ++++++------ arch/x86/kvm/svm/svm.h | 6 +++--- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 8493592b63b4..1c2a0414a88d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -702,8 +702,8 @@ out: } /* Copy state save area fields which are handled by VMRUN */ -void svm_copy_vmrun_state(struct vmcb_save_area *from_save, - struct vmcb_save_area *to_save) +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save) { to_save->es = from_save->es; to_save->cs = from_save->cs; @@ -722,7 +722,7 @@ void svm_copy_vmrun_state(struct vmcb_save_area *from_save, to_save->cpl = 0; } -void svm_copy_vmloadsave_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; to_vmcb->save.gs = from_vmcb->save.gs; @@ -1385,7 +1385,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save); + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); nested_load_control_from_vmcb12(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cfe165d74093..9a6987549e1b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2147,11 +2147,11 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) ret = kvm_skip_emulated_instruction(vcpu); if (vmload) { - svm_copy_vmloadsave_state(vmcb12, svm->vmcb); + svm_copy_vmloadsave_state(svm->vmcb, vmcb12); svm->sysenter_eip_hi = 0; svm->sysenter_esp_hi = 0; } else { - svm_copy_vmloadsave_state(svm->vmcb, vmcb12); + svm_copy_vmloadsave_state(vmcb12, svm->vmcb); } kvm_vcpu_unmap(vcpu, &map, true); @@ -4345,8 +4345,8 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); kvm_vcpu_unmap(vcpu, &map_save, true); } @@ -4394,8 +4394,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) &map_save) == -EINVAL) return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, + map_save.hva + 0x400); kvm_vcpu_unmap(vcpu, &map_save, true); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1b65ee3a9569..bd0fe94c2920 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -464,9 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); -void svm_copy_vmrun_state(struct vmcb_save_area *from_save, - struct vmcb_save_area *to_save); -void svm_copy_vmloadsave_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save); +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) From 0e691ee7b5034c91a31b565d3ff9a50e01dde445 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 22 Jul 2021 11:26:28 +0200 Subject: [PATCH 0913/1469] KVM: Documentation: Fix KVM_CAP_ENFORCE_PV_FEATURE_CPUID name 'KVM_CAP_ENFORCE_PV_CPUID' doesn't match the define in include/uapi/linux/kvm.h. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210722092628.236474-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c7b165ca70b6..1a1d2061227b 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -7049,7 +7049,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to trap and emulate MSRs that are outside of the scope of KVM as well as limit the attack surface on KVM's MSR emulation code. -8.28 KVM_CAP_ENFORCE_PV_CPUID +8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID ----------------------------- Architectures: x86 From 3b1c8c5682672d73c1e977944af8c3ebed4a0ce1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 22 Jul 2021 11:50:03 +0200 Subject: [PATCH 0914/1469] docs: virt: kvm: api.rst: replace some characters The conversion tools used during DocBook/LaTeX/html/Markdown->ReST conversion and some cut-and-pasted text contain some characters that aren't easily reachable on standard keyboards and/or could cause troubles when parsed by the documentation build system. Replace the occurences of the following characters: - U+00a0 (' '): NO-BREAK SPACE as it can cause lines being truncated on PDF output Signed-off-by: Mauro Carvalho Chehab Message-Id: Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 1a1d2061227b..dae68e68ca23 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -855,7 +855,7 @@ in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for specific cpus. The irq field is interpreted like this:: -  bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | + bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | field: | vcpu2_index | irq_type | vcpu_index | irq_id | The irq_type field has the following values: @@ -2149,10 +2149,10 @@ prior to calling the KVM_RUN ioctl. Errors: ====== ============================================================ -  ENOENT   no such register -  EINVAL   invalid register ID, or no such register or used with VMs in + ENOENT no such register + EINVAL invalid register ID, or no such register or used with VMs in protected virtualization mode on s390 -  EPERM    (arm64) register access not allowed before vcpu finalization + EPERM (arm64) register access not allowed before vcpu finalization ====== ============================================================ (These error codes are indicative only: do not rely on a specific error @@ -2590,10 +2590,10 @@ following id bit patterns:: Errors include: ======== ============================================================ -  ENOENT   no such register -  EINVAL   invalid register ID, or no such register or used with VMs in + ENOENT no such register + EINVAL invalid register ID, or no such register or used with VMs in protected virtualization mode on s390 -  EPERM    (arm64) register access not allowed before vcpu finalization + EPERM (arm64) register access not allowed before vcpu finalization ======== ============================================================ (These error codes are indicative only: do not rely on a specific error @@ -3112,13 +3112,13 @@ current state. "addr" is ignored. Errors: ====== ================================================================= -  EINVAL    the target is unknown, or the combination of features is invalid. -  ENOENT    a features bit specified is unknown. + EINVAL the target is unknown, or the combination of features is invalid. + ENOENT a features bit specified is unknown. ====== ================================================================= This tells KVM what type of CPU to present to the guest, and what -optional features it should have.  This will cause a reset of the cpu -registers to their initial values.  If this is not called, KVM_RUN will +optional features it should have. This will cause a reset of the cpu +registers to their initial values. If this is not called, KVM_RUN will return ENOEXEC for that vcpu. The initial values are defined as: @@ -3239,8 +3239,8 @@ VCPU matching underlying host. Errors: ===== ============================================================== -  E2BIG     the reg index list is too big to fit in the array specified by -             the user (the number required will be written into n). + E2BIG the reg index list is too big to fit in the array specified by + the user (the number required will be written into n). ===== ============================================================== :: @@ -3288,7 +3288,7 @@ specific device. ARM/arm64 divides the id field into two parts, a device id and an address type id specific to the individual device:: -  bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | + bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | field: | 0x00000000 | device id | addr type id | ARM/arm64 currently only require this when using the in-kernel GIC From 0a31df6823232516f61f174907e444f710941dfe Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 22 Jul 2021 14:30:18 +0200 Subject: [PATCH 0915/1469] KVM: x86: Check the right feature bit for MSR_KVM_ASYNC_PF_ACK access MSR_KVM_ASYNC_PF_ACK MSR is part of interrupt based asynchronous page fault interface and not the original (deprecated) KVM_FEATURE_ASYNC_PF. This is stated in Documentation/virt/kvm/msr.rst. Fixes: 66570e966dd9 ("kvm: x86: only provide PV features if enabled in guest's CPUID") Signed-off-by: Vitaly Kuznetsov Reviewed-by: Maxim Levitsky Reviewed-by: Oliver Upton Message-Id: <20210722123018.260035-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a4fd10604f72..4116567f3d44 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3407,7 +3407,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { vcpu->arch.apf.pageready_pending = false; @@ -3746,7 +3746,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; msr_info->data = 0; From 92766c4628ea349c8ddab0cd7bd0488f36e5c4ce Mon Sep 17 00:00:00 2001 From: Letu Ren Date: Sun, 25 Jul 2021 21:45:12 +0800 Subject: [PATCH 0916/1469] net/qla3xxx: fix schedule while atomic in ql_wait_for_drvr_lock and ql_adapter_reset When calling the 'ql_wait_for_drvr_lock' and 'ql_adapter_reset', the driver has already acquired the spin lock, so the driver should not call 'ssleep' in atomic context. This bug can be fixed by using 'mdelay' instead of 'ssleep'. Reported-by: Letu Ren Signed-off-by: Letu Ren Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qla3xxx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 2376b2729633..c00ad57575ea 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -154,7 +154,7 @@ static int ql_wait_for_drvr_lock(struct ql3_adapter *qdev) "driver lock acquired\n"); return 1; } - ssleep(1); + mdelay(1000); } while (++i < 10); netdev_err(qdev->ndev, "Timed out waiting for driver lock...\n"); @@ -3274,7 +3274,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev) if ((value & ISP_CONTROL_SR) == 0) break; - ssleep(1); + mdelay(1000); } while ((--max_wait_time)); /* @@ -3310,7 +3310,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev) ispControlStatus); if ((value & ISP_CONTROL_FSR) == 0) break; - ssleep(1); + mdelay(1000); } while ((--max_wait_time)); } if (max_wait_time == 0) From 44eff40a32e8f5228ae041006352e32638ad2368 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 26 Jul 2021 14:14:31 +0100 Subject: [PATCH 0917/1469] io_uring: fix io_prep_async_link locking io_prep_async_link() may be called after arming a linked timeout, automatically making it unsafe to traverse the linked list. Guard with completion_lock if there was a linked timeout. Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/93f7c617e2b4f012a2a175b3dab6bc2f27cebc48.1627304436.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 5a0fd6bcd318..c4d2b320cdd4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1279,8 +1279,17 @@ static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; - io_for_each_link(cur, req) - io_prep_async_work(cur); + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->completion_lock); + io_for_each_link(cur, req) + io_prep_async_work(cur); + spin_unlock_irq(&ctx->completion_lock); + } else { + io_for_each_link(cur, req) + io_prep_async_work(cur); + } } static void io_queue_async_work(struct io_kiocb *req) From d47255d3f87338164762ac56df1f28d751e27246 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 24 Jun 2021 13:20:21 +0200 Subject: [PATCH 0918/1469] drm/amdgpu: Fix resource leak on probe error path This reverts commit 4192f7b5768912ceda82be2f83c87ea7181f9980. It is not true (as stated in the reverted commit changelog) that we never unmap the BAR on failure; it actually does happen properly on amdgpu_driver_load_kms() -> amdgpu_driver_unload_kms() -> amdgpu_device_fini() error path. What's worse, this commit actually completely breaks resource freeing on probe failure (like e.g. failure to load microcode), as amdgpu_driver_unload_kms() notices adev->rmmio being NULL and bails too early, leaving all the resources that'd normally be freed in amdgpu_acpi_fini() and amdgpu_device_fini() still hanging around, leading to all sorts of oopses when someone tries to, for example, access the sysfs and procfs resources which are still around while the driver is gone. Fixes: 4192f7b57689 ("drm/amdgpu: unmap register bar on device init failure") Reported-by: Vojtech Pavlik Signed-off-by: Jiri Kosina Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d303e88e3c23..f3fd5ec710b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3504,13 +3504,13 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_device_get_job_timeout_settings(adev); if (r) { dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n"); - goto failed_unmap; + return r; } /* early init functions */ r = amdgpu_device_ip_early_init(adev); if (r) - goto failed_unmap; + return r; /* doorbell bar mapping and doorbell index init*/ amdgpu_device_doorbell_init(adev); @@ -3736,10 +3736,6 @@ release_ras_con: failed: amdgpu_vf_error_trans_all(adev); -failed_unmap: - iounmap(adev->rmmio); - adev->rmmio = NULL; - return r; } From 110aa25c3ce417a44e35990cf8ed22383277933a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Jul 2021 10:42:56 -0600 Subject: [PATCH 0919/1469] io_uring: fix race in unified task_work running We use a bit to manage if we need to add the shared task_work, but a list + lock for the pending work. Before aborting a current run of the task_work we check if the list is empty, but we do so without grabbing the lock that protects it. This can lead to races where we think we have nothing left to run, where in practice we could be racing with a task adding new work to the list. If we do hit that race condition, we could be left with work items that need processing, but the shared task_work is not active. Ensure that we grab the lock before checking if the list is empty, so we know if it's safe to exit the run or not. Link: https://lore.kernel.org/io-uring/c6bd5987-e9ae-cd02-49d0-1b3ac1ef65b1@tnonline.net/ Cc: stable@vger.kernel.org # 5.11+ Reported-by: Forza Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c4d2b320cdd4..a4331deb0427 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1959,9 +1959,13 @@ static void tctx_task_work(struct callback_head *cb) node = next; } if (wq_list_empty(&tctx->task_list)) { + spin_lock_irq(&tctx->task_lock); clear_bit(0, &tctx->task_state); - if (wq_list_empty(&tctx->task_list)) + if (wq_list_empty(&tctx->task_list)) { + spin_unlock_irq(&tctx->task_lock); break; + } + spin_unlock_irq(&tctx->task_lock); /* another tctx_task_work() is enqueued, yield */ if (test_and_set_bit(0, &tctx->task_state)) break; From 6aade587d329ebe88319dfdb8e8c7b6aede80417 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 24 Jun 2021 13:11:36 +0200 Subject: [PATCH 0920/1469] drm/amdgpu: Avoid printing of stack contents on firmware load error In case when psp_init_asd_microcode() fails to load ASD microcode file, psp_v12_0_init_microcode() tries to print the firmware filename that failed to load before bailing out. This is wrong because: - the firmware filename it would want it print is an incorrect one as psp_init_asd_microcode() and psp_v12_0_init_microcode() are loading different filenames - it tries to print fw_name, but that's not yet been initialized by that time, so it prints random stack contents, e.g. amdgpu 0000:04:00.0: Direct firmware load for amdgpu/renoir_asd.bin failed with error -2 amdgpu 0000:04:00.0: amdgpu: fail to initialize asd microcode amdgpu 0000:04:00.0: amdgpu: psp v12.0: Failed to load firmware "\xfeTO\x8e\xff\xff" Fix that by bailing out immediately, instead of priting the bogus error message. Reported-by: Vojtech Pavlik Signed-off-by: Jiri Kosina Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/psp_v12_0.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 618e5b6b85d9..536d41f327c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -67,7 +67,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) err = psp_init_asd_microcode(psp, chip_name); if (err) - goto out; + return err; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); @@ -80,7 +80,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) } else { err = amdgpu_ucode_validate(adev->psp.ta_fw); if (err) - goto out2; + goto out; ta_hdr = (const struct ta_firmware_header_v1_0 *) adev->psp.ta_fw->data; @@ -105,10 +105,9 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) return 0; -out2: +out: release_firmware(adev->psp.ta_fw); adev->psp.ta_fw = NULL; -out: if (err) { dev_err(adev->dev, "psp v12.0: Failed to load firmware \"%s\"\n", From 66291b6adb66dd3bc96b0f594d88c2ff1300d95f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 26 Jul 2021 08:26:56 +0200 Subject: [PATCH 0921/1469] ALSA: usb-audio: Fix superfluous autosuspend recovery The change to restore the autosuspend from the disabled state uses a wrong check: namely, it should have been the exact comparison of the quirk_type instead of the bitwise and (&). Otherwise it matches wrongly with the other quirk types. Although re-enabling the autosuspend for the already enabled device shouldn't matter much, it's better to fix the unbalanced call. Fixes: 9799110825db ("ALSA: usb-audio: Disable USB autosuspend properly in setup_disable_autosuspend()") Cc: Link: https://lore.kernel.org/r/s5hr1flh9ov.wl-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/card.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/card.c b/sound/usb/card.c index 2f6a62416c05..a1f8c3a026f5 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -907,7 +907,7 @@ static void usb_audio_disconnect(struct usb_interface *intf) } } - if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND) + if (chip->quirk_type == QUIRK_SETUP_DISABLE_AUTOSUSPEND) usb_enable_autosuspend(interface_to_usbdev(intf)); chip->num_interfaces--; From 0f32d9eb38c13c32895b5bf695eac639cee02d6c Mon Sep 17 00:00:00 2001 From: Brent Lu Date: Mon, 26 Jul 2021 17:45:25 +0800 Subject: [PATCH 0922/1469] ASoC: Intel: sof_da7219_mx98360a: fail to initialize soundcard The default codec for speaker amp's DAI Link is max98373 and will be overwritten in probe function if the board id is sof_da7219_mx98360a. However, the probe function does not do it because the board id is changed in earlier commit. Fixes: 1cc04d195dc2 ("ASoC: Intel: sof_da7219_max98373: shrink platform_id below 20 characters") Signed-off-by: Brent Lu Acked-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210726094525.5748-1-brent.lu@intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_da7219_max98373.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/boards/sof_da7219_max98373.c b/sound/soc/intel/boards/sof_da7219_max98373.c index 896251d742fe..b7b3b0bf994a 100644 --- a/sound/soc/intel/boards/sof_da7219_max98373.c +++ b/sound/soc/intel/boards/sof_da7219_max98373.c @@ -404,7 +404,7 @@ static int audio_probe(struct platform_device *pdev) return -ENOMEM; /* By default dais[0] is configured for max98373 */ - if (!strcmp(pdev->name, "sof_da7219_max98360a")) { + if (!strcmp(pdev->name, "sof_da7219_mx98360a")) { dais[0] = (struct snd_soc_dai_link) { .name = "SSP1-Codec", .id = 0, From 53ca18acbe645656132fb5a329833db711067e54 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 26 Jul 2021 12:01:02 +0200 Subject: [PATCH 0923/1469] spi: imx: mx51-ecspi: Fix low-speed CONFIGREG delay calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The spi_imx->spi_bus_clk may be uninitialized and thus also zero in mx51_ecspi_prepare_message(), which would lead to division by zero in kernel. Since bitbang .setup_transfer callback which initializes the spi_imx->spi_bus_clk is called after bitbang prepare_message callback, iterate over all the transfers in spi_message, find the one with lowest bus frequency, and use that bus frequency for the delay calculation. Note that it is not possible to move this CONFIGREG delay back into the .setup_transfer callback, because that is invoked too late, after the GPIO chipselects were already configured. Fixes: 135cbd378eab ("spi: imx: mx51-ecspi: Reinstate low-speed CONFIGREG delay") Signed-off-by: Marek Vasut Cc: Uwe Kleine-König Cc: Mark Brown Link: https://lore.kernel.org/r/20210726100102.5188-1-marex@denx.de Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 4aee3db6d6df..2872993550bd 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -505,7 +505,9 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, struct spi_message *msg) { struct spi_device *spi = msg->spi; + struct spi_transfer *xfer; u32 ctrl = MX51_ECSPI_CTRL_ENABLE; + u32 min_speed_hz = ~0U; u32 testreg, delay; u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG); @@ -577,8 +579,20 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, * be asserted before the SCLK polarity changes, which would disrupt * the SPI communication as the device on the other end would consider * the change of SCLK polarity as a clock tick already. + * + * Because spi_imx->spi_bus_clk is only set in bitbang prepare_message + * callback, iterate over all the transfers in spi_message, find the + * one with lowest bus frequency, and use that bus frequency for the + * delay calculation. In case all transfers have speed_hz == 0, then + * min_speed_hz is ~0 and the resulting delay is zero. */ - delay = (2 * 1000000) / spi_imx->spi_bus_clk; + list_for_each_entry(xfer, &msg->transfers, transfer_list) { + if (!xfer->speed_hz) + continue; + min_speed_hz = min(xfer->speed_hz, min_speed_hz); + } + + delay = (2 * 1000000) / min_speed_hz; if (likely(delay < 10)) /* SCLK is faster than 100 kHz */ udelay(delay); else /* SCLK is _very_ slow */ From 758684e49f4c7ea2a75e249e486659f0950cd63e Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Mon, 26 Jul 2021 14:52:48 -0400 Subject: [PATCH 0924/1469] bnxt_en: Fix static checker warning in bnxt_fw_reset_task() Now that we return when bnxt_open() fails in bnxt_fw_reset_task(), there is no need to check for 'rc' value again before invoking bnxt_reenable_sriov(). Fixes: 3958b1da725a ("bnxt_en: fix error path of FW reset") Reported-by: Dan Carpenter Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4db162cee911..89606587b156 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12131,9 +12131,8 @@ static void bnxt_fw_reset_task(struct work_struct *work) /* Make sure fw_reset_state is 0 before clearing the flag */ smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_ulp_start(bp, rc); - if (!rc) - bnxt_reenable_sriov(bp); + bnxt_ulp_start(bp, 0); + bnxt_reenable_sriov(bp); bnxt_vf_reps_alloc(bp); bnxt_vf_reps_open(bp); bnxt_dl_health_recovery_done(bp); From 24b5b1978cd5a80db58e2a19db2f9c36fe8d4f7a Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 25 Jul 2021 18:07:25 +0200 Subject: [PATCH 0925/1469] clk: stm32f4: fix post divisor setup for I2S/SAI PLLs Enabling the framebuffer leads to a system hang. Running, as a debug hack, the store_pan() function in drivers/video/fbdev/core/fbsysfs.c without taking the console_lock, allows to see the crash backtrace on the serial line. ~ # echo 0 0 > /sys/class/graphics/fb0/pan [ 9.719414] Unhandled exception: IPSR = 00000005 LR = fffffff1 [ 9.726937] CPU: 0 PID: 49 Comm: sh Not tainted 5.13.0-rc5 #9 [ 9.733008] Hardware name: STM32 (Device Tree Support) [ 9.738296] PC is at clk_gate_is_enabled+0x0/0x28 [ 9.743426] LR is at stm32f4_pll_div_set_rate+0xf/0x38 [ 9.748857] pc : [<0011e4be>] lr : [<0011f9e3>] psr: 0100000b [ 9.755373] sp : 00bc7be0 ip : 00000000 fp : 001f3ac4 [ 9.760812] r10: 002610d0 r9 : 01efe920 r8 : 00540560 [ 9.766269] r7 : 02e7ddb0 r6 : 0173eed8 r5 : 00000000 r4 : 004027c0 [ 9.773081] r3 : 0011e4bf r2 : 02e7ddb0 r1 : 0173eed8 r0 : 1d3267b8 [ 9.779911] xPSR: 0100000b [ 9.782719] CPU: 0 PID: 49 Comm: sh Not tainted 5.13.0-rc5 #9 [ 9.788791] Hardware name: STM32 (Device Tree Support) [ 9.794120] [<0000afa1>] (unwind_backtrace) from [<0000a33f>] (show_stack+0xb/0xc) [ 9.802421] [<0000a33f>] (show_stack) from [<0000a8df>] (__invalid_entry+0x4b/0x4c) The `pll_num' field in the post_div_data configuration contained a wrong value which also referenced an uninitialized hardware clock when clk_register_pll_div() was called. Fixes: 517633ef630e ("clk: stm32f4: Add post divisor for I2S & SAI PLLs") Signed-off-by: Dario Binacchi Reviewed-by: Gabriel Fernandez Link: https://lore.kernel.org/r/20210725160725.10788-1-dariobin@libero.it Signed-off-by: Stephen Boyd --- drivers/clk/clk-stm32f4.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c index 18117ce5ff85..5c75e3d906c2 100644 --- a/drivers/clk/clk-stm32f4.c +++ b/drivers/clk/clk-stm32f4.c @@ -526,7 +526,7 @@ struct stm32f4_pll { struct stm32f4_pll_post_div_data { int idx; - u8 pll_num; + int pll_idx; const char *name; const char *parent; u8 flag; @@ -557,13 +557,13 @@ static const struct clk_div_table post_divr_table[] = { #define MAX_POST_DIV 3 static const struct stm32f4_pll_post_div_data post_div_data[MAX_POST_DIV] = { - { CLK_I2SQ_PDIV, PLL_I2S, "plli2s-q-div", "plli2s-q", + { CLK_I2SQ_PDIV, PLL_VCO_I2S, "plli2s-q-div", "plli2s-q", CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 0, 5, 0, NULL}, - { CLK_SAIQ_PDIV, PLL_SAI, "pllsai-q-div", "pllsai-q", + { CLK_SAIQ_PDIV, PLL_VCO_SAI, "pllsai-q-div", "pllsai-q", CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 8, 5, 0, NULL }, - { NO_IDX, PLL_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT, + { NO_IDX, PLL_VCO_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 16, 2, 0, post_divr_table }, }; @@ -1774,7 +1774,7 @@ static void __init stm32f4_rcc_init(struct device_node *np) post_div->width, post_div->flag_div, post_div->div_table, - clks[post_div->pll_num], + clks[post_div->pll_idx], &stm32f4_clk_lock); if (post_div->idx != NO_IDX) From 953a92f0e55f370ec76e7f85e332906f1e898ef4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 16 Jul 2021 21:31:59 -0700 Subject: [PATCH 0926/1469] clk: hisilicon: hi3559a: select RESET_HISI The clk-hi3559a driver uses functions from reset.c so it should select RESET_HISI to avoid build errors. Fixes these build errors: aarch64-linux-ld: drivers/clk/hisilicon/clk-hi3559a.o: in function `hi3559av100_crg_remove': clk-hi3559a.c:(.text+0x158): undefined reference to `hisi_reset_exit' aarch64-linux-ld: drivers/clk/hisilicon/clk-hi3559a.o: in function `hi3559av100_crg_probe': clk-hi3559a.c:(.text+0x1f4): undefined reference to `hisi_reset_init' aarch64-linux-ld: clk-hi3559a.c:(.text+0x238): undefined reference to `hisi_reset_exit' Fixes: 6c81966107dc ("clk: hisilicon: Add clock driver for hi3559A SoC") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Dongjiu Geng Cc: Stephen Boyd Cc: stable@vger.kernel.org Cc: linux-clk@vger.kernel.org Cc: Michael Turquette Link: https://lore.kernel.org/r/20210717043159.12566-1-rdunlap@infradead.org Reviewed-by: Dongjiu Geng Signed-off-by: Stephen Boyd --- drivers/clk/hisilicon/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/hisilicon/Kconfig b/drivers/clk/hisilicon/Kconfig index 5ecc37aaa118..c1ec75aa4ccd 100644 --- a/drivers/clk/hisilicon/Kconfig +++ b/drivers/clk/hisilicon/Kconfig @@ -18,6 +18,7 @@ config COMMON_CLK_HI3519 config COMMON_CLK_HI3559A bool "Hi3559A Clock Driver" depends on ARCH_HISI || COMPILE_TEST + select RESET_HISI default ARCH_HISI help Build the clock driver for hi3559a. From f2a26a3cff27dfa456fef386fe5df56dcb4b47b6 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 23 Jul 2021 18:35:15 -0500 Subject: [PATCH 0927/1469] SMB3: fix readpage for large swap cache readpage was calculating the offset of the page incorrectly for the case of large swapcaches. loff_t offset = (loff_t)page->index << PAGE_SHIFT; As pointed out by Matthew Wilcox, this needs to use page_file_offset() to calculate the offset instead. Pages coming from the swap cache have page->index set to their index within the swapcache, not within the backing file. For a sufficiently large swapcache, we could have overlapping values of page->index within the same backing file. Suggested by: Matthew Wilcox (Oracle) Cc: # v5.7+ Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index cd108607a070..0a72840a88f1 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4619,7 +4619,7 @@ read_complete: static int cifs_readpage(struct file *file, struct page *page) { - loff_t offset = (loff_t)page->index << PAGE_SHIFT; + loff_t offset = page_file_offset(page); int rc = -EACCES; unsigned int xid; From 5ad4df56cd2158965f73416d41fce37906724822 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 26 Jul 2021 16:22:55 -0500 Subject: [PATCH 0928/1469] smb3: rc uninitialized in one fallocate path Clang detected a problem with rc possibly being unitialized (when length is zero) in a recently added fallocate code path. Reported-by: kernel test robot Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 23d6f4d71649..2dfd0d8297eb 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3617,7 +3617,8 @@ static int smb3_simple_fallocate_write_range(unsigned int xid, char *buf) { struct cifs_io_parms io_parms = {0}; - int rc, nbytes; + int nbytes; + int rc = 0; struct kvec iov[2]; io_parms.netfid = cfile->fid.netfid; From 35171fbfc0d94aa31b009bb475d156ad1941ab50 Mon Sep 17 00:00:00 2001 From: Nikos Liolios Date: Tue, 27 Jul 2021 06:05:10 +0300 Subject: [PATCH 0929/1469] ALSA: hda/realtek: Fix headset mic for Acer SWIFT SF314-56 (ALC256) The issue on Acer SWIFT SF314-56 is that headset microphone doesn't work. The following quirk fixed headset microphone issue. The fixup was found by trial and error. Note that the fixup of SF314-54/55 (ALC256_FIXUP_ACER_HEADSET_MIC) was not successful on my SF314-56. Signed-off-by: Nikos Liolios Cc: Link: https://lore.kernel.org/r/20210727030510.36292-1-liolios.nk@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index caaf0e8aac11..14e1ab7c7954 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8274,6 +8274,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x129c, "Acer SWIFT SF314-55", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1300, "Acer SWIFT SF314-56", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), From b070f9ca78680486927b799cf6126b128a7c2c1b Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Tue, 20 Jul 2021 11:47:10 -0700 Subject: [PATCH 0930/1469] ARM: omap2+: hwmod: fix potential NULL pointer access omap_hwmod_get_pwrdm() may access a NULL clk_hw pointer in some failure cases. Add a check for the case and bail out gracely if this happens. Reported-by: Dan Murphy Signed-off-by: Tero Kristo Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Kevin Hilman Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_hwmod.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 65934b2924fb..12b26e04686f 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -3776,6 +3776,7 @@ struct powerdomain *omap_hwmod_get_pwrdm(struct omap_hwmod *oh) struct omap_hwmod_ocp_if *oi; struct clockdomain *clkdm; struct clk_hw_omap *clk; + struct clk_hw *hw; if (!oh) return NULL; @@ -3792,7 +3793,14 @@ struct powerdomain *omap_hwmod_get_pwrdm(struct omap_hwmod *oh) c = oi->_clk; } - clk = to_clk_hw_omap(__clk_get_hw(c)); + hw = __clk_get_hw(c); + if (!hw) + return NULL; + + clk = to_clk_hw_omap(hw); + if (!clk) + return NULL; + clkdm = clk->clkdm; if (!clkdm) return NULL; From a6d90e9f22328f07343e49e08a4ca483ae8e8abb Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Tue, 20 Jul 2021 11:27:16 -0700 Subject: [PATCH 0931/1469] bus: ti-sysc: AM3: RNG is GP only Make the RNG on AM3 GP only. Based on this patch from TI v5.4 tree which is based on hwmod data which are now removed: | ARM: AM43xx: hwmod: Move RNG to a GP only links table | | On non-GP devices the RNG is controlled by the secure-side software, | like in DRA7xx hwmod we should not control this IP when we are not | a GP device. | | Signed-off-by: Andrew F. Davis Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Kevin Hilman Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 38cb116ed433..2587ed43ee8a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2951,6 +2951,8 @@ static int sysc_init_soc(struct sysc *ddata) case SOC_3430 ... SOC_3630: sysc_add_disabled(0x48304000); /* timer12 */ break; + case SOC_AM3: + sysc_add_disabled(0x48310000); /* rng */ default: break; } From 20a6b3fd8e2e2c063b25fbf2ee74d86b898e5087 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Fri, 16 Jul 2021 09:07:30 -0700 Subject: [PATCH 0932/1469] ARM: dts: am43x-epos-evm: Reduce i2c0 bus speed for tps65218 Based on the latest timing specifications for the TPS65218 from the data sheet, http://www.ti.com/lit/ds/symlink/tps65218.pdf, document SLDS206 from November 2014, we must change the i2c bus speed to better fit within the minimum high SCL time required for proper i2c transfer. When running at 400khz, measurements show that SCL spends 0.8125 uS/1.666 uS high/low which violates the requirement for minimum high period of SCL provided in datasheet Table 7.6 which is 1 uS. Switching to 100khz gives us 5 uS/5 uS high/low which both fall above the minimum given values for 100 khz, 4.0 uS/4.7 uS high/low. Without this patch occasionally a voltage set operation from the kernel will appear to have worked but the actual voltage reflected on the PMIC will not have updated, causing problems especially with cpufreq that may update to a higher OPP without actually raising the voltage on DCDC2, leading to a hang. Signed-off-by: Dave Gerlach Signed-off-by: Kevin Hilman Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am43x-epos-evm.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index aae0af10a5b1..2aa75abf85a9 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -582,7 +582,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; - clock-frequency = <400000>; + clock-frequency = <100000>; tps65218: tps65218@24 { reg = <0x24>; From 0162a9964365fd26e34575e121b17d021204c481 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Mon, 26 Jul 2021 15:15:25 +0200 Subject: [PATCH 0933/1469] ARM: dts: am437x-l4: fix typo in can@0 node Replace clock-name with clock-names. Fixes: 2a4117df9b43 ("ARM: dts: Fix dcan driver probe failed on am437x platform") Signed-off-by: Dario Binacchi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am437x-l4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index 40ef3973f2a9..ba58e6b0da1d 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -1595,7 +1595,7 @@ compatible = "ti,am4372-d_can", "ti,am3352-d_can"; reg = <0x0 0x2000>; clocks = <&dcan1_fck>; - clock-name = "fck"; + clock-names = "fck"; syscon-raminit = <&scm_conf 0x644 1>; interrupts = ; status = "disabled"; From c68ef4ad180e09805fa46965d15e1dfadf09ffa5 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 1 Jul 2021 16:00:22 +0200 Subject: [PATCH 0934/1469] omap5-board-common: remove not physically existing vdds_1v8_main fixed-regulator This device tree include file describes a fixed-regulator connecting smps7_reg output (1.8V) to some 1.8V rail and consumers (vdds_1v8_main). This regulator does not physically exist. I assume it was introduced as a wrapper around smps7_reg to provide a speaking signal name "vdds_1v8_main" as label. This fixed-regulator without real function was not an issue in driver code until Commit 98e48cd9283d ("regulator: core: resolve supply for boot-on/always-on regulators") introduced a new check for regulator initialization which makes Palmas regulator registration fail: [ 5.407712] ldo1: supplied by vsys_cobra [ 5.412748] ldo2: supplied by vsys_cobra [ 5.417603] palmas-pmic 48070000.i2c:palmas@48:palmas_pmic: failed to register 48070000.i2c:palmas@48:palmas_pmic regulator The reason is that the supply-chain of regulators is too long and goes from ldo3 through the virtual vdds_1v8_main regulator and then back to smps7. This adds a cross-dependency of probing Palmas regulators and the fixed-regulator which leads to probe deferral by the new check and is no longer resolved. Since we do not control what device tree files including this one reference (either &vdds_1v8_main or &smps7_reg or both) we keep both labels for smps7 for compatibility. Fixes: 98e48cd9283d ("regulator: core: resolve supply for boot-on/always-on regulators") Signed-off-by: H. Nikolaus Schaller Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap5-board-common.dtsi | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 45435bb88c89..373984c130e0 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -30,14 +30,6 @@ regulator-max-microvolt = <5000000>; }; - vdds_1v8_main: fixedregulator-vdds_1v8_main { - compatible = "regulator-fixed"; - regulator-name = "vdds_1v8_main"; - vin-supply = <&smps7_reg>; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - }; - vmmcsd_fixed: fixedregulator-mmcsd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -487,6 +479,7 @@ regulator-boot-on; }; + vdds_1v8_main: smps7_reg: smps7 { /* VDDS_1v8_OMAP over VDDS_1v8_MAIN */ regulator-name = "smps7"; From 9f59efcd51e332aad01e7fa2b3a97cd22d347ceb Mon Sep 17 00:00:00 2001 From: Michael Zaidman Date: Mon, 10 May 2021 19:34:28 +0300 Subject: [PATCH 0935/1469] HID: ft260: fix format type warning in ft260_word_show() Fixes: 6a82582d9fa4 ("HID: ft260: add usb hid to i2c host bridge driver") Fix warning reported by static analysis when built with W=1 for arm64 by clang version 13.0.0 >> drivers/hid/hid-ft260.c:794:44: warning: format specifies type 'short' but the argument has type 'int' [-Wformat] return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field)); ~~~ ^~~~~~~~~~~~~~~~~~~ %i include/linux/byteorder/generic.h:91:21: note: expanded from macro 'le16_to_cpu' #define le16_to_cpu __le16_to_cpu ^ include/uapi/linux/byteorder/big_endian.h:36:26: note: expanded from macro '__le16_to_cpu' #define __le16_to_cpu(x) __swab16((__force __u16)(__le16)(x)) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/uapi/linux/swab.h:105:2: note: expanded from macro '__swab16' (__builtin_constant_p((__u16)(x)) ? \ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Any sprintf style use of %h or %hi for a sub-int sized value isn't useful since integer promotion is done on the value anyway. So, use %d instead. https://lore.kernel.org/lkml/CAHk-=wgoxnmsj8GEVFJSvTwdnWm8wVJthefNk2n6+4TC=20e0Q@mail.gmail.com/ Signed-off-by: Michael Zaidman Suggested-by: Joe Perches Reported-by: kernel test robot Signed-off-by: Jiri Kosina --- drivers/hid/hid-ft260.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index f43a8406cb9a..6f10df2042c4 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -785,7 +785,7 @@ static int ft260_byte_show(struct hid_device *hdev, int id, u8 *cfg, int len, if (ret < 0) return ret; - return scnprintf(buf, PAGE_SIZE, "%hi\n", *field); + return scnprintf(buf, PAGE_SIZE, "%d\n", *field); } static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len, @@ -797,7 +797,7 @@ static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len, if (ret < 0) return ret; - return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field)); + return scnprintf(buf, PAGE_SIZE, "%d\n", le16_to_cpu(*field)); } #define FT260_ATTR_SHOW(name, reptype, id, type, func) \ From 4b0556b96e1fe7723629bd40e3813a30cd632faf Mon Sep 17 00:00:00 2001 From: Alexander Tsoy Date: Tue, 27 Jul 2021 12:33:26 +0300 Subject: [PATCH 0936/1469] ALSA: usb-audio: Add registration quirk for JBL Quantum 600 Apparently JBL Quantum 600 has multiple hardware revisions. Apply registration quirk to another device id as well. Signed-off-by: Alexander Tsoy Cc: Link: https://lore.kernel.org/r/20210727093326.1153366-1-alexander@tsoy.me Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index e7accd87e063..326d1b0ea5e6 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1899,6 +1899,7 @@ static const struct registration_quirk registration_quirks[] = { REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */ REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */ + REG_QUIRK_ENTRY(0x0ecb, 0x203c, 2), /* JBL Quantum 600 */ REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */ { 0 } /* terminator */ }; From fcef709c2c4baf758950bd7395e4b10527b81e2c Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Sun, 25 Jul 2021 18:54:52 +0530 Subject: [PATCH 0937/1469] octeontx2-af: Do NIX_RX_SW_SYNC twice NIX_RX_SW_SYNC ensures all existing transactions are finished and pkts are written to LLC/DRAM, queues should be teared down after successful SW_SYNC. Due to a HW errata, in some rare scenarios an existing transaction might end after SW_SYNC operation. To ensure operation is fully done, do the SW_SYNC twice. Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/rvu_nix.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 30067668eda7..4bfbbdf38770 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -196,11 +196,22 @@ static void nix_rx_sync(struct rvu *rvu, int blkaddr) { int err; - /*Sync all in flight RX packets to LLC/DRAM */ + /* Sync all in flight RX packets to LLC/DRAM */ rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0)); err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true); if (err) - dev_err(rvu->dev, "NIX RX software sync failed\n"); + dev_err(rvu->dev, "SYNC1: NIX RX software sync failed\n"); + + /* SW_SYNC ensures all existing transactions are finished and pkts + * are written to LLC/DRAM, queues should be teared down after + * successful SW_SYNC. Due to a HW errata, in some rare scenarios + * an existing transaction might end after SW_SYNC operation. To + * ensure operation is fully done, do the SW_SYNC twice. + */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0)); + err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true); + if (err) + dev_err(rvu->dev, "SYNC2: NIX RX software sync failed\n"); } static bool is_valid_txschq(struct rvu *rvu, int blkaddr, From c7c9d2102c9c098916ab9e0ab248006107d00d6c Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Sun, 25 Jul 2021 00:11:59 +0300 Subject: [PATCH 0938/1469] net: llc: fix skb_over_panic Syzbot reported skb_over_panic() in llc_pdu_init_as_xid_cmd(). The problem was in wrong LCC header manipulations. Syzbot's reproducer tries to send XID packet. llc_ui_sendmsg() is doing following steps: 1. skb allocation with size = len + header size len is passed from userpace and header size is 3 since addr->sllc_xid is set. 2. skb_reserve() for header_len = 3 3. filling all other space with memcpy_from_msg() Ok, at this moment we have fully loaded skb, only headers needs to be filled. Then code comes to llc_sap_action_send_xid_c(). This function pushes 3 bytes for LLC PDU header and initializes it. Then comes llc_pdu_init_as_xid_cmd(). It initalizes next 3 bytes *AFTER* LLC PDU header and call skb_push(skb, 3). This looks wrong for 2 reasons: 1. Bytes rigth after LLC header are user data, so this function was overwriting payload. 2. skb_push(skb, 3) call can cause skb_over_panic() since all free space was filled in llc_ui_sendmsg(). (This can happen is user passed 686 len: 686 + 14 (eth header) + 3 (LLC header) = 703. SKB_DATA_ALIGN(703) = 704) So, in this patch I added 2 new private constansts: LLC_PDU_TYPE_U_XID and LLC_PDU_LEN_U_XID. LLC_PDU_LEN_U_XID is used to correctly reserve header size to handle LLC + XID case. LLC_PDU_TYPE_U_XID is used by llc_pdu_header_init() function to push 6 bytes instead of 3. And finally I removed skb_push() call from llc_pdu_init_as_xid_cmd(). This changes should not affect other parts of LLC, since after all steps we just transmit buffer. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+5e5a981ad7cc54c4b2b4@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- include/net/llc_pdu.h | 31 +++++++++++++++++++++++-------- net/llc/af_llc.c | 10 +++++++++- net/llc/llc_s_ac.c | 2 +- 3 files changed, 33 insertions(+), 10 deletions(-) diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index c0f0a13ed818..49aa79c7b278 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -15,9 +15,11 @@ #include /* Lengths of frame formats */ -#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ -#define LLC_PDU_LEN_S 4 -#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ +#define LLC_PDU_LEN_S 4 +#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +/* header and 1 control byte and XID info */ +#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ @@ -50,9 +52,10 @@ #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 -#define LLC_PDU_TYPE_I 0 /* first bit */ -#define LLC_PDU_TYPE_S 1 /* first two bits */ -#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_I 0 /* first bit */ +#define LLC_PDU_TYPE_S 1 /* first two bits */ +#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) @@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { - const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; + int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; + switch (type) { + case LLC_PDU_TYPE_U: + hlen = 3; + break; + case LLC_PDU_TYPE_U_XID: + hlen = 6; + break; + } + skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); @@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ - skb_put(skb, sizeof(struct llc_xid_info)); + + /* no need to push/put since llc_pdu_header_init() has already + * pushed 3 + 3 bytes + */ } /** diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7180979114e4..ac5cadd02cfa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index b554f26c68ee..79d1cef8f15a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); From 2635c226036c1bf44b86575d0bc721505c8201e3 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 26 Jul 2021 13:21:42 -0500 Subject: [PATCH 0939/1469] ASoC: topology: Select SND_DYNAMIC_MINORS The indexes of the devices are described within the topology file, it is a possibility that the topology encodes invalid indexes when DYNAMIC_MINORS is not enabled in kernel: #define SNDRV_MINOR_COMPRESS 2 /* 2 - 3 */ #define SNDRV_MINOR_HWDEP 4 /* 4 - 7 */ #define SNDRV_MINOR_RAWMIDI 8 /* 8 - 15 */ #define SNDRV_MINOR_PCM_PLAYBACK 16 /* 16 - 23 */ #define SNDRV_MINOR_PCM_CAPTURE 24 /* 24 - 31 */ If the topology assigns an index greater than 7 for PLAYBACK/CAPTURE PCM then there will be minor number collision. As an example: card0 creates a capture PCM with index 10 -> minor = 34 card1 creates compress device with index 0 -> minor = 34 Card1 will fail to instantiate because the minor for the compress stream is already taken. To avoid seemingly mysterious issues with card creation, select the DYNAMIC_MINORS when the topology is enabled. The other option would be to try to do out of bound index checks in case of DYNAMIC_MINOR is not enabled and do not even attempt to create the device with failing the topology load. Signed-off-by: Peter Ujfalusi Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210726182142.179604-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig index 8a13462e1a63..5dcf77af07af 100644 --- a/sound/soc/Kconfig +++ b/sound/soc/Kconfig @@ -36,6 +36,7 @@ config SND_SOC_COMPRESS config SND_SOC_TOPOLOGY bool + select SND_DYNAMIC_MINORS config SND_SOC_TOPOLOGY_KUNIT_TEST tristate "KUnit tests for SoC topology" From 61bef9e68dca4316e1fc5fdf5f0c270bdbd65657 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 26 Jul 2021 13:28:55 -0500 Subject: [PATCH 0940/1469] ASoC: SOF: Intel: hda: enforce exclusion between HDaudio and SoundWire On some platforms with an external HDaudio codec, the DSDT reports the presence of SoundWire devices. Pin-mux restrictions and board reworks usually prevent coexistence between the two types of links, let's prevent unnecessary operations from starting. In the case of a single iDISP codec being detected, we still start the links even if no SoundWire machine configuration was detected, so that we can double-check what the hardware is and add the missing configuration if applicable. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20210726182855.179943-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/intel/hda.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index e1e368ff2b12..891e6e1b9121 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -187,12 +187,16 @@ static int hda_sdw_probe(struct snd_sof_dev *sdev) int hda_sdw_startup(struct snd_sof_dev *sdev) { struct sof_intel_hda_dev *hdev; + struct snd_sof_pdata *pdata = sdev->pdata; hdev = sdev->pdata->hw_pdata; if (!hdev->sdw) return 0; + if (pdata->machine && !pdata->machine->mach_params.link_mask) + return 0; + return sdw_intel_startup(hdev->sdw); } @@ -1002,6 +1006,14 @@ static int hda_generic_machine_select(struct snd_sof_dev *sdev) hda_mach->mach_params.dmic_num = dmic_num; pdata->machine = hda_mach; pdata->tplg_filename = tplg_filename; + + if (codec_num == 2) { + /* + * Prevent SoundWire links from starting when an external + * HDaudio codec is used + */ + hda_mach->mach_params.link_mask = 0; + } } } From 4d1014c1816c0395eca5d1d480f196a4c63119d0 Mon Sep 17 00:00:00 2001 From: Filip Schauer Date: Tue, 27 Jul 2021 13:23:11 +0200 Subject: [PATCH 0941/1469] drivers core: Fix oops when driver probe fails dma_range_map is freed to early, which might cause an oops when a driver probe fails. Call trace: is_free_buddy_page+0xe4/0x1d4 __free_pages+0x2c/0x88 dma_free_contiguous+0x64/0x80 dma_direct_free+0x38/0xb4 dma_free_attrs+0x88/0xa0 dmam_release+0x28/0x34 release_nodes+0x78/0x8c devres_release_all+0xa8/0x110 really_probe+0x118/0x2d0 __driver_probe_device+0xc8/0xe0 driver_probe_device+0x54/0xec __driver_attach+0xe0/0xf0 bus_for_each_dev+0x7c/0xc8 driver_attach+0x30/0x3c bus_add_driver+0x17c/0x1c4 driver_register+0xc0/0xf8 __platform_driver_register+0x34/0x40 ... This issue is introduced by commit d0243bbd5dd3 ("drivers core: Free dma_range_map when driver probe failed"). It frees dma_range_map before the call to devres_release_all, which is too early. The solution is to free dma_range_map only after devres_release_all. Fixes: d0243bbd5dd3 ("drivers core: Free dma_range_map when driver probe failed") Cc: stable Signed-off-by: Filip Schauer Link: https://lore.kernel.org/r/20210727112311.GA7645@DESKTOP-E8BN1B0.localdomain Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index daeb9b5763ae..437cd61343b2 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -653,8 +653,6 @@ dev_groups_failed: else if (drv->remove) drv->remove(dev); probe_failed: - kfree(dev->dma_range_map); - dev->dma_range_map = NULL; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); @@ -662,6 +660,8 @@ pinctrl_bind_failed: device_links_no_driver(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); From 55f24c27b6c1a840b62fe297616f1f9ea3576cb7 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Tue, 27 Jul 2021 14:47:32 +0900 Subject: [PATCH 0942/1469] dmaengine: uniphier-xdmac: Use readl_poll_timeout_atomic() in atomic state The function uniphier_xdmac_chan_stop() is only called in atomic state. Should use readl_poll_timeout_atomic() there instead of readl_poll_timeout(). Reported-by: Dan Carpenter Fixes: 667b9251440b ("dmaengine: uniphier-xdmac: Add UniPhier external DMA controller driver") Signed-off-by: Kunihiko Hayashi Link: https://lore.kernel.org/r/1627364852-28432-1-git-send-email-hayashi.kunihiko@socionext.com Signed-off-by: Vinod Koul --- drivers/dma/uniphier-xdmac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c index 16b19654873d..d6b8a202474f 100644 --- a/drivers/dma/uniphier-xdmac.c +++ b/drivers/dma/uniphier-xdmac.c @@ -209,8 +209,8 @@ static int uniphier_xdmac_chan_stop(struct uniphier_xdmac_chan *xc) writel(0, xc->reg_ch_base + XDMAC_TSS); /* wait until transfer is stopped */ - return readl_poll_timeout(xc->reg_ch_base + XDMAC_STAT, val, - !(val & XDMAC_STAT_TENF), 100, 1000); + return readl_poll_timeout_atomic(xc->reg_ch_base + XDMAC_STAT, val, + !(val & XDMAC_STAT_TENF), 100, 1000); } /* xc->vc.lock must be held by caller */ From 801e541c79bbc63af852ca21b713ba87cc97c6ad Mon Sep 17 00:00:00 2001 From: Tang Bin Date: Tue, 27 Jul 2021 20:25:06 +0800 Subject: [PATCH 0943/1469] nfc: s3fwrn5: fix undefined parameter values in dev_err() In the function s3fwrn5_fw_download(), the 'ret' is not assigned, so the correct value should be given in dev_err function. Fixes: a0302ff5906a ("nfc: s3fwrn5: remove unnecessary label") Signed-off-by: Zhang Shengju Signed-off-by: Tang Bin Signed-off-by: David S. Miller --- drivers/nfc/s3fwrn5/firmware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index eb5d7a5beac7..1340fab9565e 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -423,7 +423,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot allocate shash (code=%d)\n", ret); + "Cannot allocate shash (code=%ld)\n", PTR_ERR(tfm)); goto out; } From 9be550ee43919b070bcd77f9228bdbbbc073245b Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 21 Jul 2021 22:34:36 +0300 Subject: [PATCH 0944/1469] staging: rtl8712: get rid of flush_scheduled_work This patch is preparation for following patch for error handling refactoring. flush_scheduled_work() takes (wq_completion)events lock and it can lead to deadlock when r871xu_dev_remove() is called from workqueue. To avoid deadlock sutiation we can change flush_scheduled_work() call to flush_work() call for all possibly scheduled works in this driver, since next patch adds device_release_driver() in case of fw load failure. Signed-off-by: Pavel Skripkin Cc: stable Link: https://lore.kernel.org/r/6e028b4c457eeb7156c76c6ea3cdb3cb0207c7e1.1626895918.git.paskripkin@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/rtl8712_led.c | 8 ++++++++ drivers/staging/rtl8712/rtl871x_led.h | 1 + drivers/staging/rtl8712/rtl871x_pwrctrl.c | 8 ++++++++ drivers/staging/rtl8712/rtl871x_pwrctrl.h | 1 + drivers/staging/rtl8712/usb_intf.c | 3 ++- 5 files changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8712/rtl8712_led.c b/drivers/staging/rtl8712/rtl8712_led.c index 5901026949f2..d5fc9026b036 100644 --- a/drivers/staging/rtl8712/rtl8712_led.c +++ b/drivers/staging/rtl8712/rtl8712_led.c @@ -1820,3 +1820,11 @@ void LedControl871x(struct _adapter *padapter, enum LED_CTL_MODE LedAction) break; } } + +void r8712_flush_led_works(struct _adapter *padapter) +{ + struct led_priv *pledpriv = &padapter->ledpriv; + + flush_work(&pledpriv->SwLed0.BlinkWorkItem); + flush_work(&pledpriv->SwLed1.BlinkWorkItem); +} diff --git a/drivers/staging/rtl8712/rtl871x_led.h b/drivers/staging/rtl8712/rtl871x_led.h index ee19c873cf01..2f0768132ad8 100644 --- a/drivers/staging/rtl8712/rtl871x_led.h +++ b/drivers/staging/rtl8712/rtl871x_led.h @@ -112,6 +112,7 @@ struct led_priv { void r8712_InitSwLeds(struct _adapter *padapter); void r8712_DeInitSwLeds(struct _adapter *padapter); void LedControl871x(struct _adapter *padapter, enum LED_CTL_MODE LedAction); +void r8712_flush_led_works(struct _adapter *padapter); #endif diff --git a/drivers/staging/rtl8712/rtl871x_pwrctrl.c b/drivers/staging/rtl8712/rtl871x_pwrctrl.c index 23cff43437e2..cd6d9ff0bebc 100644 --- a/drivers/staging/rtl8712/rtl871x_pwrctrl.c +++ b/drivers/staging/rtl8712/rtl871x_pwrctrl.c @@ -224,3 +224,11 @@ void r8712_unregister_cmd_alive(struct _adapter *padapter) } mutex_unlock(&pwrctrl->mutex_lock); } + +void r8712_flush_rwctrl_works(struct _adapter *padapter) +{ + struct pwrctrl_priv *pwrctrl = &padapter->pwrctrlpriv; + + flush_work(&pwrctrl->SetPSModeWorkItem); + flush_work(&pwrctrl->rpwm_workitem); +} diff --git a/drivers/staging/rtl8712/rtl871x_pwrctrl.h b/drivers/staging/rtl8712/rtl871x_pwrctrl.h index bf6623cfaf27..b35b9c7920eb 100644 --- a/drivers/staging/rtl8712/rtl871x_pwrctrl.h +++ b/drivers/staging/rtl8712/rtl871x_pwrctrl.h @@ -108,5 +108,6 @@ void r8712_cpwm_int_hdl(struct _adapter *padapter, void r8712_set_ps_mode(struct _adapter *padapter, uint ps_mode, uint smart_ps); void r8712_set_rpwm(struct _adapter *padapter, u8 val8); +void r8712_flush_rwctrl_works(struct _adapter *padapter); #endif /* __RTL871X_PWRCTRL_H_ */ diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index 2434b13c8b12..643f21eb1128 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -606,7 +606,8 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf) padapter->surprise_removed = true; if (pnetdev->reg_state != NETREG_UNINITIALIZED) unregister_netdev(pnetdev); /* will call netdev_close() */ - flush_scheduled_work(); + r8712_flush_rwctrl_works(padapter); + r8712_flush_led_works(padapter); udelay(1); /* Stop driver mlme relation timer */ r8712_stop_drv_timers(padapter); From e9e6aa51b2735d83a67d9fa0119cf11abef80d99 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 21 Jul 2021 22:34:47 +0300 Subject: [PATCH 0945/1469] staging: rtl8712: error handling refactoring There was strange error handling logic in case of fw load failure. For some reason fw loader callback was doing clean up stuff when fw is not available. I don't see any reason behind doing this. Since this driver doesn't have EEPROM firmware let's just disconnect it in case of fw load failure. Doing clean up stuff in 2 different place which can run concurently is not good idea and syzbot found 2 bugs related to this strange approach. So, in this pacth I deleted all clean up code from fw callback and made a call to device_release_driver() under device_lock(parent) in case of fw load failure. This approach is more generic and it defend driver from UAF bugs, since all clean up code is moved to one place. Fixes: e02a3b945816 ("staging: rtl8712: fix memory leak in rtl871x_load_fw_cb") Fixes: 8c213fa59199 ("staging: r8712u: Use asynchronous firmware loading") Cc: stable Reported-and-tested-by: syzbot+5872a520e0ce0a7c7230@syzkaller.appspotmail.com Reported-and-tested-by: syzbot+cc699626e48a6ebaf295@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/d49ecc56e97c4df181d7bd4d240b031f315eacc3.1626895918.git.paskripkin@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/hal_init.c | 30 ++++++++++++------- drivers/staging/rtl8712/usb_intf.c | 48 +++++++++++++----------------- 2 files changed, 41 insertions(+), 37 deletions(-) diff --git a/drivers/staging/rtl8712/hal_init.c b/drivers/staging/rtl8712/hal_init.c index 22974277afa0..4eff3fdecdb8 100644 --- a/drivers/staging/rtl8712/hal_init.c +++ b/drivers/staging/rtl8712/hal_init.c @@ -29,21 +29,31 @@ #define FWBUFF_ALIGN_SZ 512 #define MAX_DUMP_FWSZ (48 * 1024) +static void rtl871x_load_fw_fail(struct _adapter *adapter) +{ + struct usb_device *udev = adapter->dvobjpriv.pusbdev; + struct device *dev = &udev->dev; + struct device *parent = dev->parent; + + complete(&adapter->rtl8712_fw_ready); + + dev_err(&udev->dev, "r8712u: Firmware request failed\n"); + + if (parent) + device_lock(parent); + + device_release_driver(dev); + + if (parent) + device_unlock(parent); +} + static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context) { struct _adapter *adapter = context; if (!firmware) { - struct usb_device *udev = adapter->dvobjpriv.pusbdev; - struct usb_interface *usb_intf = adapter->pusb_intf; - - dev_err(&udev->dev, "r8712u: Firmware request failed\n"); - usb_put_dev(udev); - usb_set_intfdata(usb_intf, NULL); - r8712_free_drv_sw(adapter); - adapter->dvobj_deinit(adapter); - complete(&adapter->rtl8712_fw_ready); - free_netdev(adapter->pnetdev); + rtl871x_load_fw_fail(adapter); return; } adapter->fw = firmware; diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index 643f21eb1128..505ebeb643dc 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -591,36 +591,30 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf) { struct net_device *pnetdev = usb_get_intfdata(pusb_intf); struct usb_device *udev = interface_to_usbdev(pusb_intf); + struct _adapter *padapter = netdev_priv(pnetdev); - if (pnetdev) { - struct _adapter *padapter = netdev_priv(pnetdev); + /* never exit with a firmware callback pending */ + wait_for_completion(&padapter->rtl8712_fw_ready); + usb_set_intfdata(pusb_intf, NULL); + release_firmware(padapter->fw); + if (drvpriv.drv_registered) + padapter->surprise_removed = true; + if (pnetdev->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(pnetdev); /* will call netdev_close() */ + r8712_flush_rwctrl_works(padapter); + r8712_flush_led_works(padapter); + udelay(1); + /* Stop driver mlme relation timer */ + r8712_stop_drv_timers(padapter); + r871x_dev_unload(padapter); + r8712_free_drv_sw(padapter); + free_netdev(pnetdev); - /* never exit with a firmware callback pending */ - wait_for_completion(&padapter->rtl8712_fw_ready); - pnetdev = usb_get_intfdata(pusb_intf); - usb_set_intfdata(pusb_intf, NULL); - if (!pnetdev) - goto firmware_load_fail; - release_firmware(padapter->fw); - if (drvpriv.drv_registered) - padapter->surprise_removed = true; - if (pnetdev->reg_state != NETREG_UNINITIALIZED) - unregister_netdev(pnetdev); /* will call netdev_close() */ - r8712_flush_rwctrl_works(padapter); - r8712_flush_led_works(padapter); - udelay(1); - /* Stop driver mlme relation timer */ - r8712_stop_drv_timers(padapter); - r871x_dev_unload(padapter); - r8712_free_drv_sw(padapter); - free_netdev(pnetdev); + /* decrease the reference count of the usb device structure + * when disconnect + */ + usb_put_dev(udev); - /* decrease the reference count of the usb device structure - * when disconnect - */ - usb_put_dev(udev); - } -firmware_load_fail: /* If we didn't unplug usb dongle and remove/insert module, driver * fails on sitesurvey for the first time when device is up. * Reset usb port for sitesurvey fail issue. From c7b65650c7f41d3946c4e2f0bb56dfdb92cfe127 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Tue, 27 Jul 2021 07:40:58 +0200 Subject: [PATCH 0946/1469] staging: mt7621-pci: avoid to re-disable clock for those pcies not in use Clock driver for this SoC is using some gates to properly enabling and disabling the access to peripherals. Those gates that are not in use are properly being automatically disabled by the kernel. Pcie driver is explicitly doing a 'clk_disable_unprepare' call for gates of those pcies that are not used. Since kernel has already disabled them, the following warnings appear: WARNING: CPU: 0 PID: 1 at drivers/clk/clk.c:952 clk_core_disable+0xe4/0x100 pcie2 already disabled Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0 #0 Stack : 81661680 80082d00 807c0000 00000004 00000000 80a20000 80860000 80792380 814503d4 80862e83 00000000 1431b70 81454360 00000000 00000000 80792380 81431a08 ffffefff fffffea 00000000 81431a14 0000007b 80868820 ffffffff 80792380 1431c70 803d7a24 00000009 807f3a74 00000001 815df810 00000018 0000000 80a20000 ... Call Trace: [<80007ed8>] show_stack+0x28/0xf0 [<80381e40>] dump_stack_lvl+0x60/0x80 [<8002cf90>] __warn+0xcc/0x140 [<8002d090>] warn_slowpath_fmt+0x8c/0xac [<803d7a24>] clk_core_disable+0xe4/0x100 [<803da468>] clk_disable+0x38/0x58 [<804cb730>] mt7621_pci_probe+0x980/0xa50 [<8041e624>] platform_probe+0x50/0xbc [<8041bfe4>] really_probe.part.0+0xa8/0x340 [<8041c3dc>] driver_probe_device+0x4c/0x154 [<8041cb88>] __driver_attach+0xb4/0x1b4 [<80419a38>] bus_for_each_dev+0x68/0xa4 [<8041b1e8>] bus_add_driver+0x134/0x214 [<8041d3bc>] driver_register+0x98/0x154 [<80001648>] do_one_initcall+0x50/0x1a8 [<808ea1fc>] kernel_init_freeable+0x270/0x30c [<806dd9dc>] kernel_init+0x20/0x110 [<80002d98>] ret_from_kernel_thread+0x14/0x1c WARNING: CPU: 0 PID: 1 at drivers/clk/clk.c:810 clk_core_unprepare+0xf4/0x194 pcie2 already unprepared Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 5.14.0 #0 Stack : 81661680 80082d00 807c0000 00000004 00000000 00000000 81431bc4 80a20000 80860000 80792380 814503d4 80862e83 00000000 00000001 81431b70 81454360 00000000 00000000 80792380 81431a08 ffffefff 00000000 ffffffea 00000000 81431a14 0000009b 80868820 ffffffff 80792380 00000001 81431c70 803d7764 00000009 807f3a74 00000001 815df810 00000018 8040b36c 00000000 80a20000 ... Call Trace: [<80007ed8>] show_stack+0x28/0xf0 [<80381e40>] dump_stack_lvl+0x60/0x80 [<8002cf90>] __warn+0xcc/0x140 [<8002d090>] warn_slowpath_fmt+0x8c/0xac [<803d7764>] clk_core_unprepare+0xf4/0x194 [<803d97c4>] clk_unprepare+0x30/0x48 [<804cb738>] mt7621_pci_probe+0x988/0xa50 [<8041e624>] platform_probe+0x50/0xbc [<8041bfe4>] really_probe.part.0+0xa8/0x340 [<8041c3dc>] driver_probe_device+0x4c/0x154 [<8041cb88>] __driver_attach+0xb4/0x1b4 [<80419a38>] bus_for_each_dev+0x68/0xa4 [<8041b1e8>] bus_add_driver+0x134/0x214 [<8041d3bc>] driver_register+0x98/0x154 [<80001648>] do_one_initcall+0x50/0x1a8 [<808ea1fc>] kernel_init_freeable+0x270/0x30c [<806dd9dc>] kernel_init+0x20/0x110 [<80002d98>] ret_from_kernel_thread+0x14/0x1c Avoid to explicitly disable already disabled pcie gates fixes the problem. Fixes: cc4e864a5ce4 ("staging: mt7621-pci: make use of kernel clock apis") Reported-by: DENG Qingfang Signed-off-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20210727054058.10612-1-sergio.paracuellos@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/mt7621-pci/pci-mt7621.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/staging/mt7621-pci/pci-mt7621.c b/drivers/staging/mt7621-pci/pci-mt7621.c index 691030e1a5ed..f9bdf4e33134 100644 --- a/drivers/staging/mt7621-pci/pci-mt7621.c +++ b/drivers/staging/mt7621-pci/pci-mt7621.c @@ -422,7 +422,6 @@ static void mt7621_pcie_init_ports(struct mt7621_pcie *pcie) dev_err(dev, "pcie%d no card, disable it (RST & CLK)\n", slot); mt7621_control_assert(port); - clk_disable_unprepare(port->clk); port->enabled = false; if (slot == 0) { From 30fad76ce4e98263edfa8f885c81d5426c1bf169 Mon Sep 17 00:00:00 2001 From: "Qiang.zhang" Date: Fri, 23 Jul 2021 08:43:34 +0800 Subject: [PATCH 0947/1469] USB: usbtmc: Fix RCU stall warning rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 1-...!: (2 ticks this GP) idle=d92/1/0x4000000000000000 softirq=25390/25392 fqs=3 (t=12164 jiffies g=31645 q=43226) rcu: rcu_preempt kthread starved for 12162 jiffies! g31645 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=0 rcu: Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior. rcu: RCU grace-period kthread stack dump: task:rcu_preempt state:R running task ........... usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: unknown status received: -71 usbtmc 3-1:0.0: usb_submit_urb failed: -19 The function usbtmc_interrupt() resubmits urbs when the error status of an urb is -EPROTO. In systems using the dummy_hcd usb controller this can result in endless interrupt loops when the usbtmc device is disconnected from the host system. Since host controller drivers already try to recover from transmission errors, there is no need to resubmit the urb or try other solutions to repair the error situation. In case of errors the INT pipe just stops to wait for further packets. Fixes: dbf3e7f654c0 ("Implement an ioctl to support the USMTMC-USB488 READ_STATUS_BYTE operation") Cc: stable@vger.kernel.org Reported-by: syzbot+e2eae5639e7203360018@syzkaller.appspotmail.com Signed-off-by: Qiang.zhang Acked-by: Guido Kiener Link: https://lore.kernel.org/r/20210723004334.458930-1-qiang.zhang@windriver.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 74d5a9c5238a..73f419adce61 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -2324,17 +2324,10 @@ static void usbtmc_interrupt(struct urb *urb) dev_err(dev, "overflow with length %d, actual length is %d\n", data->iin_wMaxPacketSize, urb->actual_length); fallthrough; - case -ECONNRESET: - case -ENOENT: - case -ESHUTDOWN: - case -EILSEQ: - case -ETIME: - case -EPIPE: + default: /* urb terminated, clean up */ dev_dbg(dev, "urb terminated, status: %d\n", status); return; - default: - dev_err(dev, "unknown status received: %d\n", status); } exit: rv = usb_submit_urb(urb, GFP_ATOMIC); From fa4a8dcfd51b911f101ebc461dfe22230b74dd64 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 27 Jul 2021 15:31:42 +0800 Subject: [PATCH 0948/1469] usb: gadget: remove leaked entry from udc driver list The usb_add_gadget_udc will add a new gadget to the udc class driver list. Not calling usb_del_gadget_udc in error branch will result in residual gadget entry in the udc driver list. We fix it by calling usb_del_gadget_udc to clean it when error return. Fixes: 48ba02b2e2b1 ("usb: gadget: add udc driver for max3420") Acked-by: Felipe Balbi Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20210727073142.84666-1-zhangqilong3@huawei.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/max3420_udc.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c index 34f4db554977..d2a2b20cc1ad 100644 --- a/drivers/usb/gadget/udc/max3420_udc.c +++ b/drivers/usb/gadget/udc/max3420_udc.c @@ -1255,12 +1255,14 @@ static int max3420_probe(struct spi_device *spi) err = devm_request_irq(&spi->dev, irq, max3420_irq_handler, 0, "max3420", udc); if (err < 0) - return err; + goto del_gadget; udc->thread_task = kthread_create(max3420_thread, udc, "max3420-thread"); - if (IS_ERR(udc->thread_task)) - return PTR_ERR(udc->thread_task); + if (IS_ERR(udc->thread_task)) { + err = PTR_ERR(udc->thread_task); + goto del_gadget; + } irq = of_irq_get_byname(spi->dev.of_node, "vbus"); if (irq <= 0) { /* no vbus irq implies self-powered design */ @@ -1280,10 +1282,14 @@ static int max3420_probe(struct spi_device *spi) err = devm_request_irq(&spi->dev, irq, max3420_vbus_handler, 0, "vbus", udc); if (err < 0) - return err; + goto del_gadget; } return 0; + +del_gadget: + usb_del_gadget_udc(&udc->gadget); + return err; } static int max3420_remove(struct spi_device *spi) From 2867652e4766360adf14dfda3832455e04964f2a Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Fri, 23 Jul 2021 18:59:30 +0300 Subject: [PATCH 0949/1469] usb: gadget: f_hid: fixed NULL pointer dereference Disconnecting and reconnecting the USB cable can lead to crashes and a variety of kernel log spam. The problem was found and reproduced on the Raspberry Pi [1] and the original fix was created in Raspberry's own fork [2]. Link: https://github.com/raspberrypi/linux/issues/3870 [1] Link: https://github.com/raspberrypi/linux/commit/a6e47d5f4efbd2ea6a0b6565cd2f9b7bb217ded5 [2] Signed-off-by: Maxim Devaev Signed-off-by: Phil Elwell Cc: stable Link: https://lore.kernel.org/r/20210723155928.210019-1-mdevaev@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_hid.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 02683ac0719d..08e73e8127b1 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -338,6 +338,11 @@ static ssize_t f_hidg_write(struct file *file, const char __user *buffer, spin_lock_irqsave(&hidg->write_spinlock, flags); + if (!hidg->req) { + spin_unlock_irqrestore(&hidg->write_spinlock, flags); + return -ESHUTDOWN; + } + #define WRITE_COND (!hidg->write_pending) try_again: /* write queue */ @@ -358,8 +363,14 @@ try_again: count = min_t(unsigned, count, hidg->report_length); spin_unlock_irqrestore(&hidg->write_spinlock, flags); - status = copy_from_user(req->buf, buffer, count); + if (!req) { + ERROR(hidg->func.config->cdev, "hidg->req is NULL\n"); + status = -ESHUTDOWN; + goto release_write_pending; + } + + status = copy_from_user(req->buf, buffer, count); if (status != 0) { ERROR(hidg->func.config->cdev, "copy_from_user error\n"); @@ -387,15 +398,18 @@ try_again: spin_unlock_irqrestore(&hidg->write_spinlock, flags); - status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC); - if (status < 0) { - ERROR(hidg->func.config->cdev, - "usb_ep_queue error on int endpoint %zd\n", status); + if (!hidg->in_ep->enabled) { + ERROR(hidg->func.config->cdev, "in_ep is disabled\n"); + status = -ESHUTDOWN; goto release_write_pending; - } else { - status = count; } + status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC); + if (status < 0) + goto release_write_pending; + else + status = count; + return status; release_write_pending: spin_lock_irqsave(&hidg->write_spinlock, flags); From afcff6dc690e24d636a41fd4bee6057e7c70eebd Mon Sep 17 00:00:00 2001 From: Maxim Devaev Date: Wed, 21 Jul 2021 21:03:51 +0300 Subject: [PATCH 0950/1469] usb: gadget: f_hid: added GET_IDLE and SET_IDLE handlers The USB HID standard declares mandatory support for GET_IDLE and SET_IDLE requests for Boot Keyboard. Most hosts can handle their absence, but others like some old/strange UEFIs and BIOSes consider this a critical error and refuse to work with f_hid. This primitive implementation of saving and returning idle is sufficient to meet the requirements of the standard and these devices. Acked-by: Felipe Balbi Cc: stable Signed-off-by: Maxim Devaev Link: https://lore.kernel.org/r/20210721180351.129450-1-mdevaev@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_hid.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 08e73e8127b1..8d50c8b127fd 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -41,6 +41,7 @@ struct f_hidg { unsigned char bInterfaceSubClass; unsigned char bInterfaceProtocol; unsigned char protocol; + unsigned char idle; unsigned short report_desc_length; char *report_desc; unsigned short report_length; @@ -537,6 +538,14 @@ static int hidg_setup(struct usb_function *f, goto respond; break; + case ((USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8 + | HID_REQ_GET_IDLE): + VDBG(cdev, "get_idle\n"); + length = min_t(unsigned int, length, 1); + ((u8 *) req->buf)[0] = hidg->idle; + goto respond; + break; + case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8 | HID_REQ_SET_REPORT): VDBG(cdev, "set_report | wLength=%d\n", ctrl->wLength); @@ -560,6 +569,14 @@ static int hidg_setup(struct usb_function *f, goto stall; break; + case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8 + | HID_REQ_SET_IDLE): + VDBG(cdev, "set_idle\n"); + length = 0; + hidg->idle = value; + goto respond; + break; + case ((USB_DIR_IN | USB_TYPE_STANDARD | USB_RECIP_INTERFACE) << 8 | USB_REQ_GET_DESCRIPTOR): switch (value >> 8) { @@ -787,6 +804,7 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) hidg_interface_desc.bInterfaceSubClass = hidg->bInterfaceSubClass; hidg_interface_desc.bInterfaceProtocol = hidg->bInterfaceProtocol; hidg->protocol = HID_REPORT_PROTOCOL; + hidg->idle = 1; hidg_ss_in_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length); hidg_ss_in_comp_desc.wBytesPerInterval = cpu_to_le16(hidg->report_length); From 68d9f95d6fd5399d105eaf2308c243536c5d7664 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 27 Jul 2021 13:41:34 +0300 Subject: [PATCH 0951/1469] usb: musb: Fix suspend and resume issues for PHYs on I2C and SPI As the USB PHYs typically are on I2C or SPI bus for the 2430 glue layer, we need configure the PHYs early for suspend. The musb glue layer we need to suspend only after musb_suspend() in suspend_late. Fixes: 62d472d8ad88 ("usb: musb: Add missing PM suspend and resume functions for 2430 glue") Reported-by: Andreas Kemnade Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20210727104134.52800-1-tony@atomide.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/omap2430.c | 43 ++++++++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 5 deletions(-) diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 640a46f0d118..f086960fe2b5 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -35,6 +35,7 @@ struct omap2430_glue { struct device *control_otghs; unsigned int is_runtime_suspended:1; unsigned int needs_resume:1; + unsigned int phy_suspended:1; }; #define glue_to_musb(g) platform_get_drvdata(g->musb) @@ -458,8 +459,10 @@ static int omap2430_runtime_suspend(struct device *dev) omap2430_low_level_exit(musb); - phy_power_off(musb->phy); - phy_exit(musb->phy); + if (!glue->phy_suspended) { + phy_power_off(musb->phy); + phy_exit(musb->phy); + } glue->is_runtime_suspended = 1; @@ -474,8 +477,10 @@ static int omap2430_runtime_resume(struct device *dev) if (!musb) return 0; - phy_init(musb->phy); - phy_power_on(musb->phy); + if (!glue->phy_suspended) { + phy_init(musb->phy); + phy_power_on(musb->phy); + } omap2430_low_level_init(musb); musb_writel(musb->mregs, OTG_INTERFSEL, @@ -489,7 +494,21 @@ static int omap2430_runtime_resume(struct device *dev) return 0; } +/* I2C and SPI PHYs need to be suspended before the glue layer */ static int omap2430_suspend(struct device *dev) +{ + struct omap2430_glue *glue = dev_get_drvdata(dev); + struct musb *musb = glue_to_musb(glue); + + phy_power_off(musb->phy); + phy_exit(musb->phy); + glue->phy_suspended = 1; + + return 0; +} + +/* Glue layer needs to be suspended after musb_suspend() */ +static int omap2430_suspend_late(struct device *dev) { struct omap2430_glue *glue = dev_get_drvdata(dev); @@ -501,7 +520,7 @@ static int omap2430_suspend(struct device *dev) return omap2430_runtime_suspend(dev); } -static int omap2430_resume(struct device *dev) +static int omap2430_resume_early(struct device *dev) { struct omap2430_glue *glue = dev_get_drvdata(dev); @@ -513,10 +532,24 @@ static int omap2430_resume(struct device *dev) return omap2430_runtime_resume(dev); } +static int omap2430_resume(struct device *dev) +{ + struct omap2430_glue *glue = dev_get_drvdata(dev); + struct musb *musb = glue_to_musb(glue); + + phy_init(musb->phy); + phy_power_on(musb->phy); + glue->phy_suspended = 0; + + return 0; +} + static const struct dev_pm_ops omap2430_pm_ops = { .runtime_suspend = omap2430_runtime_suspend, .runtime_resume = omap2430_runtime_resume, .suspend = omap2430_suspend, + .suspend_late = omap2430_suspend_late, + .resume_early = omap2430_resume_early, .resume = omap2430_resume, }; From 00de6a572f30ee93cad7e0704ec4232e5e72bda8 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 21 Jul 2021 16:29:05 +0300 Subject: [PATCH 0952/1469] usb: host: ohci-at91: suspend/resume ports after/before OHCI accesses On SAMA7G5 suspending ports will cut the access to OHCI registers and any subsequent access to them will lead to CPU being blocked trying to access that memory. Same thing happens on resume: if OHCI memory is accessed before resuming ports the CPU will block on that access. The OCHI memory is accessed on suspend/resume though ohci_suspend()/ohci_resume(). Acked-by: Alan Stern Signed-off-by: Claudiu Beznea Cc: stable Link: https://lore.kernel.org/r/20210721132905.1970713-1-claudiu.beznea@microchip.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ohci-at91.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index 9bbd7ddd0003..a24aea3d2759 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -611,8 +611,6 @@ ohci_hcd_at91_drv_suspend(struct device *dev) if (ohci_at91->wakeup) enable_irq_wake(hcd->irq); - ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1); - ret = ohci_suspend(hcd, ohci_at91->wakeup); if (ret) { if (ohci_at91->wakeup) @@ -632,7 +630,10 @@ ohci_hcd_at91_drv_suspend(struct device *dev) /* flush the writes */ (void) ohci_readl (ohci, &ohci->regs->control); msleep(1); + ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1); at91_stop_clock(ohci_at91); + } else { + ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1); } return ret; @@ -644,6 +645,8 @@ ohci_hcd_at91_drv_resume(struct device *dev) struct usb_hcd *hcd = dev_get_drvdata(dev); struct ohci_at91_priv *ohci_at91 = hcd_to_ohci_at91_priv(hcd); + ohci_at91_port_suspend(ohci_at91->sfr_regmap, 0); + if (ohci_at91->wakeup) disable_irq_wake(hcd->irq); else @@ -651,8 +654,6 @@ ohci_hcd_at91_drv_resume(struct device *dev) ohci_resume(hcd, false); - ohci_at91_port_suspend(ohci_at91->sfr_regmap, 0); - return 0; } From bf88fef0b6f1488abeca594d377991171c00e52a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sat, 17 Jul 2021 21:21:27 +0300 Subject: [PATCH 0953/1469] usb: otg-fsm: Fix hrtimer list corruption The HNP work can be re-scheduled while it's still in-fly. This results in re-initialization of the busy work, resetting the hrtimer's list node of the work and crashing kernel with null dereference within kernel/timer once work's timer is expired. It's very easy to trigger this problem by re-plugging USB cable quickly. Initialize HNP work only once to fix this trouble. Unable to handle kernel NULL pointer dereference at virtual address 00000126) ... PC is at __run_timers.part.0+0x150/0x228 LR is at __next_timer_interrupt+0x51/0x9c ... (__run_timers.part.0) from [] (run_timer_softirq+0x2f/0x50) (run_timer_softirq) from [] (__do_softirq+0xd5/0x2f0) (__do_softirq) from [] (irq_exit+0xab/0xb8) (irq_exit) from [] (handle_domain_irq+0x45/0x60) (handle_domain_irq) from [] (gic_handle_irq+0x6b/0x7c) (gic_handle_irq) from [] (__irq_svc+0x65/0xac) Cc: stable@vger.kernel.org Acked-by: Peter Chen Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20210717182134.30262-6-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/usb-otg-fsm.c | 6 +++++- include/linux/usb/otg-fsm.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c index 3740cf95560e..0697fde51d00 100644 --- a/drivers/usb/common/usb-otg-fsm.c +++ b/drivers/usb/common/usb-otg-fsm.c @@ -193,7 +193,11 @@ static void otg_start_hnp_polling(struct otg_fsm *fsm) if (!fsm->host_req_flag) return; - INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work); + if (!fsm->hnp_work_inited) { + INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work); + fsm->hnp_work_inited = true; + } + schedule_delayed_work(&fsm->hnp_polling_work, msecs_to_jiffies(T_HOST_REQ_POLL)); } diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index 3aee78dda16d..784659d4dc99 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -196,6 +196,7 @@ struct otg_fsm { struct mutex lock; u8 *host_req_flag; struct delayed_work hnp_polling_work; + bool hnp_work_inited; bool state_changed; }; From 4c4c1257b844ffe5d0933684e612f92c4b78e120 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Thu, 22 Jul 2021 14:27:36 +0800 Subject: [PATCH 0954/1469] virt: acrn: Do hcall_destroy_vm() before resource release The ACRN hypervisor has scenarios which could run a real-time guest VM. The real-time guest VM occupies dedicated CPU cores, be assigned with dedicated PCI devices. It can run without the Service VM after boot up. hcall_destroy_vm() returns failure when a real-time guest VM refuses. The clearing of flag ACRN_VM_FLAG_DESTROYED causes some kernel resource double-freed in a later acrn_vm_destroy(). Do hcall_destroy_vm() before resource release to drop this chance to destroy the VM if hypercall fails. Fixes: 9c5137aedd11 ("virt: acrn: Introduce VM management interfaces") Cc: stable Signed-off-by: Shuo Liu Signed-off-by: Fei Li Link: https://lore.kernel.org/r/20210722062736.15050-1-fei1.li@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/vm.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 0d002a355a93..fbc9f1042000 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -64,6 +64,14 @@ int acrn_vm_destroy(struct acrn_vm *vm) test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags)) return 0; + ret = hcall_destroy_vm(vm->vmid); + if (ret < 0) { + dev_err(acrn_dev.this_device, + "Failed to destroy VM %u\n", vm->vmid); + clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); + return ret; + } + /* Remove from global VM list */ write_lock_bh(&acrn_vm_list_lock); list_del_init(&vm->list); @@ -78,14 +86,6 @@ int acrn_vm_destroy(struct acrn_vm *vm) vm->monitor_page = NULL; } - ret = hcall_destroy_vm(vm->vmid); - if (ret < 0) { - dev_err(acrn_dev.this_device, - "Failed to destroy VM %u\n", vm->vmid); - clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); - return ret; - } - acrn_vm_all_ram_unmap(vm); dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid); From b910a0206b59eb90ea8ff76d146f4c3156da61e9 Mon Sep 17 00:00:00 2001 From: Robert Foss Date: Mon, 28 Jun 2021 10:50:33 +0200 Subject: [PATCH 0955/1469] drm/msm/dpu: Fix sm8250_mdp register length The downstream dts lists this value as 0x494, and not 0x45c. Fixes: af776a3e1c30 ("drm/msm/dpu: add SM8250 to hw catalog") Signed-off-by: Robert Foss Reviewed-by: Dmitry Baryshkov Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210628085033.9905-1-robert.foss@linaro.org Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index d01c4c919504..704dace895cb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -296,7 +296,7 @@ static const struct dpu_mdp_cfg sc7180_mdp[] = { static const struct dpu_mdp_cfg sm8250_mdp[] = { { .name = "top_0", .id = MDP_TOP, - .base = 0x0, .len = 0x45C, + .base = 0x0, .len = 0x494, .features = 0, .highest_bank_bit = 0x3, /* TODO: 2 for LP_DDR4 */ .clk_ctrls[DPU_CLK_CTRL_VIG0] = { From bceddc2cb581dffc94370517f7eedbd9aa16c74b Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 7 Jul 2021 11:01:13 -0700 Subject: [PATCH 0956/1469] drm/msm: Fix display fault handling It turns out that when the display is enabled by the bootloader, we can get some transient iommu faults from the display. Which doesn't go over too well when we install a fault handler that is gpu specific. To avoid this, defer installing the fault handler until we get around to setting up per-process pgtables (which is adreno_smmu specific). The arm-smmu fallback error reporting is sufficient for reporting display related faults (and in fact was all we had prior to f8f934c180f629bb927a04fd90d) Reported-by: Dmitry Baryshkov Reported-by: Yassine Oudjana Fixes: 2a574cc05d38 ("drm/msm: Improve the a6xx page fault handler") Signed-off-by: Rob Clark Tested-by: John Stultz Tested-by: Yassine Oudjana Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210707180113.840741-1-robdclark@gmail.com Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_iommu.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index eed2a762e9dd..bcaddbba564d 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -142,6 +142,9 @@ static const struct iommu_flush_ops null_tlb_ops = { .tlb_add_page = msm_iommu_tlb_add_page, }; +static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg); + struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev); @@ -157,6 +160,13 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) if (!ttbr1_cfg) return ERR_PTR(-ENODEV); + /* + * Defer setting the fault handler until we have a valid adreno_smmu + * to avoid accidentially installing a GPU specific fault handler for + * the display's iommu + */ + iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); if (!pagetable) return ERR_PTR(-ENOMEM); @@ -300,7 +310,6 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - iommu_set_fault_handler(domain, msm_fault_handler, iommu); atomic_set(&iommu->pagetables, 0); From 7591c532b818ef4b8e3e635d842547c08b3a32b4 Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Tue, 13 Jul 2021 08:54:01 -0700 Subject: [PATCH 0957/1469] drm/msm/dp: use dp_ctrl_off_link_stream during PHY compliance test run DP cable should always connect to DPU during the entire PHY compliance testing run. Since DP PHY compliance test is executed at irq_hpd event context, dp_ctrl_off_link_stream() should be used instead of dp_ctrl_off(). dp_ctrl_off() is used for unplug event which is triggered when DP cable is dis connected. Changes in V2: -- add fixes statement Fixes: f21c8a276c2d ("drm/msm/dp: handle irq_hpd with sink_count = 0 correctly") Signed-off-by: Kuogee Hsieh Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1626191647-13901-2-git-send-email-khsieh@codeaurora.org Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/dp/dp_ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index ee221d835fa0..eaddfd739885 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1526,7 +1526,7 @@ static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl) * running. Add the global reset just before disabling the * link clocks and core clocks. */ - ret = dp_ctrl_off(&ctrl->dp_ctrl); + ret = dp_ctrl_off_link_stream(&ctrl->dp_ctrl); if (ret) { DRM_ERROR("failed to disable DP controller\n"); return ret; From f9a39932fa54b6421e751ada7a285da809146421 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 21 Jul 2021 19:44:34 -0700 Subject: [PATCH 0958/1469] drm/msm/dp: Initialize the INTF_CONFIG register Some bootloaders set the widebus enable bit in the INTF_CONFIG register, but configuration of widebus isn't yet supported ensure that the register has a known value, with widebus disabled. Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Signed-off-by: Bjorn Andersson Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20210722024434.3313167-1-bjorn.andersson@linaro.org Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/dp/dp_catalog.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index ca96e3514790..c0423e76eed7 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -771,6 +771,7 @@ int dp_catalog_panel_timing_cfg(struct dp_catalog *dp_catalog) dp_write_link(catalog, REG_DP_HSYNC_VSYNC_WIDTH_POLARITY, dp_catalog->width_blanking); dp_write_link(catalog, REG_DP_ACTIVE_HOR_VER, dp_catalog->dp_active); + dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0); return 0; } From afc9b8b6bab8d3d3a9ae67e1d64093ad626c92a0 Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Fri, 23 Jul 2021 09:55:39 -0700 Subject: [PATCH 0959/1469] drm/msm/dp: signal audio plugged change at dp_pm_resume There is a scenario that dp cable is unplugged from DUT during system suspended will cause audio option state does not match real connection state. Fix this problem by Signaling audio plugged change with realtime connection status at dp_pm_resume() so that audio option will be in correct state after system resumed. Changes in V2: -- correct Fixes tag commit id. Fixes: f591dbb5fb8c ("drm/msm/dp: power off DP phy at suspend") Signed-off-by: Kuogee Hsieh Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1627059339-12142-1-git-send-email-khsieh@codeaurora.org Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/dp/dp_display.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 051c1be1de7e..1d204a0fbdd2 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -1311,6 +1311,10 @@ static int dp_pm_resume(struct device *dev) else dp->dp_display.is_connected = false; + dp_display_handle_plugged_change(g_dp_display, + dp->dp_display.is_connected); + + mutex_unlock(&dp->event_mutex); return 0; From fc71c9e6f41f9912d22a75dfa76bc10811af7e22 Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Wed, 14 Jul 2021 11:28:56 -0400 Subject: [PATCH 0960/1469] drm/msm/dp: Initialize dp->aux->drm_dev before registration Avoids the following WARN: [ 3.009556] ------------[ cut here ]------------ [ 3.014306] WARNING: CPU: 7 PID: 109 at drivers/gpu/drm/drm_dp_helper.c:1796 drm_dp_aux_register+0xa4/0xac [ 3.024209] Modules linked in: [ 3.027351] CPU: 7 PID: 109 Comm: kworker/7:8 Not tainted 5.10.47 #69 [ 3.033958] Hardware name: Google Lazor (rev1 - 2) (DT) [ 3.039323] Workqueue: events deferred_probe_work_func [ 3.044596] pstate: 60c00009 (nZCv daif +PAN +UAO -TCO BTYPE=--) [ 3.050761] pc : drm_dp_aux_register+0xa4/0xac [ 3.055329] lr : dp_aux_register+0x40/0x88 [ 3.059538] sp : ffffffc010ad3920 [ 3.062948] x29: ffffffc010ad3920 x28: ffffffa64196ac70 [ 3.067239] mmc1: Command Queue Engine enabled [ 3.068406] x27: ffffffa64196ac68 x26: 0000000000000001 [ 3.068407] x25: 0000000000000002 x24: 0000000000000060 [ 3.068409] x23: ffffffa642ab3400 x22: ffffffe126c10e5b [ 3.068410] x21: ffffffa641dc3188 x20: ffffffa641963c10 [ 3.068412] x19: ffffffa642aba910 x18: 00000000ffff0a00 [ 3.068414] x17: 000000476f8e002a x16: 00000000000000b8 [ 3.073008] mmc1: new HS400 Enhanced strobe MMC card at address 0001 [ 3.078448] x15: ffffffffffffffff x14: ffffffffffffffff [ 3.078450] x13: 0000000000000030 x12: 0000000000000030 [ 3.078452] x11: 0101010101010101 x10: ffffffe12647a914 [ 3.078453] x9 : ffffffe12647a8cc x8 : 0000000000000000 [ 3.084452] mmcblk1: mmc1:0001 DA4032 29.1 GiB [ 3.089372] [ 3.089372] x7 : 6c6064717372fefe x6 : ffffffa642b11494 [ 3.089374] x5 : 0000000000000000 x4 : 6d006c657869ffff [ 3.089375] x3 : 000000006c657869 x2 : 000000000000000c [ 3.089376] x1 : ffffffe126c3ae3c x0 : ffffffa642aba910 [ 3.089381] Call trace: [ 3.094931] mmcblk1boot0: mmc1:0001 DA4032 partition 1 4.00 MiB [ 3.100291] drm_dp_aux_register+0xa4/0xac [ 3.100292] dp_aux_register+0x40/0x88 [ 3.100294] dp_display_bind+0x64/0xcc [ 3.100295] component_bind_all+0xdc/0x210 [ 3.100298] msm_drm_bind+0x1e8/0x5d4 [ 3.100301] try_to_bring_up_master+0x168/0x1b0 [ 3.105861] mmcblk1boot1: mmc1:0001 DA4032 partition 2 4.00 MiB [ 3.112282] __component_add+0xa0/0x158 [ 3.112283] component_add+0x1c/0x28 [ 3.112284] dp_display_probe+0x33c/0x380 [ 3.112286] platform_drv_probe+0x9c/0xbc [ 3.112287] really_probe+0x140/0x35c [ 3.112289] driver_probe_device+0x84/0xc0 [ 3.112292] __device_attach_driver+0x94/0xb0 [ 3.117967] mmcblk1rpmb: mmc1:0001 DA4032 partition 3 16.0 MiB, chardev (239:0) [ 3.123201] bus_for_each_drv+0x8c/0xd8 [ 3.123202] __device_attach+0xc4/0x150 [ 3.123204] device_initial_probe+0x1c/0x28 [ 3.123205] bus_probe_device+0x3c/0x9c [ 3.123206] deferred_probe_work_func+0x90/0xcc [ 3.123211] process_one_work+0x218/0x3ec [ 3.131976] mmcblk1: p1 p2 p3 p4 p5 p6 p7 p8 p9 p10 p11 p12 [ 3.134123] worker_thread+0x288/0x3e8 [ 3.134124] kthread+0x148/0x1b0 [ 3.134127] ret_from_fork+0x10/0x30 [ 3.134128] ---[ end trace cfb9fce3f70f824d ]--- Signed-off-by: Sean Paul Reviewed-by: Abhinav Kumar Link: https://lore.kernel.org/r/20210714152910.55093-1-sean@poorly.run Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/dp/dp_display.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 1d204a0fbdd2..867388a399ad 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -219,6 +219,7 @@ static int dp_display_bind(struct device *dev, struct device *master, goto end; } + dp->aux->drm_dev = drm; rc = dp_aux_register(dp->aux); if (rc) { DRM_ERROR("DRM DP AUX register failed\n"); From 48e8a7b5a551f956002b60d2095bdfb58db96e59 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 24 Jun 2021 17:43:03 +0100 Subject: [PATCH 0961/1469] perf cs-etm: Split --dump-raw-trace by AUX records Currently --dump-raw-trace skips queueing and splitting buffers because of an early exit condition in cs_etm__process_auxtrace_info(). Once that is removed we can print the split data by using the queues and searching for split buffers with the same reference as the one that is currently being processed. This keeps the same behaviour of dumping in file order when an AUXTRACE event appears, rather than moving trace dump to where AUX records are in the file. There will be a newline and size printout for each fragment. For example this buffer is comprised of two AUX records, but was printed as one: 0 0 0x8098 [0x30]: PERF_RECORD_AUXTRACE size: 0xa0 offset: 0 ref: 0x491a4dfc52fc0e6e idx: 0 t . ... CoreSight ETM Trace data: size 160 bytes Idx:0; ID:10; I_ASYNC : Alignment Synchronisation. Idx:12; ID:10; I_TRACE_INFO : Trace Info.; INFO=0x0 { CC.0 } Idx:17; ID:10; I_ADDR_L_64IS0 : Address, Long, 64 bit, IS0.; Addr=0x0000000000000000; Idx:80; ID:10; I_ASYNC : Alignment Synchronisation. Idx:92; ID:10; I_TRACE_INFO : Trace Info.; INFO=0x0 { CC.0 } Idx:97; ID:10; I_ADDR_L_64IS0 : Address, Long, 64 bit, IS0.; Addr=0xFFFFDE2AD3FD76D4; But is now printed as two fragments: 0 0 0x8098 [0x30]: PERF_RECORD_AUXTRACE size: 0xa0 offset: 0 ref: 0x491a4dfc52fc0e6e idx: 0 t . ... CoreSight ETM Trace data: size 80 bytes Idx:0; ID:10; I_ASYNC : Alignment Synchronisation. Idx:12; ID:10; I_TRACE_INFO : Trace Info.; INFO=0x0 { CC.0 } Idx:17; ID:10; I_ADDR_L_64IS0 : Address, Long, 64 bit, IS0.; Addr=0x0000000000000000; . ... CoreSight ETM Trace data: size 80 bytes Idx:80; ID:10; I_ASYNC : Alignment Synchronisation. Idx:92; ID:10; I_TRACE_INFO : Trace Info.; INFO=0x0 { CC.0 } Idx:97; ID:10; I_ADDR_L_64IS0 : Address, Long, 64 bit, IS0.; Addr=0xFFFFDE2AD3FD76D4; Decoding errors that appeared in problematic files are now not present, for example: Idx:808; ID:1c; I_BAD_SEQUENCE : Invalid Sequence in packet.[I_ASYNC] ... PKTP_ETMV4I_0016 : 0x0014 (OCSD_ERR_INVALID_PCKT_HDR) [Invalid packet header]; TrcIdx=822 Signed-off-by: James Clark Reviewed-by: Mathieu Poirier Tested-by: Leo Yan Cc: Al Grant Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Branislav Rankov Cc: Denis Nikitin Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20210624164303.28632-3-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 22f8326547eb..bc1f64873c8f 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2434,6 +2434,22 @@ static int cs_etm__process_event(struct perf_session *session, return 0; } +static void dump_queued_data(struct cs_etm_auxtrace *etm, + struct perf_record_auxtrace *event) +{ + struct auxtrace_buffer *buf; + unsigned int i; + /* + * Find all buffers with same reference in the queues and dump them. + * This is because the queues can contain multiple entries of the same + * buffer that were split on aux records. + */ + for (i = 0; i < etm->queues.nr_queues; ++i) + list_for_each_entry(buf, &etm->queues.queue_array[i].head, list) + if (buf->reference == event->reference) + cs_etm__dump_event(etm, buf); +} + static int cs_etm__process_auxtrace_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool __maybe_unused) @@ -2466,7 +2482,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, cs_etm__dump_event(etm, buffer); auxtrace_buffer__put_data(buffer); } - } + } else if (dump_trace) + dump_queued_data(etm, &event->auxtrace); return 0; } @@ -3042,7 +3059,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); - return 0; } err = cs_etm__synth_events(etm, session); From 8e3341257e3b5774ec8cd3ef1ba0c0d3fada322b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 27 Jul 2021 17:25:01 +0300 Subject: [PATCH 0962/1469] Revert "thunderbolt: Hide authorized attribute if router does not support PCIe tunnels" This reverts commit 6f3badead6a078cf3c71f381f9d84ac922984a00. It turns out bolt depends on having authorized attribute visible under each device. Hiding it makes bolt crash as several people have reported on various bug trackers. For this reason revert the commit. Link: https://gitlab.freedesktop.org/bolt/bolt/-/issues/174 Link: https://bugzilla.redhat.com/show_bug.cgi?id=1979765 Link: https://bugs.archlinux.org/task/71569 Cc: stable@vger.kernel.org Cc: Christian Kellner Fixes: 6f3badead6a0 ("thunderbolt: Hide authorized attribute if router does not support PCIe tunnels") Signed-off-by: Mika Westerberg Link: https://lore.kernel.org/r/20210727142501.27476-1-mika.westerberg@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/switch.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 83b1ef3d5d03..10d6b228cc94 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1875,18 +1875,6 @@ static struct attribute *switch_attrs[] = { NULL, }; -static bool has_port(const struct tb_switch *sw, enum tb_port_type type) -{ - const struct tb_port *port; - - tb_switch_for_each_port(sw, port) { - if (!port->disabled && port->config.type == type) - return true; - } - - return false; -} - static umode_t switch_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) { @@ -1895,8 +1883,7 @@ static umode_t switch_attr_is_visible(struct kobject *kobj, if (attr == &dev_attr_authorized.attr) { if (sw->tb->security_level == TB_SECURITY_NOPCIE || - sw->tb->security_level == TB_SECURITY_DPONLY || - !has_port(sw, TB_TYPE_PCIE_UP)) + sw->tb->security_level == TB_SECURITY_DPONLY) return 0; } else if (attr == &dev_attr_device.attr) { if (!sw->device) From c07d5c9226980ca5ae21c6a2714baa95be2ce164 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 20 Jul 2021 23:10:19 +0800 Subject: [PATCH 0963/1469] perf pmu: Fix alias matching Commit c47a5599eda324ba ("perf tools: Fix pattern matching for same substring in different PMU type"), may have fixed some alias matching, but has broken some others. Firstly it cannot handle the simple scenario of PMU name in form pmu_name{digits} - it can only handle pmu_name_{digits}. Secondly it cannot handle more complex matching in the case where we have multiple tokens. In this scenario, the code failed to realise that we may examine multiple substrings in the PMU name. Fix in two ways: - Change perf_pmu__valid_suffix() to accept a PMU name without '_' in the suffix - Only pay attention to perf_pmu__valid_suffix() for the final token Also add const qualifiers as necessary to avoid casting. Fixes: c47a5599eda324ba ("perf tools: Fix pattern matching for same substring in different PMU type") Signed-off-by: John Garry Tested-by: Jin Yao Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/1626793819-79090-1-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index a1bd7007a8b4..fc683bc41715 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -742,9 +742,13 @@ struct pmu_events_map *__weak pmu_events_map__find(void) return perf_pmu__find_map(NULL); } -static bool perf_pmu__valid_suffix(char *pmu_name, char *tok) +/* + * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name + * to be valid. + */ +static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok) { - char *p; + const char *p; if (strncmp(pmu_name, tok, strlen(tok))) return false; @@ -753,12 +757,16 @@ static bool perf_pmu__valid_suffix(char *pmu_name, char *tok) if (*p == 0) return true; - if (*p != '_') - return false; + if (*p == '_') + ++p; - ++p; - if (*p == 0 || !isdigit(*p)) - return false; + /* Ensure we end in a number */ + while (1) { + if (!isdigit(*p)) + return false; + if (*(++p) == 0) + break; + } return true; } @@ -789,12 +797,19 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name) * match "socket" in "socketX_pmunameY" and then "pmuname" in * "pmunameY". */ - for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) { + while (1) { + char *next_tok = strtok_r(NULL, ",", &tmp); + name = strstr(name, tok); - if (!name || !perf_pmu__valid_suffix((char *)name, tok)) { + if (!name || + (!next_tok && !perf_pmu__valid_suffix(name, tok))) { res = false; goto out; } + if (!next_tok) + break; + tok = next_tok; + name += strlen(tok); } res = true; From 91e273712ab8dd8c31924ac7714b21e011137e98 Mon Sep 17 00:00:00 2001 From: Pratik Vishwakarma Date: Fri, 23 Jul 2021 18:08:40 +0530 Subject: [PATCH 0964/1469] drm/amdgpu: Check pmops for desired suspend state [Why] User might change the suspend behaviour from OS. [How] Check with pm for target suspend state and set s0ix flag only for s2idle state. v2: User might change default suspend state, use target state v3: squash in build fix Suggested-by: Lijo Lazar Signed-off-by: Pratik Vishwakarma Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 84a1b4bc9bb4..6cc0d4fa4d0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -1042,7 +1043,7 @@ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) #if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE) if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { if (adev->flags & AMD_IS_APU) - return true; + return pm_suspend_target_state == PM_SUSPEND_TO_IDLE; } #endif return false; From c8f8e96805b54968b4d1d54850f87fc39128a532 Mon Sep 17 00:00:00 2001 From: Victor Lu Date: Thu, 8 Jul 2021 14:50:48 -0400 Subject: [PATCH 0965/1469] drm/amd/display: Guard DST_Y_PREFETCH register overflow in DCN21 [why] DST_Y_PREFETCH can overflow when DestinationLinesForPrefetch values are too large due to the former being limited to 8 bits. [how] Set the maximum value of DestinationLinesForPrefetch to be 255 * refclk period. Reviewed-by: Laktyushkin Dmytro Acked-by: Solomon Chiu Signed-off-by: Victor Lu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index d25a7d38d21f..6655bb99fdfd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -841,6 +841,9 @@ static bool CalculatePrefetchSchedule( else *DestinationLinesForPrefetch = dst_y_prefetch_equ; + // Limit to prevent overflow in DST_Y_PREFETCH register + *DestinationLinesForPrefetch = dml_min(*DestinationLinesForPrefetch, 63.75); + dml_print("DML: VStartup: %d\n", VStartup); dml_print("DML: TCalc: %f\n", TCalc); dml_print("DML: TWait: %f\n", TWait); From 8d177577cd9118c29960401a6de9dc4db00f2052 Mon Sep 17 00:00:00 2001 From: Victor Lu Date: Tue, 6 Jul 2021 15:45:11 -0400 Subject: [PATCH 0966/1469] drm/amd/display: Add missing DCN21 IP parameter [why] IP parameter min_meta_chunk_size_bytes is read for bandwidth calculations but it was never defined. [how] Define min_meta_chunk_size_bytes and initialize value to 256. Reviewed-by: Laktyushkin Dmytro Acked-by: Solomon Chiu Signed-off-by: Victor Lu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index f3d98e3ba624..bf0a198eae15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -109,6 +109,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = { .max_page_table_levels = 4, .pte_chunk_size_kbytes = 2, .meta_chunk_size_kbytes = 2, + .min_meta_chunk_size_bytes = 256, .writeback_chunk_size_kbytes = 2, .line_buffer_size_bits = 789504, .is_line_buffer_bpp_fixed = 0, From b53e041d8e4308f7324999398aec092dbcb130f5 Mon Sep 17 00:00:00 2001 From: Dale Zhao Date: Fri, 16 Jul 2021 09:38:17 +0800 Subject: [PATCH 0967/1469] drm/amd/display: ensure dentist display clock update finished in DCN20 [Why] We don't check DENTIST_DISPCLK_CHG_DONE to ensure dentist display clockis updated to target value. In some scenarios with large display clock margin, it will deliver unfinished display clock and cause issues like display black screen. [How] Checking DENTIST_DISPCLK_CHG_DONE to ensure display clock has been update to target value before driver do other clock related actions. Reviewed-by: Cyr Aric Acked-by: Solomon Chiu Signed-off-by: Dale Zhao Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 6e0c5c664fdc..a5331b96f551 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -197,7 +197,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider); -// REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 5, 100); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000); REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider); REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100); From f2ad3accefc63e72e9932e141c21875cc04beec8 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 21 Jul 2021 18:11:51 -0400 Subject: [PATCH 0968/1469] drm/amdgpu/display: only enable aux backlight control for OLED panels We've gotten a number of reports about backlight control not working on panels which indicate that they use aux backlight control. A recent patch: commit 2d73eabe2984a435737498ab39bb1500a9ffe9a9 Author: Camille Cho Date: Thu Jul 8 18:28:37 2021 +0800 drm/amd/display: Only set default brightness for OLED [Why] We used to unconditionally set backlight path as AUX for panels capable of backlight adjustment via DPCD in set default brightness. [How] This should be limited to OLED panel only since we control backlight via PWM path for SDR mode in LCD HDR panel. Reviewed-by: Krunoslav Kovac Acked-by: Rodrigo Siqueira Signed-off-by: Camille Cho Signed-off-by: Alex Deucher Changes some other code to only use aux for backlight control on OLED panels. The commit message seems to indicate that PWM should be used for SDR mode on HDR panels. Do something similar for backlight control in general. This may need to be revisited if and when HDR started to get used. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1438 Bug: https://bugzilla.kernel.org/show_bug.cgi?id=213715 Reviewed-by: Roman Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d3a2a5ff57e9..b53f49a23ddc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2429,9 +2429,9 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll; min_cll = conn_base->hdr_sink_metadata.hdmi_type1.min_cll; - if (caps->ext_caps->bits.oled == 1 || + if (caps->ext_caps->bits.oled == 1 /*|| caps->ext_caps->bits.sdr_aux_backlight_control == 1 || - caps->ext_caps->bits.hdr_aux_backlight_control == 1) + caps->ext_caps->bits.hdr_aux_backlight_control == 1*/) caps->aux_support = true; if (amdgpu_backlight == 0) From ec30ce41f03820b6289513344b4281ca3a1151f4 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Sun, 25 Jul 2021 16:49:01 +0000 Subject: [PATCH 0969/1469] maintainers: add bugs and chat URLs for amdgpu MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add links to the issue tracker and the IRC channel for the amdgpu driver. Signed-off-by: Simon Ser Cc: Alex Deucher Cc: Christian König Cc: Pan Xinhui Signed-off-by: Alex Deucher --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 19135a9d778e..056966c9aac9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15468,6 +15468,8 @@ M: Pan, Xinhui L: amd-gfx@lists.freedesktop.org S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git +B: https://gitlab.freedesktop.org/drm/amd/-/issues +C: irc://irc.oftc.net/radeon F: drivers/gpu/drm/amd/ F: drivers/gpu/drm/radeon/ F: include/uapi/drm/amdgpu_drm.h From 773af69121ecc6c53d192661af8d53bb3db028ae Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 27 Jul 2021 10:25:55 -0600 Subject: [PATCH 0970/1469] io_uring: always reissue from task_work context As a safeguard, if we're going to queue async work, do it from task_work from the original task. This ensures that we can always sanely create threads, regards of what the reissue context may be. Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index a4331deb0427..6ba101cd4661 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2060,6 +2060,12 @@ static void io_req_task_queue(struct io_kiocb *req) io_req_task_work_add(req); } +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_async_work; + io_req_task_work_add(req); +} + static inline void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2248,7 +2254,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, !(req->flags & REQ_F_DONT_REISSUE)) { req->iopoll_completed = 0; req_ref_get(req); - io_queue_async_work(req); + io_req_task_queue_reissue(req); continue; } @@ -2771,7 +2777,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { req_ref_get(req); - io_queue_async_work(req); + io_req_task_queue_reissue(req); } else { int cflags = 0; From ec6446d5304b3c3dd692a1e244df7e40bbb5af36 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Tue, 13 Jul 2021 13:12:16 +0530 Subject: [PATCH 0971/1469] fpga: dfl: fme: Fix cpu hotplug issue in performance reporting The performance reporting driver added cpu hotplug feature but it didn't add pmu migration call in cpu offline function. This can create an issue incase the current designated cpu being used to collect fme pmu data got offline, as based on current code we are not migrating fme pmu to new target cpu. Because of that perf will still try to fetch data from that offline cpu and hence we will not get counter data. Patch fixed this issue by adding pmu_migrate_context call in fme_perf_offline_cpu function. Fixes: 724142f8c42a ("fpga: dfl: fme: add performance reporting support") Cc: stable@vger.kernel.org Tested-by: Xu Yilun Acked-by: Wu Hao Signed-off-by: Kajol Jain Signed-off-by: Moritz Fischer --- drivers/fpga/dfl-fme-perf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/fpga/dfl-fme-perf.c b/drivers/fpga/dfl-fme-perf.c index 4299145ef347..587c82be12f7 100644 --- a/drivers/fpga/dfl-fme-perf.c +++ b/drivers/fpga/dfl-fme-perf.c @@ -953,6 +953,8 @@ static int fme_perf_offline_cpu(unsigned int cpu, struct hlist_node *node) return 0; priv->cpu = target; + perf_pmu_migrate_context(&priv->pmu, cpu, target); + return 0; } From 4ee107c514139960682cc0f3623a24e86fda1a13 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 27 Jul 2021 17:26:13 +0800 Subject: [PATCH 0972/1469] clk: qcom: smd-rpm: Fix MSM8936 RPM_SMD_PCNOC_A_CLK Commit a0384ecfe2aa ("clk: qcom: smd-rpm: De-duplicate identical entries") introduces the following regression on MSM8936/MSM8939, as RPM_SMD_PCNOC_A_CLK gets pointed to pcnoc_clk by mistake. Fix it by correcting the clock to pcnoc_a_clk. [ 1.307363] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 1.313593] Mem abort info: [ 1.322512] ESR = 0x96000004 [ 1.325132] EC = 0x25: DABT (current EL), IL = 32 bits [ 1.338872] SET = 0, FnV = 0 [ 1.355483] EA = 0, S1PTW = 0 [ 1.368702] FSC = 0x04: level 0 translation fault [ 1.383294] Data abort info: [ 1.398292] ISV = 0, ISS = 0x00000004 [ 1.398297] CM = 0, WnR = 0 [ 1.398301] [0000000000000000] user address but active_mm is swapper [ 1.404193] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 1.420596] Modules linked in: [ 1.420604] CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.14.0-rc3+ #198 [ 1.441010] pc : __clk_register+0x48/0x780 [ 1.446045] lr : __clk_register+0x3c/0x780 [ 1.449953] sp : ffff800010063440 [ 1.454031] x29: ffff800010063440 x28: 0000000000000004 x27: 0000000000000066 [ 1.457423] x26: 0000000000000001 x25: 000000007fffffff x24: ffff800010f9f388 [ 1.464540] x23: ffff00007fc12a90 x22: ffff0000034b2010 x21: 0000000000000000 [ 1.471658] x20: ffff800010f9fff8 x19: ffff00000152a700 x18: 0000000000000001 [ 1.478778] x17: ffff00007fbd40c8 x16: 0000000000000460 x15: 0000000000000465 [ 1.485895] x14: ffffffffffffffff x13: 746e756f635f7265 x12: 696669746f6e5f6b [ 1.493013] x11: 0000000000000006 x10: 0000000000000000 x9 : 0000000000000000 [ 1.500131] x8 : ffff00000152a800 x7 : 0000000000000000 x6 : 000000000000003f [ 1.507249] x5 : 0000000000000040 x4 : 0000000000000000 x3 : 0000000000000004 [ 1.514367] x2 : 0000000000000000 x1 : 0000000000000cc0 x0 : ffff00000152a700 [ 1.521486] Call trace: [ 1.528598] __clk_register+0x48/0x780 [ 1.530855] clk_hw_register+0x20/0x60 [ 1.534674] devm_clk_hw_register+0x50/0xa8 [ 1.538408] rpm_smd_clk_probe+0x1a4/0x260 [ 1.542488] platform_probe+0x68/0xd8 [ 1.546653] really_probe+0x140/0x2f8 [ 1.550386] __driver_probe_device+0x78/0xe0 [ 1.554033] driver_probe_device+0x80/0x110 [ 1.558373] __device_attach_driver+0x90/0xe0 [ 1.562280] bus_for_each_drv+0x78/0xc8 [ 1.566793] __device_attach+0xf0/0x150 [ 1.570438] device_initial_probe+0x14/0x20 [ 1.574259] bus_probe_device+0x9c/0xa8 [ 1.578425] device_add+0x378/0x870 [ 1.582243] of_device_add+0x44/0x60 [ 1.585716] of_platform_device_create_pdata+0xc0/0x110 [ 1.589538] of_platform_bus_create+0x17c/0x388 [ 1.594485] of_platform_populate+0x50/0xf0 [ 1.598998] qcom_smd_rpm_probe+0xd4/0x128 [ 1.603164] rpmsg_dev_probe+0xbc/0x1a8 [ 1.607330] really_probe+0x140/0x2f8 [ 1.611063] __driver_probe_device+0x78/0xe0 [ 1.614883] driver_probe_device+0x80/0x110 [ 1.619224] __device_attach_driver+0x90/0xe0 [ 1.623131] bus_for_each_drv+0x78/0xc8 [ 1.627643] __device_attach+0xf0/0x150 [ 1.631289] device_initial_probe+0x14/0x20 [ 1.635109] bus_probe_device+0x9c/0xa8 [ 1.639275] device_add+0x378/0x870 [ 1.643095] device_register+0x20/0x30 [ 1.646567] rpmsg_register_device+0x54/0x90 [ 1.650387] qcom_channel_state_worker+0x168/0x288 [ 1.654814] process_one_work+0x1a0/0x328 [ 1.659415] worker_thread+0x4c/0x420 [ 1.663494] kthread+0x150/0x160 [ 1.667138] ret_from_fork+0x10/0x18 [ 1.670442] Code: 97f56b92 b40034a0 aa0003f3 52819801 (f94002a0) [ 1.674004] ---[ end trace 412fa6f47384cdfe ]--- Fixes: a0384ecfe2aa ("clk: qcom: smd-rpm: De-duplicate identical entries") Signed-off-by: Shawn Guo Link: https://lore.kernel.org/r/20210727092613.23056-1-shawn.guo@linaro.org Signed-off-by: Stephen Boyd --- drivers/clk/qcom/clk-smd-rpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 800b2fef1887..b2c142f3a649 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -467,7 +467,7 @@ DEFINE_CLK_SMD_RPM(msm8936, sysmmnoc_clk, sysmmnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, static struct clk_smd_rpm *msm8936_clks[] = { [RPM_SMD_PCNOC_CLK] = &msm8916_pcnoc_clk, - [RPM_SMD_PCNOC_A_CLK] = &msm8916_pcnoc_clk, + [RPM_SMD_PCNOC_A_CLK] = &msm8916_pcnoc_a_clk, [RPM_SMD_SNOC_CLK] = &msm8916_snoc_clk, [RPM_SMD_SNOC_A_CLK] = &msm8916_snoc_a_clk, [RPM_SMD_BIMC_CLK] = &msm8916_bimc_clk, From bb7262b295472eb6858b5c49893954794027cd84 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 6 Dec 2020 22:40:07 +0100 Subject: [PATCH 0973/1469] timers: Move clearing of base::timer_running under base:: Lock syzbot reported KCSAN data races vs. timer_base::timer_running being set to NULL without holding base::lock in expire_timers(). This looks innocent and most reads are clearly not problematic, but Frederic identified an issue which is: int data = 0; void timer_func(struct timer_list *t) { data = 1; } CPU 0 CPU 1 ------------------------------ -------------------------- base = lock_timer_base(timer, &flags); raw_spin_unlock(&base->lock); if (base->running_timer != timer) call_timer_fn(timer, fn, baseclk); ret = detach_if_pending(timer, base, true); base->running_timer = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); raw_spin_lock(&base->lock); x = data; If the timer has previously executed on CPU 1 and then CPU 0 can observe base->running_timer == NULL and returns, assuming the timer has completed, but it's not guaranteed on all architectures. The comment for del_timer_sync() makes that guarantee. Moving the assignment under base->lock prevents this. For non-RT kernel it's performance wise completely irrelevant whether the store happens before or after taking the lock. For an RT kernel moving the store under the lock requires an extra unlock/lock pair in the case that there is a waiter for the timer, but that's not the end of the world. Reported-by: syzbot+aa7c2385d46c5eba0b89@syzkaller.appspotmail.com Reported-by: syzbot+abea4558531bae1ba9fe@syzkaller.appspotmail.com Fixes: 030dcdd197d7 ("timers: Prepare support for PREEMPT_RT") Signed-off-by: Thomas Gleixner Tested-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/87lfea7gw8.fsf@nanos.tec.linutronix.de Cc: stable@vger.kernel.org --- kernel/time/timer.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 9eb11c2209e5..e3d2c23c413d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1265,8 +1265,10 @@ static inline void timer_base_unlock_expiry(struct timer_base *base) static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { + raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); + raw_spin_lock_irq(&base->lock); } } @@ -1457,14 +1459,14 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); - base->running_timer = NULL; raw_spin_lock(&base->lock); + base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); + raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); - raw_spin_lock_irq(&base->lock); } } } From 8373cd38a8888549ace7c7617163a2e826970a92 Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Tue, 27 Jul 2021 22:03:50 +0800 Subject: [PATCH 0974/1469] net: hns3: change the method of obtaining default ptp cycle The ptp cycle is related to the hardware, so it may cause compatibility issues if a fixed value is used in driver. Therefore, the method of obtaining this value is changed to read from the register rather than use a fixed value in driver. Fixes: 0bf5eb788512 ("net: hns3: add support for PTP") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_ptp.c | 36 +++++++++++++++---- .../hisilicon/hns3/hns3pf/hclge_ptp.h | 10 ++++-- 2 files changed, 37 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 3b1f84502e36..befa9bcc2f2f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -5,9 +5,27 @@ #include "hclge_main.h" #include "hnae3.h" +static int hclge_ptp_get_cycle(struct hclge_dev *hdev) +{ + struct hclge_ptp *ptp = hdev->ptp; + + ptp->cycle.quo = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG) & + HCLGE_PTP_CYCLE_QUO_MASK; + ptp->cycle.numer = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); + ptp->cycle.den = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + + if (ptp->cycle.den == 0) { + dev_err(&hdev->pdev->dev, "invalid ptp cycle denominator!\n"); + return -EINVAL; + } + + return 0; +} + static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) { struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle; u64 adj_val, adj_base, diff; unsigned long flags; bool is_neg = false; @@ -18,7 +36,7 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) is_neg = true; } - adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT; + adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer; adj_val = adj_base * ppb; diff = div_u64(adj_val, 1000000000ULL); @@ -29,16 +47,16 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) /* This clock cycle is defined by three part: quotient, numerator * and denominator. For example, 2.5ns, the quotient is 2, - * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator - * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT. + * denominator is fixed to ptp->cycle.den, and numerator + * is 0.5 * ptp->cycle.den. */ - quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator); + quo = div_u64_rem(adj_val, cycle->den, &numerator); spin_lock_irqsave(&hdev->ptp->lock, flags); - writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); + writel(quo & HCLGE_PTP_CYCLE_QUO_MASK, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); - writel(HCLGE_PTP_CYCLE_ADJ_UNIT, - hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + writel(cycle->den, hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); writel(HCLGE_PTP_CYCLE_ADJ_EN, hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG); spin_unlock_irqrestore(&hdev->ptp->lock, flags); @@ -475,6 +493,10 @@ int hclge_ptp_init(struct hclge_dev *hdev) ret = hclge_ptp_create_clock(hdev); if (ret) return ret; + + ret = hclge_ptp_get_cycle(hdev); + if (ret) + return ret; } ret = hclge_ptp_int_en(hdev, true); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h index 5a202b775471..dbf5f4c08019 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h @@ -29,6 +29,7 @@ #define HCLGE_PTP_TIME_ADJ_REG 0x60 #define HCLGE_PTP_TIME_ADJ_EN BIT(0) #define HCLGE_PTP_CYCLE_QUO_REG 0x64 +#define HCLGE_PTP_CYCLE_QUO_MASK GENMASK(7, 0) #define HCLGE_PTP_CYCLE_DEN_REG 0x68 #define HCLGE_PTP_CYCLE_NUM_REG 0x6C #define HCLGE_PTP_CYCLE_CFG_REG 0x70 @@ -37,9 +38,7 @@ #define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78 #define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C -#define HCLGE_PTP_CYCLE_ADJ_BASE 2 #define HCLGE_PTP_CYCLE_ADJ_MAX 500000000 -#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000 #define HCLGE_PTP_SEC_H_OFFSET 32u #define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0) @@ -47,6 +46,12 @@ #define HCLGE_PTP_FLAG_TX_EN 1 #define HCLGE_PTP_FLAG_RX_EN 2 +struct hclge_ptp_cycle { + u32 quo; + u32 numer; + u32 den; +}; + struct hclge_ptp { struct hclge_dev *hdev; struct ptp_clock *clock; @@ -58,6 +63,7 @@ struct hclge_ptp { spinlock_t lock; /* protects ptp registers */ u32 ptp_cfg; u32 last_tx_seqid; + struct hclge_ptp_cycle cycle; unsigned long tx_start; unsigned long tx_cnt; unsigned long tx_skipped; From 76b4f357d0e7d8f6f0013c733e6cba1773c266d3 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 1 Jul 2021 17:41:00 +0200 Subject: [PATCH 0975/1469] x86/kvm: fix vcpu-id indexed array sizes KVM_MAX_VCPU_ID is the maximum vcpu-id of a guest, and not the number of vcpu-ids. Fix array indexed by vcpu-id to have KVM_MAX_VCPU_ID+1 elements. Note that this is currently no real problem, as KVM_MAX_VCPU_ID is an odd number, resulting in always enough padding being available at the end of those arrays. Nevertheless this should be fixed in order to avoid rare problems in case someone is using an even number for KVM_MAX_VCPU_ID. Signed-off-by: Juergen Gross Message-Id: <20210701154105.23215-2-jgross@suse.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 2 +- arch/x86/kvm/ioapic.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 698969e18fe3..ff005fe738a4 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 660401700075..11e4065e1617 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -43,13 +43,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_ID + 1]; }; From 15b7b737deb30e1f8f116a08e723173b55ebd2f3 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Tue, 13 Jul 2021 22:09:56 +0000 Subject: [PATCH 0976/1469] KVM: selftests: Fix missing break in dirty_log_perf_test arg parsing There is a missing break statement which causes a fallthrough to the next statement where optarg will be null and a segmentation fault will be generated. Fixes: 9e965bb75aae ("KVM: selftests: Add backing src parameter to dirty_log_perf_test") Reviewed-by: Ben Gardon Signed-off-by: David Matlack Message-Id: <20210713220957.3493520-6-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/dirty_log_perf_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 04a2641261be..80cbd3a748c0 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -312,6 +312,7 @@ int main(int argc, char *argv[]) break; case 'o': p.partition_vcpu_memory_access = false; + break; case 's': p.backing_src = parse_backing_src_type(optarg); break; From c33e05d9b067433252b1008d2f37bf64e11151f1 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Tue, 13 Jul 2021 22:09:57 +0000 Subject: [PATCH 0977/1469] KVM: selftests: Introduce access_tracking_perf_test This test measures the performance effects of KVM's access tracking. Access tracking is driven by the MMU notifiers test_young, clear_young, and clear_flush_young. These notifiers do not have a direct userspace API, however the clear_young notifier can be triggered by marking a pages as idle in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to enable access tracking on guest memory. To measure performance this test runs a VM with a configurable number of vCPUs that each touch every page in disjoint regions of memory. Performance is measured in the time it takes all vCPUs to finish touching their predefined region. Example invocation: $ ./access_tracking_perf_test -v 8 Testing guest mode: PA-bits:ANY, VA-bits:48, 4K pages guest physical test memory offset: 0xffdfffff000 Populating memory : 1.337752570s Writing to populated memory : 0.010177640s Reading from populated memory : 0.009548239s Mark memory idle : 23.973131748s Writing to idle memory : 0.063584496s Mark memory idle : 24.924652964s Reading from idle memory : 0.062042814s Breaking down the results: * "Populating memory": The time it takes for all vCPUs to perform the first write to every page in their region. * "Writing to populated memory" / "Reading from populated memory": The time it takes for all vCPUs to write and read to every page in their region after it has been populated. This serves as a control for the later results. * "Mark memory idle": The time it takes for every vCPU to mark every page in their region as idle through page_idle. * "Writing to idle memory" / "Reading from idle memory": The time it takes for all vCPUs to write and read to every page in their region after it has been marked idle. This test should be portable across architectures but it is only enabled for x86_64 since that's all I have tested. Reviewed-by: Ben Gardon Signed-off-by: David Matlack Message-Id: <20210713220957.3493520-7-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/access_tracking_perf_test.c | 429 ++++++++++++++++++ 3 files changed, 431 insertions(+) create mode 100644 tools/testing/selftests/kvm/access_tracking_perf_test.c diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 06a351b4f93b..0709af0144c8 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -38,6 +38,7 @@ /x86_64/xen_vmcall_test /x86_64/xss_msr_test /x86_64/vmx_pmu_msrs_test +/access_tracking_perf_test /demand_paging_test /dirty_log_test /dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index b853be2ae3c6..5832f510a16c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test +TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c new file mode 100644 index 000000000000..e2baa187a21e --- /dev/null +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * access_tracking_perf_test + * + * Copyright (C) 2021, Google, Inc. + * + * This test measures the performance effects of KVM's access tracking. + * Access tracking is driven by the MMU notifiers test_young, clear_young, and + * clear_flush_young. These notifiers do not have a direct userspace API, + * however the clear_young notifier can be triggered by marking a pages as idle + * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to + * enable access tracking on guest memory. + * + * To measure performance this test runs a VM with a configurable number of + * vCPUs that each touch every page in disjoint regions of memory. Performance + * is measured in the time it takes all vCPUs to finish touching their + * predefined region. + * + * Note that a deterministic correctness test of access tracking is not possible + * by using page_idle as it exists today. This is for a few reasons: + * + * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This + * means subsequent guest accesses are not guaranteed to see page table + * updates made by KVM until some time in the future. + * + * 2. page_idle only operates on LRU pages. Newly allocated pages are not + * immediately allocated to LRU lists. Instead they are held in a "pagevec", + * which is drained to LRU lists some time in the future. There is no + * userspace API to force this drain to occur. + * + * These limitations are worked around in this test by using a large enough + * region of memory for each vCPU such that the number of translations cached in + * the TLB and the number of pages held in pagevecs are a small fraction of the + * overall workload. And if either of those conditions are not true this test + * will fail rather than silently passing. + */ +#include +#include +#include +#include +#include +#include + +#include "kvm_util.h" +#include "test_util.h" +#include "perf_test_util.h" +#include "guest_modes.h" + +/* Global variable used to synchronize all of the vCPU threads. */ +static int iteration = -1; + +/* Defines what vCPU threads should do during a given iteration. */ +static enum { + /* Run the vCPU to access all its memory. */ + ITERATION_ACCESS_MEMORY, + /* Mark the vCPU's memory idle in page_idle. */ + ITERATION_MARK_IDLE, +} iteration_work; + +/* Set to true when vCPU threads should exit. */ +static bool done; + +/* The iteration that was last completed by each vCPU. */ +static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; + +/* Whether to overlap the regions of memory vCPUs access. */ +static bool overlap_memory_access; + +struct test_params { + /* The backing source for the region of memory. */ + enum vm_mem_backing_src_type backing_src; + + /* The amount of memory to allocate for each vCPU. */ + uint64_t vcpu_memory_bytes; + + /* The number of vCPUs to create in the VM. */ + int vcpus; +}; + +static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) +{ + uint64_t value; + off_t offset = index * sizeof(value); + + TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value), + "pread from %s offset 0x%" PRIx64 " failed!", + filename, offset); + + return value; + +} + +#define PAGEMAP_PRESENT (1ULL << 63) +#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1) + +static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) +{ + uint64_t hva = (uint64_t) addr_gva2hva(vm, gva); + uint64_t entry; + uint64_t pfn; + + entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize()); + if (!(entry & PAGEMAP_PRESENT)) + return 0; + + pfn = entry & PAGEMAP_PFN_MASK; + if (!pfn) { + print_skip("Looking up PFNs requires CAP_SYS_ADMIN"); + exit(KSFT_SKIP); + } + + return pfn; +} + +static bool is_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64); + + return !!((bits >> (pfn % 64)) & 1); +} + +static void mark_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = 1ULL << (pfn % 64); + + TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8, + "Set page_idle bits for PFN 0x%" PRIx64, pfn); +} + +static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) +{ + uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva; + uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages; + uint64_t page; + uint64_t still_idle = 0; + uint64_t no_pfn = 0; + int page_idle_fd; + int pagemap_fd; + + /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */ + if (overlap_memory_access && vcpu_id) + return; + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle."); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap."); + + for (page = 0; page < pages; page++) { + uint64_t gva = base_gva + page * perf_test_args.guest_page_size; + uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva); + + if (!pfn) { + no_pfn++; + continue; + } + + if (is_page_idle(page_idle_fd, pfn)) { + still_idle++; + continue; + } + + mark_page_idle(page_idle_fd, pfn); + } + + /* + * Assumption: Less than 1% of pages are going to be swapped out from + * under us during this test. + */ + TEST_ASSERT(no_pfn < pages / 100, + "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.", + vcpu_id, no_pfn, pages); + + /* + * Test that at least 90% of memory has been marked idle (the rest might + * not be marked idle because the pages have not yet made it to an LRU + * list or the translations are still cached in the TLB). 90% is + * arbitrary; high enough that we ensure most memory access went through + * access tracking but low enough as to not make the test too brittle + * over time and across architectures. + */ + TEST_ASSERT(still_idle < pages / 10, + "vCPU%d: Too many pages still idle (%"PRIu64 " out of %" + PRIu64 ").\n", + vcpu_id, still_idle, pages); + + close(page_idle_fd); + close(pagemap_fd); +} + +static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id, + uint64_t expected_ucall) +{ + struct ucall uc; + uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc); + + TEST_ASSERT(expected_ucall == actual_ucall, + "Guest exited unexpectedly (expected ucall %" PRIu64 + ", got %" PRIu64 ")", + expected_ucall, actual_ucall); +} + +static bool spin_wait_for_next_iteration(int *current_iteration) +{ + int last_iteration = *current_iteration; + + do { + if (READ_ONCE(done)) + return false; + + *current_iteration = READ_ONCE(iteration); + } while (last_iteration == *current_iteration); + + return true; +} + +static void *vcpu_thread_main(void *arg) +{ + struct perf_test_vcpu_args *vcpu_args = arg; + struct kvm_vm *vm = perf_test_args.vm; + int vcpu_id = vcpu_args->vcpu_id; + int current_iteration = -1; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + while (spin_wait_for_next_iteration(¤t_iteration)) { + switch (READ_ONCE(iteration_work)) { + case ITERATION_ACCESS_MEMORY: + vcpu_run(vm, vcpu_id); + assert_ucall(vm, vcpu_id, UCALL_SYNC); + break; + case ITERATION_MARK_IDLE: + mark_vcpu_memory_idle(vm, vcpu_id); + break; + }; + + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + } + + return NULL; +} + +static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) +{ + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != + target_iteration) { + continue; + } +} + +/* The type of memory accesses to perform in the VM. */ +enum access_type { + ACCESS_READ, + ACCESS_WRITE, +}; + +static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) +{ + struct timespec ts_start; + struct timespec ts_elapsed; + int next_iteration; + int vcpu_id; + + /* Kick off the vCPUs by incrementing iteration. */ + next_iteration = ++iteration; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + /* Wait for all vCPUs to finish the iteration. */ + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + spin_wait_for_vcpu(vcpu_id, next_iteration); + + ts_elapsed = timespec_elapsed(ts_start); + pr_info("%-30s: %ld.%09lds\n", + description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec); +} + +static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, + const char *description) +{ + perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; + sync_global_to_guest(vm, perf_test_args); + iteration_work = ITERATION_ACCESS_MEMORY; + run_iteration(vm, vcpus, description); +} + +static void mark_memory_idle(struct kvm_vm *vm, int vcpus) +{ + /* + * Even though this parallelizes the work across vCPUs, this is still a + * very slow operation because page_idle forces the test to mark one pfn + * at a time and the clear_young notifier serializes on the KVM MMU + * lock. + */ + pr_debug("Marking VM memory idle (slow)...\n"); + iteration_work = ITERATION_MARK_IDLE; + run_iteration(vm, vcpus, "Mark memory idle"); +} + +static pthread_t *create_vcpu_threads(int vcpus) +{ + pthread_t *vcpu_threads; + int i; + + vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); + TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); + + for (i = 0; i < vcpus; i++) { + vcpu_last_completed_iteration[i] = iteration; + pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, + &perf_test_args.vcpu_args[i]); + } + + return vcpu_threads; +} + +static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) +{ + int i; + + /* Set done to signal the vCPU threads to exit */ + done = true; + + for (i = 0; i < vcpus; i++) + pthread_join(vcpu_threads[i], NULL); +} + +static void run_test(enum vm_guest_mode mode, void *arg) +{ + struct test_params *params = arg; + struct kvm_vm *vm; + pthread_t *vcpu_threads; + int vcpus = params->vcpus; + + vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, + params->backing_src); + + perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, + !overlap_memory_access); + + vcpu_threads = create_vcpu_threads(vcpus); + + pr_info("\n"); + access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); + + /* As a control, read and write to the populated memory first. */ + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory"); + access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory"); + + /* Repeat on memory that has been marked as idle. */ + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory"); + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); + + terminate_vcpu_threads(vcpu_threads, vcpus); + free(vcpu_threads); + perf_test_destroy_vm(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n", + name); + puts(""); + printf(" -h: Display this help message."); + guest_modes_help(); + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + printf(" -o: Overlap guest memory accesses instead of partitioning\n" + " them into a separate region of memory for each vCPU.\n"); + printf(" -s: specify the type of memory that should be used to\n" + " back the guest data region.\n\n"); + backing_src_help(); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + struct test_params params = { + .backing_src = VM_MEM_SRC_ANONYMOUS, + .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, + .vcpus = 1, + }; + int page_idle_fd; + int opt; + + guest_modes_append_default(); + + while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) { + switch (opt) { + case 'm': + guest_modes_cmdline(optarg); + break; + case 'b': + params.vcpu_memory_bytes = parse_size(optarg); + break; + case 'v': + params.vcpus = atoi(optarg); + break; + case 'o': + overlap_memory_access = true; + break; + case 's': + params.backing_src = parse_backing_src_type(optarg); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + if (page_idle_fd < 0) { + print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled"); + exit(KSFT_SKIP); + } + close(page_idle_fd); + + for_each_guest_mode(run_test, ¶ms); + + return 0; +} From 3fa5e8fd0a0e4ccc03c91df225be2e9b7100800c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 26 Jul 2021 12:39:01 -0400 Subject: [PATCH 0978/1469] KVM: SVM: delay svm_vcpu_init_msrpm after svm->vmcb is initialized Right now, svm_hv_vmcb_dirty_nested_enlightenments has an incorrect dereference of vmcb->control.reserved_sw before the vmcb is checked for being non-NULL. The compiler is usually sinking the dereference after the check; instead of doing this ourselves in the source, ensure that svm_hv_vmcb_dirty_nested_enlightenments is only called with a non-NULL VMCB. Reported-by: Dan Carpenter Cc: Vineeth Pillai Signed-off-by: Paolo Bonzini [Untested for now due to issues with my AMD machine. - Paolo] --- arch/x86/kvm/svm/svm.c | 4 ++-- arch/x86/kvm/svm/svm_onhyperv.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9a6987549e1b..4bcb95bb8ed7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1406,8 +1406,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) goto error_free_vmsa_page; } - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); @@ -1419,6 +1417,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); init_vmcb(vcpu); + svm_vcpu_init_msrpm(vcpu, svm->msrpm); + svm_init_osvw(vcpu); vcpu->arch.microcode_version = 0x01000065; diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 9b9a55abc29f..c53b8bf8d013 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( * as we mark it dirty unconditionally towards end of vcpu * init phase. */ - if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && + if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } From bb000f640e76c4c2402990d0613d4269e9c6dd29 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 26 Jul 2021 17:01:08 +0200 Subject: [PATCH 0979/1469] KVM: s390: restore old debugfs names commit bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") did replace the old definitions with the binary ones. While doing that it missed that some files are names different than the counters. This is especially important for kvm_stat which does have special handling for counters named instruction_*. Fixes: commit bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") CC: Jing Zhang Signed-off-by: Christian Borntraeger Message-Id: <20210726150108.5603-1-borntraeger@de.ibm.com> Signed-off-by: Paolo Bonzini --- arch/s390/include/asm/kvm_host.h | 18 +++++++++--------- arch/s390/kvm/diag.c | 18 +++++++++--------- arch/s390/kvm/kvm-s390.c | 18 +++++++++--------- 3 files changed, 27 insertions(+), 27 deletions(-) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 9b4473f76e56..161a9e12bfb8 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -445,15 +445,15 @@ struct kvm_vcpu_stat { u64 instruction_sigp_init_cpu_reset; u64 instruction_sigp_cpu_reset; u64 instruction_sigp_unknown; - u64 diagnose_10; - u64 diagnose_44; - u64 diagnose_9c; - u64 diagnose_9c_ignored; - u64 diagnose_9c_forward; - u64 diagnose_258; - u64 diagnose_308; - u64 diagnose_500; - u64 diagnose_other; + u64 instruction_diagnose_10; + u64 instruction_diagnose_44; + u64 instruction_diagnose_9c; + u64 diag_9c_ignored; + u64 diag_9c_forward; + u64 instruction_diagnose_258; + u64 instruction_diagnose_308; + u64 instruction_diagnose_500; + u64 instruction_diagnose_other; u64 pfault_sync; }; diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 02c146f9e5cd..807fa9da1e72 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -24,7 +24,7 @@ static int diag_release_pages(struct kvm_vcpu *vcpu) start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE; - vcpu->stat.diagnose_10++; + vcpu->stat.instruction_diagnose_10++; if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end || start < 2 * PAGE_SIZE) @@ -74,7 +74,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx", vcpu->run->s.regs.gprs[rx]); - vcpu->stat.diagnose_258++; + vcpu->stat.instruction_diagnose_258++; if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); @@ -145,7 +145,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) static int __diag_time_slice_end(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); - vcpu->stat.diagnose_44++; + vcpu->stat.instruction_diagnose_44++; kvm_vcpu_on_spin(vcpu, true); return 0; } @@ -169,7 +169,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) int tid; tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; - vcpu->stat.diagnose_9c++; + vcpu->stat.instruction_diagnose_9c++; /* yield to self */ if (tid == vcpu->vcpu_id) @@ -192,7 +192,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: yield forwarded", tid); - vcpu->stat.diagnose_9c_forward++; + vcpu->stat.diag_9c_forward++; return 0; } @@ -203,7 +203,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) return 0; no_yield: VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid); - vcpu->stat.diagnose_9c_ignored++; + vcpu->stat.diag_9c_ignored++; return 0; } @@ -213,7 +213,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff; VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode); - vcpu->stat.diagnose_308++; + vcpu->stat.instruction_diagnose_308++; switch (subcode) { case 3: vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR; @@ -245,7 +245,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) { int ret; - vcpu->stat.diagnose_500++; + vcpu->stat.instruction_diagnose_500++; /* No virtio-ccw notification? Get out quickly. */ if (!vcpu->kvm->arch.css_support || (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY)) @@ -299,7 +299,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) case 0x500: return __diag_virtio_hypercall(vcpu); default: - vcpu->stat.diagnose_other++; + vcpu->stat.instruction_diagnose_other++; return -EOPNOTSUPP; } } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b655a7d82bf0..4527ac7b5961 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -163,15 +163,15 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset), STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset), STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown), - STATS_DESC_COUNTER(VCPU, diagnose_10), - STATS_DESC_COUNTER(VCPU, diagnose_44), - STATS_DESC_COUNTER(VCPU, diagnose_9c), - STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored), - STATS_DESC_COUNTER(VCPU, diagnose_9c_forward), - STATS_DESC_COUNTER(VCPU, diagnose_258), - STATS_DESC_COUNTER(VCPU, diagnose_308), - STATS_DESC_COUNTER(VCPU, diagnose_500), - STATS_DESC_COUNTER(VCPU, diagnose_other), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_10), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_44), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c), + STATS_DESC_COUNTER(VCPU, diag_9c_ignored), + STATS_DESC_COUNTER(VCPU, diag_9c_forward), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_258), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_308), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_500), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_other), STATS_DESC_COUNTER(VCPU, pfault_sync) }; static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == From f1577ab21442476a1015d09e861c08ca76262c06 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 13 Jul 2021 17:20:16 +0300 Subject: [PATCH 0980/1469] KVM: SVM: svm_set_vintr don't warn if AVIC is active but is about to be deactivated It is possible for AVIC inhibit and AVIC active state to be mismatched. Currently we disable AVIC right away on vCPU which started the AVIC inhibit request thus this warning doesn't trigger but at least in theory, if svm_set_vintr is called at the same time on multiple vCPUs, the warning can happen. Signed-off-by: Maxim Levitsky Message-Id: <20210713142023.106183-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4bcb95bb8ed7..e8ccab50ebf6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1568,8 +1568,11 @@ static void svm_set_vintr(struct vcpu_svm *svm) { struct vmcb_control_area *control; - /* The following fields are ignored when AVIC is enabled */ - WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + /* + * The following fields are ignored when AVIC is enabled + */ + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); + svm_set_intercept(svm, INTERCEPT_VINTR); /* From feea01360cb1925dd31a3d38514eb86f61d69468 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 13 Jul 2021 17:20:17 +0300 Subject: [PATCH 0981/1469] KVM: SVM: tweak warning about enabled AVIC on nested entry It is possible that AVIC was requested to be disabled but not yet disabled, e.g if the nested entry is done right after svm_vcpu_after_set_cpuid. Signed-off-by: Maxim Levitsky Message-Id: <20210713142023.106183-3-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 1c2a0414a88d..61738ff8ef33 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -515,7 +515,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id, * avic_physical_id. */ - WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK); + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); /* Copied from vmcb01. msrpm_base can be overwritten later. */ svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl; From 5868b8225ecef4ba3f5b17e65984d60bc5fd6254 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 13 Jul 2021 17:20:18 +0300 Subject: [PATCH 0982/1469] KVM: SVM: use vmcb01 in svm_refresh_apicv_exec_ctrl Currently when SVM is enabled in guest CPUID, AVIC is inhibited as soon as the guest CPUID is set. AVIC happens to be fully disabled on all vCPUs by the time any guest entry starts (if after migration the entry can be nested). The reason is that currently we disable avic right away on vCPU from which the kvm_request_apicv_update was called and for this case, it happens to be called on all vCPUs (by svm_vcpu_after_set_cpuid). After we stop doing this, AVIC will end up being disabled only when KVM_REQ_APICV_UPDATE is processed which is after we done switching to the nested guest. Fix this by just using vmcb01 in svm_refresh_apicv_exec_ctrl for avic (which is a right thing to do anyway). Signed-off-by: Maxim Levitsky Message-Id: <20210713142023.106183-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/avic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 1d01da64c333..a8ad78a2faa1 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -646,7 +646,7 @@ out: void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = svm->vmcb01.ptr; bool activated = kvm_vcpu_apicv_active(vcpu); if (!enable_apicv) From 74775654332b2682a5580d6f954e5a9ac81e7477 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Tue, 27 Jul 2021 19:12:47 +0800 Subject: [PATCH 0983/1469] KVM: use cpu_relax when halt polling SMT siblings share caches and other hardware, and busy halt polling will degrade its sibling performance if its sibling is working Sean Christopherson suggested as below: "Rather than disallowing halt-polling entirely, on x86 it should be sufficient to simply have the hardware thread yield to its sibling(s) via PAUSE. It probably won't get back all performance, but I would expect it to be close. This compiles on all KVM architectures, and AFAICT the intended usage of cpu_relax() is identical for all architectures." Suggested-by: Sean Christopherson Signed-off-by: Li RongQing Message-Id: <20210727111247.55510-1-lirongqing@baidu.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 986959833d70..0d732813fa80 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3110,6 +3110,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ++vcpu->stat.generic.halt_poll_invalid; goto out; } + cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); } From 8750f9bbda115f3f79bfe43be85551ee5e12b6ff Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 27 Jul 2021 08:43:10 -0400 Subject: [PATCH 0984/1469] KVM: add missing compat KVM_CLEAR_DIRTY_LOG The arguments to the KVM_CLEAR_DIRTY_LOG ioctl include a pointer, therefore it needs a compat ioctl implementation. Otherwise, 32-bit userspace fails to invoke it on 64-bit kernels; for x86 it might work fine by chance if the padding is zero, but not on big-endian architectures. Reported-by: Thomas Sattler Cc: stable@vger.kernel.org Fixes: 2a31b9db1535 ("kvm: introduce manual dirty log reprotect") Reviewed-by: Peter Xu Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0d732813fa80..d20fba0fc290 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4391,6 +4391,16 @@ struct compat_kvm_dirty_log { }; }; +struct compat_kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4400,6 +4410,24 @@ static long kvm_vm_compat_ioctl(struct file *filp, if (kvm->mm != current->mm) return -EIO; switch (ioctl) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct compat_kvm_clear_dirty_log compat_log; + struct kvm_clear_dirty_log log; + + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + return -EFAULT; + log.slot = compat_log.slot; + log.num_pages = compat_log.num_pages; + log.first_page = compat_log.first_page; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; From 2bcc025ab9bbd029b1730cde71cb4e4f0ed35d0f Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sat, 17 Jul 2021 14:27:42 +0300 Subject: [PATCH 0985/1469] clk: tegra: Implement disable_unused() of tegra_clk_sdmmc_mux_ops Implement disable_unused() callback of tegra_clk_sdmmc_mux_ops to fix imbalanced disabling of the unused MMC clock on Tegra210 Jetson Nano. Fixes: c592c8a28f58 ("clk: tegra: Fix refcounting of gate clocks") Reported-by: Jon Hunter # T210 Nano Tested-by: Jon Hunter # T210 Nano Acked-by: Jon Hunter Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20210717112742.7196-1-digetx@gmail.com Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-sdmmc-mux.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/clk/tegra/clk-sdmmc-mux.c b/drivers/clk/tegra/clk-sdmmc-mux.c index 316912d3b1a4..4f2c3309eea4 100644 --- a/drivers/clk/tegra/clk-sdmmc-mux.c +++ b/drivers/clk/tegra/clk-sdmmc-mux.c @@ -194,6 +194,15 @@ static void clk_sdmmc_mux_disable(struct clk_hw *hw) gate_ops->disable(gate_hw); } +static void clk_sdmmc_mux_disable_unused(struct clk_hw *hw) +{ + struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw); + const struct clk_ops *gate_ops = sdmmc_mux->gate_ops; + struct clk_hw *gate_hw = &sdmmc_mux->gate.hw; + + gate_ops->disable_unused(gate_hw); +} + static void clk_sdmmc_mux_restore_context(struct clk_hw *hw) { struct clk_hw *parent = clk_hw_get_parent(hw); @@ -218,6 +227,7 @@ static const struct clk_ops tegra_clk_sdmmc_mux_ops = { .is_enabled = clk_sdmmc_mux_is_enabled, .enable = clk_sdmmc_mux_enable, .disable = clk_sdmmc_mux_disable, + .disable_unused = clk_sdmmc_mux_disable_unused, .restore_context = clk_sdmmc_mux_restore_context, }; From 343597d558e79fe704ba8846b5b2ed24056b89c2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:04:58 -0700 Subject: [PATCH 0986/1469] bpf, sockmap: Zap ingress queues after stopping strparser We don't want strparser to run and pass skbs into skmsg handlers when the psock is null. We just sk_drop them in this case. When removing a live socket from map it means extra drops that we do not need to incur. Move the zap below strparser close to avoid this condition. This way we stop the stream parser first stopping it from processing packets and then delete the psock. Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-2-john.fastabend@gmail.com --- net/core/skmsg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 15d71288e741..28115ef742e8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -773,8 +773,6 @@ static void sk_psock_destroy(struct work_struct *work) void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sk_psock_stop(psock, false); - write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); @@ -784,6 +782,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); + sk_psock_stop(psock, false); + INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } From 476d98018f32e68e7c5d4e8456940cf2b6d66f10 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:04:59 -0700 Subject: [PATCH 0987/1469] bpf, sockmap: On cleanup we additionally need to remove cached skb Its possible if a socket is closed and the receive thread is under memory pressure it may have cached a skb. We need to ensure these skbs are free'd along with the normal ingress_skb queue. Before 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") tear down and backlog processing both had sock_lock for the common case of socket close or unhash. So it was not possible to have both running in parrallel so all we would need is the kfree in those kernels. But, latest kernels include the commit 799aa7f98d5e and this requires a bit more work. Without the ingress_lock guarding reading/writing the state->skb case its possible the tear down could run before the state update causing it to leak memory or worse when the backlog reads the state it could potentially run interleaved with the tear down and we might end up free'ing the state->skb from tear down side but already have the reference from backlog side. To resolve such races we wrap accesses in ingress_lock on both sides serializing tear down and backlog case. In both cases this only happens after an EAGAIN error case so having an extra lock in place is likely fine. The normal path will skip the locks. Note, we check state->skb before grabbing lock. This works because we can only enqueue with the mutex we hold already. Avoiding a race on adding state->skb after the check. And if tear down path is running that is also fine if the tear down path then removes state->skb we will simply set skb=NULL and the subsequent goto is skipped. This slight complication avoids locking in normal case. With this fix we no longer see this warning splat from tcp side on socket close when we hit the above case with redirect to ingress self. [224913.935822] WARNING: CPU: 3 PID: 32100 at net/core/stream.c:208 sk_stream_kill_queues+0x212/0x220 [224913.935841] Modules linked in: fuse overlay bpf_preload x86_pkg_temp_thermal intel_uncore wmi_bmof squashfs sch_fq_codel efivarfs ip_tables x_tables uas xhci_pci ixgbe mdio xfrm_algo xhci_hcd wmi [224913.935897] CPU: 3 PID: 32100 Comm: fgs-bench Tainted: G I 5.14.0-rc1alu+ #181 [224913.935908] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019 [224913.935914] RIP: 0010:sk_stream_kill_queues+0x212/0x220 [224913.935923] Code: 8b 83 20 02 00 00 85 c0 75 20 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 df e8 2b 11 fe ff eb c3 0f 0b e9 7c ff ff ff 0f 0b eb ce <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 90 0f 1f 44 00 00 41 57 41 [224913.935932] RSP: 0018:ffff88816271fd38 EFLAGS: 00010206 [224913.935941] RAX: 0000000000000ae8 RBX: ffff88815acd5240 RCX: dffffc0000000000 [224913.935948] RDX: 0000000000000003 RSI: 0000000000000ae8 RDI: ffff88815acd5460 [224913.935954] RBP: ffff88815acd5460 R08: ffffffff955c0ae8 R09: fffffbfff2e6f543 [224913.935961] R10: ffffffff9737aa17 R11: fffffbfff2e6f542 R12: ffff88815acd5390 [224913.935967] R13: ffff88815acd5480 R14: ffffffff98d0c080 R15: ffffffff96267500 [224913.935974] FS: 00007f86e6bd1700(0000) GS:ffff888451cc0000(0000) knlGS:0000000000000000 [224913.935981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [224913.935988] CR2: 000000c0008eb000 CR3: 00000001020e0005 CR4: 00000000003706e0 [224913.935994] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [224913.936000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [224913.936007] Call Trace: [224913.936016] inet_csk_destroy_sock+0xba/0x1f0 [224913.936033] __tcp_close+0x620/0x790 [224913.936047] tcp_close+0x20/0x80 [224913.936056] inet_release+0x8f/0xf0 [224913.936070] __sock_release+0x72/0x120 [224913.936083] sock_close+0x14/0x20 Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-3-john.fastabend@gmail.com --- net/core/skmsg.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 28115ef742e8..036cdb33a94a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -590,23 +590,42 @@ static void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } +static void sk_psock_skb_state(struct sk_psock *psock, + struct sk_psock_work_state *state, + struct sk_buff *skb, + int len, int off) +{ + spin_lock_bh(&psock->ingress_lock); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + state->skb = skb; + state->len = len; + state->off = off; + } else { + sock_drop(psock->sk, skb); + } + spin_unlock_bh(&psock->ingress_lock); +} + static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool ingress; u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (state->skb) { + if (unlikely(state->skb)) { + spin_lock_bh(&psock->ingress_lock); skb = state->skb; len = state->len; off = state->off; state->skb = NULL; - goto start; + spin_unlock_bh(&psock->ingress_lock); } + if (skb) + goto start; while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; @@ -621,9 +640,8 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - state->skb = skb; - state->len = len; - state->off = off; + sk_psock_skb_state(psock, state, skb, + len, off); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -722,6 +740,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } + kfree_skb(psock->work_state.skb); + /* We null the skb here to ensure that calls to sk_psock_backlog + * do not pick up the free'd skb. + */ + psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } From 9635720b7c88592214562cb72605bdab6708006c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:05:00 -0700 Subject: [PATCH 0988/1469] bpf, sockmap: Fix memleak on ingress msg enqueue If backlog handler is running during a tear down operation we may enqueue data on the ingress msg queue while tear down is trying to free it. sk_psock_backlog() sk_psock_handle_skb() skb_psock_skb_ingress() sk_psock_skb_ingress_enqueue() sk_psock_queue_msg(psock,msg) spin_lock(ingress_lock) sk_psock_zap_ingress() _sk_psock_purge_ingerss_msg() _sk_psock_purge_ingress_msg() -- free ingress_msg list -- spin_unlock(ingress_lock) spin_lock(ingress_lock) list_add_tail(msg,ingress_msg) <- entry on list with no one left to free it. spin_unlock(ingress_lock) To fix we only enqueue from backlog if the ENABLED bit is set. The tear down logic clears the bit with ingress_lock set so we wont enqueue the msg in the last step. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 54 ++++++++++++++++++++++++++++--------------- net/core/skmsg.c | 6 ----- 2 files changed, 35 insertions(+), 25 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 96f319099744..14ab0c0bc924 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + +static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) +{ + if (msg->skb) + sock_drop(psock->sk, msg->skb); + kfree(msg); +} + static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); - list_add_tail(&msg->list, &psock->ingress_msg); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + list_add_tail(&msg->list, &psock->ingress_msg); + else + drop_sk_msg(psock, msg); spin_unlock_bh(&psock->ingress_lock); } @@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk, psock->psock_update_sk_prot(sk, psock, true); } -static inline void sk_psock_set_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - set_bit(bit, &psock->state); -} - -static inline void sk_psock_clear_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - clear_bit(bit, &psock->state); -} - -static inline bool sk_psock_test_state(const struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - return test_bit(bit, &psock->state); -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 036cdb33a94a..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -584,12 +584,6 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) -{ - sk_drops_add(sk, skb); - kfree_skb(skb); -} - static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, struct sk_buff *skb, From b93af3055d6f32d3b0361cfdb110c9399c1241ba Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 27 Jul 2021 17:32:53 +0800 Subject: [PATCH 0989/1469] blk-mq-sched: Fix blk_mq_sched_alloc_tags() error handling If the blk_mq_sched_alloc_tags() -> blk_mq_alloc_rqs() call fails, then we call blk_mq_sched_free_tags() -> blk_mq_free_rqs(). It is incorrect to do so, as any rqs would have already been freed in the blk_mq_alloc_rqs() call. Fix by calling blk_mq_free_rq_map() only directly. Fixes: 6917ff0b5bd41 ("blk-mq-sched: refactor scheduler initialization") Signed-off-by: John Garry Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/1627378373-148090-1-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index c838d81ac058..0f006cabfd91 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -515,17 +515,6 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, percpu_ref_put(&q->q_usage_counter); } -static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, - struct blk_mq_hw_ctx *hctx, - unsigned int hctx_idx) -{ - if (hctx->sched_tags) { - blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); - blk_mq_free_rq_map(hctx->sched_tags, set->flags); - hctx->sched_tags = NULL; - } -} - static int blk_mq_sched_alloc_tags(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) @@ -539,8 +528,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, return -ENOMEM; ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); - if (ret) - blk_mq_sched_free_tags(set, hctx, hctx_idx); + if (ret) { + blk_mq_free_rq_map(hctx->sched_tags, set->flags); + hctx->sched_tags = NULL; + } return ret; } From 8b54874ef1617185048029a3083d510569e93751 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 26 Jul 2021 09:20:14 +0300 Subject: [PATCH 0990/1469] net/mlx5: Fix flow table chaining Fix a bug when flow table is created in priority that already has other flow tables as shown in the below diagram. If the new flow table (FT-B) has the lowest level in the priority, we need to connect the flow tables from the previous priority (p0) to this new table. In addition when this flow table is destroyed (FT-B), we need to connect the flow tables from the previous priority (p0) to the next level flow table (FT-C) in the same priority of the destroyed table (if exists). --------- |root_ns| --------- | -------------------------------- | | | ---------- ---------- --------- |p(prio)-x| | p-y | | p-n | ---------- ---------- --------- | | ---------------- ------------------ |ns(e.g bypass)| |ns(e.g. kernel) | ---------------- ------------------ | | | ------- ------ ---- | p0 | | p1 | |p2| ------- ------ ---- | | \ -------- ------- ------ | FT-A | |FT-B | |FT-C| -------- ------- ------ Fixes: f90edfd279f3 ("net/mlx5_core: Connect flow tables") Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d7bf0a3e4a52..c0697e1b7118 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1024,17 +1024,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { - struct mlx5_flow_table *next_ft; + struct mlx5_flow_table *next_ft, *first_ft; int err = 0; /* Connect_prev_fts and update_root_ft_create are mutually exclusive */ - if (list_empty(&prio->node.children)) { + first_ft = list_first_entry_or_null(&prio->node.children, + struct mlx5_flow_table, node.list); + if (!first_ft || first_ft->level > ft->level) { err = connect_prev_fts(dev, ft, prio); if (err) return err; - next_ft = find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(prio); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -2120,7 +2122,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) node.list) == ft)) return 0; - next_ft = find_next_chained_ft(prio); + next_ft = find_next_ft(ft); err = connect_fwd_rules(dev, next_ft, ft); if (err) return err; From 90b22b9bcd242a3ba238f2c6f7eab771799001f8 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Thu, 8 Jul 2021 15:24:58 +0300 Subject: [PATCH 0991/1469] net/mlx5e: Disable Rx ntuple offload for uplink representor Rx ntuple offload is not supported in switchdev mode. Tryng to enable it cause kernel panic. BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 80000001065a5067 P4D 80000001065a5067 PUD 106594067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 7 PID: 1089 Comm: ethtool Not tainted 5.13.0-rc7_for_upstream_min_debug_2021_06_23_16_44 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5e_arfs_enable+0x70/0xd0 [mlx5_core] Code: 44 24 10 00 00 00 00 48 c7 44 24 18 00 00 00 00 49 63 c4 48 89 e2 44 89 e6 48 69 c0 20 08 00 00 48 89 ef 48 03 85 68 ac 00 00 <48> 8b 40 08 48 89 44 24 08 e8 d2 aa fd ff 48 83 05 82 96 18 00 01 RSP: 0018:ffff8881047679e0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000004000000000 RCX: 0000004000000000 RDX: ffff8881047679e0 RSI: 0000000000000000 RDI: ffff888115100880 RBP: ffff888115100880 R08: ffffffffa00f6cb0 R09: ffff888104767a18 R10: ffff8881151000a0 R11: ffff888109479540 R12: 0000000000000000 R13: ffff888104767bb8 R14: ffff888115100000 R15: ffff8881151000a0 FS: 00007f41a64ab740(0000) GS:ffff8882f5dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 0000000104cbc005 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: set_feature_arfs+0x1e/0x40 [mlx5_core] mlx5e_handle_feature+0x43/0xa0 [mlx5_core] mlx5e_set_features+0x139/0x1b0 [mlx5_core] __netdev_update_features+0x2b3/0xaf0 ethnl_set_features+0x176/0x3a0 ? __nla_parse+0x22/0x30 genl_family_rcv_msg_doit+0xe2/0x140 genl_rcv_msg+0xde/0x1d0 ? features_reply_size+0xe0/0xe0 ? genl_get_cmd+0xd0/0xd0 netlink_rcv_skb+0x4e/0xf0 genl_rcv+0x24/0x40 netlink_unicast+0x1f6/0x2b0 netlink_sendmsg+0x225/0x450 sock_sendmsg+0x33/0x40 __sys_sendto+0xd4/0x120 ? __sys_recvmsg+0x4e/0x90 ? exc_page_fault+0x219/0x740 __x64_sys_sendto+0x25/0x30 do_syscall_64+0x3f/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f41a65b0cba Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 76 c3 0f 1f 44 00 00 55 48 83 ec 30 44 89 4c RSP: 002b:00007ffd8d688358 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00000000010f42a0 RCX: 00007f41a65b0cba RDX: 0000000000000058 RSI: 00000000010f43b0 RDI: 0000000000000003 RBP: 000000000047ae60 R08: 00007f41a667c000 R09: 000000000000000c R10: 0000000000000000 R11: 0000000000000246 R12: 00000000010f4340 R13: 00000000010f4350 R14: 00007ffd8d688400 R15: 00000000010f42a0 Modules linked in: mlx5_vdpa vhost_iotlb vdpa xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad ib_ipoib rdma_cm iw_cm ib_cm mlx5_ib ib_uverbs ib_core overlay mlx5_core ptp pps_core fuse CR2: 0000000000000008 ---[ end trace c66523f2aba94b43 ]--- Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode") Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 29 +++++++++++++------ 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d09e65557e75..c6f99fc77411 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3829,6 +3829,24 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) return 0; } +static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev, + netdev_features_t features) +{ + features &= ~NETIF_F_HW_TLS_RX; + if (netdev->features & NETIF_F_HW_TLS_RX) + netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n"); + + features &= ~NETIF_F_HW_TLS_TX; + if (netdev->features & NETIF_F_HW_TLS_TX) + netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n"); + + features &= ~NETIF_F_NTUPLE; + if (netdev->features & NETIF_F_NTUPLE) + netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n"); + + return features; +} + static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_features_t features) { @@ -3860,15 +3878,8 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n"); } - if (mlx5e_is_uplink_rep(priv)) { - features &= ~NETIF_F_HW_TLS_RX; - if (netdev->features & NETIF_F_HW_TLS_RX) - netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n"); - - features &= ~NETIF_F_HW_TLS_TX; - if (netdev->features & NETIF_F_HW_TLS_TX) - netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n"); - } + if (mlx5e_is_uplink_rep(priv)) + features = mlx5e_fix_uplink_rep_features(netdev, features); mutex_unlock(&priv->state_lock); From c671972534c6f7fce789ac8156a2bc3bd146f806 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Tue, 22 Jun 2021 17:07:02 +0300 Subject: [PATCH 0992/1469] net/mlx5: E-Switch, Set destination vport vhca id only when merged eswitch is supported Destination vport vhca id is valid flag is set only merged eswitch isn't supported. Change destination vport vhca id value to be set also only when merged eswitch is supported. Fixes: e4ad91f23f10 ("net/mlx5e: Split offloaded eswitch TC rules for port mirroring") Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7579f3402776..b0a2ca9037ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -382,10 +382,11 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f { dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport; - dest[dest_idx].vport.vhca_id = - MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); - if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + dest[dest_idx].vport.vhca_id = + MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + } if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; From dd3fddb82780bfa24124834edd90bbc63bd689cc Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Wed, 2 Jun 2021 14:17:07 +0300 Subject: [PATCH 0993/1469] net/mlx5: E-Switch, handle devcom events only for ports on the same device This is the same check as LAG mode checks if to enable lag. This will fix adding peer miss rules if lag is not supported and even an incorrect rules in socket direct mode. Also fix the incorrect comment on mlx5_get_next_phys_dev() as flow #1 doesn't exists. Fixes: ac004b832128 ("net/mlx5e: E-Switch, Add peer miss rules") Signed-off-by: Roi Dayan Reviewed-by: Maor Dickman Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 5 +---- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 +++ 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index ceebfc20f65e..def2156e50ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -500,10 +500,7 @@ static int next_phys_dev(struct device *dev, const void *data) return 1; } -/* This function is called with two flows: - * 1. During initialization of mlx5_core_dev and we don't need to lock it. - * 2. During LAG configure stage and caller holds &mlx5_intf_mutex. - */ +/* Must be called with intf_mutex held */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { struct auxiliary_device *adev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b0a2ca9037ac..011e766e4f67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2368,6 +2368,9 @@ static int mlx5_esw_offloads_devcom_event(int event, switch (event) { case ESW_OFFLOADS_DEVCOM_PAIR: + if (mlx5_get_next_phys_dev(esw->dev) != peer_esw->dev) + break; + if (mlx5_eswitch_vport_match_metadata_enabled(esw) != mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; From e2351e517068718724f1d3b4010e2a41ec91fa76 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 30 Jun 2021 13:45:05 +0300 Subject: [PATCH 0994/1469] net/mlx5e: RX, Avoid possible data corruption when relaxed ordering and LRO combined When HW aggregates packets for an LRO session, it writes the payload of two consecutive packets of a flow contiguously, so that they usually share a cacheline. The first byte of a packet's payload is written immediately after the last byte of the preceding packet. In this flow, there are two consecutive write requests to the shared cacheline: 1. Regular write for the earlier packet. 2. Read-modify-write for the following packet. In case of relaxed-ordering on, these two writes might be re-ordered. Using the end padding optimization (to avoid partial write for the last cacheline of a packet) becomes problematic if the two writes occur out-of-order, as the padding would overwrite payload that belongs to the following packet, causing data corruption. Avoid this by disabling the end padding optimization when both LRO and relaxed-ordering are enabled. Fixes: 17347d5430c4 ("net/mlx5e: Add support for PCI relaxed ordering") Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 150c8e82c738..2cbf18c967f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -471,6 +471,15 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, param->cq_period_mode = params->rx_cq_moderation.cq_period_mode; } +static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +{ + bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) && + MLX5_CAP_GEN(mdev, relaxed_ordering_write); + + return ro && params->lro_en ? + MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN; +} + int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -508,7 +517,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } MLX5_SET(wq, wq, wq_type, params->rq_wq_type); - MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN); + MLX5_SET(wq, wq, end_padding_mode, rq_end_pad_mode(mdev, params)); MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn); From 9841d58f3550d11c6181424427e8ad8c9c80f1b6 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 30 Jun 2021 13:33:31 +0300 Subject: [PATCH 0995/1469] net/mlx5e: Add NETIF_F_HW_TC to hw_features when HTB offload is available If a feature flag is only present in features, but not in hw_features, the user can't reset it. Although hw_features may contain NETIF_F_HW_TC by the point where the driver checks whether HTB offload is supported, this flag is controlled by another condition that may not hold. Set it explicitly to make sure the user can disable it. Fixes: 214baf22870c ("net/mlx5e: Support HTB offload") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c6f99fc77411..c5a2e3e6fe4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4870,6 +4870,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (MLX5_CAP_ETH(mdev, scatter_fcs)) netdev->hw_features |= NETIF_F_RXFCS; + if (mlx5_qos_is_supported(mdev)) + netdev->hw_features |= NETIF_F_HW_TC; + netdev->features = netdev->hw_features; /* Defaults */ @@ -4890,8 +4893,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_NTUPLE; #endif } - if (mlx5_qos_is_supported(mdev)) - netdev->features |= NETIF_F_HW_TC; netdev->features |= NETIF_F_HIGHDMA; netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER; From a759f845d1f78634b54744db0fa48524ef6d0e14 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 30 Jun 2021 11:17:12 +0300 Subject: [PATCH 0996/1469] net/mlx5e: Consider PTP-RQ when setting RX VLAN stripping Add PTP-RQ to the loop when setting rx-vlan-offload feature via ethtool. On PTP-RQ's creation, set rx-vlan-offload into its parameters. Fixes: a099da8ffcf6 ("net/mlx5e: Add RQ to PTP channel") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 5 ++++- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 778e229310a9..07b429b94d93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -482,8 +482,11 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, params->log_sq_size = orig->log_sq_size; mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param); } - if (test_bit(MLX5E_PTP_STATE_RX, c->state)) + /* RQ */ + if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { + params->vlan_strip_disable = orig->vlan_strip_disable; mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams); + } } static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c5a2e3e6fe4b..37c440837945 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3384,7 +3384,7 @@ static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool en static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { - int err = 0; + int err; int i; for (i = 0; i < chs->num; i++) { @@ -3392,6 +3392,8 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) if (err) return err; } + if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state)) + return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd); return 0; } From 497008e783452a2ec45c7ec5835cfe6950dcb097 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 21 Jun 2021 18:04:07 +0300 Subject: [PATCH 0997/1469] net/mlx5e: Fix page allocation failure for trap-RQ over SF Set the correct device pointer to the trap-RQ, to allow access to dma_mask and avoid allocation request with the wrong pci-dev. WARNING: CPU: 1 PID: 12005 at kernel/dma/mapping.c:151 dma_map_page_attrs+0x139/0x1c0 ... all Trace: ? __page_pool_alloc_pages_slow+0x5a/0x210 mlx5e_post_rx_wqes+0x258/0x400 [mlx5_core] mlx5e_trap_napi_poll+0x44/0xc0 [mlx5_core] __napi_poll+0x24/0x150 net_rx_action+0x22b/0x280 __do_softirq+0xc7/0x27e do_softirq+0x61/0x80 __local_bh_enable_ip+0x4b/0x50 mlx5e_handle_action_trap+0x2dd/0x4d0 [mlx5_core] blocking_notifier_call_chain+0x5a/0x80 mlx5_devlink_trap_action_set+0x8b/0x100 [mlx5_core] Fixes: 5543e989fe5e ("net/mlx5e: Add trap entity to ETH driver") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/trap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 86ab4e864fe6..7f94508594fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -37,7 +37,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params struct mlx5e_priv *priv = t->priv; rq->wq_type = params->rq_wq_type; - rq->pdev = mdev->device; + rq->pdev = t->pdev; rq->netdev = priv->netdev; rq->priv = priv; rq->clock = &mdev->clock; From 678b1ae1af4aef488fcc42baa663e737b9a531ba Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 22 Jun 2021 10:24:17 +0300 Subject: [PATCH 0998/1469] net/mlx5e: Fix page allocation failure for ptp-RQ over SF Set the correct pci-device pointer to the ptp-RQ. This allows access to dma_mask and avoids allocation request with wrong pci-device. Fixes: a099da8ffcf6 ("net/mlx5e: Add RQ to PTP channel") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 07b429b94d93..efef4adce086 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -497,7 +497,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, int err; rq->wq_type = params->rq_wq_type; - rq->pdev = mdev->device; + rq->pdev = c->pdev; rq->netdev = priv->netdev; rq->priv = priv; rq->clock = &mdev->clock; From 7f331bf0f060c2727e36d64f9b098b4ee5f3dfad Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 16 Jun 2021 19:11:03 +0300 Subject: [PATCH 0999/1469] net/mlx5: Unload device upon firmware fatal error When fw_fatal reporter reports an error, the firmware in not responding. Unload the device to ensure that the driver closes all its resources, even if recovery is not due (user disabled auto-recovery or reporter is in grace period). On successful recovery the device is loaded back up. Fixes: b3bd076f7501 ("net/mlx5: Report devlink health on FW fatal issues") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9ff163c5bcde..9abeb80ffa31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -626,8 +626,16 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) } fw_reporter_ctx.err_synd = health->synd; fw_reporter_ctx.miss_counter = health->miss_counter; - devlink_health_report(health->fw_fatal_reporter, - "FW fatal error reported", &fw_reporter_ctx); + if (devlink_health_report(health->fw_fatal_reporter, + "FW fatal error reported", &fw_reporter_ctx) == -ECANCELED) { + /* If recovery wasn't performed, due to grace period, + * unload the driver. This ensures that the driver + * closes all its resources and it is not subjected to + * requests from the kernel. + */ + mlx5_core_err(dev, "Driver is in error state. Unloading\n"); + mlx5_unload_one(dev); + } } static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = { From b1c2f6312c5005c928a72e668bf305a589d828d4 Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Mon, 26 Apr 2021 15:16:26 +0300 Subject: [PATCH 1000/1469] net/mlx5e: Fix nullptr in mlx5e_hairpin_get_mdev() The result of __dev_get_by_index() is not checked for NULL and then gets dereferenced immediately. Also, __dev_get_by_index() must be called while holding either RTNL lock or @dev_base_lock, which isn't satisfied by mlx5e_hairpin_get_mdev() or its callers. This makes the underlying hlist_for_each_entry() loop not safe, and can have adverse effects in itself. Fix by using dev_get_by_index() and handling nullptr return value when ifindex device is not found. Update mlx5e_hairpin_get_mdev() callers to check for possible PTR_ERR() result. Fixes: 77ab67b7f0f9 ("net/mlx5e: Basic setup of hairpin object") Addresses-Coverity: ("Dereference null return value") Signed-off-by: Dima Chumak Reviewed-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 33 +++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 629a61e8022f..d273758255c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -452,12 +452,32 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, static struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex) { + struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_priv *priv; - netdev = __dev_get_by_index(net, ifindex); + netdev = dev_get_by_index(net, ifindex); + if (!netdev) + return ERR_PTR(-ENODEV); + priv = netdev_priv(netdev); - return priv->mdev; + mdev = priv->mdev; + dev_put(netdev); + + /* Mirred tc action holds a refcount on the ifindex net_device (see + * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev + * after dev_put(netdev), while we're in the context of adding a tc flow. + * + * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then + * stored in a hairpin object, which exists until all flows, that refer to it, get + * removed. + * + * On the other hand, after a hairpin object has been created, the peer net_device may + * be removed/unbound while there are still some hairpin flows that are using it. This + * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to + * NETDEV_UNREGISTER event of the peer net_device. + */ + return mdev; } static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp) @@ -666,6 +686,10 @@ mlx5e_hairpin_create(struct mlx5e_priv *priv, struct mlx5_hairpin_params *params func_mdev = priv->mdev; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + err = PTR_ERR(peer_mdev); + goto create_pair_err; + } pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params); if (IS_ERR(pair)) { @@ -804,6 +828,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, int err; peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); + if (IS_ERR(peer_mdev)) { + NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device"); + return PTR_ERR(peer_mdev); + } + if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; From 740452e09cf5fc489ce60831cf11abef117b5d26 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Mon, 26 Apr 2021 11:06:37 +0800 Subject: [PATCH 1001/1469] net/mlx5: Fix mlx5_vport_tbl_attr chain from u16 to u32 The offending refactor commit uses u16 chain wrongly. Actually, it should be u32. Fixes: c620b772152b ("net/mlx5: Refactor tc flow attributes structure") CC: Ariel Levkovich Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 48cac5bf606d..d562edf5b0bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -636,7 +636,7 @@ struct esw_vport_tbl_namespace { }; struct mlx5_vport_tbl_attr { - u16 chain; + u32 chain; u16 prio; u16 vport; const struct esw_vport_tbl_namespace *vport_ns; From c3df5fb57fe8756d67fd56ed29da65cdfde839f9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Jul 2021 13:12:20 -1000 Subject: [PATCH 1002/1469] cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync 0fa294fb1985 ("cgroup: Replace cgroup_rstat_mutex with a spinlock") added cgroup_rstat_flush_irqsafe() allowing flushing to happen from the irq context. However, rstat paths use u64_stats_sync to synchronize access to 64bit stat counters on 32bit machines. u64_stats_sync is implemented using seq_lock and trying to read from an irq context can lead to A-A deadlock if the irq happens to interrupt the stat update. Fix it by using the irqsafe variants - u64_stats_update_begin_irqsave() and u64_stats_update_end_irqrestore() - in the update paths. Note that none of this matters on 64bit machines. All these are just for 32bit SMP setups. Note that the interface was introduced way back, its first and currently only use was recently added by 2d146aa3aa84 ("mm: memcontrol: switch to rstat"). Stable tagging targets this commit. Signed-off-by: Tejun Heo Reported-by: Rik van Riel Fixes: 2d146aa3aa84 ("mm: memcontrol: switch to rstat") Cc: stable@vger.kernel.org # v5.13+ --- block/blk-cgroup.c | 14 ++++++++------ kernel/cgroup/rstat.c | 19 +++++++++++-------- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 575d7a2e7203..31fe9be179d9 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -790,6 +790,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) struct blkcg_gq *parent = blkg->parent; struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); struct blkg_iostat cur, delta; + unsigned long flags; unsigned int seq; /* fetch the current per-cpu values */ @@ -799,21 +800,21 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) } while (u64_stats_fetch_retry(&bisc->sync, seq)); /* propagate percpu delta to global */ - u64_stats_update_begin(&blkg->iostat.sync); + flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, &cur); blkg_iostat_sub(&delta, &bisc->last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(&bisc->last, &delta); - u64_stats_update_end(&blkg->iostat.sync); + u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { - u64_stats_update_begin(&parent->iostat.sync); + flags = u64_stats_update_begin_irqsave(&parent->iostat.sync); blkg_iostat_set(&delta, &blkg->iostat.cur); blkg_iostat_sub(&delta, &blkg->iostat.last); blkg_iostat_add(&parent->iostat.cur, &delta); blkg_iostat_add(&blkg->iostat.last, &delta); - u64_stats_update_end(&parent->iostat.sync); + u64_stats_update_end_irqrestore(&parent->iostat.sync, flags); } } @@ -848,6 +849,7 @@ static void blkcg_fill_root_iostats(void) memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; + unsigned long flags; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += @@ -864,9 +866,9 @@ static void blkcg_fill_root_iostats(void) tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; - u64_stats_update_begin(&blkg->iostat.sync); + flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); - u64_stats_update_end(&blkg->iostat.sync); + u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 7f0e58917432..b264ab5652ba 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -347,19 +347,20 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) } static struct cgroup_rstat_cpu * -cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) +cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); - u64_stats_update_begin(&rstatc->bsync); + *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, - struct cgroup_rstat_cpu *rstatc) + struct cgroup_rstat_cpu *rstatc, + unsigned long flags) { - u64_stats_update_end(&rstatc->bsync); + u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } @@ -367,18 +368,20 @@ static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; + unsigned long flags; - rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; - cgroup_base_stat_cputime_account_end(cgrp, rstatc); + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; + unsigned long flags; - rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_USER: @@ -394,7 +397,7 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, break; } - cgroup_base_stat_cputime_account_end(cgrp, rstatc); + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* From 5ab189cf3abbc9994bae3be524c5b88589ed56e2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Jul 2021 14:38:09 -1000 Subject: [PATCH 1003/1469] blk-iocost: fix operation ordering in iocg_wake_fn() iocg_wake_fn() open-codes wait_queue_entry removal and wakeup because it wants the wq_entry to be always removed whether it ended up waking the task or not. finish_wait() tests whether wq_entry needs removal without grabbing the wait_queue lock and expects the waker to use list_del_init_careful() after all waking operations are complete, which iocg_wake_fn() didn't do. The operation order was wrong and the regular list_del_init() was used. The result is that if a waiter wakes up racing the waker, it can free pop the wq_entry off stack before the waker is still looking at it, which can lead to a backtrace like the following. [7312084.588951] general protection fault, probably for non-canonical address 0x586bf4005b2b88: 0000 [#1] SMP ... [7312084.647079] RIP: 0010:queued_spin_lock_slowpath+0x171/0x1b0 ... [7312084.858314] Call Trace: [7312084.863548] _raw_spin_lock_irqsave+0x22/0x30 [7312084.872605] try_to_wake_up+0x4c/0x4f0 [7312084.880444] iocg_wake_fn+0x71/0x80 [7312084.887763] __wake_up_common+0x71/0x140 [7312084.895951] iocg_kick_waitq+0xe8/0x2b0 [7312084.903964] ioc_rqos_throttle+0x275/0x650 [7312084.922423] __rq_qos_throttle+0x20/0x30 [7312084.930608] blk_mq_make_request+0x120/0x650 [7312084.939490] generic_make_request+0xca/0x310 [7312084.957600] submit_bio+0x173/0x200 [7312084.981806] swap_readpage+0x15c/0x240 [7312084.989646] read_swap_cache_async+0x58/0x60 [7312084.998527] swap_cluster_readahead+0x201/0x320 [7312085.023432] swapin_readahead+0x2df/0x450 [7312085.040672] do_swap_page+0x52f/0x820 [7312085.058259] handle_mm_fault+0xa16/0x1420 [7312085.066620] do_page_fault+0x2c6/0x5c0 [7312085.074459] page_fault+0x2f/0x40 Fix it by switching to list_del_init_careful() and putting it at the end. Signed-off-by: Tejun Heo Reported-by: Rik van Riel Fixes: 7caa47151ab2 ("blkcg: implement blk-iocost") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Jens Axboe --- block/blk-iocost.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index c2d6bc88d3f1..5fac3757e6e0 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1440,16 +1440,17 @@ static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); + wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it - * actually changed the task state. We want the wait always - * removed. Remove explicitly and use default_wake_function(). + * actually changed the task state. We want the wait always removed. + * Remove explicitly and use default_wake_function(). Note that the + * order of operations is important as finish_wait() tests whether + * @wq_entry is removed without grabbing the lock. */ - list_del_init(&wq_entry->entry); - wait->committed = true; - default_wake_function(wq_entry, mode, flags, key); + list_del_init_careful(&wq_entry->entry); return 0; } From 340e84573878b2b9d63210482af46883366361b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 22 Jul 2021 09:53:54 +0200 Subject: [PATCH 1004/1469] block: delay freeing the gendisk blkdev_get_no_open acquires a reference to the block_device through the block device inode and then tries to acquire a device model reference to the gendisk. But at this point the disk migh already be freed (although the race is free). Fix this by only freeing the gendisk from the whole device bdevs ->free_inode callback as well. Fixes: 22ae8ce8b892 ("block: simplify bdev/disk lookup in blkdev_get") Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210722075402.983367-2-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 3 +-- fs/block_dev.c | 2 ++ 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/block/genhd.c b/block/genhd.c index af4d2ab4a633..298ee78c1bda 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1079,10 +1079,9 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); - bdput(disk->part0); if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) blk_put_queue(disk->queue); - kfree(disk); + bdput(disk->part0); /* frees the disk */ } struct class block_class = { .name = "block", diff --git a/fs/block_dev.c b/fs/block_dev.c index ca8bf1869ca8..a38b0f33211c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -812,6 +812,8 @@ static void bdev_free_inode(struct inode *inode) free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); + if (!bdev_is_partition(bdev)) + kfree(bdev->bd_disk); kmem_cache_free(bdev_cachep, BDEV_I(inode)); } From fa20bada3f934e3b3e4af4c77e5b518cd5a282e5 Mon Sep 17 00:00:00 2001 From: Maxim Devaev Date: Tue, 27 Jul 2021 21:58:00 +0300 Subject: [PATCH 1005/1469] usb: gadget: f_hid: idle uses the highest byte for duration SET_IDLE value must be shifted 8 bits to the right to get duration. This confirmed by USBCV test. Fixes: afcff6dc690e ("usb: gadget: f_hid: added GET_IDLE and SET_IDLE handlers") Cc: stable Signed-off-by: Maxim Devaev Link: https://lore.kernel.org/r/20210727185800.43796-1-mdevaev@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_hid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 8d50c8b127fd..bb476e121eae 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -573,7 +573,7 @@ static int hidg_setup(struct usb_function *f, | HID_REQ_SET_IDLE): VDBG(cdev, "set_idle\n"); length = 0; - hidg->idle = value; + hidg->idle = value >> 8; goto respond; break; From d54db74ad6e0dea8c253fb68c689b836657ab914 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Mon, 7 Jun 2021 14:46:38 +0800 Subject: [PATCH 1006/1469] dmaengine: stm32-dma: Fix PM usage counter imbalance in stm32 dma ops pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. We fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced. Fixes: 48bc73ba14bcd ("dmaengine: stm32-dma: Add PM Runtime support") Fixes: 05f8740a0e6fc ("dmaengine: stm32-dma: add suspend/resume power management support") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20210607064640.121394-2-zhangqilong3@huawei.com Signed-off-by: Vinod Koul --- drivers/dma/stm32-dma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index f54ecb123a52..7dd1d3d0bf06 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1200,7 +1200,7 @@ static int stm32_dma_alloc_chan_resources(struct dma_chan *c) chan->config_init = false; - ret = pm_runtime_get_sync(dmadev->ddev.dev); + ret = pm_runtime_resume_and_get(dmadev->ddev.dev); if (ret < 0) return ret; @@ -1470,7 +1470,7 @@ static int stm32_dma_suspend(struct device *dev) struct stm32_dma_device *dmadev = dev_get_drvdata(dev); int id, ret, scr; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; From baa16371c9525f24d508508e4d296c031e1de29c Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Mon, 7 Jun 2021 14:46:39 +0800 Subject: [PATCH 1007/1469] dmaengine: stm32-dmamux: Fix PM usage counter unbalance in stm32 dmamux ops pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. We fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced. Fixes: 4f3ceca254e0f ("dmaengine: stm32-dmamux: Add PM Runtime support") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20210607064640.121394-3-zhangqilong3@huawei.com Signed-off-by: Vinod Koul --- drivers/dma/stm32-dmamux.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c index ef0d0555103d..a42164389ebc 100644 --- a/drivers/dma/stm32-dmamux.c +++ b/drivers/dma/stm32-dmamux.c @@ -137,7 +137,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, /* Set dma request */ spin_lock_irqsave(&dmamux->lock, flags); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { spin_unlock_irqrestore(&dmamux->lock, flags); goto error; @@ -336,7 +336,7 @@ static int stm32_dmamux_suspend(struct device *dev) struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev); int i, ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; @@ -361,7 +361,7 @@ static int stm32_dmamux_resume(struct device *dev) if (ret < 0) return ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; From eda97cb095f2958bbad55684a6ca3e7d7af0176a Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Sat, 17 Jul 2021 22:00:21 +0300 Subject: [PATCH 1008/1469] dmaengine: of-dma: router_xlate to return -EPROBE_DEFER if controller is not yet available If the router_xlate can not find the controller in the available DMA devices then it should return with -EPORBE_DEFER in a same way as the of_dma_request_slave_channel() does. The issue can be reproduced if the event router is registered before the DMA controller itself and a driver would request for a channel before the controller is registered. In of_dma_request_slave_channel(): 1. of_dma_find_controller() would find the dma_router 2. ofdma->of_dma_xlate() would fail and returned NULL 3. -ENODEV is returned as error code with this patch we would return in this case the correct -EPROBE_DEFER and the client can try to request the channel later. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210717190021.21897-1-peter.ujfalusi@gmail.com Signed-off-by: Vinod Koul --- drivers/dma/of-dma.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c index ec00b20ae8e4..ac61ecda2926 100644 --- a/drivers/dma/of-dma.c +++ b/drivers/dma/of-dma.c @@ -67,8 +67,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec, return NULL; ofdma_target = of_dma_find_controller(&dma_spec_target); - if (!ofdma_target) - return NULL; + if (!ofdma_target) { + ofdma->dma_router->route_free(ofdma->dma_router->dev, + route_data); + chan = ERR_PTR(-EPROBE_DEFER); + goto err; + } chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target); if (IS_ERR_OR_NULL(chan)) { @@ -89,6 +93,7 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec, } } +err: /* * Need to put the node back since the ofdma->of_dma_route_allocate * has taken it for generating the new, translated dma_spec From 46573e3ab08fb041d5ba7bf7bf3215a1e724c78c Mon Sep 17 00:00:00 2001 From: Tang Bin Date: Wed, 28 Jul 2021 09:49:25 +0800 Subject: [PATCH 1009/1469] nfc: s3fwrn5: fix undefined parameter values in dev_err() In the function s3fwrn5_fw_download(), the 'ret' is not assigned, so the correct value should be given in dev_err function. Fixes: a0302ff5906a ("nfc: s3fwrn5: remove unnecessary label") Signed-off-by: Zhang Shengju Signed-off-by: Tang Bin Reviewed-by: Nathan Chancellor Signed-off-by: David S. Miller --- drivers/nfc/s3fwrn5/firmware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index 1340fab9565e..e3e72b8a29e3 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -423,7 +423,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot allocate shash (code=%ld)\n", PTR_ERR(tfm)); + "Cannot allocate shash (code=%pe)\n", tfm); goto out; } From 557fb5862c9272ad9b21407afe1da8acfd9b53eb Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 27 Jul 2021 23:40:54 -0300 Subject: [PATCH 1010/1469] sctp: fix return value check in __sctp_rcv_asconf_lookup As Ben Hutchings noticed, this check should have been inverted: the call returns true in case of success. Reported-by: Ben Hutchings Fixes: 0c5dc070ff3d ("sctp: validate from_addr_param return") Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index eb3c2a34a31c..5ef86fdb1176 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - if (af->from_addr_param(&paddr, param, peer_port, 0)) + if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); From 76a16be07b209a3f507c72abe823bd3af1c8661a Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Wed, 28 Jul 2021 15:43:13 +0800 Subject: [PATCH 1011/1469] tulip: windbond-840: Fix missing pci_disable_device() in probe and remove Replace pci_enable_device() with pcim_enable_device(), pci_disable_device() and pci_release_regions() will be called in release automatically. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: David S. Miller --- drivers/net/ethernet/dec/tulip/winbond-840.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index f6ff1f76eacb..1876f15dd827 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -357,7 +357,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; void __iomem *ioaddr; - i = pci_enable_device(pdev); + i = pcim_enable_device(pdev); if (i) return i; pci_set_master(pdev); @@ -379,7 +379,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size); if (!ioaddr) - goto err_out_free_res; + goto err_out_netdev; for (i = 0; i < 3; i++) ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); @@ -458,8 +458,6 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) err_out_cleardev: pci_iounmap(pdev, ioaddr); -err_out_free_res: - pci_release_regions(pdev); err_out_netdev: free_netdev (dev); return -ENODEV; @@ -1526,7 +1524,6 @@ static void w840_remove1(struct pci_dev *pdev) if (dev) { struct netdev_private *np = netdev_priv(dev); unregister_netdev(dev); - pci_release_regions(pdev); pci_iounmap(pdev, np->base_addr); free_netdev(dev); } From 5e7b30d24a5b8cb691c173b45b50e3ca0191be19 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 28 Jul 2021 08:49:09 +0200 Subject: [PATCH 1012/1469] nfc: nfcsim: fix use after free during module unload MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a use after free memory corruption during module exit: - nfcsim_exit() - nfcsim_device_free(dev0) - nfc_digital_unregister_device() This iterates over command queue and frees all commands, - dev->up = false - nfcsim_link_shutdown() - nfcsim_link_recv_wake() This wakes the sleeping thread nfcsim_link_recv_skb(). - nfcsim_link_recv_skb() Wake from wait_event_interruptible_timeout(), call directly the deb->cb callback even though (dev->up == false), - digital_send_cmd_complete() Dereference of "struct digital_cmd" cmd which was freed earlier by nfc_digital_unregister_device(). This causes memory corruption shortly after (with unrelated stack trace): nfc nfc0: NFC: nfcsim_recv_wq: Device is down llcp: nfc_llcp_recv: err -19 nfc nfc1: NFC: nfcsim_recv_wq: Device is down BUG: unable to handle page fault for address: ffffffffffffffed Call Trace: fsnotify+0x54b/0x5c0 __fsnotify_parent+0x1fe/0x300 ? vfs_write+0x27c/0x390 vfs_write+0x27c/0x390 ksys_write+0x63/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae KASAN report: BUG: KASAN: use-after-free in digital_send_cmd_complete+0x16/0x50 Write of size 8 at addr ffff88800a05f720 by task kworker/0:2/71 Workqueue: events nfcsim_recv_wq [nfcsim] Call Trace:  dump_stack_lvl+0x45/0x59  print_address_description.constprop.0+0x21/0x140  ? digital_send_cmd_complete+0x16/0x50  ? digital_send_cmd_complete+0x16/0x50  kasan_report.cold+0x7f/0x11b  ? digital_send_cmd_complete+0x16/0x50  ? digital_dep_link_down+0x60/0x60  digital_send_cmd_complete+0x16/0x50  nfcsim_recv_wq+0x38f/0x3d5 [nfcsim]  ? nfcsim_in_send_cmd+0x4a/0x4a [nfcsim]  ? lock_is_held_type+0x98/0x110  ? finish_wait+0x110/0x110  ? rcu_read_lock_sched_held+0x9c/0xd0  ? rcu_read_lock_bh_held+0xb0/0xb0  ? lockdep_hardirqs_on_prepare+0x12e/0x1f0 This flow of calling digital_send_cmd_complete() callback on driver exit is specific to nfcsim which implements reading and sending work queues. Since the NFC digital device was unregistered, the callback should not be called. Fixes: 204bddcb508f ("NFC: nfcsim: Make use of the Digital layer") Cc: Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- drivers/nfc/nfcsim.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index a9864fcdfba6..dd27c85190d3 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -192,8 +192,7 @@ static void nfcsim_recv_wq(struct work_struct *work) if (!IS_ERR(skb)) dev_kfree_skb(skb); - - skb = ERR_PTR(-ENODEV); + return; } dev->cb(dev->nfc_digital_dev, dev->arg, skb); From e9c6729acb38bcf027e40a5b50b2e1b0aa4bc170 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 23 Jul 2021 17:08:40 +0200 Subject: [PATCH 1013/1469] HID: fix typo in Kconfig There is a missing space in "relyingon". Add it. Signed-off-by: Christophe JAILLET Signed-off-by: Jiri Kosina --- drivers/hid/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 160554903ef9..76937f716fbe 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -576,7 +576,7 @@ config HID_LOGITECH_HIDPP depends on HID_LOGITECH select POWER_SUPPLY help - Support for Logitech devices relyingon the HID++ Logitech specification + Support for Logitech devices relying on the HID++ Logitech specification Say Y if you want support for Logitech devices relying on the HID++ specification. Such devices are the various Logitech Touchpads (T650, From ebe0b42a4252333aa4af60fd4d11b69405aa6068 Mon Sep 17 00:00:00 2001 From: Haochen Tong Date: Sun, 18 Jul 2021 01:04:31 +0800 Subject: [PATCH 1014/1469] HID: apple: Add support for Keychron K1 wireless keyboard The Keychron K1 wireless keyboard has a set of Apple-like function keys and an Fn key that works like on an Apple bluetooth keyboard. It identifies as an Apple Alu RevB ANSI keyboard (05ac:024f) over USB and BT. Use hid-apple for it so the Fn key and function keys work correctly. Signed-off-by: Haochen Tong Signed-off-by: Jiri Kosina --- drivers/hid/hid-apple.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 6b8f0d004d34..dc6bd4299c54 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -501,6 +501,8 @@ static const struct hid_device_id apple_devices[] = { APPLE_RDESC_JIS }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO), .driver_data = APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO), From 0818ec1f508fc3b8e957f6c7f77b988c5bc24da7 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 19 Jul 2021 11:27:31 +0100 Subject: [PATCH 1015/1469] HID: Kconfig: Fix spelling mistake "Uninterruptable" -> "Uninterruptible" There is a spelling mistake in the Kconfig text. Fix it. Signed-off-by: Colin Ian King Signed-off-by: Jiri Kosina --- drivers/hid/usbhid/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/usbhid/Kconfig b/drivers/hid/usbhid/Kconfig index dcf3a235870f..7c2032f7f44d 100644 --- a/drivers/hid/usbhid/Kconfig +++ b/drivers/hid/usbhid/Kconfig @@ -38,7 +38,7 @@ config USB_HIDDEV help Say Y here if you want to support HID devices (from the USB specification standpoint) that aren't strictly user interface - devices, like monitor controls and Uninterruptable Power Supplies. + devices, like monitor controls and Uninterruptible Power Supplies. This module supports these devices separately using a separate event interface on /dev/usb/hiddevX (char 180:96 to 180:111). From 6ca2350e11f09d5d3e53777d1eff8ff6d300ed93 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 19 Jul 2021 13:55:28 -0700 Subject: [PATCH 1016/1469] HID: wacom: Re-enable touch by default for Cintiq 24HDT / 27QHDT Commit 670e90924bfe ("HID: wacom: support named keys on older devices") added support for sending named events from the soft buttons on the 24HDT and 27QHDT. In the process, however, it inadvertantly disabled the touchscreen of the 24HDT and 27QHDT by default. The `wacom_set_shared_values` function would normally enable touch by default but because it checks the state of the non-shared `has_mute_touch_switch` flag and `wacom_setup_touch_input_capabilities` sets the state of the /shared/ version, touch ends up being disabled by default. This patch sets the non-shared flag, letting `wacom_set_shared_values` take care of copying the value over to the shared version and setting the default touch state to "on". Fixes: 670e90924bfe ("HID: wacom: support named keys on older devices") CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Jason Gerecke Reviewed-by: Ping Cheng Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 81d7d12bcf34..496a000ef862 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -3831,7 +3831,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, wacom_wac->shared->touch->product == 0xF6) { input_dev->evbit[0] |= BIT_MASK(EV_SW); __set_bit(SW_MUTE_DEVICE, input_dev->swbit); - wacom_wac->shared->has_mute_touch_switch = true; + wacom_wac->has_mute_touch_switch = true; } fallthrough; From 7cc8524f65ce1a350042836c7cf837046aaa6e21 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 19 Jul 2021 13:55:31 -0700 Subject: [PATCH 1017/1469] HID: wacom: Skip processing of touches with negative slot values The `input_mt_get_slot_by_key` function may return a negative value if an error occurs (e.g. running out of slots). If this occurs we should really avoid reporting any data for the slot. Signed-off-by: Ping Cheng Signed-off-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 496a000ef862..81ba642adcb7 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2548,6 +2548,9 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac, int slot; slot = input_mt_get_slot_by_key(input, hid_data->id); + if (slot < 0) + return; + input_mt_slot(input, slot); input_mt_report_slot_state(input, MT_TOOL_FINGER, prox); } From a59c7b6c6ff6d5437f293709e766f939d7107266 Mon Sep 17 00:00:00 2001 From: Ping Bao Date: Wed, 21 Jul 2021 15:56:15 -0700 Subject: [PATCH 1018/1469] platform/x86: intel-hid: add Alder Lake ACPI device ID Alder Lake has a new ACPI ID for Intel HID event filter device. Signed-off-by: Ping Bao Link: https://lore.kernel.org/r/20210721225615.20575-1-ping.a.bao@intel.com Signed-off-by: Hans de Goede --- drivers/platform/x86/intel-hid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 078648a9201b..e5fbe017f8e1 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -25,6 +25,7 @@ static const struct acpi_device_id intel_hid_ids[] = { {"INT33D5", 0}, {"INTC1051", 0}, {"INTC1054", 0}, + {"INTC1070", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids); From 2b2c66f607d00d17f879c0d946d44340bfbdc501 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 26 Jul 2021 17:36:30 +0200 Subject: [PATCH 1019/1469] platform/x86: gigabyte-wmi: add support for B550 Aorus Elite V2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported as working here: https://github.com/t-8ch/linux-gigabyte-wmi-driver/issues/1#issuecomment-879398883 Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20210726153630.65213-1-linux@weissschuh.net Signed-off-by: Hans de Goede --- drivers/platform/x86/gigabyte-wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 5529d7b0abea..fbb224a82e34 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), From 1e60cebf82948cfdc9497ea4553bab125587593c Mon Sep 17 00:00:00 2001 From: zhang kai Date: Wed, 28 Jul 2021 18:54:18 +0800 Subject: [PATCH 1020/1469] net: let flow have same hash in two directions using same source and destination ip/port for flow hash calculation within the two directions. Signed-off-by: zhang kai Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2aadbfc5193b..4b2415d34873 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1504,7 +1504,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow) } EXPORT_SYMBOL(flow_get_u32_dst); -/* Sort the source and destination IP (and the ports if the IP are the same), +/* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) @@ -1515,11 +1515,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) case FLOW_DISSECTOR_KEY_IPV4_ADDRS: addr_diff = (__force u32)keys->addrs.v4addrs.dst - (__force u32)keys->addrs.v4addrs.src; - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); + + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; @@ -1527,13 +1527,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); + } + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; From 89fb62fde3b226f99b7015280cf132e2a7438edf Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Wed, 28 Jul 2021 20:11:07 +0800 Subject: [PATCH 1021/1469] sis900: Fix missing pci_disable_device() in probe and remove Replace pci_enable_device() with pcim_enable_device(), pci_disable_device() and pci_release_regions() will be called in release automatically. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: David S. Miller --- drivers/net/ethernet/sis/sis900.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index ca9c00b7f588..cff87de9178a 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -443,7 +443,7 @@ static int sis900_probe(struct pci_dev *pci_dev, #endif /* setup various bits in PCI command register */ - ret = pci_enable_device(pci_dev); + ret = pcim_enable_device(pci_dev); if(ret) return ret; i = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32)); @@ -469,7 +469,7 @@ static int sis900_probe(struct pci_dev *pci_dev, ioaddr = pci_iomap(pci_dev, 0, 0); if (!ioaddr) { ret = -ENOMEM; - goto err_out_cleardev; + goto err_out; } sis_priv = netdev_priv(net_dev); @@ -581,8 +581,6 @@ err_unmap_tx: sis_priv->tx_ring_dma); err_out_unmap: pci_iounmap(pci_dev, ioaddr); -err_out_cleardev: - pci_release_regions(pci_dev); err_out: free_netdev(net_dev); return ret; @@ -2499,7 +2497,6 @@ static void sis900_remove(struct pci_dev *pci_dev) sis_priv->tx_ring_dma); pci_iounmap(pci_dev, sis_priv->ioaddr); free_netdev(net_dev); - pci_release_regions(pci_dev); } static int __maybe_unused sis900_suspend(struct device *dev) From ef04688871f3386b6d40ade8f5c664290420f819 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 27 Jul 2021 10:50:31 -0600 Subject: [PATCH 1022/1469] io_uring: don't block level reissue off completion path Some setups, like SCSI, can throw spurious -EAGAIN off the softirq completion path. Normally we expect this to happen inline as part of submission, but apparently SCSI has a weird corner case where it can happen as part of normal completions. This should be solved by having the -EAGAIN bubble back up the stack as part of submission, but previous attempts at this failed and we're not just quite there yet. Instead we currently use REQ_F_REISSUE to handle this case. For now, catch it in io_rw_should_reissue() and prevent a reissue from a bogus path. Cc: stable@vger.kernel.org Reported-by: Fabian Ebner Tested-by: Fabian Ebner Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6ba101cd4661..83f67d33bf67 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2447,6 +2447,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req) */ if (percpu_ref_is_dying(&ctx->refs)) return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; return true; } #else From a890d01e4ee016978776e45340e521b3bbbdf41f Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Wed, 28 Jul 2021 11:03:22 +0800 Subject: [PATCH 1023/1469] io_uring: fix poll requests leaking second poll entries For pure poll requests, it doesn't remove the second poll wait entry when it's done, neither after vfs_poll() or in the poll completion handler. We should remove the second poll wait entry. And we use io_poll_remove_double() rather than io_poll_remove_waitqs() since the latter has some redundant logic. Fixes: 88e41cf928a6 ("io_uring: add multishot mode for IORING_OP_POLL_ADD") Cc: stable@vger.kernel.org # 5.13+ Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210728030322.12307-1-haoxu@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 83f67d33bf67..bf548af0426c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4939,7 +4939,6 @@ static bool io_poll_complete(struct io_kiocb *req, __poll_t mask) if (req->poll.events & EPOLLONESHOT) flags = 0; if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) { - io_poll_remove_waitqs(req); req->poll.done = true; flags = 0; } @@ -4962,6 +4961,7 @@ static void io_poll_task_func(struct io_kiocb *req) done = io_poll_complete(req, req->result); if (done) { + io_poll_remove_double(req); hash_del(&req->hash_node); } else { req->result = 0; @@ -5149,7 +5149,7 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, ipt->error = -EINVAL; spin_lock_irq(&ctx->completion_lock); - if (ipt->error) + if (ipt->error || (mask && (poll->events & EPOLLONESHOT))) io_poll_remove_double(req); if (likely(poll->head)) { spin_lock(&poll->head->lock); @@ -5221,7 +5221,6 @@ static int io_arm_poll_handler(struct io_kiocb *req) ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, io_async_wake); if (ret || ipt.error) { - io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); if (ret) return IO_APOLL_READY; From 31428c78748cafdd9352e1f622eb89bf453d9700 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 26 Jul 2021 20:41:23 +0100 Subject: [PATCH 1024/1469] ASoC: component: Remove misplaced prefix handling in pin control functions When the component level pin control functions were added they for some no longer obvious reason handled adding prefixing of widget names. This meant that when the lack of prefix handling in the DAPM level pin operations was fixed by ae4fc532244b3bb4d (ASoC: dapm: use component prefix when checking widget names) the one device using the component level API ended up with the prefix being applied twice, causing all lookups to fail. Fix this by removing the redundant prefixing from the component code, which has the nice side effect of also making that code much simpler. Reported-by: Richard Fitzgerald Signed-off-by: Mark Brown Tested-by: Lucas Tanure Link: https://lore.kernel.org/r/20210726194123.54585-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/soc-component.c | 63 +++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 36 deletions(-) diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index 3a5e84e16a87..c8dfd0de30e4 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -148,86 +148,75 @@ int snd_soc_component_set_bias_level(struct snd_soc_component *component, return soc_component_ret(component, ret); } -static int soc_component_pin(struct snd_soc_component *component, - const char *pin, - int (*pin_func)(struct snd_soc_dapm_context *dapm, - const char *pin)) -{ - struct snd_soc_dapm_context *dapm = - snd_soc_component_get_dapm(component); - char *full_name; - int ret; - - if (!component->name_prefix) { - ret = pin_func(dapm, pin); - goto end; - } - - full_name = kasprintf(GFP_KERNEL, "%s %s", component->name_prefix, pin); - if (!full_name) { - ret = -ENOMEM; - goto end; - } - - ret = pin_func(dapm, full_name); - kfree(full_name); -end: - return soc_component_ret(component, ret); -} - int snd_soc_component_enable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_enable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_enable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_enable_pin); int snd_soc_component_enable_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_enable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_enable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_enable_pin_unlocked); int snd_soc_component_disable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_disable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_disable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_disable_pin); int snd_soc_component_disable_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_disable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_disable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_disable_pin_unlocked); int snd_soc_component_nc_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_nc_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_nc_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_nc_pin); int snd_soc_component_nc_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_nc_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_nc_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_nc_pin_unlocked); int snd_soc_component_get_pin_status(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_get_pin_status); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_get_pin_status(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_get_pin_status); int snd_soc_component_force_enable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_force_enable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_force_enable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_force_enable_pin); @@ -235,7 +224,9 @@ int snd_soc_component_force_enable_pin_unlocked( struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_force_enable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_force_enable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_force_enable_pin_unlocked); From acbf58e530416e167c3b323111f4013d9f2b0a7d Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 28 Jul 2021 11:44:16 +0100 Subject: [PATCH 1025/1469] ASoC: wm_adsp: Let soc_cleanup_component_debugfs remove debugfs soc_cleanup_component_debugfs will debugfs_remove_recursive the component->debugfs_root, so adsp doesn't need to also remove the same entry. By doing that adsp also creates a race with core component, which causes a NULL pointer dereference Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20210728104416.636591-1-tanureal@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 549d98241dae..fe15cbc7bcaf 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -747,7 +747,6 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp, static void wm_adsp2_cleanup_debugfs(struct wm_adsp *dsp) { wm_adsp_debugfs_clear(dsp); - debugfs_remove_recursive(dsp->debugfs_root); } #else static inline void wm_adsp2_init_debugfs(struct wm_adsp *dsp, From 830b69f6c059bc46451e7c4be8b796d483acb0bd Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 27 Jul 2021 17:49:48 +0100 Subject: [PATCH 1026/1469] MAINTAINERS: Add sound devicetree bindings for Wolfson Micro devices Include all wm* sound bindings in the section for Wolfson Micro drivers. This section already includes the actual driver source files. Also update the existing entry to match all wlf,* sound bindings. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20210727164948.4308-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 516a9fead7e3..225e6c885b66 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19744,7 +19744,8 @@ F: Documentation/devicetree/bindings/extcon/wlf,arizona.yaml F: Documentation/devicetree/bindings/mfd/wlf,arizona.yaml F: Documentation/devicetree/bindings/mfd/wm831x.txt F: Documentation/devicetree/bindings/regulator/wlf,arizona.yaml -F: Documentation/devicetree/bindings/sound/wlf,arizona.yaml +F: Documentation/devicetree/bindings/sound/wlf,*.yaml +F: Documentation/devicetree/bindings/sound/wm* F: Documentation/hwmon/wm83??.rst F: arch/arm/mach-s3c/mach-crag6410* F: drivers/clk/clk-wm83*.c From 36c2530ea963884eeb0097169f853fdc36f16ad7 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 27 Jul 2021 18:04:28 +0200 Subject: [PATCH 1027/1469] spi: imx: mx51-ecspi: Fix CONFIGREG delay comment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For (2 * 1000000) / min_speed_hz < 10 to be true in naturals with zero, the min_speed_hz must be above 200000 (i.e. 200001 rounds down to 9, so the condition triggers). Update the comment. No functional change. Fixes: 6fd8b8503a0dc ("spi: spi-imx: Fix out-of-order CS/SCLK operation at low speeds") Signed-off-by: Marek Vasut Cc: Uwe Kleine-König Cc: Mark Brown Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210727160428.7673-1-marex@denx.de Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 2872993550bd..fa68e9817929 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -593,7 +593,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, } delay = (2 * 1000000) / min_speed_hz; - if (likely(delay < 10)) /* SCLK is faster than 100 kHz */ + if (likely(delay < 10)) /* SCLK is faster than 200 kHz */ udelay(delay); else /* SCLK is _very_ slow */ usleep_range(delay, delay + 10); From e0eef3690dc66b3ecc6e0f1267f332403eb22bea Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 28 Jul 2021 23:19:58 +0800 Subject: [PATCH 1028/1469] Revert "ACPI: resources: Add checks for ACPI IRQ override" The commit 0ec4e55e9f57 ("ACPI: resources: Add checks for ACPI IRQ override") introduces regression on some platforms, at least it makes the UART can't get correct irq setting on two different platforms, and it makes the kernel can't bootup on these two platforms. This reverts commit 0ec4e55e9f571f08970ed115ec0addc691eda613. Regression-discuss: https://bugzilla.kernel.org/show_bug.cgi?id=213031 Reported-by: PGNd Cc: 5.4+ # 5.4+ Signed-off-by: Hui Wang Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index dc01fb550b28..ee78a210c606 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -423,13 +423,6 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, } } -static bool irq_is_legacy(struct acpi_resource_irq *irq) -{ - return irq->triggering == ACPI_EDGE_SENSITIVE && - irq->polarity == ACPI_ACTIVE_HIGH && - irq->shareable == ACPI_EXCLUSIVE; -} - /** * acpi_dev_resource_interrupt - Extract ACPI interrupt resource information. * @ares: Input ACPI resource object. @@ -468,7 +461,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, } acpi_dev_get_irqresource(res, irq->interrupts[index], irq->triggering, irq->polarity, - irq->shareable, irq_is_legacy(irq)); + irq->shareable, true); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: ext_irq = &ares->data.extended_irq; From 41a8457f3f6f829be1f8f8fa7577a46b9b7223ef Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 27 Jul 2021 09:18:24 -0700 Subject: [PATCH 1029/1469] ACPI: DPTF: Fix reading of attributes The current assumption that methods to read PCH FIVR attributes will return integer, is not correct. There is no good way to return integer as negative numbers are also valid. These read methods return a package of integers. The first integer returns status, which is 0 on success and any other value for failure. When the returned status is zero, then the second integer returns the actual value. This change fixes this issue by replacing acpi_evaluate_integer() with acpi_evaluate_object() and use acpi_extract_package() to extract results. Fixes: 2ce6324eadb01 ("ACPI: DPTF: Add PCH FIVR participant driver") Signed-off-by: Srinivas Pandruvada Cc: 5.10+ # 5.10+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/dptf/dptf_pch_fivr.c | 51 ++++++++++++++++++++++++++----- 1 file changed, 43 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 5fca18296bf6..550b9081fcbc 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -9,6 +9,42 @@ #include #include +struct pch_fivr_resp { + u64 status; + u64 result; +}; + +static int pch_fivr_read(acpi_handle handle, char *method, struct pch_fivr_resp *fivr_resp) +{ + struct acpi_buffer resp = { sizeof(struct pch_fivr_resp), fivr_resp}; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_buffer format = { sizeof("NN"), "NN" }; + union acpi_object *obj; + acpi_status status; + int ret = -EFAULT; + + status = acpi_evaluate_object(handle, method, NULL, &buffer); + if (ACPI_FAILURE(status)) + return ret; + + obj = buffer.pointer; + if (!obj || obj->type != ACPI_TYPE_PACKAGE) + goto release_buffer; + + status = acpi_extract_package(obj, &format, &resp); + if (ACPI_FAILURE(status)) + goto release_buffer; + + if (fivr_resp->status) + goto release_buffer; + + ret = 0; + +release_buffer: + kfree(buffer.pointer); + return ret; +} + /* * Presentation of attributes which are defined for INT1045 * They are: @@ -23,15 +59,14 @@ static ssize_t name##_show(struct device *dev,\ char *buf)\ {\ struct acpi_device *acpi_dev = dev_get_drvdata(dev);\ - unsigned long long val;\ - acpi_status status;\ + struct pch_fivr_resp fivr_resp;\ + int status;\ \ - status = acpi_evaluate_integer(acpi_dev->handle, #method,\ - NULL, &val);\ - if (ACPI_SUCCESS(status))\ - return sprintf(buf, "%d\n", (int)val);\ - else\ - return -EINVAL;\ + status = pch_fivr_read(acpi_dev->handle, #method, &fivr_resp);\ + if (status)\ + return status;\ +\ + return sprintf(buf, "%llu\n", fivr_resp.result);\ } #define PCH_FIVR_STORE(name, method) \ From 240246f6b913b0c23733cfd2def1d283f8cc9bbe Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 9 Jul 2021 11:29:22 -0500 Subject: [PATCH 1030/1469] btrfs: mark compressed range uptodate only if all bio succeed In compression write endio sequence, the range which the compressed_bio writes is marked as uptodate if the last bio of the compressed (sub)bios is completed successfully. There could be previous bio which may have failed which is recorded in cb->errors. Set the writeback range as uptodate only if cb->errors is zero, as opposed to checking only the last bio's status. Backporting notes: in all versions up to 4.4 the last argument is always replaced by "!cb->errors". CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/compression.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 9a023ae0f98b..30d82cdf128c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -352,7 +352,7 @@ static void end_compressed_bio_write(struct bio *bio) btrfs_record_physical_zoned(inode, cb->start, bio); btrfs_writepage_endio_finish_ordered(BTRFS_I(inode), NULL, cb->start, cb->start + cb->len - 1, - bio->bi_status == BLK_STS_OK); + !cb->errors); end_compressed_writeback(inode, cb); /* note, our inode could be gone now */ From ecc64fab7d49c678e70bd4c35fe64d2ab3e3d212 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 27 Jul 2021 11:24:43 +0100 Subject: [PATCH 1031/1469] btrfs: fix lost inode on log replay after mix of fsync, rename and inode eviction When checking if we need to log the new name of a renamed inode, we are checking if the inode and its parent inode have been logged before, and if not we don't log the new name. The check however is buggy, as it directly compares the logged_trans field of the inodes versus the ID of the current transaction. The problem is that logged_trans is a transient field, only stored in memory and never persisted in the inode item, so if an inode was logged before, evicted and reloaded, its logged_trans field is set to a value of 0, meaning the check will return false and the new name of the renamed inode is not logged. If the old parent directory was previously fsynced and we deleted the logged directory entries corresponding to the old name, we end up with a log that when replayed will delete the renamed inode. The following example triggers the problem: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ mkdir /mnt/A $ mkdir /mnt/B $ echo -n "hello world" > /mnt/A/foo $ sync # Add some new file to A and fsync directory A. $ touch /mnt/A/bar $ xfs_io -c "fsync" /mnt/A # Now trigger inode eviction. We are only interested in triggering # eviction for the inode of directory A. $ echo 2 > /proc/sys/vm/drop_caches # Move foo from directory A to directory B. # This deletes the directory entries for foo in A from the log, and # does not add the new name for foo in directory B to the log, because # logged_trans of A is 0, which is less than the current transaction ID. $ mv /mnt/A/foo /mnt/B/foo # Now make an fsync to anything except A, B or any file inside them, # like for example create a file at the root directory and fsync this # new file. This syncs the log that contains all the changes done by # previous rename operation. $ touch /mnt/baz $ xfs_io -c "fsync" /mnt/baz # Mount the filesystem and replay the log. $ mount /dev/sdc /mnt # Check the filesystem content. $ ls -1R /mnt /mnt/: A B baz /mnt/A: bar /mnt/B: $ # File foo is gone, it's neither in A/ nor in B/. Fix this by using the inode_logged() helper at btrfs_log_new_name(), which safely checks if an inode was logged before in the current transaction. A test case for fstests will follow soon. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9fd0348be7f5..e6430ac9bbe8 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6503,8 +6503,8 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ - if (inode->logged_trans < trans->transid && - (!old_dir || old_dir->logged_trans < trans->transid)) + if (!inode_logged(trans, inode) && + (!old_dir || !inode_logged(trans, old_dir))) return; /* From b2a616676839e2a6b02c8e40be7f886f882ed194 Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Tue, 27 Jul 2021 15:13:03 +0800 Subject: [PATCH 1032/1469] btrfs: fix rw device counting in __btrfs_free_extra_devids When removing a writeable device in __btrfs_free_extra_devids, the rw device count should be decremented. This error was caught by Syzbot which reported a warning in close_fs_devices: WARNING: CPU: 1 PID: 9355 at fs/btrfs/volumes.c:1168 close_fs_devices+0x763/0x880 fs/btrfs/volumes.c:1168 Modules linked in: CPU: 0 PID: 9355 Comm: syz-executor552 Not tainted 5.13.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:close_fs_devices+0x763/0x880 fs/btrfs/volumes.c:1168 RSP: 0018:ffffc9000333f2f0 EFLAGS: 00010293 RAX: ffffffff8365f5c3 RBX: 0000000000000001 RCX: ffff888029afd4c0 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff88802846f508 R08: ffffffff8365f525 R09: ffffed100337d128 R10: ffffed100337d128 R11: 0000000000000000 R12: dffffc0000000000 R13: ffff888019be8868 R14: 1ffff1100337d10d R15: 1ffff1100337d10a FS: 00007f6f53828700(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000047c410 CR3: 00000000302a6000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_close_devices+0xc9/0x450 fs/btrfs/volumes.c:1180 open_ctree+0x8e1/0x3968 fs/btrfs/disk-io.c:3693 btrfs_fill_super fs/btrfs/super.c:1382 [inline] btrfs_mount_root+0xac5/0xc60 fs/btrfs/super.c:1749 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x86/0x270 fs/super.c:1498 fc_mount fs/namespace.c:993 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1023 btrfs_mount+0x3d3/0xb50 fs/btrfs/super.c:1809 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x86/0x270 fs/super.c:1498 do_new_mount fs/namespace.c:2905 [inline] path_mount+0x196f/0x2be0 fs/namespace.c:3235 do_mount fs/namespace.c:3248 [inline] __do_sys_mount fs/namespace.c:3456 [inline] __se_sys_mount+0x2f9/0x3b0 fs/namespace.c:3433 do_syscall_64+0x3f/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae Because fs_devices->rw_devices was not 0 after closing all devices. Here is the call trace that was observed: btrfs_mount_root(): btrfs_scan_one_device(): device_list_add(); <---------------- device added btrfs_open_devices(): open_fs_devices(): btrfs_open_one_device(); <-------- writable device opened, rw device count ++ btrfs_fill_super(): open_ctree(): btrfs_free_extra_devids(): __btrfs_free_extra_devids(); <--- writable device removed, rw device count not decremented fail_tree_roots: btrfs_close_devices(): close_fs_devices(); <------- rw device count off by 1 As a note, prior to commit cf89af146b7e ("btrfs: dev-replace: fail mount if we don't have replace item with target device"), rw_devices was decremented on removing a writable device in __btrfs_free_extra_devids only if the BTRFS_DEV_STATE_REPLACE_TGT bit was not set for the device. However, this check does not need to be reinstated as it is now redundant and incorrect. In __btrfs_free_extra_devids, we skip removing the device if it is the target for replacement. This is done by checking whether device->devid == BTRFS_DEV_REPLACE_DEVID. Since BTRFS_DEV_STATE_REPLACE_TGT is set only on the device with devid BTRFS_DEV_REPLACE_DEVID, no devices should have the BTRFS_DEV_STATE_REPLACE_TGT bit set after the check, and so it's redundant to test for that bit. Additionally, following commit 82372bc816d7 ("Btrfs: make the logic of source device removing more clear"), rw_devices is incremented whenever a writeable device is added to the alloc list (including the target device in btrfs_dev_replace_finishing), so all removals of writable devices from the alloc list should also be accompanied by a decrement to rw_devices. Reported-by: syzbot+a70e2ad0879f160b9217@syzkaller.appspotmail.com Fixes: cf89af146b7e ("btrfs: dev-replace: fail mount if we don't have replace item with target device") CC: stable@vger.kernel.org # 5.10+ Tested-by: syzbot+a70e2ad0879f160b9217@syzkaller.appspotmail.com Reviewed-by: Anand Jain Signed-off-by: Desmond Cheong Zhi Xi Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c6c14315b1c9..4c83256ae37f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1078,6 +1078,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); + fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; From cbcf01128d0a92e131bd09f1688fe032480b65ca Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 28 Jul 2021 14:47:20 +0200 Subject: [PATCH 1033/1469] af_unix: fix garbage collect vs MSG_PEEK unix_gc() assumes that candidate sockets can never gain an external reference (i.e. be installed into an fd) while the unix_gc_lock is held. Except for MSG_PEEK this is guaranteed by modifying inflight count under the unix_gc_lock. MSG_PEEK does not touch any variable protected by unix_gc_lock (file count is not), yet it needs to be serialized with garbage collection. Do this by locking/unlocking unix_gc_lock: 1) increment file count 2) lock/unlock barrier to make sure incremented file count is visible to garbage collection 3) install file into fd This is a lock barrier (unlike smp_mb()) that ensures that garbage collection is run completely before or completely after the barrier. Cc: Signed-off-by: Greg Kroah-Hartman Signed-off-by: Miklos Szeredi Signed-off-by: Linus Torvalds --- net/unix/af_unix.c | 51 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 2 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 23c92ad15c61..ba7ced947e51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1526,6 +1526,53 @@ out: return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -2175,7 +2222,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2418,7 +2465,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); From 25905f602fdb0cfa147017056636768a7aa1ff6f Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 21 Jul 2021 12:25:20 -0700 Subject: [PATCH 1034/1469] dmaengine: idxd: Change license on idxd.h to LGPL This file was given GPL-2.0 license. But LGPL-2.1 makes more sense as it needs to be used by libraries outside of the kernel source tree. Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- include/uapi/linux/idxd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index e33997b4d750..edc346a77c91 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ /* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ #ifndef _USR_IDXD_H_ #define _USR_IDXD_H_ From 345daff2e994ee844d6a609c37f085695fbb4c4d Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Tue, 27 Jul 2021 17:24:18 +0200 Subject: [PATCH 1035/1469] ucounts: Fix race condition between alloc_ucounts and put_ucounts The race happens because put_ucounts() doesn't use spinlock and get_ucounts is not under spinlock: CPU0 CPU1 ---- ---- alloc_ucounts() put_ucounts() spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); atomic_dec_and_test(&ucounts->count)) spin_unlock_irq(&ucounts_lock); spin_lock_irqsave(&ucounts_lock, flags); hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); ucounts = get_ucounts(ucounts); ================================================================== BUG: KASAN: use-after-free in instrument_atomic_read_write include/linux/instrumented.h:101 [inline] BUG: KASAN: use-after-free in atomic_add_negative include/asm-generic/atomic-instrumented.h:556 [inline] BUG: KASAN: use-after-free in get_ucounts kernel/ucount.c:152 [inline] BUG: KASAN: use-after-free in get_ucounts kernel/ucount.c:150 [inline] BUG: KASAN: use-after-free in alloc_ucounts+0x19b/0x5b0 kernel/ucount.c:188 Write of size 4 at addr ffff88802821e41c by task syz-executor.4/16785 CPU: 1 PID: 16785 Comm: syz-executor.4 Not tainted 5.14.0-rc1-next-20210712-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:105 print_address_description.constprop.0.cold+0x6c/0x309 mm/kasan/report.c:233 __kasan_report mm/kasan/report.c:419 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:436 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x13d/0x180 mm/kasan/generic.c:189 instrument_atomic_read_write include/linux/instrumented.h:101 [inline] atomic_add_negative include/asm-generic/atomic-instrumented.h:556 [inline] get_ucounts kernel/ucount.c:152 [inline] get_ucounts kernel/ucount.c:150 [inline] alloc_ucounts+0x19b/0x5b0 kernel/ucount.c:188 set_cred_ucounts+0x171/0x3a0 kernel/cred.c:684 __sys_setuid+0x285/0x400 kernel/sys.c:623 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x4665d9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fde54097188 EFLAGS: 00000246 ORIG_RAX: 0000000000000069 RAX: ffffffffffffffda RBX: 000000000056bf80 RCX: 00000000004665d9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00000000000000ff RBP: 00000000004bfcb9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000056bf80 R13: 00007ffc8655740f R14: 00007fde54097300 R15: 0000000000022000 Allocated by task 16784: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] ____kasan_kmalloc mm/kasan/common.c:513 [inline] ____kasan_kmalloc mm/kasan/common.c:472 [inline] __kasan_kmalloc+0x9b/0xd0 mm/kasan/common.c:522 kmalloc include/linux/slab.h:591 [inline] kzalloc include/linux/slab.h:721 [inline] alloc_ucounts+0x23d/0x5b0 kernel/ucount.c:169 set_cred_ucounts+0x171/0x3a0 kernel/cred.c:684 __sys_setuid+0x285/0x400 kernel/sys.c:623 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Freed by task 16785: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track+0x1c/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:360 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xfb/0x130 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:229 [inline] slab_free_hook mm/slub.c:1650 [inline] slab_free_freelist_hook+0xdf/0x240 mm/slub.c:1675 slab_free mm/slub.c:3235 [inline] kfree+0xeb/0x650 mm/slub.c:4295 put_ucounts kernel/ucount.c:200 [inline] put_ucounts+0x117/0x150 kernel/ucount.c:192 put_cred_rcu+0x27a/0x520 kernel/cred.c:124 rcu_do_batch kernel/rcu/tree.c:2550 [inline] rcu_core+0x7ab/0x1380 kernel/rcu/tree.c:2785 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_record_aux_stack+0xe5/0x110 mm/kasan/generic.c:348 insert_work+0x48/0x370 kernel/workqueue.c:1332 __queue_work+0x5c1/0xed0 kernel/workqueue.c:1498 queue_work_on+0xee/0x110 kernel/workqueue.c:1525 queue_work include/linux/workqueue.h:507 [inline] call_usermodehelper_exec+0x1f0/0x4c0 kernel/umh.c:435 kobject_uevent_env+0xf8f/0x1650 lib/kobject_uevent.c:618 netdev_queue_add_kobject net/core/net-sysfs.c:1621 [inline] netdev_queue_update_kobjects+0x374/0x450 net/core/net-sysfs.c:1655 register_queue_kobjects net/core/net-sysfs.c:1716 [inline] netdev_register_kobject+0x35a/0x430 net/core/net-sysfs.c:1959 register_netdevice+0xd33/0x1500 net/core/dev.c:10331 nsim_init_netdevsim drivers/net/netdevsim/netdev.c:317 [inline] nsim_create+0x381/0x4d0 drivers/net/netdevsim/netdev.c:364 __nsim_dev_port_add+0x32e/0x830 drivers/net/netdevsim/dev.c:1295 nsim_dev_port_add_all+0x53/0x150 drivers/net/netdevsim/dev.c:1355 nsim_dev_probe+0xcb5/0x1190 drivers/net/netdevsim/dev.c:1496 call_driver_probe drivers/base/dd.c:517 [inline] really_probe+0x23c/0xcd0 drivers/base/dd.c:595 __driver_probe_device+0x338/0x4d0 drivers/base/dd.c:747 driver_probe_device+0x4c/0x1a0 drivers/base/dd.c:777 __device_attach_driver+0x20b/0x2f0 drivers/base/dd.c:894 bus_for_each_drv+0x15f/0x1e0 drivers/base/bus.c:427 __device_attach+0x228/0x4a0 drivers/base/dd.c:965 bus_probe_device+0x1e4/0x290 drivers/base/bus.c:487 device_add+0xc2f/0x2180 drivers/base/core.c:3356 nsim_bus_dev_new drivers/net/netdevsim/bus.c:431 [inline] new_device_store+0x436/0x710 drivers/net/netdevsim/bus.c:298 bus_attr_store+0x72/0xa0 drivers/base/bus.c:122 sysfs_kf_write+0x110/0x160 fs/sysfs/file.c:139 kernfs_fop_write_iter+0x342/0x500 fs/kernfs/file.c:296 call_write_iter include/linux/fs.h:2152 [inline] new_sync_write+0x426/0x650 fs/read_write.c:518 vfs_write+0x75a/0xa40 fs/read_write.c:605 ksys_write+0x12d/0x250 fs/read_write.c:658 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Second to last potentially related work creation: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_record_aux_stack+0xe5/0x110 mm/kasan/generic.c:348 insert_work+0x48/0x370 kernel/workqueue.c:1332 __queue_work+0x5c1/0xed0 kernel/workqueue.c:1498 queue_work_on+0xee/0x110 kernel/workqueue.c:1525 queue_work include/linux/workqueue.h:507 [inline] call_usermodehelper_exec+0x1f0/0x4c0 kernel/umh.c:435 kobject_uevent_env+0xf8f/0x1650 lib/kobject_uevent.c:618 kobject_synth_uevent+0x701/0x850 lib/kobject_uevent.c:208 uevent_store+0x20/0x50 drivers/base/core.c:2371 dev_attr_store+0x50/0x80 drivers/base/core.c:2072 sysfs_kf_write+0x110/0x160 fs/sysfs/file.c:139 kernfs_fop_write_iter+0x342/0x500 fs/kernfs/file.c:296 call_write_iter include/linux/fs.h:2152 [inline] new_sync_write+0x426/0x650 fs/read_write.c:518 vfs_write+0x75a/0xa40 fs/read_write.c:605 ksys_write+0x12d/0x250 fs/read_write.c:658 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88802821e400 which belongs to the cache kmalloc-192 of size 192 The buggy address is located 28 bytes inside of 192-byte region [ffff88802821e400, ffff88802821e4c0) The buggy address belongs to the page: page:ffffea0000a08780 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2821e flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 dead000000000100 dead000000000122 ffff888010841a00 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x12cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY), pid 1, ts 12874702440, free_ts 12637793385 prep_new_page mm/page_alloc.c:2433 [inline] get_page_from_freelist+0xa72/0x2f80 mm/page_alloc.c:4166 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5374 alloc_page_interleave+0x1e/0x200 mm/mempolicy.c:2119 alloc_pages+0x238/0x2a0 mm/mempolicy.c:2242 alloc_slab_page mm/slub.c:1713 [inline] allocate_slab+0x32b/0x4c0 mm/slub.c:1853 new_slab mm/slub.c:1916 [inline] new_slab_objects mm/slub.c:2662 [inline] ___slab_alloc+0x4ba/0x820 mm/slub.c:2825 __slab_alloc.constprop.0+0xa7/0xf0 mm/slub.c:2865 slab_alloc_node mm/slub.c:2947 [inline] slab_alloc mm/slub.c:2989 [inline] __kmalloc+0x312/0x330 mm/slub.c:4133 kmalloc include/linux/slab.h:596 [inline] kzalloc include/linux/slab.h:721 [inline] __register_sysctl_table+0x112/0x1090 fs/proc/proc_sysctl.c:1318 rds_tcp_init_net+0x1db/0x4f0 net/rds/tcp.c:551 ops_init+0xaf/0x470 net/core/net_namespace.c:140 __register_pernet_operations net/core/net_namespace.c:1137 [inline] register_pernet_operations+0x35a/0x850 net/core/net_namespace.c:1214 register_pernet_device+0x26/0x70 net/core/net_namespace.c:1301 rds_tcp_init+0x77/0xe0 net/rds/tcp.c:717 do_one_initcall+0x103/0x650 init/main.c:1285 do_initcall_level init/main.c:1360 [inline] do_initcalls init/main.c:1376 [inline] do_basic_setup init/main.c:1396 [inline] kernel_init_freeable+0x6b8/0x741 init/main.c:1598 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1343 [inline] free_pcp_prepare+0x312/0x7d0 mm/page_alloc.c:1394 free_unref_page_prepare mm/page_alloc.c:3329 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3408 __vunmap+0x783/0xb70 mm/vmalloc.c:2587 free_work+0x58/0x70 mm/vmalloc.c:82 process_one_work+0x98d/0x1630 kernel/workqueue.c:2276 worker_thread+0x658/0x11f0 kernel/workqueue.c:2422 kthread+0x3e5/0x4d0 kernel/kthread.c:319 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 Memory state around the buggy address: ffff88802821e300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88802821e380: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc >ffff88802821e400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88802821e480: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88802821e500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== - The race fix has two parts. * Changing the code to guarantee that ucounts->count is only decremented when ucounts_lock is held. This guarantees that find_ucounts will never find a structure with a zero reference count. * Changing alloc_ucounts to increment ucounts->count while ucounts_lock is held. This guarantees the reference count on the found data structure will not be decremented to zero (and the data structure freed) before the reference count is incremented. -- Eric Biederman Reported-by: syzbot+01985d7909f9468f013c@syzkaller.appspotmail.com Reported-by: syzbot+59dd63761094a80ad06d@syzkaller.appspotmail.com Reported-by: syzbot+6cd79f45bb8fa1c9eeae@syzkaller.appspotmail.com Reported-by: syzbot+b6e65bd125a05f803d6b@syzkaller.appspotmail.com Fixes: b6c336528926 ("Use atomic_t for ucounts reference counting") Cc: Hillf Danton Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/7b2ace1759b281cdd2d66101d6b305deef722efb.1627397820.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- kernel/ucount.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/ucount.c b/kernel/ucount.c index 87799e2379bd..77be3bbe3cc4 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -160,6 +160,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; + long overflow; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -184,8 +185,12 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) return new; } } + overflow = atomic_add_negative(1, &ucounts->count); spin_unlock_irq(&ucounts_lock); - ucounts = get_ucounts(ucounts); + if (overflow) { + put_ucounts(ucounts); + return NULL; + } return ucounts; } @@ -193,8 +198,7 @@ void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - if (atomic_dec_and_test(&ucounts->count)) { - spin_lock_irqsave(&ucounts_lock, flags); + if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); From b946dbcfa4df80ec81b442964e07ad37000cc059 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Wed, 28 Jul 2021 16:38:29 +1000 Subject: [PATCH 1036/1469] cifs: add missing parsing of backupuid We lost parsing of backupuid in the switch to new mount API. Add it back. Signed-off-by: Ronnie Sahlberg Reviewed-by: Shyam Prasad N Cc: # v5.11+ Reported-by: Xiaoli Feng Signed-off-by: Steve French --- fs/cifs/fs_context.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 9a59d7ff9a11..eed59bc1d913 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -925,6 +925,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->cred_uid = uid; ctx->cruid_specified = true; break; + case Opt_backupuid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto cifs_parse_mount_err; + ctx->backupuid = uid; + ctx->backupuid_specified = true; + break; case Opt_backupgid: gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) From f5e81d1117501546b7be050c5fbafa6efd2c722c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 13 Jul 2021 08:18:31 +0000 Subject: [PATCH 1037/1469] bpf: Introduce BPF nospec instruction for mitigating Spectre v4 In case of JITs, each of the JIT backends compiles the BPF nospec instruction /either/ to a machine instruction which emits a speculation barrier /or/ to /no/ machine instruction in case the underlying architecture is not affected by Speculative Store Bypass or has different mitigations in place already. This covers both x86 and (implicitly) arm64: In case of x86, we use 'lfence' instruction for mitigation. In case of arm64, we rely on the firmware mitigation as controlled via the ssbd kernel parameter. Whenever the mitigation is enabled, it works for all of the kernel code with no need to provide any additional instructions here (hence only comment in arm64 JIT). Other archs can follow as needed. The BPF nospec instruction is specifically targeting Spectre v4 since i) we don't use a serialization barrier for the Spectre v1 case, and ii) mitigation instructions for v1 and v4 might be different on some archs. The BPF nospec is required for a future commit, where the BPF verifier does annotate intermediate BPF programs with speculation barriers. Co-developed-by: Piotr Krysiuk Co-developed-by: Benedict Schlueter Signed-off-by: Daniel Borkmann Signed-off-by: Piotr Krysiuk Signed-off-by: Benedict Schlueter Acked-by: Alexei Starovoitov --- arch/arm/net/bpf_jit_32.c | 3 +++ arch/arm64/net/bpf_jit_comp.c | 13 +++++++++++++ arch/mips/net/ebpf_jit.c | 3 +++ arch/powerpc/net/bpf_jit_comp32.c | 6 ++++++ arch/powerpc/net/bpf_jit_comp64.c | 6 ++++++ arch/riscv/net/bpf_jit_comp32.c | 4 ++++ arch/riscv/net/bpf_jit_comp64.c | 4 ++++ arch/s390/net/bpf_jit_comp.c | 5 +++++ arch/sparc/net/bpf_jit_comp_64.c | 3 +++ arch/x86/net/bpf_jit_comp.c | 7 +++++++ arch/x86/net/bpf_jit_comp32.c | 6 ++++++ include/linux/filter.h | 15 +++++++++++++++ kernel/bpf/core.c | 19 ++++++++++++++++++- kernel/bpf/disasm.c | 16 +++++++++------- 14 files changed, 102 insertions(+), 8 deletions(-) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 897634d0a67c..a951276f0547 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1602,6 +1602,9 @@ exit: rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code)); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index dccf98a37283..41c23f474ea6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -823,6 +823,19 @@ emit_cond_jmp: return ret; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + /* + * Nothing required here. + * + * In case of arm64, we rely on the firmware mitigation of + * Speculative Store Bypass as controlled via the ssbd kernel + * parameter. Whenever the mitigation is enabled, it works + * for all of the kernel code with no need to provide any + * additional instructions. + */ + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 939dd06764bc..3a73e9375712 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1355,6 +1355,9 @@ jeq_common: } break; + case BPF_ST | BPF_NOSPEC: /* speculation barrier */ + break; + case BPF_ST | BPF_B | BPF_MEM: case BPF_ST | BPF_H | BPF_MEM: case BPF_ST | BPF_W | BPF_MEM: diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 34bb1583fc0c..beb12cbc8c29 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -737,6 +737,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * } break; + /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + /* * BPF_ST(X) */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index de8595880fee..b87a63dba9c8 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -627,6 +627,12 @@ emit_clear: } break; + /* + * BPF_ST NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; + /* * BPF_ST(X) */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 81de865f4c7c..e6497424cbf6 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1251,6 +1251,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, return -1; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_W: diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 87e3bf5b9086..3af4131c22c7 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -939,6 +939,10 @@ out_be: emit_ld(rd, 0, RV_REG_T1, ctx); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: emit_imm(RV_REG_T1, imm, ctx); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 2ae419f5115a..88419263a89a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1153,6 +1153,11 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, break; } break; + /* + * BPF_NOSPEC (speculation barrier) + */ + case BPF_ST | BPF_NOSPEC: + break; /* * BPF_ST(X) */ diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 4b8d3c65d266..9a2f20cbd48b 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1287,6 +1287,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) return 1; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4b951458c9fc..16d76f814e9b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1219,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; + /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: if (is_ereg(dst_reg)) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3da88ded6ee3..3bfda5f502cb 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, i++; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..83b896044e79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -73,6 +73,11 @@ struct ctl_table_header; /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 +/* unused opcode to mark speculation barrier for mitigating + * Speculative Store Bypass + */ +#define BPF_NOSPEC 0xc0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -390,6 +395,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = 0 }) +/* Speculation barrier */ + +#define BPF_ST_NOSPEC() \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_NOSPEC, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9b1577498373..b1a5fc04492b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,8 @@ #include #include #include + +#include #include /* Registers */ @@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, @@ -1621,7 +1624,21 @@ out: COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP - /* STX and ST and LDX*/ + /* ST, STX and LDX*/ + ST_NOSPEC: + /* Speculation barrier for mitigating Speculative Store Bypass. + * In case of arm64, we rely on the firmware mitigation as + * controlled via the ssbd kernel parameter. Whenever the + * mitigation is enabled, it works for all of the kernel code + * with no need to provide any additional instructions here. + * In case of x86, we use 'lfence' insn for mitigation. We + * reuse preexisting logic from Spectre v1 mitigation that + * happens to produce the required code on x86 for v4 as well. + */ +#ifdef CONFIG_X86 + barrier_nospec(); +#endif + CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index bbfc6bb79240..ca3cd9aaa6ce 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_%02x\n", insn->code); } } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) == BPF_MEM) { + verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { + verbose(cbs->private_data, "(%02x) nospec\n", insn->code); + } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); - return; } - verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); From 2039f26f3aca5b0e419b98f65dd36481337b86ee Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 13 Jul 2021 08:18:31 +0000 Subject: [PATCH 1038/1469] bpf: Fix leakage due to insufficient speculative store bypass mitigation Spectre v4 gadgets make use of memory disambiguation, which is a set of techniques that execute memory access instructions, that is, loads and stores, out of program order; Intel's optimization manual, section 2.4.4.5: A load instruction micro-op may depend on a preceding store. Many microarchitectures block loads until all preceding store addresses are known. The memory disambiguator predicts which loads will not depend on any previous stores. When the disambiguator predicts that a load does not have such a dependency, the load takes its data from the L1 data cache. Eventually, the prediction is verified. If an actual conflict is detected, the load and all succeeding instructions are re-executed. af86ca4e3088 ("bpf: Prevent memory disambiguation attack") tried to mitigate this attack by sanitizing the memory locations through preemptive "fast" (low latency) stores of zero prior to the actual "slow" (high latency) store of a pointer value such that upon dependency misprediction the CPU then speculatively executes the load of the pointer value and retrieves the zero value instead of the attacker controlled scalar value previously stored at that location, meaning, subsequent access in the speculative domain is then redirected to the "zero page". The sanitized preemptive store of zero prior to the actual "slow" store is done through a simple ST instruction based on r10 (frame pointer) with relative offset to the stack location that the verifier has been tracking on the original used register for STX, which does not have to be r10. Thus, there are no memory dependencies for this store, since it's only using r10 and immediate constant of zero; hence af86ca4e3088 /assumed/ a low latency operation. However, a recent attack demonstrated that this mitigation is not sufficient since the preemptive store of zero could also be turned into a "slow" store and is thus bypassed as well: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value 31: (7b) *(u64 *)(r10 -16) = r2 // r9 will remain "fast" register, r10 will become "slow" register below 32: (bf) r9 = r10 // JIT maps BPF reg to x86 reg: // r9 -> r15 (callee saved) // r10 -> rbp // train store forward prediction to break dependency link between both r9 // and r10 by evicting them from the predictor's LRU table. 33: (61) r0 = *(u32 *)(r7 +24576) 34: (63) *(u32 *)(r7 +29696) = r0 35: (61) r0 = *(u32 *)(r7 +24580) 36: (63) *(u32 *)(r7 +29700) = r0 37: (61) r0 = *(u32 *)(r7 +24584) 38: (63) *(u32 *)(r7 +29704) = r0 39: (61) r0 = *(u32 *)(r7 +24588) 40: (63) *(u32 *)(r7 +29708) = r0 [...] 543: (61) r0 = *(u32 *)(r7 +25596) 544: (63) *(u32 *)(r7 +30716) = r0 // prepare call to bpf_ringbuf_output() helper. the latter will cause rbp // to spill to stack memory while r13/r14/r15 (all callee saved regs) remain // in hardware registers. rbp becomes slow due to push/pop latency. below is // disasm of bpf_ringbuf_output() helper for better visual context: // // ffffffff8117ee20: 41 54 push r12 // ffffffff8117ee22: 55 push rbp // ffffffff8117ee23: 53 push rbx // ffffffff8117ee24: 48 f7 c1 fc ff ff ff test rcx,0xfffffffffffffffc // ffffffff8117ee2b: 0f 85 af 00 00 00 jne ffffffff8117eee0 <-- jump taken // [...] // ffffffff8117eee0: 49 c7 c4 ea ff ff ff mov r12,0xffffffffffffffea // ffffffff8117eee7: 5b pop rbx // ffffffff8117eee8: 5d pop rbp // ffffffff8117eee9: 4c 89 e0 mov rax,r12 // ffffffff8117eeec: 41 5c pop r12 // ffffffff8117eeee: c3 ret 545: (18) r1 = map[id:4] 547: (bf) r2 = r7 548: (b7) r3 = 0 549: (b7) r4 = 4 550: (85) call bpf_ringbuf_output#194288 // instruction 551 inserted by verifier \ 551: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here // storing map value pointer r7 at fp-16 | since value of r10 is "slow". 552: (7b) *(u64 *)(r10 -16) = r7 / // following "fast" read to the same memory location, but due to dependency // misprediction it will speculatively execute before insn 551/552 completes. 553: (79) r2 = *(u64 *)(r9 -16) // in speculative domain contains attacker controlled r2. in non-speculative // domain this contains r7, and thus accesses r7 +0 below. 554: (71) r3 = *(u8 *)(r2 +0) // leak r3 As can be seen, the current speculative store bypass mitigation which the verifier inserts at line 551 is insufficient since /both/, the write of the zero sanitation as well as the map value pointer are a high latency instruction due to prior memory access via push/pop of r10 (rbp) in contrast to the low latency read in line 553 as r9 (r15) which stays in hardware registers. Thus, architecturally, fp-16 is r7, however, microarchitecturally, fp-16 can still be r2. Initial thoughts to address this issue was to track spilled pointer loads from stack and enforce their load via LDX through r10 as well so that /both/ the preemptive store of zero /as well as/ the load use the /same/ register such that a dependency is created between the store and load. However, this option is not sufficient either since it can be bypassed as well under speculation. An updated attack with pointer spill/fills now _all_ based on r10 would look as follows: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value [...] // longer store forward prediction training sequence than before. 2062: (61) r0 = *(u32 *)(r7 +25588) 2063: (63) *(u32 *)(r7 +30708) = r0 2064: (61) r0 = *(u32 *)(r7 +25592) 2065: (63) *(u32 *)(r7 +30712) = r0 2066: (61) r0 = *(u32 *)(r7 +25596) 2067: (63) *(u32 *)(r7 +30716) = r0 // store the speculative load address (scalar) this time after the store // forward prediction training. 2068: (7b) *(u64 *)(r10 -16) = r2 // preoccupy the CPU store port by running sequence of dummy stores. 2069: (63) *(u32 *)(r7 +29696) = r0 2070: (63) *(u32 *)(r7 +29700) = r0 2071: (63) *(u32 *)(r7 +29704) = r0 2072: (63) *(u32 *)(r7 +29708) = r0 2073: (63) *(u32 *)(r7 +29712) = r0 2074: (63) *(u32 *)(r7 +29716) = r0 2075: (63) *(u32 *)(r7 +29720) = r0 2076: (63) *(u32 *)(r7 +29724) = r0 2077: (63) *(u32 *)(r7 +29728) = r0 2078: (63) *(u32 *)(r7 +29732) = r0 2079: (63) *(u32 *)(r7 +29736) = r0 2080: (63) *(u32 *)(r7 +29740) = r0 2081: (63) *(u32 *)(r7 +29744) = r0 2082: (63) *(u32 *)(r7 +29748) = r0 2083: (63) *(u32 *)(r7 +29752) = r0 2084: (63) *(u32 *)(r7 +29756) = r0 2085: (63) *(u32 *)(r7 +29760) = r0 2086: (63) *(u32 *)(r7 +29764) = r0 2087: (63) *(u32 *)(r7 +29768) = r0 2088: (63) *(u32 *)(r7 +29772) = r0 2089: (63) *(u32 *)(r7 +29776) = r0 2090: (63) *(u32 *)(r7 +29780) = r0 2091: (63) *(u32 *)(r7 +29784) = r0 2092: (63) *(u32 *)(r7 +29788) = r0 2093: (63) *(u32 *)(r7 +29792) = r0 2094: (63) *(u32 *)(r7 +29796) = r0 2095: (63) *(u32 *)(r7 +29800) = r0 2096: (63) *(u32 *)(r7 +29804) = r0 2097: (63) *(u32 *)(r7 +29808) = r0 2098: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; same as before, also including the // sanitation store with 0 from the current mitigation by the verifier. 2099: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here 2100: (7b) *(u64 *)(r10 -16) = r7 | since store unit is still busy. // load from stack intended to bypass stores. 2101: (79) r2 = *(u64 *)(r10 -16) 2102: (71) r3 = *(u8 *)(r2 +0) // leak r3 [...] Looking at the CPU microarchitecture, the scheduler might issue loads (such as seen in line 2101) before stores (line 2099,2100) because the load execution units become available while the store execution unit is still busy with the sequence of dummy stores (line 2069-2098). And so the load may use the prior stored scalar from r2 at address r10 -16 for speculation. The updated attack may work less reliable on CPU microarchitectures where loads and stores share execution resources. This concludes that the sanitizing with zero stores from af86ca4e3088 ("bpf: Prevent memory disambiguation attack") is insufficient. Moreover, the detection of stack reuse from af86ca4e3088 where previously data (STACK_MISC) has been written to a given stack slot where a pointer value is now to be stored does not have sufficient coverage as precondition for the mitigation either; for several reasons outlined as follows: 1) Stack content from prior program runs could still be preserved and is therefore not "random", best example is to split a speculative store bypass attack between tail calls, program A would prepare and store the oob address at a given stack slot and then tail call into program B which does the "slow" store of a pointer to the stack with subsequent "fast" read. From program B PoV such stack slot type is STACK_INVALID, and therefore also must be subject to mitigation. 2) The STACK_SPILL must not be coupled to register_is_const(&stack->spilled_ptr) condition, for example, the previous content of that memory location could also be a pointer to map or map value. Without the fix, a speculative store bypass is not mitigated in such precondition and can then lead to a type confusion in the speculative domain leaking kernel memory near these pointer types. While brainstorming on various alternative mitigation possibilities, we also stumbled upon a retrospective from Chrome developers [0]: [...] For variant 4, we implemented a mitigation to zero the unused memory of the heap prior to allocation, which cost about 1% when done concurrently and 4% for scavenging. Variant 4 defeats everything we could think of. We explored more mitigations for variant 4 but the threat proved to be more pervasive and dangerous than we anticipated. For example, stack slots used by the register allocator in the optimizing compiler could be subject to type confusion, leading to pointer crafting. Mitigating type confusion for stack slots alone would have required a complete redesign of the backend of the optimizing compiler, perhaps man years of work, without a guarantee of completeness. [...] From BPF side, the problem space is reduced, however, options are rather limited. One idea that has been explored was to xor-obfuscate pointer spills to the BPF stack: [...] // preoccupy the CPU store port by running sequence of dummy stores. [...] 2106: (63) *(u32 *)(r7 +29796) = r0 2107: (63) *(u32 *)(r7 +29800) = r0 2108: (63) *(u32 *)(r7 +29804) = r0 2109: (63) *(u32 *)(r7 +29808) = r0 2110: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; xored with random 'secret' value // of 943576462 before store ... 2111: (b4) w11 = 943576462 2112: (af) r11 ^= r7 2113: (7b) *(u64 *)(r10 -16) = r11 2114: (79) r11 = *(u64 *)(r10 -16) 2115: (b4) w2 = 943576462 2116: (af) r2 ^= r11 // ... and restored with the same 'secret' value with the help of AX reg. 2117: (71) r3 = *(u8 *)(r2 +0) [...] While the above would not prevent speculation, it would make data leakage infeasible by directing it to random locations. In order to be effective and prevent type confusion under speculation, such random secret would have to be regenerated for each store. The additional complexity involved for a tracking mechanism that prevents jumps such that restoring spilled pointers would not get corrupted is not worth the gain for unprivileged. Hence, the fix in here eventually opted for emitting a non-public BPF_ST | BPF_NOSPEC instruction which the x86 JIT translates into a lfence opcode. Inserting the latter in between the store and load instruction is one of the mitigations options [1]. The x86 instruction manual notes: [...] An LFENCE that follows an instruction that stores to memory might complete before the data being stored have become globally visible. [...] The latter meaning that the preceding store instruction finished execution and the store is at minimum guaranteed to be in the CPU's store queue, but it's not guaranteed to be in that CPU's L1 cache at that point (globally visible). The latter would only be guaranteed via sfence. So the load which is guaranteed to execute after the lfence for that local CPU would have to rely on store-to-load forwarding. [2], in section 2.3 on store buffers says: [...] For every store operation that is added to the ROB, an entry is allocated in the store buffer. This entry requires both the virtual and physical address of the target. Only if there is no free entry in the store buffer, the frontend stalls until there is an empty slot available in the store buffer again. Otherwise, the CPU can immediately continue adding subsequent instructions to the ROB and execute them out of order. On Intel CPUs, the store buffer has up to 56 entries. [...] One small upside on the fix is that it lifts constraints from af86ca4e3088 where the sanitize_stack_off relative to r10 must be the same when coming from different paths. The BPF_ST | BPF_NOSPEC gets emitted after a BPF_STX or BPF_ST instruction. This happens either when we store a pointer or data value to the BPF stack for the first time, or upon later pointer spills. The former needs to be enforced since otherwise stale stack data could be leaked under speculation as outlined earlier. For non-x86 JITs the BPF_ST | BPF_NOSPEC mapping is currently optimized away, but others could emit a speculation barrier as well if necessary. For real-world unprivileged programs e.g. generated by LLVM, pointer spill/fill is only generated upon register pressure and LLVM only tries to do that for pointers which are not used often. The program main impact will be the initial BPF_ST | BPF_NOSPEC sanitation for the STACK_INVALID case when the first write to a stack slot occurs e.g. upon map lookup. In future we might refine ways to mitigate the latter cost. [0] https://arxiv.org/pdf/1902.05178.pdf [1] https://msrc-blog.microsoft.com/2018/05/21/analysis-and-mitigation-of-speculative-store-bypass-cve-2018-3639/ [2] https://arxiv.org/pdf/1905.05725.pdf Fixes: af86ca4e3088 ("bpf: Prevent memory disambiguation attack") Fixes: f7cf25b2026d ("bpf: track spill/fill of constants") Co-developed-by: Piotr Krysiuk Co-developed-by: Benedict Schlueter Signed-off-by: Daniel Borkmann Signed-off-by: Piotr Krysiuk Signed-off-by: Benedict Schlueter Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- kernel/bpf/verifier.c | 87 +++++++++++++----------------------- 2 files changed, 33 insertions(+), 56 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7ba7e800d472..828d08afeee0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,8 +340,8 @@ struct bpf_insn_aux_data { }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ - int sanitize_stack_off; /* stack slot to be cleared */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ + bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 657062cb4d85..f9bda5476ea5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; + if (!env->bypass_spec_v4) { + bool sanitize = reg && is_spillable_regtype(reg->type); + + for (i = 0; i < size; i++) { + if (state->stack[spi].slot_type[i] == STACK_INVALID) { + sanitize = true; + break; + } + } + + if (sanitize) + env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + } if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { @@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - - if (!env->bypass_spec_v4) { - bool sanitize = false; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - register_is_const(&state->stack[spi].spilled_ptr)) - sanitize = true; - for (i = 0; i < BPF_REG_SIZE; i++) - if (state->stack[spi].slot_type[i] == STACK_MISC) { - sanitize = true; - break; - } - if (sanitize) { - int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; - int soff = (-spi - 1) * BPF_REG_SIZE; - - /* detected reuse of integer stack slot with a pointer - * which means either llvm is reusing stack slot or - * an attacker is trying to exploit CVE-2018-3639 - * (speculative store bypass) - * Have to sanitize that slot with preemptive - * store of zero. - */ - if (*poff && *poff != soff) { - /* disallow programs where single insn stores - * into two different stack slots, since verifier - * cannot sanitize them - */ - verbose(env, - "insn %d cannot access two stack slots fp%d and fp%d", - insn_idx, *poff, soff); - return -EINVAL; - } - *poff = soff; - } - } save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; @@ -11913,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; + bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || - insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) + insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; - else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || - insn->code == (BPF_STX | BPF_MEM | BPF_H) || - insn->code == (BPF_STX | BPF_MEM | BPF_W) || - insn->code == (BPF_STX | BPF_MEM | BPF_DW)) + ctx_access = true; + } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || + insn->code == (BPF_STX | BPF_MEM | BPF_H) || + insn->code == (BPF_STX | BPF_MEM | BPF_W) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW) || + insn->code == (BPF_ST | BPF_MEM | BPF_B) || + insn->code == (BPF_ST | BPF_MEM | BPF_H) || + insn->code == (BPF_ST | BPF_MEM | BPF_W) || + insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - else + ctx_access = BPF_CLASS(insn->code) == BPF_STX; + } else { continue; + } if (type == BPF_WRITE && - env->insn_aux_data[i + delta].sanitize_stack_off) { + env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { - /* Sanitize suspicious stack slot with zero. - * There are no memory dependencies for this store, - * since it's only using frame pointer and immediate - * constant of zero - */ - BPF_ST_MEM(BPF_DW, BPF_REG_FP, - env->insn_aux_data[i + delta].sanitize_stack_off, - 0), - /* the original STX instruction will immediately - * overwrite the same stack slot with appropriate value - */ *insn, + BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); @@ -11955,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } + if (!ctx_access) + continue; + switch (env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) From d712d3fb484b7fa8d1d57e9ca6f134bb9d8c18b1 Mon Sep 17 00:00:00 2001 From: Igor Pylypiv Date: Wed, 7 Jul 2021 11:59:45 -0700 Subject: [PATCH 1039/1469] scsi: pm80xx: Fix TMF task completion race condition The TMF timeout timer may trigger at the same time when the response from a controller is being handled. When this happens the SAS task may get freed before the response processing is finished. Fix this by calling complete() only when SAS_TASK_STATE_DONE is not set. A similar race condition was fixed in commit b90cd6f2b905 ("scsi: libsas: fix a race condition when smp task timeout") Link: https://lore.kernel.org/r/20210707185945.35559-1-ipylypiv@google.com Reviewed-by: Vishakha Channapattan Acked-by: Jack Wang Signed-off-by: Igor Pylypiv Signed-off-by: Martin K. Petersen --- drivers/scsi/pm8001/pm8001_sas.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 48548a95327b..32e60f0c3b14 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -684,8 +684,7 @@ int pm8001_dev_found(struct domain_device *dev) void pm8001_task_done(struct sas_task *task) { - if (!del_timer(&task->slow_task->timer)) - return; + del_timer(&task->slow_task->timer); complete(&task->slow_task->completion); } @@ -693,9 +692,14 @@ static void pm8001_tmf_timedout(struct timer_list *t) { struct sas_task_slow *slow = from_timer(slow, t, timer); struct sas_task *task = slow->task; + unsigned long flags; - task->task_state_flags |= SAS_TASK_STATE_ABORTED; - complete(&task->slow_task->completion); + spin_lock_irqsave(&task->task_state_lock, flags); + if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { + task->task_state_flags |= SAS_TASK_STATE_ABORTED; + complete(&task->slow_task->completion); + } + spin_unlock_irqrestore(&task->task_state_lock, flags); } #define PM8001_TASK_TIMEOUT 20 @@ -748,13 +752,10 @@ static int pm8001_exec_internal_tmf_task(struct domain_device *dev, } res = -TMF_RESP_FUNC_FAILED; /* Even TMF timed out, return direct. */ - if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { - if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { - pm8001_dbg(pm8001_ha, FAIL, - "TMF task[%x]timeout.\n", - tmf->tmf); - goto ex_err; - } + if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { + pm8001_dbg(pm8001_ha, FAIL, "TMF task[%x]timeout.\n", + tmf->tmf); + goto ex_err; } if (task->task_status.resp == SAS_TASK_COMPLETE && @@ -834,12 +835,9 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha, wait_for_completion(&task->slow_task->completion); res = TMF_RESP_FUNC_FAILED; /* Even TMF timed out, return direct. */ - if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { - if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { - pm8001_dbg(pm8001_ha, FAIL, - "TMF task timeout.\n"); - goto ex_err; - } + if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { + pm8001_dbg(pm8001_ha, FAIL, "TMF task timeout.\n"); + goto ex_err; } if (task->task_status.resp == SAS_TASK_COMPLETE && From 77541f78eadfe9fdb018a7b8b69f0f2af2cf4b82 Mon Sep 17 00:00:00 2001 From: Harshvardhan Jha Date: Thu, 8 Jul 2021 13:16:42 +0530 Subject: [PATCH 1040/1469] scsi: megaraid_mm: Fix end of loop tests for list_for_each_entry() The list_for_each_entry() iterator, "adapter" in this code, can never be NULL. If we exit the loop without finding the correct adapter then "adapter" points invalid memory that is an offset from the list head. This will eventually lead to memory corruption and presumably a kernel crash. Link: https://lore.kernel.org/r/20210708074642.23599-1-harshvardhan.jha@oracle.com Acked-by: Sumit Saxena Signed-off-by: Harshvardhan Jha Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_mm.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c index abf7b401f5b9..c509440bd161 100644 --- a/drivers/scsi/megaraid/megaraid_mm.c +++ b/drivers/scsi/megaraid/megaraid_mm.c @@ -238,7 +238,7 @@ mraid_mm_get_adapter(mimd_t __user *umimd, int *rval) mimd_t mimd; uint32_t adapno; int iterator; - + bool is_found; if (copy_from_user(&mimd, umimd, sizeof(mimd_t))) { *rval = -EFAULT; @@ -254,12 +254,16 @@ mraid_mm_get_adapter(mimd_t __user *umimd, int *rval) adapter = NULL; iterator = 0; + is_found = false; list_for_each_entry(adapter, &adapters_list_g, list) { - if (iterator++ == adapno) break; + if (iterator++ == adapno) { + is_found = true; + break; + } } - if (!adapter) { + if (!is_found) { *rval = -ENODEV; return NULL; } @@ -725,6 +729,7 @@ ioctl_done(uioc_t *kioc) uint32_t adapno; int iterator; mraid_mmadp_t* adapter; + bool is_found; /* * When the kioc returns from driver, make sure it still doesn't @@ -747,19 +752,23 @@ ioctl_done(uioc_t *kioc) iterator = 0; adapter = NULL; adapno = kioc->adapno; + is_found = false; con_log(CL_ANN, ( KERN_WARNING "megaraid cmm: completed " "ioctl that was timedout before\n")); list_for_each_entry(adapter, &adapters_list_g, list) { - if (iterator++ == adapno) break; + if (iterator++ == adapno) { + is_found = true; + break; + } } kioc->timedout = 0; - if (adapter) { + if (is_found) mraid_mm_dealloc_kioc( adapter, kioc ); - } + } else { wake_up(&wait_q); From 640b7ea5f888b521dcf28e2564ce75d08a783fd7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 27 Jul 2021 23:38:24 +0300 Subject: [PATCH 1041/1469] alpha: register early reserved memory in memblock The memory reserved by console/PALcode or non-volatile memory is not added to memblock.memory. Since commit fa3354e4ea39 (mm: free_area_init: use maximal zone PFNs rather than zone sizes) the initialization of the memory map relies on the accuracy of memblock.memory to properly calculate zone sizes. The holes in memblock.memory caused by absent regions reserved by the firmware cause incorrect initialization of struct pages which leads to BUG() during the initial page freeing: BUG: Bad page state in process swapper pfn:2ffc53 page:fffffc000ecf14c0 refcount:0 mapcount:1 mapping:0000000000000000 index:0x0 flags: 0x0() raw: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 page dumped because: nonzero mapcount Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.7.0-03841-gfa3354e4ea39-dirty #26 fffffc0001b5bd68 fffffc0001b5be80 fffffc00011cd148 fffffc000ecf14c0 fffffc00019803df fffffc0001b5be80 fffffc00011ce340 fffffc000ecf14c0 0000000000000000 fffffc0001b5be80 fffffc0001b482c0 fffffc00027d6618 fffffc00027da7d0 00000000002ff97a 0000000000000000 fffffc0001b5be80 fffffc00011d1abc fffffc000ecf14c0 fffffc0002d00000 fffffc0001b5be80 fffffc0001b2350c 0000000000300000 fffffc0001b48298 fffffc0001b482c0 Trace: [] bad_page+0x168/0x1b0 [] free_pcp_prepare+0x1e0/0x290 [] free_unref_page+0x2c/0xa0 [] cmp_ex_sort+0x0/0x30 [] cmp_ex_sort+0x0/0x30 [] _stext+0x1c/0x20 Fix this by registering the reserved ranges in memblock.memory. Link: https://lore.kernel.org/lkml/20210726192311.uffqnanxw3ac5wwi@ivybridge Fixes: fa3354e4ea39 ("mm: free_area_init: use maximal zone PFNs rather than zone sizes") Reported-by: Matt Turner Cc: Signed-off-by: Mike Rapoport Signed-off-by: Matt Turner --- arch/alpha/kernel/setup.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 7d56c217b235..b4fbbba30aa2 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -319,18 +319,19 @@ setup_memory(void *kernel_end) i, cluster->usage, cluster->start_pfn, cluster->start_pfn + cluster->numpages); - /* Bit 0 is console/PALcode reserved. Bit 1 is - non-volatile memory -- we might want to mark - this for later. */ - if (cluster->usage & 3) - continue; - end = cluster->start_pfn + cluster->numpages; if (end > max_low_pfn) max_low_pfn = end; memblock_add(PFN_PHYS(cluster->start_pfn), cluster->numpages << PAGE_SHIFT); + + /* Bit 0 is console/PALcode reserved. Bit 1 is + non-volatile memory -- we might want to mark + this for later. */ + if (cluster->usage & 3) + memblock_reserve(PFN_PHYS(cluster->start_pfn), + cluster->numpages << PAGE_SHIFT); } /* From aa35772f61752d4c636d46be51a4f7ca6c029ee6 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Wed, 23 Jun 2021 09:02:47 +0200 Subject: [PATCH 1042/1469] usb: cdns3: Fixed incorrect gadget state For delayed status phase, the usb_gadget->state was set to USB_STATE_ADDRESS and it has never been updated to USB_STATE_CONFIGURED. Patch updates the gadget state to correct USB_STATE_CONFIGURED. As a result of this bug the controller was not able to enter to Test Mode while using MSC function. Cc: Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20210623070247.46151-1-pawell@gli-login.cadence.com Signed-off-by: Peter Chen --- drivers/usb/cdns3/cdns3-ep0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/cdns3/cdns3-ep0.c b/drivers/usb/cdns3/cdns3-ep0.c index 02ec7ab4bb48..e29989d57bef 100644 --- a/drivers/usb/cdns3/cdns3-ep0.c +++ b/drivers/usb/cdns3/cdns3-ep0.c @@ -731,6 +731,7 @@ static int cdns3_gadget_ep0_queue(struct usb_ep *ep, request->actual = 0; priv_dev->status_completion_no_call = true; priv_dev->pending_status_request = request; + usb_gadget_set_state(&priv_dev->gadget, USB_STATE_CONFIGURED); spin_unlock_irqrestore(&priv_dev->lock, flags); /* From aa82f94e869edd72f4fadb08c6ffca8927e4934e Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Fri, 25 Jun 2021 12:25:02 +0200 Subject: [PATCH 1043/1469] usb: cdnsp: Fix incorrect supported maximum speed Driver had hardcoded in initialization maximum supported speed to USB_SPEED_SUPER_PLUS but it should consider the speed returned from usb_get_maximum_speed function. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20210625102502.26336-1-pawell@gli-login.cadence.com Signed-off-by: Peter Chen --- drivers/usb/cdns3/cdnsp-gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index c23f53e9b1ef..27df0c697897 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1882,7 +1882,7 @@ static int __cdnsp_gadget_init(struct cdns *cdns) pdev->gadget.name = "cdnsp-gadget"; pdev->gadget.speed = USB_SPEED_UNKNOWN; pdev->gadget.sg_supported = 1; - pdev->gadget.max_speed = USB_SPEED_SUPER_PLUS; + pdev->gadget.max_speed = max_speed; pdev->gadget.lpm_capable = 1; pdev->setup_buf = kzalloc(CDNSP_EP0_SETUP_SIZE, GFP_KERNEL); From e913aada06830338633fb8524733b0ad3d38a7c1 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Wed, 23 Jun 2021 09:27:28 +0200 Subject: [PATCH 1044/1469] usb: cdnsp: Fixed issue with ZLP The condition "if (need_zero_pkt && zero_len_trb)" was always false and it caused that TRB for ZLP was not prepared. Fix causes that after preparing last TRB in TD, the driver prepares additional TD with ZLP when a ZLP is required. Cc: Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20210623072728.41275-1-pawell@gli-login.cadence.com Signed-off-by: Peter Chen --- drivers/usb/cdns3/cdnsp-ring.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 68972746e363..1b1438457fb0 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1932,15 +1932,13 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) } if (enqd_len + trb_buff_len >= full_len) { - if (need_zero_pkt && zero_len_trb) { - zero_len_trb = true; - } else { - field &= ~TRB_CHAIN; - field |= TRB_IOC; - more_trbs_coming = false; - need_zero_pkt = false; - preq->td.last_trb = ring->enqueue; - } + if (need_zero_pkt) + zero_len_trb = !zero_len_trb; + + field &= ~TRB_CHAIN; + field |= TRB_IOC; + more_trbs_coming = false; + preq->td.last_trb = ring->enqueue; } /* Only set interrupt on short packet for OUT endpoints. */ @@ -1955,7 +1953,7 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) length_field = TRB_LEN(trb_buff_len) | TRB_TD_SIZE(remainder) | TRB_INTR_TARGET(0); - cdnsp_queue_trb(pdev, ring, more_trbs_coming | need_zero_pkt, + cdnsp_queue_trb(pdev, ring, more_trbs_coming | zero_len_trb, lower_32_bits(send_addr), upper_32_bits(send_addr), length_field, From 5df09c15bab98463203c83ecab88b9321466e626 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 22 Jun 2021 21:37:48 +0200 Subject: [PATCH 1045/1469] usb: cdnsp: Fix the IMAN_IE_SET and IMAN_IE_CLEAR macro IMAN_IE is BIT(1), so these macro are respectively equivalent to BIT(1) and 0, whatever the value of 'p'. The purpose was to set and reset a single bit in 'p'. Fix these macros to do that correctly. Acked-by: Pawel Laszczak Fixes: e93e58d27402 ("usb: cdnsp: Device side header file for CDNSP driver") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/d12bfcc9cbffb89e27b120668821b3c4f09b6755.1624390584.git.christophe.jaillet@wanadoo.fr Signed-off-by: Peter Chen --- drivers/usb/cdns3/cdnsp-gadget.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index 783ca8ffde00..f740fa6089d8 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -383,8 +383,8 @@ struct cdnsp_intr_reg { #define IMAN_IE BIT(1) #define IMAN_IP BIT(0) /* bits 2:31 need to be preserved */ -#define IMAN_IE_SET(p) (((p) & IMAN_IE) | 0x2) -#define IMAN_IE_CLEAR(p) (((p) & IMAN_IE) & ~(0x2)) +#define IMAN_IE_SET(p) ((p) | IMAN_IE) +#define IMAN_IE_CLEAR(p) ((p) & ~IMAN_IE) /* IMOD - Interrupter Moderation Register - irq_control bitmasks. */ /* From 0d4867a185460397af56b9afe3e2243d3e610e37 Mon Sep 17 00:00:00 2001 From: Alexander Monakov Date: Wed, 21 Jul 2021 20:01:41 +0300 Subject: [PATCH 1046/1469] ALSA: hda/realtek: add mic quirk for Acer SF314-42 The Acer Swift SF314-42 laptop is using Realtek ALC255 codec. Add a quirk so microphone in a headset connected via the right-hand side jack is usable. Signed-off-by: Alexander Monakov Cc: Link: https://lore.kernel.org/r/20210721170141.24807-1-amonakov@ispras.ru Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 14e1ab7c7954..21c521596c9d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8278,6 +8278,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), From db8d3a21275c807a4047a21bde3b57d49ca55d82 Mon Sep 17 00:00:00 2001 From: Michael Zaidman Date: Thu, 29 Jul 2021 13:26:03 +0300 Subject: [PATCH 1047/1469] HID: ft260: fix device removal due to USB disconnect This commit fixes a functional regression introduced by the commit 82f09a637dd3 ("HID: ft260: improve error handling of ft260_hid_feature_report_get()") when upon USB disconnect, the FTDI FT260 i2c device is still available within the /dev folder. In my company's product, where the host USB to FT260 USB connection is hard-wired in the PCB, the issue is not reproducible. To reproduce it, I used the VirtualBox Ubuntu 20.04 VM and the UMFT260EV1A development module for the FTDI FT260 chip: Plug the UMFT260EV1A module into a USB port and attach it to VM. The VM shows 2 i2c devices under the /dev: michael@michael-VirtualBox:~$ ls /dev/i2c-* /dev/i2c-0 /dev/i2c-1 The i2c-0 is not related to the FTDI FT260: michael@michael-VirtualBox:~$ cat /sys/bus/i2c/devices/i2c-0/name SMBus PIIX4 adapter at 4100 The i2c-1 is created by hid-ft260.ko: michael@michael-VirtualBox:~$ cat /sys/bus/i2c/devices/i2c-1/name FT260 usb-i2c bridge on hidraw1 Now, detach the FTDI FT260 USB device from VM. We expect the /dev/i2c-1 to disappear, but it's still here: michael@michael-VirtualBox:~$ ls /dev/i2c-* /dev/i2c-0 /dev/i2c-1 And the kernel log shows: [ +0.001202] usb 2-2: USB disconnect, device number 3 [ +0.000109] ft260 0003:0403:6030.0002: failed to retrieve system status [ +0.000316] ft260 0003:0403:6030.0003: failed to retrieve system status It happens because the commit 82f09a637dd3 changed the ft260_get_system_config() return logic. This caused the ft260_is_interface_enabled() to exit with error upon the FT260 device USB disconnect, which in turn, aborted the ft260_remove() before deleting the FT260 i2c device and cleaning its sysfs stuff. This commit restores the FT260 USB removal functionality and improves the ft260_is_interface_enabled() code to handle correctly all chip modes defined by the device interface configuration pins DCNF0 and DCNF1. Signed-off-by: Michael Zaidman Acked-by: Aaron Jones (FTDI-UK) Signed-off-by: Jiri Kosina --- drivers/hid/hid-ft260.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 6f10df2042c4..4ef1c3b8094e 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -742,7 +742,7 @@ static int ft260_is_interface_enabled(struct hid_device *hdev) int ret; ret = ft260_get_system_config(hdev, &cfg); - if (ret) + if (ret < 0) return ret; ft260_dbg("interface: 0x%02x\n", interface); @@ -754,23 +754,16 @@ static int ft260_is_interface_enabled(struct hid_device *hdev) switch (cfg.chip_mode) { case FT260_MODE_ALL: case FT260_MODE_BOTH: - if (interface == 1) { + if (interface == 1) hid_info(hdev, "uart interface is not supported\n"); - return 0; - } - ret = 1; + else + ret = 1; break; case FT260_MODE_UART: - if (interface == 0) { - hid_info(hdev, "uart is unsupported on interface 0\n"); - ret = 0; - } + hid_info(hdev, "uart interface is not supported\n"); break; case FT260_MODE_I2C: - if (interface == 1) { - hid_info(hdev, "i2c is unsupported on interface 1\n"); - ret = 0; - } + ret = 1; break; } return ret; @@ -1004,11 +997,9 @@ err_hid_stop: static void ft260_remove(struct hid_device *hdev) { - int ret; struct ft260_device *dev = hid_get_drvdata(hdev); - ret = ft260_is_interface_enabled(hdev); - if (ret <= 0) + if (!dev) return; sysfs_remove_group(&hdev->dev.kobj, &ft260_attr_group); From 7280305eb57dd32735f795ed4ee679bf9854f9d0 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 28 Jul 2021 18:00:24 +0200 Subject: [PATCH 1048/1469] btrfs: calculate number of eb pages properly in csum_tree_block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building with -Warray-bounds on systems with 64K pages there's a warning: fs/btrfs/disk-io.c: In function ‘csum_tree_block’: fs/btrfs/disk-io.c:226:34: warning: array subscript 1 is above array bounds of ‘struct page *[1]’ [-Warray-bounds] 226 | kaddr = page_address(buf->pages[i]); | ~~~~~~~~~~^~~ ./include/linux/mm.h:1630:48: note: in definition of macro ‘page_address’ 1630 | #define page_address(page) lowmem_page_address(page) | ^~~~ In file included from fs/btrfs/ctree.h:32, from fs/btrfs/disk-io.c:23: fs/btrfs/extent_io.h:98:15: note: while referencing ‘pages’ 98 | struct page *pages[1]; | ^~~~~ The compiler has no way to know that in that case the nodesize is exactly PAGE_SIZE, so the resulting number of pages will be correct (1). Let's use num_extent_pages that makes the case nodesize == PAGE_SIZE explicitly 1. Reported-by: Gustavo A. R. Silva Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b117dd3b8172..a59ab7b9aea0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -209,7 +209,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; - const int num_pages = fs_info->nodesize >> PAGE_SHIFT; + const int num_pages = num_extent_pages(buf); const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; From 153cca9caa81ca8912a70528daca4b9a523c6898 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 29 Jul 2021 10:21:34 +0200 Subject: [PATCH 1049/1469] platform/x86: Add and use a dual_accel_detect() helper Various 360 degree hinges (yoga) style 2-in-1 devices use 2 accelerometers to allow the OS to determine the angle between the display and the base of the device. On Windows these are read by a special HingeAngleService process which calls undocumented ACPI methods, to let the firmware know if the 2-in-1 is in tablet- or laptop-mode. The firmware may use this to disable the kbd and touchpad to avoid spurious input in tablet-mode as well as to report SW_TABLET_MODE info to the OS. Since Linux does not call these undocumented methods, the SW_TABLET_MODE info reported by various pdx86 drivers is incorrect on these devices. Before this commit the intel-hid and thinkpad_acpi code already had 2 hardcoded checks for ACPI hardware-ids of dual-accel sensors to avoid reporting broken info. And now we also have a bug-report about the same problem in the intel-vbtn code. Since there are at least 3 different ACPI hardware-ids in play, add a new dual_accel_detect() helper which checks for all 3, rather then adding different hardware-ids to the drivers as bug-reports trickle in. Having shared code which checks all known hardware-ids is esp. important for the intel-hid and intel-vbtn drivers as these are generic drivers which are used on a lot of devices. The BOSC0200 hardware-id requires special handling, because often it is used for a single-accelerometer setup. Only in a few cases it refers to a dual-accel setup, in which case there will be 2 I2cSerialBus resources in the device's resource-list, so the helper checks for this. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=209011 Reported-and-tested-by: Julius Lehmann Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210729082134.6683-1-hdegoede@redhat.com --- drivers/platform/x86/Kconfig | 3 + drivers/platform/x86/dual_accel_detect.h | 75 ++++++++++++++++++++++++ drivers/platform/x86/intel-hid.c | 21 ++----- drivers/platform/x86/intel-vbtn.c | 18 +++++- drivers/platform/x86/thinkpad_acpi.c | 3 +- 5 files changed, 101 insertions(+), 19 deletions(-) create mode 100644 drivers/platform/x86/dual_accel_detect.h diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 7d385c3b2239..d12db6c316ea 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -508,6 +508,7 @@ config THINKPAD_ACPI depends on RFKILL || RFKILL = n depends on ACPI_VIDEO || ACPI_VIDEO = n depends on BACKLIGHT_CLASS_DEVICE + depends on I2C select ACPI_PLATFORM_PROFILE select HWMON select NVRAM @@ -691,6 +692,7 @@ config INTEL_HID_EVENT tristate "INTEL HID Event" depends on ACPI depends on INPUT + depends on I2C select INPUT_SPARSEKMAP help This driver provides support for the Intel HID Event hotkey interface. @@ -742,6 +744,7 @@ config INTEL_VBTN tristate "INTEL VIRTUAL BUTTON" depends on ACPI depends on INPUT + depends on I2C select INPUT_SPARSEKMAP help This driver provides support for the Intel Virtual Button interface. diff --git a/drivers/platform/x86/dual_accel_detect.h b/drivers/platform/x86/dual_accel_detect.h new file mode 100644 index 000000000000..1a069159da91 --- /dev/null +++ b/drivers/platform/x86/dual_accel_detect.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Helper code to detect 360 degree hinges (yoga) style 2-in-1 devices using 2 accelerometers + * to allow the OS to determine the angle between the display and the base of the device. + * + * On Windows these are read by a special HingeAngleService process which calls undocumented + * ACPI methods, to let the firmware know if the 2-in-1 is in tablet- or laptop-mode. + * The firmware may use this to disable the kbd and touchpad to avoid spurious input in + * tablet-mode as well as to report SW_TABLET_MODE info to the OS. + * + * Since Linux does not call these undocumented methods, the SW_TABLET_MODE info reported + * by various drivers/platform/x86 drivers is incorrect. These drivers use the detection + * code in this file to disable SW_TABLET_MODE reporting to avoid reporting broken info + * (instead userspace can derive the status itself by directly reading the 2 accels). + */ + +#include +#include + +static int dual_accel_i2c_resource_count(struct acpi_resource *ares, void *data) +{ + struct acpi_resource_i2c_serialbus *sb; + int *count = data; + + if (i2c_acpi_get_i2c_resource(ares, &sb)) + *count = *count + 1; + + return 1; +} + +static int dual_accel_i2c_client_count(struct acpi_device *adev) +{ + int ret, count = 0; + LIST_HEAD(r); + + ret = acpi_dev_get_resources(adev, &r, dual_accel_i2c_resource_count, &count); + if (ret < 0) + return ret; + + acpi_dev_free_resource_list(&r); + return count; +} + +static bool dual_accel_detect_bosc0200(void) +{ + struct acpi_device *adev; + int count; + + adev = acpi_dev_get_first_match_dev("BOSC0200", NULL, -1); + if (!adev) + return false; + + count = dual_accel_i2c_client_count(adev); + + acpi_dev_put(adev); + + return count == 2; +} + +static bool dual_accel_detect(void) +{ + /* Systems which use a pair of accels with KIOX010A / KIOX020A ACPI ids */ + if (acpi_dev_present("KIOX010A", NULL, -1)) + return true; + + /* Systems which use a single DUAL250E ACPI device to model 2 accels */ + if (acpi_dev_present("DUAL250E", NULL, -1)) + return true; + + /* Systems which use a single BOSC0200 ACPI device to model 2 accels */ + if (dual_accel_detect_bosc0200()) + return true; + + return false; +} diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index e5fbe017f8e1..2e4e97a626a5 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -14,6 +14,7 @@ #include #include #include +#include "dual_accel_detect.h" /* When NOT in tablet mode, VGBS returns with the flag 0x40 */ #define TABLET_MODE_FLAG BIT(6) @@ -122,6 +123,7 @@ struct intel_hid_priv { struct input_dev *array; struct input_dev *switches; bool wakeup_mode; + bool dual_accel; }; #define HID_EVENT_FILTER_UUID "eeec56b3-4442-408f-a792-4edd4d758054" @@ -451,22 +453,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) * SW_TABLET_MODE report, in these cases we enable support when receiving * the first event instead of during driver setup. * - * Some 360 degree hinges (yoga) style 2-in-1 devices use 2 accelerometers - * to allow the OS to determine the angle between the display and the base - * of the device. On Windows these are read by a special HingeAngleService - * process which calls an ACPI DSM (Device Specific Method) on the - * ACPI KIOX010A device node for the sensor in the display, to let the - * firmware know if the 2-in-1 is in tablet- or laptop-mode so that it can - * disable the kbd and touchpad to avoid spurious input in tablet-mode. - * - * The linux kxcjk1013 driver calls the DSM for this once at probe time - * to ensure that the builtin kbd and touchpad work. On some devices this - * causes a "spurious" 0xcd event on the intel-hid ACPI dev. In this case - * there is not a functional tablet-mode switch, so we should not register - * the tablet-mode switch device. + * See dual_accel_detect.h for more info on the dual_accel check. */ - if (!priv->switches && (event == 0xcc || event == 0xcd) && - !acpi_dev_present("KIOX010A", NULL, -1)) { + if (!priv->switches && !priv->dual_accel && (event == 0xcc || event == 0xcd)) { dev_info(&device->dev, "switch event received, enable switches supports\n"); err = intel_hid_switches_setup(device); if (err) @@ -607,6 +596,8 @@ static int intel_hid_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); + priv->dual_accel = dual_accel_detect(); + err = intel_hid_input_setup(device); if (err) { pr_err("Failed to setup Intel HID hotkeys\n"); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 888a764efad1..309166431063 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -14,6 +14,7 @@ #include #include #include +#include "dual_accel_detect.h" /* Returned when NOT in tablet mode on some HP Stream x360 11 models */ #define VGBS_TABLET_MODE_FLAG_ALT 0x10 @@ -66,6 +67,7 @@ static const struct key_entry intel_vbtn_switchmap[] = { struct intel_vbtn_priv { struct input_dev *buttons_dev; struct input_dev *switches_dev; + bool dual_accel; bool has_buttons; bool has_switches; bool wakeup_mode; @@ -160,6 +162,10 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) input_dev = priv->buttons_dev; } else if ((ke = sparse_keymap_entry_from_scancode(priv->switches_dev, event))) { if (!priv->has_switches) { + /* See dual_accel_detect.h for more info */ + if (priv->dual_accel) + return; + dev_info(&device->dev, "Registering Intel Virtual Switches input-dev after receiving a switch event\n"); ret = input_register_device(priv->switches_dev); if (ret) @@ -248,11 +254,15 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { {} /* Array terminator */ }; -static bool intel_vbtn_has_switches(acpi_handle handle) +static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel) { unsigned long long vgbs; acpi_status status; + /* See dual_accel_detect.h for more info */ + if (dual_accel) + return false; + if (!dmi_check_system(dmi_switches_allow_list)) return false; @@ -263,13 +273,14 @@ static bool intel_vbtn_has_switches(acpi_handle handle) static int intel_vbtn_probe(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); - bool has_buttons, has_switches; + bool dual_accel, has_buttons, has_switches; struct intel_vbtn_priv *priv; acpi_status status; int err; + dual_accel = dual_accel_detect(); has_buttons = acpi_has_method(handle, "VBDL"); - has_switches = intel_vbtn_has_switches(handle); + has_switches = intel_vbtn_has_switches(handle, dual_accel); if (!has_buttons && !has_switches) { dev_warn(&device->dev, "failed to read Intel Virtual Button driver\n"); @@ -281,6 +292,7 @@ static int intel_vbtn_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); + priv->dual_accel = dual_accel; priv->has_buttons = has_buttons; priv->has_switches = has_switches; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 603156a6e3ed..50ff04c84650 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -73,6 +73,7 @@ #include #include #include +#include "dual_accel_detect.h" /* ThinkPad CMOS commands */ #define TP_CMOS_VOLUME_DOWN 0 @@ -3232,7 +3233,7 @@ static int hotkey_init_tablet_mode(void) * the laptop/tent/tablet mode to the EC. The bmc150 iio driver * does not support this, so skip the hotkey on these models. */ - if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1)) + if (has_tablet_mode && !dual_accel_detect()) tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS; type = "GMMS"; } else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) { From 3c18e9baee0ef97510dcda78c82285f52626764b Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sat, 24 Jul 2021 17:27:39 +0200 Subject: [PATCH 1050/1469] USB: serial: ch341: fix character loss at high transfer rates The chip supports high transfer rates, but with the small default buffers (64 bytes read), some entire blocks are regularly lost. This typically happens at 1.5 Mbps (which is the default speed on Rockchip devices) when used as a console to access U-Boot where the output of the "help" command misses many lines and where "printenv" mangles the environment. The FTDI driver doesn't suffer at all from this. One difference is that it uses 512 bytes rx buffers and 256 bytes tx buffers. Adopting these values completely resolved the issue, even the output of "dmesg" is reliable. I preferred to leave the Tx value unchanged as it is not involved in this issue, while a change could increase the risk of triggering the same issue with other devices having too small buffers. I verified that it backports well (and works) at least to 5.4. It's of low importance enough to be dropped where it doesn't trivially apply anymore. Cc: stable@vger.kernel.org Signed-off-by: Willy Tarreau Link: https://lore.kernel.org/r/20210724152739.18726-1-w@1wt.eu Signed-off-by: Johan Hovold --- drivers/usb/serial/ch341.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index 2db917eab799..8a521b5ea769 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -851,6 +851,7 @@ static struct usb_serial_driver ch341_device = { .owner = THIS_MODULE, .name = "ch341-uart", }, + .bulk_in_size = 512, .id_table = id_table, .num_ports = 1, .open = ch341_open, From 333cf507465fbebb3727f5b53e77538467df312a Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Thu, 29 Jul 2021 11:34:49 +0530 Subject: [PATCH 1051/1469] powerpc/pseries: Fix regression while building external modules With commit c9f3401313a5 ("powerpc: Always enable queued spinlocks for 64s, disable for others") CONFIG_PPC_QUEUED_SPINLOCKS is always enabled on ppc64le, external modules that use spinlock APIs are failing. ERROR: modpost: GPL-incompatible module XXX.ko uses GPL-only symbol 'shared_processor' Before the above commit, modules were able to build without any issues. Also this problem is not seen on other architectures. This problem can be workaround if CONFIG_UNINLINE_SPIN_UNLOCK is enabled in the config. However CONFIG_UNINLINE_SPIN_UNLOCK is not enabled by default and only enabled in certain conditions like CONFIG_DEBUG_SPINLOCKS is set in the kernel config. #include spinlock_t spLock; static int __init spinlock_test_init(void) { spin_lock_init(&spLock); spin_lock(&spLock); spin_unlock(&spLock); return 0; } static void __exit spinlock_test_exit(void) { printk("spinlock_test unloaded\n"); } module_init(spinlock_test_init); module_exit(spinlock_test_exit); MODULE_DESCRIPTION ("spinlock_test"); MODULE_LICENSE ("non-GPL"); MODULE_AUTHOR ("Srikar Dronamraju"); Given that spin locks are one of the basic facilities for module code, this effectively makes it impossible to build/load almost any non GPL modules on ppc64le. This was first reported at https://github.com/openzfs/zfs/issues/11172 Currently shared_processor is exported as GPL only symbol. Fix this for parity with other architectures by exposing shared_processor to non-GPL modules too. Fixes: 14c73bd344da ("powerpc/vcpu: Assume dedicated processors as non-preempt") Cc: stable@vger.kernel.org # v5.5+ Reported-by: marc.c.dionne@gmail.com Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210729060449.292780-1-srikar@linux.vnet.ibm.com --- arch/powerpc/platforms/pseries/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 631a0d57b6cd..6b0886668465 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -77,7 +77,7 @@ #include "../../../../drivers/pci/pci.h" DEFINE_STATIC_KEY_FALSE(shared_processor); -EXPORT_SYMBOL_GPL(shared_processor); +EXPORT_SYMBOL(shared_processor); int CMO_PrPSP = -1; int CMO_SecPSP = -1; From a88603f4b92ecef9e2359e40bcb99ad399d85dd7 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 29 Jul 2021 22:56:36 +1000 Subject: [PATCH 1052/1469] powerpc/vdso: Don't use r30 to avoid breaking Go lang The Go runtime uses r30 for some special value called 'g'. It assumes that value will remain unchanged even when calling VDSO functions. Although r30 is non-volatile across function calls, the callee is free to use it, as long as the callee saves the value and restores it before returning. It used to be true by accident that the VDSO didn't use r30, because the VDSO was hand-written asm. When we switched to building the VDSO from C the compiler started using r30, at least in some builds, leading to crashes in Go. eg: ~/go/src$ ./all.bash Building Go cmd/dist using /usr/lib/go-1.16. (go1.16.2 linux/ppc64le) Building Go toolchain1 using /usr/lib/go-1.16. go build os/exec: /usr/lib/go-1.16/pkg/tool/linux_ppc64le/compile: signal: segmentation fault go build reflect: /usr/lib/go-1.16/pkg/tool/linux_ppc64le/compile: signal: segmentation fault go tool dist: FAILED: /usr/lib/go-1.16/bin/go install -gcflags=-l -tags=math_big_pure_go compiler_bootstrap bootstrap/cmd/...: exit status 1 There are patches in flight to fix Go[1], but until they are released and widely deployed we can workaround it in the VDSO by avoiding use of r30. Note this only works with GCC, clang does not support -ffixed-rN. 1: https://go-review.googlesource.com/c/go/+/328110 Fixes: ab037dd87a2f ("powerpc/vdso: Switch VDSO to generic C implementation.") Cc: stable@vger.kernel.org # v5.11+ Reported-by: Paul Menzel Tested-by: Paul Menzel Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210729131244.2595519-1-mpe@ellerman.id.au --- arch/powerpc/kernel/vdso64/Makefile | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 2813e3f98db6..3c5baaa6f1e7 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -27,6 +27,13 @@ KASAN_SANITIZE := n ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both + +# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true +# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is +# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code +# generation is minimal, it will just use r29 instead. +ccflags-y += $(call cc-option, -ffixed-r30) + asflags-y := -D__VDSO64__ -s targets += vdso64.lds From 06e91df16f3e1ca1a1886968fb22d4258f3b6b6f Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Thu, 29 Jul 2021 16:31:09 +0800 Subject: [PATCH 1053/1469] tty: serial: fsl_lpuart: fix the wrong return value in lpuart32_get_mctrl Patch e60c2991f18b make the lpuart32_get_mctrl always return 0, actually this will break the functions of device which use flow control such as Bluetooth. For lpuart32 plaform, the hardware can handle the CTS automatically. So we should set TIOCM_CTS active. Also need to set CAR and DSR active. Patch has been tested on lpuart32 platforms such as imx8qm and imx8ulp. Fixes: e60c2991f18b ("serial: fsl_lpuart: remove RTSCTS handling from get_mctrl()") Cc: stable Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20210729083109.31541-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 508128ddfa01..f0e5da77ed6d 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1415,7 +1415,7 @@ static unsigned int lpuart_get_mctrl(struct uart_port *port) static unsigned int lpuart32_get_mctrl(struct uart_port *port) { - unsigned int mctrl = 0; + unsigned int mctrl = TIOCM_CAR | TIOCM_DSR | TIOCM_CTS; u32 reg; reg = lpuart32_read(port, UARTCTRL); From 7c4a509d3815a260c423c0633bd73695250ac26d Mon Sep 17 00:00:00 2001 From: Zhiyong Tao Date: Thu, 29 Jul 2021 16:46:40 +0800 Subject: [PATCH 1054/1469] serial: 8250_mtk: fix uart corruption issue when rx power off Fix uart corruption issue when rx power off. Add spin lock in mtk8250_dma_rx_complete function in APDMA mode. when uart is used as a communication port with external device(GPS). when external device(GPS) power off, the power of rx pin is also from 1.8v to 0v. Even if there is not any data in rx. But uart rx pin can capture the data "0". If uart don't receive any data in specified cycle, uart will generates BI(Break interrupt) interrupt. If external device(GPS) power off, we found that BI interrupt appeared continuously and very frequently. When uart interrupt type is BI, uart IRQ handler(8250 framwork API:serial8250_handle_irq) will push data to tty buffer. mtk8250_dma_rx_complete is a task of mtk_uart_apdma_rx_handler. mtk8250_dma_rx_complete priority is lower than uart irq handler(serial8250_handle_irq). if we are in process of mtk8250_dma_rx_complete, uart appear BI interrupt:1)serial8250_handle_irq will priority execution.2)it may cause write tty buffer conflict in mtk8250_dma_rx_complete. So the spin lock protect the rx receive data process is not break. Signed-off-by: Zhiyong Tao Cc: stable Link: https://lore.kernel.org/r/20210729084640.17613-2-zhiyong.tao@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_mtk.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f7d3023f860f..fb65dc601b23 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -93,10 +93,13 @@ static void mtk8250_dma_rx_complete(void *param) struct dma_tx_state state; int copied, total, cnt; unsigned char *ptr; + unsigned long flags; if (data->rx_status == DMA_RX_SHUTDOWN) return; + spin_lock_irqsave(&up->port.lock, flags); + dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); total = dma->rx_size - state.residue; cnt = total; @@ -120,6 +123,8 @@ static void mtk8250_dma_rx_complete(void *param) tty_flip_buffer_push(tty_port); mtk8250_rx_dma(up); + + spin_unlock_irqrestore(&up->port.lock, flags); } static void mtk8250_rx_dma(struct uart_8250_port *up) From 0d6434e10b5377a006f6dd995c8fc5e2d82acddc Mon Sep 17 00:00:00 2001 From: Anirudh Rayabharam Date: Wed, 28 Jul 2021 14:21:06 +0530 Subject: [PATCH 1055/1469] firmware_loader: use -ETIMEDOUT instead of -EAGAIN in fw_load_sysfs_fallback The only motivation for using -EAGAIN in commit 0542ad88fbdd81bb ("firmware loader: Fix _request_firmware_load() return val for fw load abort") was to distinguish the error from -ENOMEM, and so there is no real reason in keeping it. -EAGAIN is typically used to tell the userspace to try something again and in this case re-using the sysfs loading interface cannot be retried when a timeout happens, so the return value is also bogus. -ETIMEDOUT is received when the wait times out and returning that is much more telling of what the reason for the failure was. So, just propagate that instead of returning -EAGAIN. Suggested-by: Luis Chamberlain Reviewed-by: Shuah Khan Acked-by: Luis Chamberlain Signed-off-by: Anirudh Rayabharam Cc: stable Link: https://lore.kernel.org/r/20210728085107.4141-2-mail@anirudhrb.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/fallback.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index 91899d185e31..1a48be0a030e 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -535,8 +535,6 @@ static int fw_load_sysfs_fallback(struct fw_sysfs *fw_sysfs, long timeout) if (fw_state_is_aborted(fw_priv)) { if (retval == -ERESTARTSYS) retval = -EINTR; - else - retval = -EAGAIN; } else if (fw_priv->is_paged_buf && !fw_priv->data) retval = -ENOMEM; From 75d95e2e39b27f733f21e6668af1c9893a97de5e Mon Sep 17 00:00:00 2001 From: Anirudh Rayabharam Date: Wed, 28 Jul 2021 14:21:07 +0530 Subject: [PATCH 1056/1469] firmware_loader: fix use-after-free in firmware_fallback_sysfs This use-after-free happens when a fw_priv object has been freed but hasn't been removed from the pending list (pending_fw_head). The next time fw_load_sysfs_fallback tries to insert into the list, it ends up accessing the pending_list member of the previously freed fw_priv. The root cause here is that all code paths that abort the fw load don't delete it from the pending list. For example: _request_firmware() -> fw_abort_batch_reqs() -> fw_state_aborted() To fix this, delete the fw_priv from the list in __fw_set_state() if the new state is DONE or ABORTED. This way, all aborts will remove the fw_priv from the list. Accordingly, remove calls to list_del_init that were being made before calling fw_state_(aborted|done). Also, in fw_load_sysfs_fallback, don't add the fw_priv to the pending list if it is already aborted. Instead, just jump out and return early. Fixes: bcfbd3523f3c ("firmware: fix a double abort case with fw_load_sysfs_fallback") Cc: stable Reported-by: syzbot+de271708674e2093097b@syzkaller.appspotmail.com Tested-by: syzbot+de271708674e2093097b@syzkaller.appspotmail.com Reviewed-by: Shuah Khan Acked-by: Luis Chamberlain Signed-off-by: Anirudh Rayabharam Link: https://lore.kernel.org/r/20210728085107.4141-3-mail@anirudhrb.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/fallback.c | 12 ++++++++---- drivers/base/firmware_loader/firmware.h | 10 +++++++++- drivers/base/firmware_loader/main.c | 2 ++ 3 files changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index 1a48be0a030e..d7d63c1aa993 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -89,12 +89,11 @@ static void __fw_load_abort(struct fw_priv *fw_priv) { /* * There is a small window in which user can write to 'loading' - * between loading done and disappearance of 'loading' + * between loading done/aborted and disappearance of 'loading' */ - if (fw_sysfs_done(fw_priv)) + if (fw_state_is_aborted(fw_priv) || fw_sysfs_done(fw_priv)) return; - list_del_init(&fw_priv->pending_list); fw_state_aborted(fw_priv); } @@ -280,7 +279,6 @@ static ssize_t firmware_loading_store(struct device *dev, * Same logic as fw_load_abort, only the DONE bit * is ignored and we set ABORT only on failure. */ - list_del_init(&fw_priv->pending_list); if (rc) { fw_state_aborted(fw_priv); written = rc; @@ -513,6 +511,11 @@ static int fw_load_sysfs_fallback(struct fw_sysfs *fw_sysfs, long timeout) } mutex_lock(&fw_lock); + if (fw_state_is_aborted(fw_priv)) { + mutex_unlock(&fw_lock); + retval = -EINTR; + goto out; + } list_add(&fw_priv->pending_list, &pending_fw_head); mutex_unlock(&fw_lock); @@ -538,6 +541,7 @@ static int fw_load_sysfs_fallback(struct fw_sysfs *fw_sysfs, long timeout) } else if (fw_priv->is_paged_buf && !fw_priv->data) retval = -ENOMEM; +out: device_del(f_dev); err_put_dev: put_device(f_dev); diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h index 63bd29fdcb9c..a3014e9e2c85 100644 --- a/drivers/base/firmware_loader/firmware.h +++ b/drivers/base/firmware_loader/firmware.h @@ -117,8 +117,16 @@ static inline void __fw_state_set(struct fw_priv *fw_priv, WRITE_ONCE(fw_st->status, status); - if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED) + if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED) { +#ifdef CONFIG_FW_LOADER_USER_HELPER + /* + * Doing this here ensures that the fw_priv is deleted from + * the pending list in all abort/done paths. + */ + list_del_init(&fw_priv->pending_list); +#endif complete_all(&fw_st->completion); + } } static inline void fw_state_aborted(struct fw_priv *fw_priv) diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 4fdb8219cd08..68c549d71230 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -783,8 +783,10 @@ static void fw_abort_batch_reqs(struct firmware *fw) return; fw_priv = fw->priv; + mutex_lock(&fw_lock); if (!fw_state_is_aborted(fw_priv)) fw_state_aborted(fw_priv); + mutex_unlock(&fw_lock); } /* called from request_firmware() and request_firmware_work_func() */ From b1e27239b9169f07edba0ca0e52805645a1768ba Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:46 -0700 Subject: [PATCH 1057/1469] xfs: flush data dev on external log write We incorrectly flush the log device instead of the data device when trying to ensure metadata is correctly on disk before writing the unmount record. Fixes: eef983ffeae7 ("xfs: journal IO cache flush reductions") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 36fa2650b081..96434cc4df6e 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -833,7 +833,7 @@ xlog_write_unmount_record( * stamp the tail LSN into the unmount record. */ if (log->l_targ != log->l_mp->m_ddev_targp) - blkdev_issue_flush(log->l_targ->bt_bdev); + blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev); return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS); } From b5d721eaae47eaa4b4c2754699dadacc4cbca2e0 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:47 -0700 Subject: [PATCH 1058/1469] xfs: external logs need to flush data device The recent journal flush/FUA changes replaced the flushing of the data device on every iclog write with an up-front async data device cache flush. Unfortunately, the assumption of which this was based on has been proven incorrect by the flush vs log tail update ordering issue. As the fix for that issue uses the XLOG_ICL_NEED_FLUSH flag to indicate that data device needs a cache flush, we now need to (once again) ensure that an iclog write to external logs that need a cache flush to be issued actually issue a cache flush to the data device as well as the log device. Fixes: eef983ffeae7 ("xfs: journal IO cache flush reductions") Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 96434cc4df6e..a3c4d48195d9 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -827,13 +827,6 @@ xlog_write_unmount_record( /* account for space used by record data */ ticket->t_curr_res -= sizeof(ulf); - /* - * For external log devices, we need to flush the data device cache - * first to ensure all metadata writeback is on stable storage before we - * stamp the tail LSN into the unmount record. - */ - if (log->l_targ != log->l_mp->m_ddev_targp) - blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev); return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS); } @@ -1796,10 +1789,20 @@ xlog_write_iclog( * metadata writeback and causing priority inversions. */ iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE; - if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) + if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { iclog->ic_bio.bi_opf |= REQ_PREFLUSH; + /* + * For external log devices, we also need to flush the data + * device cache first to ensure all metadata writeback covered + * by the LSN in this iclog is on stable storage. This is slow, + * but it *must* complete before we issue the external log IO. + */ + if (log->l_targ != log->l_mp->m_ddev_targp) + blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev); + } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; + iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) { From 9d3920644081edf311878b56e0c1e1477991a195 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:47 -0700 Subject: [PATCH 1059/1469] xfs: fold __xlog_state_release_iclog into xlog_state_release_iclog Fold __xlog_state_release_iclog into its only caller to prepare make an upcoming fix easier. Signed-off-by: Dave Chinner [hch: split from a larger patch] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 45 +++++++++++++++++---------------------------- 1 file changed, 17 insertions(+), 28 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a3c4d48195d9..82f5996d3889 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -487,29 +487,6 @@ out_error: return error; } -static bool -__xlog_state_release_iclog( - struct xlog *log, - struct xlog_in_core *iclog) -{ - lockdep_assert_held(&log->l_icloglock); - - if (iclog->ic_state == XLOG_STATE_WANT_SYNC) { - /* update tail before writing to iclog */ - xfs_lsn_t tail_lsn = xlog_assign_tail_lsn(log->l_mp); - - iclog->ic_state = XLOG_STATE_SYNCING; - iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); - xlog_verify_tail_lsn(log, iclog, tail_lsn); - /* cycle incremented when incrementing curr_block */ - trace_xlog_iclog_syncing(iclog, _RET_IP_); - return true; - } - - ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); - return false; -} - /* * Flush iclog to disk if this is the last reference to the given iclog and the * it is in the WANT_SYNC state. @@ -519,19 +496,31 @@ xlog_state_release_iclog( struct xlog *log, struct xlog_in_core *iclog) { + xfs_lsn_t tail_lsn; lockdep_assert_held(&log->l_icloglock); trace_xlog_iclog_release(iclog, _RET_IP_); if (iclog->ic_state == XLOG_STATE_IOERROR) return -EIO; - if (atomic_dec_and_test(&iclog->ic_refcnt) && - __xlog_state_release_iclog(log, iclog)) { - spin_unlock(&log->l_icloglock); - xlog_sync(log, iclog); - spin_lock(&log->l_icloglock); + if (!atomic_dec_and_test(&iclog->ic_refcnt)) + return 0; + + if (iclog->ic_state != XLOG_STATE_WANT_SYNC) { + ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); + return 0; } + /* update tail before writing to iclog */ + tail_lsn = xlog_assign_tail_lsn(log->l_mp); + iclog->ic_state = XLOG_STATE_SYNCING; + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); + xlog_verify_tail_lsn(log, iclog, tail_lsn); + trace_xlog_iclog_syncing(iclog, _RET_IP_); + + spin_unlock(&log->l_icloglock); + xlog_sync(log, iclog); + spin_lock(&log->l_icloglock); return 0; } From 0dc8f7f139f07aaca1afcec0ade5718c4ebba91e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:48 -0700 Subject: [PATCH 1060/1469] xfs: fix ordering violation between cache flushes and tail updates There is a race between the new CIL async data device metadata IO completion cache flush and the log tail in the iclog the flush covers being updated. This can be seen by repeating generic/482 in a loop and eventually log recovery fails with a failures such as this: XFS (dm-3): Starting recovery (logdev: internal) XFS (dm-3): bad inode magic/vsn daddr 228352 #0 (magic=0) XFS (dm-3): Metadata corruption detected at xfs_inode_buf_verify+0x180/0x190, xfs_inode block 0x37c00 xfs_inode_buf_verify XFS (dm-3): Unmount and run xfs_repair XFS (dm-3): First 128 bytes of corrupted metadata buffer: 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000050: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000060: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000070: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ XFS (dm-3): metadata I/O error in "xlog_recover_items_pass2+0x55/0xc0" at daddr 0x37c00 len 32 error 117 Analysis of the logwrite replay shows that there were no writes to the data device between the FUA @ write 124 and the FUA at write @ 125, but log recovery @ 125 failed. The difference was the one log write @ 125 moved the tail of the log forwards from (1,8) to (1,32) and so the inode create intent in (1,8) was not replayed and so the inode cluster was zero on disk when replay of the first inode item in (1,32) was attempted. What this meant was that the journal write that occurred at @ 125 did not ensure that metadata completed before the iclog was written was correctly on stable storage. The tail of the log moved forward, so IO must have been completed between the two iclog writes. This means that there is a race condition between the unconditional async cache flush in the CIL push work and the tail LSN that is written to the iclog. This happens like so: CIL push work AIL push work ------------- ------------- Add to committing list start async data dev cache flush ..... xlog_write .... push inode create buffer ..... xlog_write(commit record) .... log tail moves xlog_assign_tail_lsn() start_lsn == commit_lsn xlog_state_release_iclog __xlog_state_release_iclog() xlog_sync() .... submit_bio() Essentially, this can only occur if the commit iclog is issued without a cache flush. If the iclog bio is submitted with REQ_PREFLUSH, then it will guarantee that all the completed IO is one stable storage before the iclog bio with the new tail LSN in it is written to the log. IOWs, the tail lsn that is written to the iclog needs to be sampled *before* we issue the cache flush that guarantees all IO up to that LSN has been completed. To fix this without giving up the performance advantage of the flush/FUA optimisations (e.g. g/482 runtime halves with 5.14-rc1 compared to 5.13), we need to ensure that we always issue a cache flush if the tail LSN changes between the initial async flush and the commit record being written. THis requires sampling the tail_lsn before we start the flush, and then passing the sampled tail LSN to xlog_state_release_iclog() so it can determine if the the tail LSN has changed while writing the checkpoint. If the tail LSN has changed, then it needs to set the NEED_FLUSH flag on the iclog and we'll issue another cache flush before writing the iclog. Fixes: eef983ffeae7 ("xfs: journal IO cache flush reductions") Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 36 ++++++++++++++++++++++++++---------- fs/xfs/xfs_log_cil.c | 13 +++++++++++-- fs/xfs/xfs_log_priv.h | 3 ++- 3 files changed, 39 insertions(+), 13 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 82f5996d3889..e8c6c96d4f7c 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -489,12 +489,17 @@ out_error: /* * Flush iclog to disk if this is the last reference to the given iclog and the - * it is in the WANT_SYNC state. + * it is in the WANT_SYNC state. If the caller passes in a non-zero + * @old_tail_lsn and the current log tail does not match, there may be metadata + * on disk that must be persisted before this iclog is written. To satisfy that + * requirement, set the XLOG_ICL_NEED_FLUSH flag as a condition for writing this + * iclog with the new log tail value. */ int xlog_state_release_iclog( struct xlog *log, - struct xlog_in_core *iclog) + struct xlog_in_core *iclog, + xfs_lsn_t old_tail_lsn) { xfs_lsn_t tail_lsn; lockdep_assert_held(&log->l_icloglock); @@ -503,6 +508,19 @@ xlog_state_release_iclog( if (iclog->ic_state == XLOG_STATE_IOERROR) return -EIO; + /* + * Grabbing the current log tail needs to be atomic w.r.t. the writing + * of the tail LSN into the iclog so we guarantee that the log tail does + * not move between deciding if a cache flush is required and writing + * the LSN into the iclog below. + */ + if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) { + tail_lsn = xlog_assign_tail_lsn(log->l_mp); + + if (old_tail_lsn && tail_lsn != old_tail_lsn) + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; + } + if (!atomic_dec_and_test(&iclog->ic_refcnt)) return 0; @@ -511,8 +529,6 @@ xlog_state_release_iclog( return 0; } - /* update tail before writing to iclog */ - tail_lsn = xlog_assign_tail_lsn(log->l_mp); iclog->ic_state = XLOG_STATE_SYNCING; iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); xlog_verify_tail_lsn(log, iclog, tail_lsn); @@ -858,7 +874,7 @@ out_err: * iclog containing the unmount record is written. */ iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); xlog_wait_on_iclog(iclog); if (tic) { @@ -2302,7 +2318,7 @@ xlog_write_copy_finish( return 0; release_iclog: - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); spin_unlock(&log->l_icloglock); return error; } @@ -2521,7 +2537,7 @@ next_lv: ASSERT(optype & XLOG_COMMIT_TRANS); *commit_iclog = iclog; } else { - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); } spin_unlock(&log->l_icloglock); @@ -2959,7 +2975,7 @@ restart: * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, 0); spin_unlock(&log->l_icloglock); if (error) return error; @@ -3195,7 +3211,7 @@ xfs_log_force( atomic_inc(&iclog->ic_refcnt); lsn = be64_to_cpu(iclog->ic_header.h_lsn); xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog)) + if (xlog_state_release_iclog(log, iclog, 0)) goto out_error; if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) @@ -3275,7 +3291,7 @@ xlog_force_lsn( } atomic_inc(&iclog->ic_refcnt); xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog)) + if (xlog_state_release_iclog(log, iclog, 0)) goto out_error; if (log_flushed) *log_flushed = 1; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index b128aaa9b870..4c44bc3786c0 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -654,8 +654,9 @@ xlog_cil_push_work( struct xfs_trans_header thdr; struct xfs_log_iovec lhdr; struct xfs_log_vec lvhdr = { NULL }; + xfs_lsn_t preflush_tail_lsn; xfs_lsn_t commit_lsn; - xfs_lsn_t push_seq; + xfs_csn_t push_seq; struct bio bio; DECLARE_COMPLETION_ONSTACK(bdev_flush); @@ -730,7 +731,15 @@ xlog_cil_push_work( * because we hold the flush lock exclusively. Hence we can now issue * a cache flush to ensure all the completed metadata in the journal we * are about to overwrite is on stable storage. + * + * Because we are issuing this cache flush before we've written the + * tail lsn to the iclog, we can have metadata IO completions move the + * tail forwards between the completion of this flush and the iclog + * being written. In this case, we need to re-issue the cache flush + * before the iclog write. To detect whether the log tail moves, sample + * the tail LSN *before* we issue the flush. */ + preflush_tail_lsn = atomic64_read(&log->l_tail_lsn); xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev, &bdev_flush); @@ -941,7 +950,7 @@ restart: * storage. */ commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA; - xlog_state_release_iclog(log, commit_iclog); + xlog_state_release_iclog(log, commit_iclog, preflush_tail_lsn); spin_unlock(&log->l_icloglock); return; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 4c41bbfa33b0..7cbde0b4f990 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -497,7 +497,8 @@ int xlog_commit_record(struct xlog *log, struct xlog_ticket *ticket, void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket); void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); -int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog); +int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog, + xfs_lsn_t log_tail_lsn); /* * When we crack an atomic LSN, we sample it first so that the value will not From 45eddb414047c366744cc60dd6cef7c7e58c6ab9 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:48 -0700 Subject: [PATCH 1061/1469] xfs: factor out forced iclog flushes We force iclogs in several places - we need them all to have the same cache flush semantics, so start by factoring out the iclog force into a common helper. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 42 ++++++++++++++++++------------------------ 1 file changed, 18 insertions(+), 24 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index e8c6c96d4f7c..184c68ea62bb 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -778,6 +778,20 @@ xfs_log_mount_cancel( xfs_log_unmount(mp); } +/* + * Flush out the iclog to disk ensuring that device caches are flushed and + * the iclog hits stable storage before any completion waiters are woken. + */ +static inline int +xlog_force_iclog( + struct xlog_in_core *iclog) +{ + atomic_inc(&iclog->ic_refcnt); + if (iclog->ic_state == XLOG_STATE_ACTIVE) + xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); + return xlog_state_release_iclog(iclog->ic_log, iclog, 0); +} + /* * Wait for the iclog and all prior iclogs to be written disk as required by the * log force state machine. Waiting on ic_force_wait ensures iclog completions @@ -863,18 +877,8 @@ out_err: spin_lock(&log->l_icloglock); iclog = log->l_iclog; - atomic_inc(&iclog->ic_refcnt); - if (iclog->ic_state == XLOG_STATE_ACTIVE) - xlog_state_switch_iclogs(log, iclog, 0); - else - ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC || - iclog->ic_state == XLOG_STATE_IOERROR); - /* - * Ensure the journal is fully flushed and on stable storage once the - * iclog containing the unmount record is written. - */ iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); - error = xlog_state_release_iclog(log, iclog, 0); + error = xlog_force_iclog(iclog); xlog_wait_on_iclog(iclog); if (tic) { @@ -3201,17 +3205,9 @@ xfs_log_force( iclog = iclog->ic_prev; } else if (iclog->ic_state == XLOG_STATE_ACTIVE) { if (atomic_read(&iclog->ic_refcnt) == 0) { - /* - * We are the only one with access to this iclog. - * - * Flush it out now. There should be a roundoff of zero - * to show that someone has already taken care of the - * roundoff from the previous sync. - */ - atomic_inc(&iclog->ic_refcnt); + /* We have exclusive access to this iclog. */ lsn = be64_to_cpu(iclog->ic_header.h_lsn); - xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog, 0)) + if (xlog_force_iclog(iclog)) goto out_error; if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) @@ -3289,9 +3285,7 @@ xlog_force_lsn( &log->l_icloglock); return -EAGAIN; } - atomic_inc(&iclog->ic_refcnt); - xlog_state_switch_iclogs(log, iclog, 0); - if (xlog_state_release_iclog(log, iclog, 0)) + if (xlog_force_iclog(iclog)) goto out_error; if (log_flushed) *log_flushed = 1; From 2bf1ec0ff067ff8f692d261b29c713f3583f7e2a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:49 -0700 Subject: [PATCH 1062/1469] xfs: log forces imply data device cache flushes After fixing the tail_lsn vs cache flush race, generic/482 continued to fail in a similar way where cache flushes were missing before iclog FUA writes. Tracing of iclog state changes during the fsstress workload portion of the test (via xlog_iclog* events) indicated that iclog writes were coming from two sources - CIL pushes and log forces (due to fsync/O_SYNC operations). All of the cases where a recovery problem was triggered indicated that the log force was the source of the iclog write that was not preceeded by a cache flush. This was an oversight in the modifications made in commit eef983ffeae7 ("xfs: journal IO cache flush reductions"). Log forces for fsync imply a data device cache flush has been issued if an iclog was flushed to disk and is indicated to the caller via the log_flushed parameter so they can elide the device cache flush if the journal issued one. The change in eef983ffeae7 results in iclogs only issuing a cache flush if XLOG_ICL_NEED_FLUSH is set on the iclog, but this was not added to the iclogs that the log force code flushes to disk. Hence log forces are no longer guaranteeing that a cache flush is issued, hence opening up a potential on-disk ordering failure. Log forces should also set XLOG_ICL_NEED_FUA as well to ensure that the actual iclogs it forces to the journal are also on stable storage before it returns to the caller. This patch introduces the xlog_force_iclog() helper function to encapsulate the process of taking a reference to an iclog, switching its state if WANT_SYNC and flushing it to stable storage correctly. Both xfs_log_force() and xfs_log_force_lsn() are converted to use it, as is xlog_unmount_write() which has an elaborate method of doing exactly the same "write this iclog to stable storage" operation. Further, if the log force code needs to wait on a iclog in the WANT_SYNC state, it needs to ensure that iclog also results in a cache flush being issued. This covers the case where the iclog contains the commit record of the CIL flush that the log force triggered, but it hasn't been written yet because there is still an active reference to the iclog. Note: this whole cache flush whack-a-mole patch is a result of log forces still being iclog state centric rather than being CIL sequence centric. Most of this nasty code will go away in future when log forces are converted to wait on CIL sequence push completion rather than iclog completion. With the CIL push algorithm guaranteeing that the CIL checkpoint is fully on stable storage when it completes, we no longer need to iterate iclogs and push them to ensure a CIL sequence push has completed and so all this nasty iclog iteration and flushing code will go away. Fixes: eef983ffeae7 ("xfs: journal IO cache flush reductions") Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 184c68ea62bb..160b8bb7ee60 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -787,6 +787,7 @@ xlog_force_iclog( struct xlog_in_core *iclog) { atomic_inc(&iclog->ic_refcnt); + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); return xlog_state_release_iclog(iclog->ic_log, iclog, 0); @@ -877,7 +878,6 @@ out_err: spin_lock(&log->l_icloglock); iclog = log->l_iclog; - iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); error = xlog_force_iclog(iclog); xlog_wait_on_iclog(iclog); @@ -3214,22 +3214,23 @@ xfs_log_force( goto out_unlock; } else { /* - * Someone else is writing to this iclog. - * - * Use its call to flush out the data. However, the - * other thread may not force out this LR, so we mark - * it WANT_SYNC. + * Someone else is still writing to this iclog, so we + * need to ensure that when they release the iclog it + * gets synced immediately as we may be waiting on it. */ xlog_state_switch_iclogs(log, iclog, 0); } - } else { - /* - * If the head iclog is not active nor dirty, we just attach - * ourselves to the head and go to sleep if necessary. - */ - ; } + /* + * The iclog we are about to wait on may contain the checkpoint pushed + * by the above xlog_cil_force() call, but it may not have been pushed + * to disk yet. Like the ACTIVE case above, we need to make sure caches + * are flushed when this iclog is written. + */ + if (iclog->ic_state == XLOG_STATE_WANT_SYNC) + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; + if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: @@ -3262,7 +3263,8 @@ xlog_force_lsn( goto out_unlock; } - if (iclog->ic_state == XLOG_STATE_ACTIVE) { + switch (iclog->ic_state) { + case XLOG_STATE_ACTIVE: /* * We sleep here if we haven't already slept (e.g. this is the * first time we've looked at the correct iclog buf) and the @@ -3289,6 +3291,25 @@ xlog_force_lsn( goto out_error; if (log_flushed) *log_flushed = 1; + break; + case XLOG_STATE_WANT_SYNC: + /* + * This iclog may contain the checkpoint pushed by the + * xlog_cil_force_seq() call, but there are other writers still + * accessing it so it hasn't been pushed to disk yet. Like the + * ACTIVE case above, we need to make sure caches are flushed + * when this iclog is written. + */ + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; + break; + default: + /* + * The entire checkpoint was written by the CIL force and is on + * its way to disk already. It will be stable when it + * completes, so we don't need to manipulate caches here at all. + * We just need to wait for completion if necessary. + */ + break; } if (flags & XFS_LOG_SYNC) From 8191d8222c514c69a8e1ac46bd9812b9e0aab7d0 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:49 -0700 Subject: [PATCH 1063/1469] xfs: avoid unnecessary waits in xfs_log_force_lsn() Before waiting on a iclog in xfs_log_force_lsn(), we don't check to see if the iclog has already been completed and the contents on stable storage. We check for completed iclogs in xfs_log_force(), so we should do the same thing for xfs_log_force_lsn(). This fixed some random up-to-30s pauses seen in unmounting filesystems in some tests. A log force ends up waiting on completed iclog, and that doesn't then get flushed (and hence the log force get completed) until the background log worker issues a log force that flushes the iclog in question. Then the unmount unblocks and continues. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 42 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 160b8bb7ee60..1c328efdca66 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3143,6 +3143,35 @@ xlog_state_switch_iclogs( log->l_iclog = iclog->ic_next; } +/* + * Force the iclog to disk and check if the iclog has been completed before + * xlog_force_iclog() returns. This can happen on synchronous (e.g. + * pmem) or fast async storage because we drop the icloglock to issue the IO. + * If completion has already occurred, tell the caller so that it can avoid an + * unnecessary wait on the iclog. + */ +static int +xlog_force_and_check_iclog( + struct xlog_in_core *iclog, + bool *completed) +{ + xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn); + int error; + + *completed = false; + error = xlog_force_iclog(iclog); + if (error) + return error; + + /* + * If the iclog has already been completed and reused the header LSN + * will have been rewritten by completion + */ + if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) + *completed = true; + return 0; +} + /* * Write out all data in the in-core log as of this exact moment in time. * @@ -3177,7 +3206,6 @@ xfs_log_force( { struct xlog *log = mp->m_log; struct xlog_in_core *iclog; - xfs_lsn_t lsn; XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, 0, _RET_IP_); @@ -3206,11 +3234,12 @@ xfs_log_force( } else if (iclog->ic_state == XLOG_STATE_ACTIVE) { if (atomic_read(&iclog->ic_refcnt) == 0) { /* We have exclusive access to this iclog. */ - lsn = be64_to_cpu(iclog->ic_header.h_lsn); - if (xlog_force_iclog(iclog)) + bool completed; + + if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; - if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) + if (completed) goto out_unlock; } else { /* @@ -3250,6 +3279,7 @@ xlog_force_lsn( bool already_slept) { struct xlog_in_core *iclog; + bool completed; spin_lock(&log->l_icloglock); iclog = log->l_iclog; @@ -3287,10 +3317,12 @@ xlog_force_lsn( &log->l_icloglock); return -EAGAIN; } - if (xlog_force_iclog(iclog)) + if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; + if (completed) + goto out_unlock; break; case XLOG_STATE_WANT_SYNC: /* From 32baa63d82ee3f5ab3bd51bae6bf7d1c15aed8c7 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:49 -0700 Subject: [PATCH 1064/1469] xfs: logging the on disk inode LSN can make it go backwards When we log an inode, we format the "log inode" core and set an LSN in that inode core. We do that via xfs_inode_item_format_core(), which calls: xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn); to format the log inode. It writes the LSN from the inode item into the log inode, and if recovery decides the inode item needs to be replayed, it recovers the log inode LSN field and writes it into the on disk inode LSN field. Now this might seem like a reasonable thing to do, but it is wrong on multiple levels. Firstly, if the item is not yet in the AIL, item->li_lsn is zero. i.e. the first time the inode it is logged and formatted, the LSN we write into the log inode will be zero. If we only log it once, recovery will run and can write this zero LSN into the inode. This means that the next time the inode is logged and log recovery runs, it will *always* replay changes to the inode regardless of whether the inode is newer on disk than the version in the log and that violates the entire purpose of recording the LSN in the inode at writeback time (i.e. to stop it going backwards in time on disk during recovery). Secondly, if we commit the CIL to the journal so the inode item moves to the AIL, and then relog the inode, the LSN that gets stamped into the log inode will be the LSN of the inode's current location in the AIL, not it's age on disk. And it's not the LSN that will be associated with the current change. That means when log recovery replays this inode item, the LSN that ends up on disk is the LSN for the previous changes in the log, not the current changes being replayed. IOWs, after recovery the LSN on disk is not in sync with the LSN of the modifications that were replayed into the inode. This, again, violates the recovery ordering semantics that on-disk writeback LSNs provide. Hence the inode LSN in the log dinode is -always- invalid. Thirdly, recovery actually has the LSN of the log transaction it is replaying right at hand - it uses it to determine if it should replay the inode by comparing it to the on-disk inode's LSN. But it doesn't use that LSN to stamp the LSN into the inode which will be written back when the transaction is fully replayed. It uses the one in the log dinode, which we know is always going to be incorrect. Looking back at the change history, the inode logging was broken by commit 93f958f9c41f ("xfs: cull unnecessary icdinode fields") way back in 2016 by a stupid idiot who thought he knew how this code worked. i.e. me. That commit replaced an in memory di_lsn field that was updated only at inode writeback time from the inode item.li_lsn value - and hence always contained the same LSN that appeared in the on-disk inode - with a read of the inode item LSN at inode format time. CLearly these are not the same thing. Before 93f958f9c41f, the log recovery behaviour was irrelevant, because the LSN in the log inode always matched the on-disk LSN at the time the inode was logged, hence recovery of the transaction would never make the on-disk LSN in the inode go backwards or get out of sync. A symptom of the problem is this, caught from a failure of generic/482. Before log recovery, the inode has been allocated but never used: xfs_db> inode 393388 xfs_db> p core.magic = 0x494e core.mode = 0 .... v3.crc = 0x99126961 (correct) v3.change_count = 0 v3.lsn = 0 v3.flags2 = 0 v3.cowextsize = 0 v3.crtime.sec = Thu Jan 1 10:00:00 1970 v3.crtime.nsec = 0 After log recovery: xfs_db> p core.magic = 0x494e core.mode = 020444 .... v3.crc = 0x23e68f23 (correct) v3.change_count = 2 v3.lsn = 0 v3.flags2 = 0 v3.cowextsize = 0 v3.crtime.sec = Thu Jul 22 17:03:03 2021 v3.crtime.nsec = 751000000 ... You can see that the LSN of the on-disk inode is 0, even though it clearly has been written to disk. I point out this inode, because the generic/482 failure occurred because several adjacent inodes in this specific inode cluster were not replayed correctly and still appeared to be zero on disk when all the other metadata (inobt, finobt, directories, etc) indicated they should be allocated and written back. The fix for this is two-fold. The first is that we need to either revert the LSN changes in 93f958f9c41f or stop logging the inode LSN altogether. If we do the former, log recovery does not need to change but we add 8 bytes of memory per inode to store what is largely a write-only inode field. If we do the latter, log recovery needs to stamp the on-disk inode in the same manner that inode writeback does. I prefer the latter, because we shouldn't really be trying to log and replay changes to the on disk LSN as the on-disk value is the canonical source of the on-disk version of the inode. It also matches the way we recover buffer items - we create a buf_log_item that carries the current recovery transaction LSN that gets stamped into the buffer by the write verifier when it gets written back when the transaction is fully recovered. However, this might break log recovery on older kernels even more, so I'm going to simply ignore the logged value in recovery and stamp the on-disk inode with the LSN of the transaction being recovered that will trigger writeback on transaction recovery completion. This will ensure that the on-disk inode LSN always reflects the LSN of the last change that was written to disk, regardless of whether it comes from log recovery or runtime writeback. Fixes: 93f958f9c41f ("xfs: cull unnecessary icdinode fields") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_log_format.h | 11 +++++++++- fs/xfs/xfs_inode_item_recover.c | 39 ++++++++++++++++++++++++--------- 2 files changed, 39 insertions(+), 11 deletions(-) diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index d548ea4b6aab..2c5bcbc19264 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -411,7 +411,16 @@ struct xfs_log_dinode { /* start of the extended dinode, writable fields */ uint32_t di_crc; /* CRC of the inode */ uint64_t di_changecount; /* number of attribute changes */ - xfs_lsn_t di_lsn; /* flush sequence */ + + /* + * The LSN we write to this field during formatting is not a reflection + * of the current on-disk LSN. It should never be used for recovery + * sequencing, nor should it be recovered into the on-disk inode at all. + * See xlog_recover_inode_commit_pass2() and xfs_log_dinode_to_disk() + * for details. + */ + xfs_lsn_t di_lsn; + uint64_t di_flags2; /* more random flags */ uint32_t di_cowextsize; /* basic cow extent size for file */ uint8_t di_pad2[12]; /* more padding for future expansion */ diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 7b79518b6c20..e0072a6cd2d3 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -145,7 +145,8 @@ xfs_log_dinode_to_disk_ts( STATIC void xfs_log_dinode_to_disk( struct xfs_log_dinode *from, - struct xfs_dinode *to) + struct xfs_dinode *to, + xfs_lsn_t lsn) { to->di_magic = cpu_to_be16(from->di_magic); to->di_mode = cpu_to_be16(from->di_mode); @@ -182,7 +183,7 @@ xfs_log_dinode_to_disk( to->di_flags2 = cpu_to_be64(from->di_flags2); to->di_cowextsize = cpu_to_be32(from->di_cowextsize); to->di_ino = cpu_to_be64(from->di_ino); - to->di_lsn = cpu_to_be64(from->di_lsn); + to->di_lsn = cpu_to_be64(lsn); memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2)); uuid_copy(&to->di_uuid, &from->di_uuid); to->di_flushiter = 0; @@ -261,16 +262,25 @@ xlog_recover_inode_commit_pass2( } /* - * If the inode has an LSN in it, recover the inode only if it's less - * than the lsn of the transaction we are replaying. Note: we still - * need to replay an owner change even though the inode is more recent - * than the transaction as there is no guarantee that all the btree - * blocks are more recent than this transaction, too. + * If the inode has an LSN in it, recover the inode only if the on-disk + * inode's LSN is older than the lsn of the transaction we are + * replaying. We can have multiple checkpoints with the same start LSN, + * so the current LSN being equal to the on-disk LSN doesn't necessarily + * mean that the on-disk inode is more recent than the change being + * replayed. + * + * We must check the current_lsn against the on-disk inode + * here because the we can't trust the log dinode to contain a valid LSN + * (see comment below before replaying the log dinode for details). + * + * Note: we still need to replay an owner change even though the inode + * is more recent than the transaction as there is no guarantee that all + * the btree blocks are more recent than this transaction, too. */ if (dip->di_version >= 3) { xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn); - if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { + if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) { trace_xfs_log_recover_inode_skip(log, in_f); error = 0; goto out_owner_change; @@ -368,8 +378,17 @@ xlog_recover_inode_commit_pass2( goto out_release; } - /* recover the log dinode inode into the on disk inode */ - xfs_log_dinode_to_disk(ldip, dip); + /* + * Recover the log dinode inode into the on disk inode. + * + * The LSN in the log dinode is garbage - it can be zero or reflect + * stale in-memory runtime state that isn't coherent with the changes + * logged in this transaction or the changes written to the on-disk + * inode. Hence we write the current lSN into the inode because that + * matches what xfs_iflush() would write inode the inode when flushing + * the changes in this transaction. + */ + xfs_log_dinode_to_disk(ldip, dip, current_lsn); fields = in_f->ilf_fields; if (fields & XFS_ILOG_DEV) From d8f4c2d0398fa1d92cacf854daf80d21a46bfefc Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:50 -0700 Subject: [PATCH 1065/1469] xfs: Enforce attr3 buffer recovery order From the department of "WTAF? How did we miss that!?"... When we are recovering a buffer, the first thing we do is check the buffer magic number and extract the LSN from the buffer. If the LSN is older than the current LSN, we replay the modification to it. If the metadata on disk is newer than the transaction in the log, we skip it. This is a fundamental v5 filesystem metadata recovery behaviour. generic/482 failed with an attribute writeback failure during log recovery. The write verifier caught the corruption before it got written to disk, and the attr buffer dump looked like: XFS (dm-3): Metadata corruption detected at xfs_attr3_leaf_verify+0x275/0x2e0, xfs_attr3_leaf block 0x19be8 XFS (dm-3): Unmount and run xfs_repair XFS (dm-3): First 128 bytes of corrupted metadata buffer: 00000000: 00 00 00 00 00 00 00 00 3b ee 00 00 4d 2a 01 e1 ........;...M*.. 00000010: 00 00 00 00 00 01 9b e8 00 00 00 01 00 00 05 38 ...............8 ^^^^^^^^^^^^^^^^^^^^^^^ 00000020: df 39 5e 51 58 ac 44 b6 8d c5 e7 10 44 09 bc 17 .9^QX.D.....D... 00000030: 00 00 00 00 00 02 00 83 00 03 00 cc 0f 24 01 00 .............$.. 00000040: 00 68 0e bc 0f c8 00 10 00 00 00 00 00 00 00 00 .h.............. 00000050: 00 00 3c 31 0f 24 01 00 00 00 3c 32 0f 88 01 00 ..<1.$....<2.... 00000060: 00 00 3c 33 0f d8 01 00 00 00 00 00 00 00 00 00 ..<3............ 00000070: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ ..... The highlighted bytes are the LSN that was replayed into the buffer: 0x100000538. This is cycle 1, block 0x538. Prior to replay, that block on disk looks like this: $ sudo xfs_db -c "fsb 0x417d" -c "type attr3" -c p /dev/mapper/thin-vol hdr.info.hdr.forw = 0 hdr.info.hdr.back = 0 hdr.info.hdr.magic = 0x3bee hdr.info.crc = 0xb5af0bc6 (correct) hdr.info.bno = 105448 hdr.info.lsn = 0x100000900 ^^^^^^^^^^^ hdr.info.uuid = df395e51-58ac-44b6-8dc5-e7104409bc17 hdr.info.owner = 131203 hdr.count = 2 hdr.usedbytes = 120 hdr.firstused = 3796 hdr.holes = 1 hdr.freemap[0-2] = [base,size] Note the LSN stamped into the buffer on disk: 1/0x900. The version on disk is much newer than the log transaction that was being replayed. That's a bug, and should -never- happen. So I immediately went to look at xlog_recover_get_buf_lsn() to check that we handled the LSN correctly. I was wondering if there was a similar "two commits with the same start LSN skips the second replay" problem with buffers. I didn't get that far, because I found a much more basic, rudimentary bug: xlog_recover_get_buf_lsn() doesn't recognise buffers with XFS_ATTR3_LEAF_MAGIC set in them!!! IOWs, attr3 leaf buffers fall through the magic number checks unrecognised, so trigger the "recover immediately" behaviour instead of undergoing an LSN check. IOWs, we incorrectly replay ATTR3 leaf buffers and that causes silent on disk corruption of inode attribute forks and potentially other things.... Git history shows this is *another* zero day bug, this time introduced in commit 50d5c8d8e938 ("xfs: check LSN ordering for v5 superblocks during recovery") which failed to handle the attr3 leaf buffers in recovery. And we've failed to handle them ever since... Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_buf_item_recover.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index d44e8b4a3391..05fd816edf59 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -796,6 +796,7 @@ xlog_recover_get_buf_lsn( switch (magicda) { case XFS_DIR3_LEAF1_MAGIC: case XFS_DIR3_LEAFN_MAGIC: + case XFS_ATTR3_LEAF_MAGIC: case XFS_DA3_NODE_MAGIC: lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); uuid = &((struct xfs_da3_blkinfo *)blk)->uuid; From b2ae3a9ef91152931b99620c431cf3805daa1429 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 27 Jul 2021 16:23:50 -0700 Subject: [PATCH 1066/1469] xfs: need to see iclog flags in tracing Because I cannot tell if the NEED_FLUSH flag is being set correctly by the log force and CIL push machinery without it. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log_priv.h | 13 ++++++++++--- fs/xfs/xfs_trace.h | 5 ++++- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 7cbde0b4f990..f3e79a45d60a 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -59,6 +59,16 @@ enum xlog_iclog_state { { XLOG_STATE_DIRTY, "XLOG_STATE_DIRTY" }, \ { XLOG_STATE_IOERROR, "XLOG_STATE_IOERROR" } +/* + * In core log flags + */ +#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */ +#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */ + +#define XLOG_ICL_STRINGS \ + { XLOG_ICL_NEED_FLUSH, "XLOG_ICL_NEED_FLUSH" }, \ + { XLOG_ICL_NEED_FUA, "XLOG_ICL_NEED_FUA" } + /* * Log ticket flags @@ -143,9 +153,6 @@ enum xlog_iclog_state { #define XLOG_COVER_OPS 5 -#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */ -#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */ - /* Ticket reservation region accounting */ #define XLOG_TIC_LEN_MAX 15 diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index f9d8d605f9b1..19260291ff8b 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3944,6 +3944,7 @@ DECLARE_EVENT_CLASS(xlog_iclog_class, __field(uint32_t, state) __field(int32_t, refcount) __field(uint32_t, offset) + __field(uint32_t, flags) __field(unsigned long long, lsn) __field(unsigned long, caller_ip) ), @@ -3952,15 +3953,17 @@ DECLARE_EVENT_CLASS(xlog_iclog_class, __entry->state = iclog->ic_state; __entry->refcount = atomic_read(&iclog->ic_refcnt); __entry->offset = iclog->ic_offset; + __entry->flags = iclog->ic_flags; __entry->lsn = be64_to_cpu(iclog->ic_header.h_lsn); __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx caller %pS", + TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->state, XLOG_STATE_STRINGS), __entry->refcount, __entry->offset, __entry->lsn, + __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS), (char *)__entry->caller_ip) ); From 9d110014205cb1129fa570d8de83d486fa199354 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Jul 2021 17:14:11 -0700 Subject: [PATCH 1067/1469] xfs: limit iclog tail updates From the department of "generic/482 keeps on giving", we bring you another tail update race condition: iclog: S1 C1 +-----------------------+-----------------------+ S2 EOIC Two checkpoints in a single iclog. One is complete, the other just contains the start record and overruns into a new iclog. Timeline: Before S1: Cache flush, log tail = X At S1: Metadata stable, write start record and checkpoint At C1: Write commit record, set NEED_FUA Single iclog checkpoint, so no need for NEED_FLUSH Log tail still = X, so no need for NEED_FLUSH After C1, Before S2: Cache flush, log tail = X At S2: Metadata stable, write start record and checkpoint After S2: Log tail moves to X+1 At EOIC: End of iclog, more journal data to write Releases iclog Not a commit iclog, so no need for NEED_FLUSH Writes log tail X+1 into iclog. At this point, the iclog has tail X+1 and NEED_FUA set. There has been no cache flush for the metadata between X and X+1, and the iclog writes the new tail permanently to the log. THis is sufficient to violate on disk metadata/journal ordering. We have two options here. The first is to detect this case in some manner and ensure that the partial checkpoint write sets NEED_FLUSH when the iclog is already marked NEED_FUA and the log tail changes. This seems somewhat fragile and quite complex to get right, and it doesn't actually make it obvious what underlying problem it is actually addressing from reading the code. The second option seems much cleaner to me, because it is derived directly from the requirements of the C1 commit record in the iclog. That is, when we write this commit record to the iclog, we've guaranteed that the metadata/data ordering is correct for tail update purposes. Hence if we only write the log tail into the iclog for the *first* commit record rather than the log tail at the last release, we guarantee that the log tail does not move past where the the first commit record in the log expects it to be. IOWs, taking the first option means that replay of C1 becomes dependent on future operations doing the right thing, not just the C1 checkpoint itself doing the right thing. This makes log recovery almost impossible to reason about because now we have to take into account what might or might not have happened in the future when looking at checkpoints in the log rather than just having to reconstruct the past... Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_log.c | 50 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 13 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 1c328efdca66..60ac5fd63f1e 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -78,13 +78,12 @@ xlog_verify_iclog( STATIC void xlog_verify_tail_lsn( struct xlog *log, - struct xlog_in_core *iclog, - xfs_lsn_t tail_lsn); + struct xlog_in_core *iclog); #else #define xlog_verify_dest_ptr(a,b) #define xlog_verify_grant_tail(a) #define xlog_verify_iclog(a,b,c) -#define xlog_verify_tail_lsn(a,b,c) +#define xlog_verify_tail_lsn(a,b) #endif STATIC int @@ -489,12 +488,31 @@ out_error: /* * Flush iclog to disk if this is the last reference to the given iclog and the - * it is in the WANT_SYNC state. If the caller passes in a non-zero - * @old_tail_lsn and the current log tail does not match, there may be metadata - * on disk that must be persisted before this iclog is written. To satisfy that - * requirement, set the XLOG_ICL_NEED_FLUSH flag as a condition for writing this - * iclog with the new log tail value. + * it is in the WANT_SYNC state. + * + * If the caller passes in a non-zero @old_tail_lsn and the current log tail + * does not match, there may be metadata on disk that must be persisted before + * this iclog is written. To satisfy that requirement, set the + * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new + * log tail value. + * + * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the + * log tail is updated correctly. NEED_FUA indicates that the iclog will be + * written to stable storage, and implies that a commit record is contained + * within the iclog. We need to ensure that the log tail does not move beyond + * the tail that the first commit record in the iclog ordered against, otherwise + * correct recovery of that checkpoint becomes dependent on future operations + * performed on this iclog. + * + * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the + * current tail into iclog. Once the iclog tail is set, future operations must + * not modify it, otherwise they potentially violate ordering constraints for + * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in + * the iclog will get zeroed on activation of the iclog after sync, so we + * always capture the tail lsn on the iclog on the first NEED_FUA release + * regardless of the number of active reference counts on this iclog. */ + int xlog_state_release_iclog( struct xlog *log, @@ -519,6 +537,10 @@ xlog_state_release_iclog( if (old_tail_lsn && tail_lsn != old_tail_lsn) iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; + + if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) && + !iclog->ic_header.h_tail_lsn) + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); } if (!atomic_dec_and_test(&iclog->ic_refcnt)) @@ -530,8 +552,9 @@ xlog_state_release_iclog( } iclog->ic_state = XLOG_STATE_SYNCING; - iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); - xlog_verify_tail_lsn(log, iclog, tail_lsn); + if (!iclog->ic_header.h_tail_lsn) + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); + xlog_verify_tail_lsn(log, iclog); trace_xlog_iclog_syncing(iclog, _RET_IP_); spin_unlock(&log->l_icloglock); @@ -2579,6 +2602,7 @@ xlog_state_activate_iclog( memset(iclog->ic_header.h_cycle_data, 0, sizeof(iclog->ic_header.h_cycle_data)); iclog->ic_header.h_lsn = 0; + iclog->ic_header.h_tail_lsn = 0; } /* @@ -3614,10 +3638,10 @@ xlog_verify_grant_tail( STATIC void xlog_verify_tail_lsn( struct xlog *log, - struct xlog_in_core *iclog, - xfs_lsn_t tail_lsn) + struct xlog_in_core *iclog) { - int blocks; + xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn); + int blocks; if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) { blocks = From 81a448d7b0668ae39c08e6f34a54cc7eafb844f1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 26 Jul 2021 16:43:17 -0700 Subject: [PATCH 1068/1469] xfs: prevent spoofing of rtbitmap blocks when recovering buffers While reviewing the buffer item recovery code, the thought occurred to me: in V5 filesystems we use log sequence number (LSN) tracking to avoid replaying older metadata updates against newer log items. However, we use the magic number of the ondisk buffer to find the LSN of the ondisk metadata, which means that if an attacker can control the layout of the realtime device precisely enough that the start of an rt bitmap block matches the magic and UUID of some other kind of block, they can control the purported LSN of that spoofed block and thereby break log replay. Since realtime bitmap and summary blocks don't have headers at all, we have no way to tell if a block really should be replayed. The best we can do is replay unconditionally and hope for the best. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Carlos Maiolino --- fs/xfs/xfs_buf_item_recover.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 05fd816edf59..4775485b4062 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -698,7 +698,8 @@ xlog_recover_do_inode_buffer( static xfs_lsn_t xlog_recover_get_buf_lsn( struct xfs_mount *mp, - struct xfs_buf *bp) + struct xfs_buf *bp, + struct xfs_buf_log_format *buf_f) { uint32_t magic32; uint16_t magic16; @@ -706,11 +707,20 @@ xlog_recover_get_buf_lsn( void *blk = bp->b_addr; uuid_t *uuid; xfs_lsn_t lsn = -1; + uint16_t blft; /* v4 filesystems always recover immediately */ if (!xfs_sb_version_hascrc(&mp->m_sb)) goto recover_immediately; + /* + * realtime bitmap and summary file blocks do not have magic numbers or + * UUIDs, so we must recover them immediately. + */ + blft = xfs_blft_from_flags(buf_f); + if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF) + goto recover_immediately; + magic32 = be32_to_cpu(*(__be32 *)blk); switch (magic32) { case XFS_ABTB_CRC_MAGIC: @@ -920,7 +930,7 @@ xlog_recover_buf_commit_pass2( * the verifier will be reset to match whatever recover turns that * buffer into. */ - lsn = xlog_recover_get_buf_lsn(mp, bp); + lsn = xlog_recover_get_buf_lsn(mp, bp, buf_f); if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { trace_xfs_log_recover_buf_skip(log, buf_f); xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN); From facee1be7689f8cf573b9ffee6a5c28ee193615e Mon Sep 17 00:00:00 2001 From: David Brazdil Date: Wed, 28 Jul 2021 15:32:31 +0000 Subject: [PATCH 1069/1469] KVM: arm64: Fix off-by-one in range_is_memory Hyp checks whether an address range only covers RAM by checking the start/endpoints against a list of memblock_region structs. However, the endpoint here is exclusive but internally is treated as inclusive. Fix the off-by-one error that caused valid address ranges to be rejected. Cc: Quentin Perret Fixes: 90134ac9cabb6 ("KVM: arm64: Protect the .hyp sections from the host") Signed-off-by: David Brazdil Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210728153232.1018911-2-dbrazdil@google.com --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index d938ce95d3bd..a6ce991b1467 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -193,7 +193,7 @@ static bool range_is_memory(u64 start, u64 end) { struct kvm_mem_range r1, r2; - if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2)) + if (!find_mem_range(start, &r1) || !find_mem_range(end - 1, &r2)) return false; if (r1.start != r2.start) return false; From c4d7c51845af9542d42cd18a25c570583abf2768 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Thu, 29 Jul 2021 17:00:36 +0100 Subject: [PATCH 1070/1469] KVM: arm64: Fix race when enabling KVM_ARM_CAP_MTE When enabling KVM_CAP_ARM_MTE the ioctl checks that there are no VCPUs created to ensure that the capability is enabled before the VM is running. However no locks are held at that point so it is (theoretically) possible for another thread in the VMM to create VCPUs between the check and actually setting mte_enabled. Close the race by taking kvm->lock. Reported-by: Alexandru Elisei Fixes: 673638f434ee ("KVM: arm64: Expose KVM_ARM_CAP_MTE") Signed-off-by: Steven Price Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210729160036.20433-1-steven.price@arm.com --- arch/arm64/kvm/arm.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e9a2b8f27792..0ca72f5cda41 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -94,10 +94,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.return_nisv_io_abort_to_user = true; break; case KVM_CAP_ARM_MTE: - if (!system_supports_mte() || kvm->created_vcpus) - return -EINVAL; - r = 0; - kvm->arch.mte_enabled = true; + mutex_lock(&kvm->lock); + if (!system_supports_mte() || kvm->created_vcpus) { + r = -EINVAL; + } else { + r = 0; + kvm->arch.mte_enabled = true; + } + mutex_unlock(&kvm->lock); break; default: r = -EINVAL; From 696e572dc85c674b31f4f13f59d8e217ee1b057f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 26 Jul 2021 15:06:22 -0500 Subject: [PATCH 1071/1469] ARM: riscpc: Fix fall-through warning for Clang Fix the following fallthrough warning: arch/arm/mach-rpc/riscpc.c:52:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] default: ^ arch/arm/mach-rpc/riscpc.c:52:2: note: insert 'break;' to avoid fall-through default: ^ break; Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/202107260355.bF00i5bi-lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/arm/mach-rpc/riscpc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index d23970bd638d..f70fb9c4b0cb 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -49,6 +49,7 @@ static int __init parse_tag_acorn(const struct tag *tag) fallthrough; /* ??? */ case 256: vram_size += PAGE_SIZE * 256; + break; default: break; } From ee86f680ff4c9b406d49d4e22ddf10805b8a2137 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 29 Jul 2021 18:09:27 +0100 Subject: [PATCH 1072/1469] ASoC: cs42l42: Correct definition of ADC Volume control The ADC volume is a signed 8-bit number with range -97 to +12, with -97 being mute. Use a SOC_SINGLE_S8_TLV() to define this and fix the DECLARE_TLV_DB_SCALE() to have the correct start and mute flag. Fixes: 2c394ca79604 ("ASoC: Add support for CS42L42 codec") Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20210729170929.6589-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index eff013f295be..2fd20511f246 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -405,7 +405,7 @@ static const struct regmap_config cs42l42_regmap = { .use_single_write = true, }; -static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false); +static DECLARE_TLV_DB_SCALE(adc_tlv, -9700, 100, true); static DECLARE_TLV_DB_SCALE(mixer_tlv, -6300, 100, true); static const char * const cs42l42_hpf_freq_text[] = { @@ -444,8 +444,7 @@ static const struct snd_kcontrol_new cs42l42_snd_controls[] = { CS42L42_ADC_INV_SHIFT, true, false), SOC_SINGLE("ADC Boost Switch", CS42L42_ADC_CTL, CS42L42_ADC_DIG_BOOST_SHIFT, true, false), - SOC_SINGLE_SX_TLV("ADC Volume", CS42L42_ADC_VOLUME, - CS42L42_ADC_VOL_SHIFT, 0xA0, 0x6C, adc_tlv), + SOC_SINGLE_S8_TLV("ADC Volume", CS42L42_ADC_VOLUME, -97, 12, adc_tlv), SOC_SINGLE("ADC WNF Switch", CS42L42_ADC_WNF_HPF_CTL, CS42L42_ADC_WNF_EN_SHIFT, true, false), SOC_SINGLE("ADC HPF Switch", CS42L42_ADC_WNF_HPF_CTL, From 64324bac750b84ca54711fb7d332132fcdb87293 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 29 Jul 2021 18:09:28 +0100 Subject: [PATCH 1073/1469] ASoC: cs42l42: Don't allow SND_SOC_DAIFMT_LEFT_J The driver has no support for left-justified protocol so it should not have been allowing this to be passed to cs42l42_set_dai_fmt(). Signed-off-by: Richard Fitzgerald Fixes: 2c394ca79604 ("ASoC: Add support for CS42L42 codec") Link: https://lore.kernel.org/r/20210729170929.6589-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 2fd20511f246..38e243a815b1 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -788,7 +788,6 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) /* interface format */ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: - case SND_SOC_DAIFMT_LEFT_J: break; default: return -EINVAL; From 926ef1a4c245c093acc07807e466ad2ef0ff6ccb Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 29 Jul 2021 18:09:29 +0100 Subject: [PATCH 1074/1469] ASoC: cs42l42: Fix bclk calculation for mono An I2S frame always has a left and right channel slot even if mono data is being sent. So if channels==1 the actual bitclock frequency is 2 * snd_soc_params_to_bclk(params). Signed-off-by: Richard Fitzgerald Fixes: 2cdba9b045c7 ("ASoC: cs42l42: Use bclk from hw_params if set_sysclk was not called") Link: https://lore.kernel.org/r/20210729170929.6589-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 38e243a815b1..08ca05bfbeb3 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -830,6 +830,10 @@ static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, cs42l42->srate = params_rate(params); cs42l42->bclk = snd_soc_params_to_bclk(params); + /* I2S frame always has 2 channels even for mono audio */ + if (channels == 1) + cs42l42->bclk *= 2; + switch(substream->stream) { case SNDRV_PCM_STREAM_CAPTURE: if (channels == 2) { From eb4f520ca691f109f5fb1d16fc9cc26447a941e1 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 26 Jul 2021 15:33:53 -0500 Subject: [PATCH 1075/1469] scsi: acornscsi: Fix fall-through warning for clang Fix the following fallthrough warning (on ARM): drivers/scsi/arm/acornscsi.c:2651:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] case res_success: ^ drivers/scsi/arm/acornscsi.c:2651:2: note: insert '__attribute__((fallthrough));' to silence this warning case res_success: ^ __attribute__((fallthrough)); drivers/scsi/arm/acornscsi.c:2651:2: note: insert 'break;' to avoid fall-through case res_success: ^ break; Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/202107260355.bF00i5bi-lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/scsi/arm/acornscsi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c index 84fc7a0c6ff4..4a84599ff491 100644 --- a/drivers/scsi/arm/acornscsi.c +++ b/drivers/scsi/arm/acornscsi.c @@ -2642,6 +2642,7 @@ int acornscsi_abort(struct scsi_cmnd *SCpnt) //#endif clear_bit(SCpnt->device->id * 8 + (u8)(SCpnt->device->lun & 0x7), host->busyluns); + fallthrough; /* * We found the command, and cleared it out. Either From cb163627e6d32dbaca4d89b2292788cee895b06d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 26 Jul 2021 15:46:47 -0500 Subject: [PATCH 1076/1469] scsi: fas216: Fix fall-through warning for Clang Fix the following fallthrough warning (on ARM): drivers/scsi/arm/fas216.c:1379:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] default: ^ drivers/scsi/arm/fas216.c:1379:2: note: insert 'break;' to avoid fall-through default: ^ break; Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/202107260355.bF00i5bi-lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/scsi/arm/fas216.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 6baa9b36367d..9c4458a99025 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -1375,6 +1375,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne case IS_COMPLETE: break; } + break; default: break; From 0aab5dce395636eddf4e5f33eba88390328a95b4 Mon Sep 17 00:00:00 2001 From: Edmund Dea Date: Tue, 25 Aug 2020 14:51:17 -0700 Subject: [PATCH 1077/1469] drm/kmb: Enable LCD DMA for low TVDDCV There's an undocumented dependency between LCD layer enable bits [2-5] and the AXI pipelined read enable bit [28] in the LCD_CONTROL register. The proper order of operation is: 1) Clear AXI pipelined read enable bit 2) Set LCD layers 3) Set AXI pipelined read enable bit With this update, LCD can start DMA when TVDDCV is reduced down to 700mV. Fixes: 7f7b96a8a0a1 ("drm/kmb: Add support for KeemBay Display") Signed-off-by: Edmund Dea Signed-off-by: Anitha Chrisanthus Acked-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210728003126.1425028-1-anitha.chrisanthus@intel.com --- drivers/gpu/drm/kmb/kmb_drv.c | 14 ++++++++++++++ drivers/gpu/drm/kmb/kmb_plane.c | 15 +++++++++++++-- 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c index 96ea1a2c11dd..c0b1c6f99249 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.c +++ b/drivers/gpu/drm/kmb/kmb_drv.c @@ -203,6 +203,7 @@ static irqreturn_t handle_lcd_irq(struct drm_device *dev) unsigned long status, val, val1; int plane_id, dma0_state, dma1_state; struct kmb_drm_private *kmb = to_kmb(dev); + u32 ctrl = 0; status = kmb_read_lcd(kmb, LCD_INT_STATUS); @@ -227,6 +228,19 @@ static irqreturn_t handle_lcd_irq(struct drm_device *dev) kmb_clr_bitmask_lcd(kmb, LCD_CONTROL, kmb->plane_status[plane_id].ctrl); + ctrl = kmb_read_lcd(kmb, LCD_CONTROL); + if (!(ctrl & (LCD_CTRL_VL1_ENABLE | + LCD_CTRL_VL2_ENABLE | + LCD_CTRL_GL1_ENABLE | + LCD_CTRL_GL2_ENABLE))) { + /* If no LCD layers are using DMA, + * then disable DMA pipelined AXI read + * transactions. + */ + kmb_clr_bitmask_lcd(kmb, LCD_CONTROL, + LCD_CTRL_PIPELINE_DMA); + } + kmb->plane_status[plane_id].disable = false; } } diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c index d5b6195856d1..ecee6782612d 100644 --- a/drivers/gpu/drm/kmb/kmb_plane.c +++ b/drivers/gpu/drm/kmb/kmb_plane.c @@ -427,8 +427,14 @@ static void kmb_plane_atomic_update(struct drm_plane *plane, kmb_set_bitmask_lcd(kmb, LCD_CONTROL, ctrl); - /* FIXME no doc on how to set output format,these values are - * taken from the Myriadx tests + /* Enable pipeline AXI read transactions for the DMA + * after setting graphics layers. This must be done + * in a separate write cycle. + */ + kmb_set_bitmask_lcd(kmb, LCD_CONTROL, LCD_CTRL_PIPELINE_DMA); + + /* FIXME no doc on how to set output format, these values are taken + * from the Myriadx tests */ out_format |= LCD_OUTF_FORMAT_RGB888; @@ -526,6 +532,11 @@ struct kmb_plane *kmb_plane_init(struct drm_device *drm) plane->id = i; } + /* Disable pipeline AXI read transactions for the DMA + * prior to setting graphics layers + */ + kmb_clr_bitmask_lcd(kmb, LCD_CONTROL, LCD_CTRL_PIPELINE_DMA); + return primary; cleanup: drmm_kfree(drm, plane); From eb92830cdbc232a0e8166c48061ca276132646a7 Mon Sep 17 00:00:00 2001 From: Edmund Dea Date: Wed, 26 Aug 2020 13:17:29 -0700 Subject: [PATCH 1078/1469] drm/kmb: Define driver date and major/minor version Added macros for date and version Fixes: 7f7b96a8a0a1 ("drm/kmb: Add support for KeemBay Display") Signed-off-by: Edmund Dea Signed-off-by: Anitha Chrisanthus Acked-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20210728003126.1425028-2-anitha.chrisanthus@intel.com --- drivers/gpu/drm/kmb/kmb_drv.c | 8 ++++---- drivers/gpu/drm/kmb/kmb_drv.h | 5 +++++ 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c index c0b1c6f99249..f54392ec4fab 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.c +++ b/drivers/gpu/drm/kmb/kmb_drv.c @@ -425,10 +425,10 @@ static const struct drm_driver kmb_driver = { .fops = &fops, DRM_GEM_CMA_DRIVER_OPS_VMAP, .name = "kmb-drm", - .desc = "KEEMBAY DISPLAY DRIVER ", - .date = "20201008", - .major = 1, - .minor = 0, + .desc = "KEEMBAY DISPLAY DRIVER", + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, }; static int kmb_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/kmb/kmb_drv.h b/drivers/gpu/drm/kmb/kmb_drv.h index 02e806712a64..ebbaa5f422d5 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.h +++ b/drivers/gpu/drm/kmb/kmb_drv.h @@ -15,6 +15,11 @@ #define KMB_MAX_HEIGHT 1080 /*Max height in pixels */ #define KMB_MIN_WIDTH 1920 /*Max width in pixels */ #define KMB_MIN_HEIGHT 1080 /*Max height in pixels */ + +#define DRIVER_DATE "20210223" +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 1 + #define KMB_LCD_DEFAULT_CLK 200000000 #define KMB_SYS_CLK_MHZ 500 From bc546c0c9abb3bb2fb46866b3d1e6ade9695a5f6 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Wed, 13 Jan 2021 14:31:03 +0800 Subject: [PATCH 1079/1469] scsi: scsi_dh_rdac: Avoid crash during rdac_bus_attach() The following BUG_ON() was observed during RDAC scan: [595952.944297] kernel BUG at drivers/scsi/device_handler/scsi_dh_rdac.c:427! [595952.951143] Internal error: Oops - BUG: 0 [#1] SMP ...... [595953.251065] Call trace: [595953.259054] check_ownership+0xb0/0x118 [595953.269794] rdac_bus_attach+0x1f0/0x4b0 [595953.273787] scsi_dh_handler_attach+0x3c/0xe8 [595953.278211] scsi_dh_add_device+0xc4/0xe8 [595953.282291] scsi_sysfs_add_sdev+0x8c/0x2a8 [595953.286544] scsi_probe_and_add_lun+0x9fc/0xd00 [595953.291142] __scsi_scan_target+0x598/0x630 [595953.295395] scsi_scan_target+0x120/0x130 [595953.299481] fc_user_scan+0x1a0/0x1c0 [scsi_transport_fc] [595953.304944] store_scan+0xb0/0x108 [595953.308420] dev_attr_store+0x44/0x60 [595953.312160] sysfs_kf_write+0x58/0x80 [595953.315893] kernfs_fop_write+0xe8/0x1f0 [595953.319888] __vfs_write+0x60/0x190 [595953.323448] vfs_write+0xac/0x1c0 [595953.326836] ksys_write+0x74/0xf0 [595953.330221] __arm64_sys_write+0x24/0x30 Code is in check_ownership: list_for_each_entry_rcu(tmp, &h->ctlr->dh_list, node) { /* h->sdev should always be valid */ BUG_ON(!tmp->sdev); tmp->sdev->access_state = access_state; } rdac_bus_attach initialize_controller list_add_rcu(&h->node, &h->ctlr->dh_list); h->sdev = sdev; rdac_bus_detach list_del_rcu(&h->node); h->sdev = NULL; Fix the race between rdac_bus_attach() and rdac_bus_detach() where h->sdev is NULL when processing the RDAC attach. Link: https://lore.kernel.org/r/20210113063103.2698953-1-yebin10@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: Ye Bin Signed-off-by: Martin K. Petersen --- drivers/scsi/device_handler/scsi_dh_rdac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 25f6e1ac9e7b..66652ab409cc 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -453,8 +453,8 @@ static int initialize_controller(struct scsi_device *sdev, if (!h->ctlr) err = SCSI_DH_RES_TEMP_UNAVAIL; else { - list_add_rcu(&h->node, &h->ctlr->dh_list); h->sdev = sdev; + list_add_rcu(&h->node, &h->ctlr->dh_list); } spin_unlock(&list_lock); err = SCSI_DH_OK; @@ -778,11 +778,11 @@ static void rdac_bus_detach( struct scsi_device *sdev ) spin_lock(&list_lock); if (h->ctlr) { list_del_rcu(&h->node); - h->sdev = NULL; kref_put(&h->ctlr->kref, release_controller); } spin_unlock(&list_lock); sdev->handler_data = NULL; + synchronize_rcu(); kfree(h); } From 70edd2e6f652f67d854981fd67f9ad0f1deaea92 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Mon, 26 Jul 2021 17:24:02 +0530 Subject: [PATCH 1080/1469] scsi: core: Avoid printing an error if target_alloc() returns -ENXIO Avoid printing a 'target allocation failed' error if the driver target_alloc() callback function returns -ENXIO. This return value indicates that the corresponding H:C:T:L entry is empty. Removing this error reduces the scan time if the user issues SCAN_WILD_CARD scan operation through sysfs parameter on a host with a lot of empty H:C:T:L entries. Avoiding the printk on -ENXIO matches the behavior of the other callback functions during scanning. Link: https://lore.kernel.org/r/20210726115402.1936-1-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_scan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index b059bf2b61d4..5b6996a2401b 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -475,7 +475,8 @@ static struct scsi_target *scsi_alloc_target(struct device *parent, error = shost->hostt->target_alloc(starget); if(error) { - dev_printk(KERN_ERR, dev, "target allocation failed, error %d\n", error); + if (error != -ENXIO) + dev_err(dev, "target allocation failed, error %d\n", error); /* don't want scsi_target_reap to do the final * put because it will be under the host lock */ scsi_target_destroy(starget); From a264cf5e81c78e2b9918b8b9ef2ace9dde1850df Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Fri, 16 Jul 2021 14:52:20 -0600 Subject: [PATCH 1081/1469] scsi: ibmvfc: Fix command state accounting and stale response detection Prior to commit 1f4a4a19508d ("scsi: ibmvfc: Complete commands outside the host/queue lock") responses to commands were completed sequentially with the host lock held such that a command had a basic binary state of active or free. It was therefore a simple affair of ensuring the assocaiated ibmvfc_event to a VIOS response was valid by testing that it was not already free. The lock relexation work to complete commands outside the lock inadverdently made it a trinary command state such that a command is either in flight, received and being completed, or completed and now free. This breaks the stale command detection logic as a command may be still marked active and been placed on the delayed completion list when a second stale response for the same command arrives. This can lead to double completions and list corruption. This issue was exposed by a recent VIOS regression were a missing memory barrier could occasionally result in the ibmvfc client receiving a duplicate response for the same command. Fix the issue by introducing the atomic ibmvfc_event.active to track the trinary state of a command. The state is explicitly set to 1 when a command is successfully sent. The CRQ response handlers use atomic_dec_if_positive() to test for stale responses and correctly transition to the completion state when a active command is received. Finally, atomic_dec_and_test() is used to sanity check transistions when commands are freed as a result of a completion, or moved to the purge list as a result of error handling or adapter reset. Link: https://lore.kernel.org/r/20210716205220.1101150-1-tyreld@linux.ibm.com Fixes: 1f4a4a19508d ("scsi: ibmvfc: Complete commands outside the host/queue lock") Cc: stable@vger.kernel.org Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvfc.c | 19 +++++++++++++++++-- drivers/scsi/ibmvscsi/ibmvfc.h | 1 + 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index bee1bec49c09..935b01ee44b7 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -807,6 +807,13 @@ static int ibmvfc_init_event_pool(struct ibmvfc_host *vhost, for (i = 0; i < size; ++i) { struct ibmvfc_event *evt = &pool->events[i]; + /* + * evt->active states + * 1 = in flight + * 0 = being completed + * -1 = free/freed + */ + atomic_set(&evt->active, -1); atomic_set(&evt->free, 1); evt->crq.valid = 0x80; evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i)); @@ -1017,6 +1024,7 @@ static void ibmvfc_free_event(struct ibmvfc_event *evt) BUG_ON(!ibmvfc_valid_event(pool, evt)); BUG_ON(atomic_inc_return(&evt->free) != 1); + BUG_ON(atomic_dec_and_test(&evt->active)); spin_lock_irqsave(&evt->queue->l_lock, flags); list_add_tail(&evt->queue_list, &evt->queue->free); @@ -1072,6 +1080,12 @@ static void ibmvfc_complete_purge(struct list_head *purge_list) **/ static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code) { + /* + * Anything we are failing should still be active. Otherwise, it + * implies we already got a response for the command and are doing + * something bad like double completing it. + */ + BUG_ON(!atomic_dec_and_test(&evt->active)); if (evt->cmnd) { evt->cmnd->result = (error_code << 16); evt->done = ibmvfc_scsi_eh_done; @@ -1723,6 +1737,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt, evt->done(evt); } else { + atomic_set(&evt->active, 1); spin_unlock_irqrestore(&evt->queue->l_lock, flags); ibmvfc_trc_start(evt); } @@ -3251,7 +3266,7 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost, return; } - if (unlikely(atomic_read(&evt->free))) { + if (unlikely(atomic_dec_if_positive(&evt->active))) { dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n", crq->ioba); return; @@ -3778,7 +3793,7 @@ static void ibmvfc_handle_scrq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost return; } - if (unlikely(atomic_read(&evt->free))) { + if (unlikely(atomic_dec_if_positive(&evt->active))) { dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n", crq->ioba); return; diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index 4f0f3baefae4..92fb889d7eb0 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -745,6 +745,7 @@ struct ibmvfc_event { struct ibmvfc_target *tgt; struct scsi_cmnd *cmnd; atomic_t free; + atomic_t active; union ibmvfc_iu *xfer_iu; void (*done)(struct ibmvfc_event *evt); void (*_done)(struct ibmvfc_event *evt); From 5c04243a56a7977185b00400e59ca7e108004faf Mon Sep 17 00:00:00 2001 From: Li Manyi Date: Mon, 26 Jul 2021 19:49:13 +0800 Subject: [PATCH 1082/1469] scsi: sr: Return correct event when media event code is 3 Media event code 3 is defined in the MMC-6 spec as follows: "MediaRemoval: The media has been removed from the specified slot, and the Drive is unable to access the media without user intervention. This applies to media changers only." This indicated that treating the condition as an EJECT_REQUEST was appropriate. However, doing so had the unfortunate side-effect of causing the drive tray to be physically ejected on resume. Instead treat the event as a MEDIA_CHANGE request. Fixes: 7dd753ca59d6 ("scsi: sr: Return appropriate error code when disk is ejected") Link: https://bugzilla.kernel.org/show_bug.cgi?id=213759 Link: https://lore.kernel.org/r/20210726114913.6760-1-limanyi@uniontech.com Signed-off-by: Li Manyi Signed-off-by: Martin K. Petersen --- drivers/scsi/sr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 94c254e9012e..a6d3ac0a6cbc 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -221,7 +221,7 @@ static unsigned int sr_get_events(struct scsi_device *sdev) else if (med->media_event_code == 2) return DISK_EVENT_MEDIA_CHANGE; else if (med->media_event_code == 3) - return DISK_EVENT_EJECT_REQUEST; + return DISK_EVENT_MEDIA_CHANGE; return 0; } From f0f82e2476f6adb9c7a0135cfab8091456990c99 Mon Sep 17 00:00:00 2001 From: lijinlin Date: Tue, 27 Jul 2021 11:44:55 +0800 Subject: [PATCH 1083/1469] scsi: core: Fix capacity set to zero after offlinining device After adding physical volumes to a volume group through vgextend, the kernel will rescan the partitions. This in turn will cause the device capacity to be queried. If the device status is set to offline through sysfs at this time, READ CAPACITY command will return a result which the host byte is DID_NO_CONNECT, and the capacity of the device will be set to zero in read_capacity_error(). After setting device status back to running, the capacity of the device will remain stuck at zero. Fix this issue by rescanning device when the device state changes to SDEV_RUNNING. Link: https://lore.kernel.org/r/20210727034455.1494960-1-lijinlin3@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: lijinlin Signed-off-by: Wu Bo Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_sysfs.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 32489d25158f..ae9bfc658203 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -807,11 +807,14 @@ store_state_field(struct device *dev, struct device_attribute *attr, mutex_lock(&sdev->state_mutex); ret = scsi_device_set_state(sdev, state); /* - * If the device state changes to SDEV_RUNNING, we need to run - * the queue to avoid I/O hang. + * If the device state changes to SDEV_RUNNING, we need to + * rescan the device to revalidate it, and run the queue to + * avoid I/O hang. */ - if (ret == 0 && state == SDEV_RUNNING) + if (ret == 0 && state == SDEV_RUNNING) { + scsi_rescan_device(dev); blk_mq_run_hw_queues(sdev->request_queue, true); + } mutex_unlock(&sdev->state_mutex); return ret == 0 ? count : -EINVAL; From 8a7b46fa7902a3d36ce44a64f4d66586d66206ea Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 26 Jul 2021 11:26:44 +0200 Subject: [PATCH 1084/1469] MAINTAINERS: add Yasushi SHOJI as reviewer for the Microchip CAN BUS Analyzer Tool driver This patch adds Yasushi SHOJI as a reviewer for the Microchip CAN BUS Analyzer Tool driver. Link: https://lore.kernel.org/r/20210726111619.1023991-1-mkl@pengutronix.de Acked-by: Yasushi SHOJI Signed-off-by: Marc Kleine-Budde --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 58afeb12d3b3..42ea3183e87c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11327,6 +11327,12 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-maxiradio* +MCAB MICROCHIP CAN BUS ANALYZER TOOL DRIVER +R: Yasushi SHOJI +L: linux-can@vger.kernel.org +S: Maintained +F: drivers/net/can/usb/mcba_usb.c + MCAN MMIO DEVICE DRIVER M: Chandrasekar Ramakrishnan L: linux-can@vger.kernel.org From f6b3c7848e66e9046c8a79a5b88fd03461cc252b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 29 Jul 2021 17:12:46 +0300 Subject: [PATCH 1085/1469] can: hi311x: fix a signedness bug in hi3110_cmd() The hi3110_cmd() is supposed to return zero on success and negative error codes on failure, but it was accidentally declared as a u8 when it needs to be an int type. Fixes: 57e83fb9b746 ("can: hi311x: Add Holt HI-311x CAN driver") Link: https://lore.kernel.org/r/20210729141246.GA1267@kili Signed-off-by: Dan Carpenter Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/hi311x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index dd17b8c53e1c..89d9c986a229 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -218,7 +218,7 @@ static int hi3110_spi_trans(struct spi_device *spi, int len) return ret; } -static u8 hi3110_cmd(struct spi_device *spi, u8 command) +static int hi3110_cmd(struct spi_device *spi, u8 command) { struct hi3110_priv *priv = spi_get_drvdata(spi); From fc43fb69a7af92839551f99c1a96a37b77b3ae7a Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Sun, 25 Jul 2021 13:36:30 +0300 Subject: [PATCH 1086/1469] can: mcba_usb_start(): add missing urb->transfer_dma initialization Yasushi reported, that his Microchip CAN Analyzer stopped working since commit 91c02557174b ("can: mcba_usb: fix memory leak in mcba_usb"). The problem was in missing urb->transfer_dma initialization. In my previous patch to this driver I refactored mcba_usb_start() code to avoid leaking usb coherent buffers. To archive it, I passed local stack variable to usb_alloc_coherent() and then saved it to private array to correctly free all coherent buffers on ->close() call. But I forgot to initialize urb->transfer_dma with variable passed to usb_alloc_coherent(). All of this was causing device to not work, since dma addr 0 is not valid and following log can be found on bug report page, which points exactly to problem described above. | DMAR: [DMA Write] Request device [00:14.0] PASID ffffffff fault addr 0 [fault reason 05] PTE Write access is not set Fixes: 91c02557174b ("can: mcba_usb: fix memory leak in mcba_usb") Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=990850 Link: https://lore.kernel.org/r/20210725103630.23864-1-paskripkin@gmail.com Cc: linux-stable Reported-by: Yasushi SHOJI Signed-off-by: Pavel Skripkin Tested-by: Yasushi SHOJI [mkl: fixed typos in commit message - thanks Yasushi SHOJI] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/mcba_usb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index a45865bd7254..a1a154c08b7f 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -653,6 +653,8 @@ static int mcba_usb_start(struct mcba_priv *priv) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_IN), buf, MCBA_USB_RX_BUFF_SIZE, From 8dde723fcde4479f256441da03793e37181d9f21 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 29 Jul 2021 20:51:26 +0200 Subject: [PATCH 1087/1469] ALSA: usb-audio: Avoid unnecessary or invalid connector selection at resume The recent fix for the resume on Lenovo machines seems causing a regression on others. It's because the change always triggers the connector selection no matter which widget node type is. This patch addresses the regression by setting the resume callback selectively only for the connector widget. Fixes: 44609fc01f28 ("ALSA: usb-audio: Check connector value on resume") Cc: BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213897 Link: https://lore.kernel.org/r/20210729185126.24432-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/mixer.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index f4cdaf1ba44a..9b713b4a5ec4 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1816,6 +1816,15 @@ static void get_connector_control_name(struct usb_mixer_interface *mixer, strlcat(name, " - Output Jack", name_size); } +/* get connector value to "wake up" the USB audio */ +static int connector_mixer_resume(struct usb_mixer_elem_list *list) +{ + struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list); + + get_connector_value(cval, NULL, NULL); + return 0; +} + /* Build a mixer control for a UAC connector control (jack-detect) */ static void build_connector_control(struct usb_mixer_interface *mixer, const struct usbmix_name_map *imap, @@ -1833,6 +1842,10 @@ static void build_connector_control(struct usb_mixer_interface *mixer, if (!cval) return; snd_usb_mixer_elem_init_std(&cval->head, mixer, term->id); + + /* set up a specific resume callback */ + cval->head.resume = connector_mixer_resume; + /* * UAC2: The first byte from reading the UAC2_TE_CONNECTOR control returns the * number of channels connected. @@ -3642,23 +3655,15 @@ static int restore_mixer_value(struct usb_mixer_elem_list *list) return 0; } -static int default_mixer_resume(struct usb_mixer_elem_list *list) -{ - struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list); - - /* get connector value to "wake up" the USB audio */ - if (cval->val_type == USB_MIXER_BOOLEAN && cval->channels == 1) - get_connector_value(cval, NULL, NULL); - - return 0; -} - static int default_mixer_reset_resume(struct usb_mixer_elem_list *list) { - int err = default_mixer_resume(list); + int err; - if (err < 0) - return err; + if (list->resume) { + err = list->resume(list); + if (err < 0) + return err; + } return restore_mixer_value(list); } @@ -3697,7 +3702,7 @@ void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list, list->id = unitid; list->dump = snd_usb_mixer_dump_cval; #ifdef CONFIG_PM - list->resume = default_mixer_resume; + list->resume = NULL; list->reset_resume = default_mixer_reset_resume; #endif } From 0e865f0c31928d6a313269ef624907eec55287c4 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 27 Jul 2021 19:59:57 +0300 Subject: [PATCH 1088/1469] can: usb_8dev: fix memory leak In usb_8dev_start() MAX_RX_URBS coherent buffers are allocated and there is nothing, that frees them: 1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see usb_8dev_start) and this flag cannot be used with coherent buffers. So, all allocated buffers should be freed with usb_free_coherent() explicitly. Side note: This code looks like a copy-paste of other can drivers. The same patch was applied to mcba_usb driver and it works nice with real hardware. There is no change in functionality, only clean-up code for coherent buffers. Fixes: 0024d8ad1639 ("can: usb_8dev: Add support for USB2CAN interface from 8 devices") Link: https://lore.kernel.org/r/d39b458cd425a1cf7f512f340224e6e9563b07bd.1627404470.git.paskripkin@gmail.com Cc: linux-stable Signed-off-by: Pavel Skripkin Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/usb_8dev.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index b6e7ef0d5bc6..d1b83bd1b3cb 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -137,7 +137,8 @@ struct usb_8dev_priv { u8 *cmd_msg_buffer; struct mutex usb_8dev_cmd_lock; - + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; /* tx frame */ @@ -733,6 +734,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -742,7 +744,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) } buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -750,6 +752,8 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_RX), @@ -767,6 +771,9 @@ static int usb_8dev_start(struct usb_8dev_priv *priv) break; } + priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -836,6 +843,10 @@ static void unlink_all_urbs(struct usb_8dev_priv *priv) usb_kill_anchored_urbs(&priv->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, RX_BUFFER_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); atomic_set(&priv->active_tx_urbs, 0); From 9969e3c5f40c166e3396acc36c34f9de502929f6 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 27 Jul 2021 20:00:33 +0300 Subject: [PATCH 1089/1469] can: ems_usb: fix memory leak In ems_usb_start() MAX_RX_URBS coherent buffers are allocated and there is nothing, that frees them: 1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see ems_usb_start) and this flag cannot be used with coherent buffers. So, all allocated buffers should be freed with usb_free_coherent() explicitly. Side note: This code looks like a copy-paste of other can drivers. The same patch was applied to mcba_usb driver and it works nice with real hardware. There is no change in functionality, only clean-up code for coherent buffers. Fixes: 702171adeed3 ("ems_usb: Added support for EMS CPC-USB/ARM7 CAN/USB interface") Link: https://lore.kernel.org/r/59aa9fbc9a8cbf9af2bbd2f61a659c480b415800.1627404470.git.paskripkin@gmail.com Cc: linux-stable Signed-off-by: Pavel Skripkin Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/ems_usb.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 0a37af4a3fa4..2b5302e72435 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -255,6 +255,8 @@ struct ems_usb { unsigned int free_slots; /* remember number of available slots */ struct ems_cpc_msg active_params; /* active controller parameters */ + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; static void ems_usb_read_interrupt_callback(struct urb *urb) @@ -587,6 +589,7 @@ static int ems_usb_start(struct ems_usb *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -596,7 +599,7 @@ static int ems_usb_start(struct ems_usb *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -604,6 +607,8 @@ static int ems_usb_start(struct ems_usb *dev) break; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2), buf, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); @@ -619,6 +624,9 @@ static int ems_usb_start(struct ems_usb *dev) break; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -684,6 +692,10 @@ static void unlink_all_urbs(struct ems_usb *dev) usb_kill_anchored_urbs(&dev->rx_submitted); + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + usb_kill_anchored_urbs(&dev->tx_submitted); atomic_set(&dev->active_tx_urbs, 0); From 928150fad41ba16df7fcc9f7f945747d0f56cbb6 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 27 Jul 2021 20:00:46 +0300 Subject: [PATCH 1090/1469] can: esd_usb2: fix memory leak In esd_usb2_setup_rx_urbs() MAX_RX_URBS coherent buffers are allocated and there is nothing, that frees them: 1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see esd_usb2_setup_rx_urbs) and this flag cannot be used with coherent buffers. So, all allocated buffers should be freed with usb_free_coherent() explicitly. Side note: This code looks like a copy-paste of other can drivers. The same patch was applied to mcba_usb driver and it works nice with real hardware. There is no change in functionality, only clean-up code for coherent buffers. Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device") Link: https://lore.kernel.org/r/b31b096926dcb35998ad0271aac4b51770ca7cc8.1627404470.git.paskripkin@gmail.com Cc: linux-stable Signed-off-by: Pavel Skripkin Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/esd_usb2.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 65b58f8fc328..66fa8b07c2e6 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -195,6 +195,8 @@ struct esd_usb2 { int net_count; u32 version; int rxinitdone; + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; }; struct esd_usb2_net_priv { @@ -545,6 +547,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -554,7 +557,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) } buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { dev_warn(dev->udev->dev.parent, "No memory left for USB buffer\n"); @@ -562,6 +565,8 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) goto freeurb; } + urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), buf, RX_BUFFER_SIZE, @@ -574,8 +579,12 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev) usb_unanchor_urb(urb); usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, urb->transfer_dma); + goto freeurb; } + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + freeurb: /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); @@ -663,6 +672,11 @@ static void unlink_all_urbs(struct esd_usb2 *dev) int i, j; usb_kill_anchored_urbs(&dev->rx_submitted); + + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + for (i = 0; i < dev->net_count; i++) { priv = dev->nets[i]; if (priv) { From fe911792eae32f03d27d8f3de2f0271862d435ac Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 23 Jun 2021 10:45:20 +0200 Subject: [PATCH 1091/1469] media: Revert "media: rtl28xxu: fix zero-length control request" This reverts commit 25d5ce3a606a1eb23a9265d615a92a876ff9cb5f. The patch in question causes a regression and was superseded by a second version. Unfortunately, the first revision ended up being applied instead of the correct one. Link: https://lore.kernel.org/r/YL3MCGY5wTsW2kEF@hovoldconsulting.com Signed-off-by: Johan Hovold Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 83705730e37e..0cbdb95f8d35 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -612,9 +612,8 @@ static int rtl28xxu_read_config(struct dvb_usb_device *d) static int rtl28xxu_identify_state(struct dvb_usb_device *d, const char **name) { struct rtl28xxu_dev *dev = d_to_priv(d); - u8 buf[1]; int ret; - struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 1, buf}; + struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 0, NULL}; dev_dbg(&d->intf->dev, "\n"); From 76f22c93b209c811bd489950f17f8839adb31901 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 23 Jun 2021 10:45:21 +0200 Subject: [PATCH 1092/1469] media: rtl28xxu: fix zero-length control request The direction of the pipe argument must match the request-type direction bit or control requests may fail depending on the host-controller-driver implementation. Control transfers without a data stage are treated as OUT requests by the USB stack and should be using usb_sndctrlpipe(). Failing to do so will now trigger a warning. The driver uses a zero-length i2c-read request for type detection so update the control-request code to use usb_sndctrlpipe() in this case. Note that actually trying to read the i2c register in question does not work as the register might not exist (e.g. depending on the demodulator) as reported by Eero Lehtinen . Reported-by: syzbot+faf11bbadc5a372564da@syzkaller.appspotmail.com Reported-by: Eero Lehtinen Tested-by: Eero Lehtinen Fixes: d0f232e823af ("[media] rtl28xxu: add heuristic to detect chip type") Cc: stable@vger.kernel.org # 4.0 Cc: Antti Palosaari Signed-off-by: Johan Hovold Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 0cbdb95f8d35..795a012d4020 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -37,7 +37,16 @@ static int rtl28xxu_ctrl_msg(struct dvb_usb_device *d, struct rtl28xxu_req *req) } else { /* read */ requesttype = (USB_TYPE_VENDOR | USB_DIR_IN); - pipe = usb_rcvctrlpipe(d->udev, 0); + + /* + * Zero-length transfers must use usb_sndctrlpipe() and + * rtl28xxu_identify_state() uses a zero-length i2c read + * command to determine the chip type. + */ + if (req->size) + pipe = usb_rcvctrlpipe(d->udev, 0); + else + pipe = usb_sndctrlpipe(d->udev, 0); } ret = usb_control_msg(d->udev, pipe, 0, requesttype, req->value, From c592b46907adbeb81243f7eb7a468c36692658b8 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 30 Jun 2021 09:58:23 +0200 Subject: [PATCH 1093/1469] media: videobuf2-core: dequeue if start_streaming fails If a vb2_queue sets q->min_buffers_needed then when the number of queued buffers reaches q->min_buffers_needed, vb2_core_qbuf() will call the start_streaming() callback. If start_streaming() returns an error, then that error was just returned by vb2_core_qbuf(), but the buffer was still queued. However, userspace expects that if VIDIOC_QBUF fails, the buffer is returned dequeued. So if start_streaming() fails, then remove the buffer from the queue, thus avoiding this unwanted side-effect. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Tested-by: Kieran Bingham Fixes: b3379c6201bb ("[media] vb2: only call start_streaming if sufficient buffers are queued") Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 02281d13505f..508ac295eb06 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1573,6 +1573,7 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, struct media_request *req) { struct vb2_buffer *vb; + enum vb2_buffer_state orig_state; int ret; if (q->error) { @@ -1673,6 +1674,7 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, * Add to the queued buffers list, a buffer will stay on it until * dequeued in dqbuf. */ + orig_state = vb->state; list_add_tail(&vb->queued_entry, &q->queued_list); q->queued_count++; q->waiting_for_buffers = false; @@ -1703,8 +1705,17 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, if (q->streaming && !q->start_streaming_called && q->queued_count >= q->min_buffers_needed) { ret = vb2_start_streaming(q); - if (ret) + if (ret) { + /* + * Since vb2_core_qbuf will return with an error, + * we should return it to state DEQUEUED since + * the error indicates that the buffer wasn't queued. + */ + list_del(&vb->queued_entry); + q->queued_count--; + vb->state = orig_state; return ret; + } } dprintk(q, 2, "qbuf of buffer %d succeeded\n", vb->index); From f1de1c7803595e937ce9b922807f499851225021 Mon Sep 17 00:00:00 2001 From: Eugen Hristev Date: Mon, 5 Jul 2021 14:57:08 +0200 Subject: [PATCH 1094/1469] media: atmel: fix build when ISC=m and XISC=y Building VIDEO_ATMEL_ISC as module and VIDEO_ATMEL_XISC as built-in (or viceversa) causes build errors: or1k-linux-ld: drivers/media/platform/atmel/atmel-isc-base.o: in function `isc_async_complete': atmel-isc-base.c:(.text+0x40d0): undefined reference to `__this_module' or1k-linux-ld: atmel-isc-base.c:(.text+0x40f0): undefined reference to `__this_module' or1k-linux-ld: drivers/media/platform/atmel/atmel-isc-base.o:(.rodata+0x390): undefined reference to `__this_module' or1k-linux-ld: drivers/media/platform/atmel/atmel-isc-base.o:(__param+0x4): undefined reference to `__this_module' or1k-linux-ld: drivers/media/platform/atmel/atmel-isc-base.o:(__param+0x18): undefined reference to `__this_module' This is caused by the file atmel-isc-base.c which is common code between the two drivers. The solution is to create another Kconfig symbol that is automatically selected and generates the module atmel-isc-base.ko. This module can be loaded when both drivers are modules, or built-in when at least one of them is built-in. Reported-by: kernel test robot Fixes: c9aa973884a1 ("media: atmel: atmel-isc: add microchip-xisc driver") Signed-off-by: Eugen Hristev Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/atmel/Kconfig | 8 ++++++++ drivers/media/platform/atmel/Makefile | 5 +++-- drivers/media/platform/atmel/atmel-isc-base.c | 11 +++++++++++ 3 files changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/atmel/Kconfig b/drivers/media/platform/atmel/Kconfig index 99b51213f871..dda2f27da317 100644 --- a/drivers/media/platform/atmel/Kconfig +++ b/drivers/media/platform/atmel/Kconfig @@ -8,6 +8,7 @@ config VIDEO_ATMEL_ISC select VIDEOBUF2_DMA_CONTIG select REGMAP_MMIO select V4L2_FWNODE + select VIDEO_ATMEL_ISC_BASE help This module makes the ATMEL Image Sensor Controller available as a v4l2 device. @@ -19,10 +20,17 @@ config VIDEO_ATMEL_XISC select VIDEOBUF2_DMA_CONTIG select REGMAP_MMIO select V4L2_FWNODE + select VIDEO_ATMEL_ISC_BASE help This module makes the ATMEL eXtended Image Sensor Controller available as a v4l2 device. +config VIDEO_ATMEL_ISC_BASE + tristate + default n + help + ATMEL ISC and XISC common code base. + config VIDEO_ATMEL_ISI tristate "ATMEL Image Sensor Interface (ISI) support" depends on VIDEO_V4L2 && OF diff --git a/drivers/media/platform/atmel/Makefile b/drivers/media/platform/atmel/Makefile index c5c01556c653..46d264ab7948 100644 --- a/drivers/media/platform/atmel/Makefile +++ b/drivers/media/platform/atmel/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only -atmel-isc-objs = atmel-sama5d2-isc.o atmel-isc-base.o -atmel-xisc-objs = atmel-sama7g5-isc.o atmel-isc-base.o +atmel-isc-objs = atmel-sama5d2-isc.o +atmel-xisc-objs = atmel-sama7g5-isc.o obj-$(CONFIG_VIDEO_ATMEL_ISI) += atmel-isi.o +obj-$(CONFIG_VIDEO_ATMEL_ISC_BASE) += atmel-isc-base.o obj-$(CONFIG_VIDEO_ATMEL_ISC) += atmel-isc.o obj-$(CONFIG_VIDEO_ATMEL_XISC) += atmel-xisc.o diff --git a/drivers/media/platform/atmel/atmel-isc-base.c b/drivers/media/platform/atmel/atmel-isc-base.c index 19daa49bf604..136ab7cf36ed 100644 --- a/drivers/media/platform/atmel/atmel-isc-base.c +++ b/drivers/media/platform/atmel/atmel-isc-base.c @@ -378,6 +378,7 @@ int isc_clk_init(struct isc_device *isc) return 0; } +EXPORT_SYMBOL_GPL(isc_clk_init); void isc_clk_cleanup(struct isc_device *isc) { @@ -392,6 +393,7 @@ void isc_clk_cleanup(struct isc_device *isc) clk_unregister(isc_clk->clk); } } +EXPORT_SYMBOL_GPL(isc_clk_cleanup); static int isc_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, @@ -1578,6 +1580,7 @@ irqreturn_t isc_interrupt(int irq, void *dev_id) return ret; } +EXPORT_SYMBOL_GPL(isc_interrupt); static void isc_hist_count(struct isc_device *isc, u32 *min, u32 *max) { @@ -2212,6 +2215,7 @@ const struct v4l2_async_notifier_operations isc_async_ops = { .unbind = isc_async_unbind, .complete = isc_async_complete, }; +EXPORT_SYMBOL_GPL(isc_async_ops); void isc_subdev_cleanup(struct isc_device *isc) { @@ -2224,6 +2228,7 @@ void isc_subdev_cleanup(struct isc_device *isc) INIT_LIST_HEAD(&isc->subdev_entities); } +EXPORT_SYMBOL_GPL(isc_subdev_cleanup); int isc_pipeline_init(struct isc_device *isc) { @@ -2264,6 +2269,7 @@ int isc_pipeline_init(struct isc_device *isc) return 0; } +EXPORT_SYMBOL_GPL(isc_pipeline_init); /* regmap configuration */ #define ATMEL_ISC_REG_MAX 0xd5c @@ -2273,4 +2279,9 @@ const struct regmap_config isc_regmap_config = { .val_bits = 32, .max_register = ATMEL_ISC_REG_MAX, }; +EXPORT_SYMBOL_GPL(isc_regmap_config); +MODULE_AUTHOR("Songjun Wu"); +MODULE_AUTHOR("Eugen Hristev"); +MODULE_DESCRIPTION("Atmel ISC common code base"); +MODULE_LICENSE("GPL v2"); From 341abd693d10e5f337a51f140ae3e7a1ae0febf6 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Thu, 29 Jul 2021 06:33:06 +0200 Subject: [PATCH 1095/1469] serial: 8250_pci: Avoid irq sharing for MSI(-X) interrupts. This attempts to fix a bug found with a serial port card which uses an MCS9922 chip, one of the 4 models for which MSI-X interrupts are currently supported. I don't possess such a card, and i'm not experienced with the serial subsystem, so this patch is based on what i think i found as a likely reason for failure, based on walking the user who actually owns the card through some diagnostic. The user who reported the problem finds the following in his dmesg output for the relevant ttyS4 and ttyS5: [ 0.580425] serial 0000:02:00.0: enabling device (0000 -> 0003) [ 0.601448] 0000:02:00.0: ttyS4 at I/O 0x3010 (irq = 125, base_baud = 115200) is a ST16650V2 [ 0.603089] serial 0000:02:00.1: enabling device (0000 -> 0003) [ 0.624119] 0000:02:00.1: ttyS5 at I/O 0x3000 (irq = 126, base_baud = 115200) is a ST16650V2 ... [ 6.323784] genirq: Flags mismatch irq 128. 00000080 (ttyS5) vs. 00000000 (xhci_hcd) [ 6.324128] genirq: Flags mismatch irq 128. 00000080 (ttyS5) vs. 00000000 (xhci_hcd) ... Output of setserial -a: /dev/ttyS4, Line 4, UART: 16650V2, Port: 0x3010, IRQ: 127 Baud_base: 115200, close_delay: 50, divisor: 0 closing_wait: 3000 Flags: spd_normal skip_test This suggests to me that the serial driver wants to register and share a MSI/MSI-X irq 128 with the xhci_hcd driver, whereas the xhci driver does not want to share the irq, as flags 0x00000080 (== IRQF_SHARED) from the serial port driver means to share the irq, and this mismatch ends in some failed irq init? With this setup, data reception works very unreliable, with dropped data, already at a transmission rate of only a 16 Bytes chunk every 1/120th of a second, ie. 1920 Bytes/sec, presumably due to rx fifo overflow due to mishandled or not used at all rx irq's? See full discussion thread with attempted diagnosis at: https://psychtoolbox.discourse.group/t/issues-with-iscan-serial-port-recording/3886 Disabling the use of MSI interrupts for the serial port pci card did fix the reliability problems. The user executed the following sequence of commands to achieve this: echo 0000:02:00.0 | sudo tee /sys/bus/pci/drivers/serial/unbind echo 0000:02:00.1 | sudo tee /sys/bus/pci/drivers/serial/unbind echo 0 | sudo tee /sys/bus/pci/devices/0000:02:00.0/msi_bus echo 0 | sudo tee /sys/bus/pci/devices/0000:02:00.1/msi_bus echo 0000:02:00.0 | sudo tee /sys/bus/pci/drivers/serial/bind echo 0000:02:00.1 | sudo tee /sys/bus/pci/drivers/serial/bind This resulted in the following log output: [ 82.179021] pci 0000:02:00.0: MSI/MSI-X disallowed for future drivers [ 87.003031] pci 0000:02:00.1: MSI/MSI-X disallowed for future drivers [ 98.537010] 0000:02:00.0: ttyS4 at I/O 0x3010 (irq = 17, base_baud = 115200) is a ST16650V2 [ 103.648124] 0000:02:00.1: ttyS5 at I/O 0x3000 (irq = 18, base_baud = 115200) is a ST16650V2 This patch attempts to fix the problem by disabling irq sharing when using MSI irq's. Note that all i know for sure is that disabling MSI irq's fixed the problem for the user, so this patch could be wrong and is untested. Please review with caution, keeping this in mind. Fixes: 8428413b1d14 ("serial: 8250_pci: Implement MSI(-X) support") Cc: Ralf Ramsauer Cc: stable Reviewed-by: Andy Shevchenko Signed-off-by: Mario Kleiner Link: https://lore.kernel.org/r/20210729043306.18528-1-mario.kleiner.de@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 02985cf90ef2..a808c283883e 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -4002,6 +4002,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board) if (pci_match_id(pci_use_msi, dev)) { dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n"); pci_set_master(dev); + uart.port.flags &= ~UPF_SHARE_IRQ; rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES); } else { dev_dbg(&dev->dev, "Using legacy interrupts\n"); From fa7a549d321a4189677b0cea86e58d9db7977f7b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 14 Jul 2021 17:37:49 -0400 Subject: [PATCH 1096/1469] KVM: x86: accept userspace interrupt only if no event is injected Once an exception has been injected, any side effects related to the exception (such as setting CR2 or DR6) have been taked place. Therefore, once KVM sets the VM-entry interruption information field or the AMD EVENTINJ field, the next VM-entry must deliver that exception. Pending interrupts are processed after injected exceptions, so in theory it would not be a problem to use KVM_INTERRUPT when an injected exception is present. However, DOSEMU is using run->ready_for_interrupt_injection to detect interrupt windows and then using KVM_SET_SREGS/KVM_SET_REGS to inject the interrupt manually. For this to work, the interrupt window must be delayed after the completion of the previous event injection. Cc: stable@vger.kernel.org Reported-by: Stas Sergeev Tested-by: Stas Sergeev Fixes: 71cc849b7093 ("KVM: x86: Fix split-irqchip vs interrupt injection window request") Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4116567f3d44..e5d5c5ed7dd4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4358,8 +4358,17 @@ static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { - return kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_accept_dm_intr(vcpu); + /* + * Do not cause an interrupt window exit if an exception + * is pending or an event needs reinjection; userspace + * might want to inject the interrupt manually using KVM_SET_REGS + * or KVM_SET_SREGS. For that to work, we must be at an + * instruction boundary and with no events half-injected. + */ + return (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_accept_dm_intr(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + !vcpu->arch.exception.pending); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, From 3a0670824979a986a2314c921aa092e60730eeae Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 20 Jun 2021 20:54:21 +0200 Subject: [PATCH 1097/1469] ARM: dts: stm32: Prefer HW RTC on DHCOM SoM The DHCOM SoM has two RTC, one is the STM32 RTC built into the SoC and another is Microcrystal RV RTC. By default, only the later has battery backup, the former does not. The order in which the RTCs are probed on boot is random, which means the kernel might pick up system time from the STM32 RTC which has no battery backup. This then leads to incorrect initial system time setup, even though the HW RTC has correct time configured in it. Add DT alias entries, so that the RTCs get assigned fixed IDs and the HW RTC is always picked by the kernel as the default RTC, thus resulting in correct system time in early userspace. Fixes: 34e0c7847dcf ("ARM: dts: stm32: Add DH Electronics DHCOM STM32MP1 SoM and PDK2 board") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index 2af0a6752674..8349c9099e30 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -12,6 +12,8 @@ aliases { ethernet0 = ðernet0; ethernet1 = &ksz8851; + rtc0 = &hwrtc; + rtc1 = &rtc; }; memory@c0000000 { @@ -248,7 +250,7 @@ /delete-property/dmas; /delete-property/dma-names; - rtc@32 { + hwrtc: rtc@32 { compatible = "microcrystal,rv8803"; reg = <0x32>; }; From 36862c1ebc92a7e6fcc55002965c44b8ad17d4ca Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 21 Jul 2021 20:12:53 +0200 Subject: [PATCH 1098/1469] ARM: dts: stm32: Disable LAN8710 EDPD on DHCOM The LAN8710 Energy Detect Power Down (EDPD) functionality might cause unreliable cable detection. There are multiple accounts of this in the SMSC PHY driver patches which attempted to make EDPD reliable, however it seems there is always some sort of corner case left. Unfortunatelly, there is no errata documented which would confirm this to be a silicon bug on the LAN87xx series of PHYs (LAN8700, LAN8710, LAN8720 at least). Disable EDPD on the DHCOM SoM, just like multiple other boards already do as well, to make the cable detection reliable. Fixes: 34e0c7847dcf ("ARM: dts: stm32: Add DH Electronics DHCOM STM32MP1 SoM and PDK2 board") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index 8349c9099e30..8c41f819f776 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -140,6 +140,7 @@ reset-gpios = <&gpioh 3 GPIO_ACTIVE_LOW>; reset-assert-us = <500>; reset-deassert-us = <500>; + smsc,disable-energy-detect; interrupt-parent = <&gpioi>; interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; From 15f68f027ebd961b99a1c420f96ff3838c5e4450 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 21 Jul 2021 20:10:40 +0200 Subject: [PATCH 1099/1469] ARM: dts: stm32: Fix touchscreen IRQ line assignment on DHCOM While 7e5f3155dcbb4 ("ARM: dts: stm32: Fix LED5 on STM32MP1 DHCOM PDK2") fixed the LED0 assignment on the PDK2 board, the same commit did not update the touchscreen IRQ line assignment, which is the same GPIO line, shared between the LED0 output and touchscreen IRQ input. To make this more convoluted, the same EXTI input (not the same GPIO line) is shared between Button B which is Active-Low IRQ, and touchscreen IRQ which is Edge-Falling IRQ, which cannot be used at the same time. In case the LCD board with touchscreen is in use, which is the case here, LED0 must be disabled, Button B must be polled, so the touchscreen interrupt works as it should. Update the touchscreen IRQ line assignment, disable LED0 and use polled GPIO button driver for Button B, since the DT here describes baseboard with LCD board. Fixes: 7e5f3155dcbb4 ("ARM: dts: stm32: Fix LED5 on STM32MP1 DHCOM PDK2") Signed-off-by: Marek Vasut Cc: Alexandre Torgue Cc: Patrice Chotard Cc: Patrick Delaunay Cc: linux-stm32@st-md-mailman.stormreply.com To: linux-arm-kernel@lists.infradead.org Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 24 +++++++++++-------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index c5ea08fec535..6cf1c8b4c6e2 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -37,7 +37,7 @@ poll-interval = <20>; /* - * The EXTi IRQ line 3 is shared with touchscreen and ethernet, + * The EXTi IRQ line 3 is shared with ethernet, * so mark this as polled GPIO key. */ button-0 { @@ -46,6 +46,16 @@ gpios = <&gpiof 3 GPIO_ACTIVE_LOW>; }; + /* + * The EXTi IRQ line 6 is shared with touchscreen, + * so mark this as polled GPIO key. + */ + button-1 { + label = "TA2-GPIO-B"; + linux,code = ; + gpios = <&gpiod 6 GPIO_ACTIVE_LOW>; + }; + /* * The EXTi IRQ line 0 is shared with PMIC, * so mark this as polled GPIO key. @@ -60,13 +70,6 @@ gpio-keys { compatible = "gpio-keys"; - button-1 { - label = "TA2-GPIO-B"; - linux,code = ; - gpios = <&gpiod 6 GPIO_ACTIVE_LOW>; - wakeup-source; - }; - button-3 { label = "TA4-GPIO-D"; linux,code = ; @@ -82,6 +85,7 @@ label = "green:led5"; gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>; default-state = "off"; + status = "disabled"; }; led-1 { @@ -185,8 +189,8 @@ touchscreen@38 { compatible = "edt,edt-ft5406"; reg = <0x38>; - interrupt-parent = <&gpiog>; - interrupts = <2 IRQ_TYPE_EDGE_FALLING>; /* GPIO E */ + interrupt-parent = <&gpioc>; + interrupts = <6 IRQ_TYPE_EDGE_FALLING>; /* GPIO E */ }; }; From ce5a595744126be4f1327e29e3c5ae9aac6b38d5 Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Wed, 21 Jul 2021 10:54:31 -0700 Subject: [PATCH 1100/1469] interconnect: qcom: icc-rpmh: Ensure floor BW is enforced for all nodes We currently only enforce BW floors for a subset of nodes in a path. All BCMs that need updating are queued in the pre_aggregate/aggregate phase. The first set() commits all queued BCMs and subsequent set() calls short-circuit without committing anything. Since the floor BW isn't set in sum_avg/max_peak until set(), then some BCMs are committed before their associated nodes reflect the floor. Set the floor as each node is being aggregated. This ensures that all all relevant floors are set before the BCMs are committed. Fixes: 266cd33b5913 ("interconnect: qcom: Ensure that the floor bandwidth value is enforced") Signed-off-by: Mike Tipton Link: https://lore.kernel.org/r/20210721175432.2119-4-mdtipton@codeaurora.org [georgi: Removed unused variable] Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpmh.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c index bf01d09dba6c..f6fae64861ce 100644 --- a/drivers/interconnect/qcom/icc-rpmh.c +++ b/drivers/interconnect/qcom/icc-rpmh.c @@ -57,6 +57,11 @@ int qcom_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, qn->sum_avg[i] += avg_bw; qn->max_peak[i] = max_t(u32, qn->max_peak[i], peak_bw); } + + if (node->init_avg || node->init_peak) { + qn->sum_avg[i] = max_t(u64, qn->sum_avg[i], node->init_avg); + qn->max_peak[i] = max_t(u64, qn->max_peak[i], node->init_peak); + } } *agg_avg += avg_bw; @@ -79,7 +84,6 @@ EXPORT_SYMBOL_GPL(qcom_icc_aggregate); int qcom_icc_set(struct icc_node *src, struct icc_node *dst) { struct qcom_icc_provider *qp; - struct qcom_icc_node *qn; struct icc_node *node; if (!src) @@ -88,12 +92,6 @@ int qcom_icc_set(struct icc_node *src, struct icc_node *dst) node = src; qp = to_qcom_provider(node->provider); - qn = node->data; - - qn->sum_avg[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->sum_avg[QCOM_ICC_BUCKET_AMC], - node->avg_bw); - qn->max_peak[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->max_peak[QCOM_ICC_BUCKET_AMC], - node->peak_bw); qcom_icc_bcm_voter_commit(qp->voter); From f84f5b6f72e68bbaeb850b58ac167e4a3a47532a Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Wed, 21 Jul 2021 10:54:32 -0700 Subject: [PATCH 1101/1469] interconnect: qcom: icc-rpmh: Add BCMs to commit list in pre_aggregate We're only adding BCMs to the commit list in aggregate(), but there are cases where pre_aggregate() is called without subsequently calling aggregate(). In particular, in icc_sync_state() when a node with initial BW has zero requests. Since BCMs aren't added to the commit list in these cases, we don't actually send the zero BW request to HW. So the resources remain on unnecessarily. Add BCMs to the commit list in pre_aggregate() instead, which is always called even when there are no requests. Fixes: 976daac4a1c5 ("interconnect: qcom: Consolidate interconnect RPMh support") Signed-off-by: Mike Tipton Link: https://lore.kernel.org/r/20210721175432.2119-5-mdtipton@codeaurora.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpmh.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c index f6fae64861ce..27cc5f03611c 100644 --- a/drivers/interconnect/qcom/icc-rpmh.c +++ b/drivers/interconnect/qcom/icc-rpmh.c @@ -20,13 +20,18 @@ void qcom_icc_pre_aggregate(struct icc_node *node) { size_t i; struct qcom_icc_node *qn; + struct qcom_icc_provider *qp; qn = node->data; + qp = to_qcom_provider(node->provider); for (i = 0; i < QCOM_ICC_NUM_BUCKETS; i++) { qn->sum_avg[i] = 0; qn->max_peak[i] = 0; } + + for (i = 0; i < qn->num_bcms; i++) + qcom_icc_bcm_voter_add(qp->voter, qn->bcms[i]); } EXPORT_SYMBOL_GPL(qcom_icc_pre_aggregate); @@ -44,10 +49,8 @@ int qcom_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, { size_t i; struct qcom_icc_node *qn; - struct qcom_icc_provider *qp; qn = node->data; - qp = to_qcom_provider(node->provider); if (!tag) tag = QCOM_ICC_TAG_ALWAYS; @@ -67,9 +70,6 @@ int qcom_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, *agg_avg += avg_bw; *agg_peak = max_t(u32, *agg_peak, peak_bw); - for (i = 0; i < qn->num_bcms; i++) - qcom_icc_bcm_voter_add(qp->voter, qn->bcms[i]); - return 0; } EXPORT_SYMBOL_GPL(qcom_icc_aggregate); From 094121ef815f29d9e6a01fafca365831454ce293 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 28 Jul 2021 20:21:15 +0200 Subject: [PATCH 1102/1469] arch: Kconfig: clean up obsolete use of HAVE_IDE The arch-specific Kconfig files use HAVE_IDE to indicate if IDE is supported. As IDE support and the HAVE_IDE config vanishes with commit b7fb14d3ac63 ("ide: remove the legacy ide driver"), there is no need to mention HAVE_IDE in all those arch-specific Kconfig files. The issue was identified with ./scripts/checkkconfigsymbols.py. Fixes: b7fb14d3ac63 ("ide: remove the legacy ide driver") Suggested-by: Randy Dunlap Signed-off-by: Lukas Bulwahn Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20210728182115.4401-1-lukas.bulwahn@gmail.com Reviewed-by: Christoph Hellwig Acked-by: Geert Uytterhoeven Signed-off-by: Jens Axboe --- arch/alpha/Kconfig | 1 - arch/arm/Kconfig | 6 ------ arch/arm/mach-davinci/Kconfig | 1 - arch/h8300/Kconfig.cpu | 1 - arch/ia64/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - 13 files changed, 18 deletions(-) diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 77d3280dc678..a6d4c2f744e3 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -14,7 +14,6 @@ config ALPHA select PCI_SYSCALL if PCI select HAVE_AOUT select HAVE_ASM_MODVERSIONS - select HAVE_IDE select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select NEED_DMA_MAP_STATE diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 06b6187b67af..f2ce83e643e7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -95,7 +95,6 @@ config ARM select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7) - select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -361,7 +360,6 @@ config ARCH_FOOTBRIDGE bool "FootBridge" select CPU_SA110 select FOOTBRIDGE - select HAVE_IDE select NEED_MACH_IO_H if !MMU select NEED_MACH_MEMORY_H help @@ -429,7 +427,6 @@ config ARCH_PXA select GENERIC_IRQ_MULTI_HANDLER select GPIO_PXA select GPIOLIB - select HAVE_IDE select IRQ_DOMAIN select PLAT_PXA select SPARSE_IRQ @@ -445,7 +442,6 @@ config ARCH_RPC select ARM_HAS_SG_CHAIN select CPU_SA110 select FIQ - select HAVE_IDE select HAVE_PATA_PLATFORM select ISA_DMA_API select LEGACY_TIMER_TICK @@ -468,7 +464,6 @@ config ARCH_SA1100 select CPU_SA1100 select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select HAVE_IDE select IRQ_DOMAIN select ISA select NEED_MACH_MEMORY_H @@ -504,7 +499,6 @@ config ARCH_OMAP1 select GENERIC_IRQ_CHIP select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select HAVE_IDE select HAVE_LEGACY_CLK select IRQ_DOMAIN select NEED_MACH_IO_H if PCCARD diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index de11030748d0..1d3aef84287d 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -9,7 +9,6 @@ menuconfig ARCH_DAVINCI select PM_GENERIC_DOMAINS_OF if PM && OF select REGMAP_MMIO select RESET_CONTROLLER - select HAVE_IDE select PINCTRL_SINGLE if ARCH_DAVINCI diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu index b5e14d513e62..c30baa0499fc 100644 --- a/arch/h8300/Kconfig.cpu +++ b/arch/h8300/Kconfig.cpu @@ -44,7 +44,6 @@ config H8300_H8MAX bool "H8MAX" select H83069 select RAMKERNEL - select HAVE_IDE help H8MAX Evaluation Board Support More Information. (Japanese Only) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index cf425c2c63af..4993c7ac7ff6 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -25,7 +25,6 @@ config IA64 select HAVE_ASM_MODVERSIONS select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_EXIT_THREAD - select HAVE_IDE select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 96989ad46f66..d632a1d576f9 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -23,7 +23,6 @@ config M68K select HAVE_DEBUG_BUGVERBOSE select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_HAS_NO_UNALIGNED select HAVE_FUTEX_CMPXCHG if MMU && FUTEX - select HAVE_IDE select HAVE_MOD_ARCH_SPECIFIC select HAVE_UID16 select MMU_GATHER_NO_RANGE if MMU diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cee6087cd686..6dfb27d531dd 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -71,7 +71,6 @@ config MIPS select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index bde9907bc5b2..4f8c1fbf8f2f 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -3,7 +3,6 @@ config PARISC def_bool y select ARCH_32BIT_OFF_T if !64BIT select ARCH_MIGHT_HAVE_PC_PARPORT - select HAVE_IDE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d01e3401581d..663766fbf505 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -220,7 +220,6 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC_BOOK3S_64 && SMP select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 45a0549421cd..b683b69a4556 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -39,7 +39,6 @@ config SUPERH select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_FTRACE_MCOUNT_RECORD select HAVE_HW_BREAKPOINT - select HAVE_IDE if HAS_IOPORT_MAP select HAVE_IOREMAP_PROT if MMU && !X2TLB select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c5fa7932b550..f0c0f955e169 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -19,7 +19,6 @@ config SPARC select OF select OF_PROMTREE select HAVE_ASM_MODVERSIONS - select HAVE_IDE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_SECCOMP if SPARC64 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 49270655e827..88fb922c23a0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -202,7 +202,6 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT - select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 2332b2156993..3878880469d1 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -327,7 +327,6 @@ config XTENSA_PLATFORM_ISS config XTENSA_PLATFORM_XT2000 bool "XT2000" - select HAVE_IDE help XT2000 is the name of Tensilica's feature-rich emulation platform. This hardware is capable of running a full Linux distribution. From 7561c14d8a4d1a24a40b1839d927d488e2d6345a Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar Date: Wed, 28 Jul 2021 13:24:53 +0200 Subject: [PATCH 1103/1469] s390/vdso: add .got.plt in vdso linker script KCFLAGS="-mno-pic-data-is-text-relative" make leads to bfd assertion error in s390_got_pointer(): LD arch/s390/kernel/vdso64/vdso64.so.dbg ld: BFD version 2.35-18.fc33 assertion fail elf-s390-common.c:74 readelf -Wr vdso64_generic.o | grep GOT 0000000000000032 000000110000001a R_390_GOTENT 0000000000000000 _vdso_data + 2 (...) Add .got.plt in linker script to avoid this. Suggested-by: Ilya Leoshkevich Signed-off-by: Sumanth Korikkar Signed-off-by: Heiko Carstens --- arch/s390/kernel/vdso32/vdso32.lds.S | 1 + arch/s390/kernel/vdso64/vdso64.lds.S | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S index bff50b6acd6d..edf5ff1debe1 100644 --- a/arch/s390/kernel/vdso32/vdso32.lds.S +++ b/arch/s390/kernel/vdso32/vdso32.lds.S @@ -51,6 +51,7 @@ SECTIONS .rela.dyn ALIGN(8) : { *(.rela.dyn) } .got ALIGN(8) : { *(.got .toc) } + .got.plt ALIGN(8) : { *(.got.plt) } _end = .; PROVIDE(end = .); diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S index d4fb336d747b..4461ea151e49 100644 --- a/arch/s390/kernel/vdso64/vdso64.lds.S +++ b/arch/s390/kernel/vdso64/vdso64.lds.S @@ -51,6 +51,7 @@ SECTIONS .rela.dyn ALIGN(8) : { *(.rela.dyn) } .got ALIGN(8) : { *(.got .toc) } + .got.plt ALIGN(8) : { *(.got.plt) } _end = .; PROVIDE(end = .); From 88731c8f3636b133e27df88febcd7cd2fdece0a7 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 29 Jul 2021 15:29:19 +0200 Subject: [PATCH 1104/1469] s390/boot: fix zstd build for -march=z900 zstd decompression uses __builtin_clz() which fails back to __clzdi2() when the kernel is built for older hardware like z900. This leads to build failures like the following: s390x-11.1.0-ld: /devel/src/kernel/arch/s390/boot/compressed/../../../../lib/zstd/bitstream.h:148: undefined reference to `__clzdi2' Fix that by optionally including lib/clz_ctz.c into the decompressor. Reported-by: kernel test robot Fixes: 7b034d9c1b08 ("s390/boot: add zstd support") Signed-off-by: Vasily Gorbik Link: https://lore.kernel.org/r/patch-1.thread-f0f589.git-f0f58936888f.your-ad-here.call-01627564869-ext-2765@work.hours Signed-off-by: Heiko Carstens --- arch/s390/boot/compressed/Makefile | 1 + arch/s390/boot/compressed/clz_ctz.c | 2 ++ 2 files changed, 3 insertions(+) create mode 100644 arch/s390/boot/compressed/clz_ctz.c diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 660c799d875d..e30d3fdbbc78 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -11,6 +11,7 @@ UBSAN_SANITIZE := n KASAN_SANITIZE := n obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o +obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o obj-all := $(obj-y) piggy.o syms.o targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 diff --git a/arch/s390/boot/compressed/clz_ctz.c b/arch/s390/boot/compressed/clz_ctz.c new file mode 100644 index 000000000000..c3ebf248596b --- /dev/null +++ b/arch/s390/boot/compressed/clz_ctz.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../../../../lib/clz_ctz.c" From 1e9faef4d26de33bd6b5018695996e7394119e5b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 30 Jul 2021 14:21:56 +0200 Subject: [PATCH 1105/1469] USB: serial: pl2303: fix HX type detection The device release number for HX-type devices is configurable in EEPROM/OTPROM and cannot be used reliably for type detection. Assume all (non-H) devices with bcdUSB 1.1 and unknown bcdDevice to be of HX type while adding a bcdDevice check for HXD and TB (1.1 and 2.0, respectively). Reported-by: Chris Fixes: 8a7bf7510d1f ("USB: serial: pl2303: amend and tighten type detection") Cc: stable@vger.kernel.org # 5.13 Link: https://lore.kernel.org/r/20210730122156.718-1-johan@kernel.org Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- drivers/usb/serial/pl2303.c | 41 ++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 16 deletions(-) diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 2f2f5047452b..17601e32083e 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -418,24 +418,33 @@ static int pl2303_detect_type(struct usb_serial *serial) bcdDevice = le16_to_cpu(desc->bcdDevice); bcdUSB = le16_to_cpu(desc->bcdUSB); - switch (bcdDevice) { - case 0x100: - /* - * Assume it's an HXN-type if the device doesn't support the old read - * request value. - */ - if (bcdUSB == 0x200 && !pl2303_supports_hx_status(serial)) - return TYPE_HXN; + switch (bcdUSB) { + case 0x110: + switch (bcdDevice) { + case 0x300: + return TYPE_HX; + case 0x400: + return TYPE_HXD; + default: + return TYPE_HX; + } break; - case 0x300: - if (bcdUSB == 0x200) + case 0x200: + switch (bcdDevice) { + case 0x100: + /* + * Assume it's an HXN-type if the device doesn't + * support the old read request value. + */ + if (!pl2303_supports_hx_status(serial)) + return TYPE_HXN; + break; + case 0x300: return TYPE_TA; - - return TYPE_HX; - case 0x400: - return TYPE_HXD; - case 0x500: - return TYPE_TB; + case 0x500: + return TYPE_TB; + } + break; } dev_err(&serial->interface->dev, From 4d77f36f2c8c62b230f4a5eb264c169fa04c4a5a Mon Sep 17 00:00:00 2001 From: xinhui pan Date: Tue, 27 Jul 2021 17:43:37 +0800 Subject: [PATCH 1106/1469] drm/amdgpu: Fix out-of-bounds read when update mapping MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If one GTT BO has been evicted/swapped out, it should sit in CPU domain. TTM only alloc struct ttm_resource instead of struct ttm_range_mgr_node for sysMem. Now when we update mapping for such invalidated BOs, we might walk out of bounds of struct ttm_resource. Three possible fix: 1) Let sysMem manager alloc struct ttm_range_mgr_node, like ttm_range_manager does. 2) Pass pages_addr to update_mapping function too, but need memset pages_addr[] to zero when unpopulate. 3) Init amdgpu_res_cursor directly. bug is detected by kfence. ================================================================== BUG: KFENCE: out-of-bounds read in amdgpu_vm_bo_update_mapping+0x564/0x6e0 Out-of-bounds read at 0x000000008ea93fe9 (64B right of kfence-#167): amdgpu_vm_bo_update_mapping+0x564/0x6e0 [amdgpu] amdgpu_vm_bo_update+0x282/0xa40 [amdgpu] amdgpu_vm_handle_moved+0x19e/0x1f0 [amdgpu] amdgpu_cs_vm_handling+0x4e4/0x640 [amdgpu] amdgpu_cs_ioctl+0x19e7/0x23c0 [amdgpu] drm_ioctl_kernel+0xf3/0x180 [drm] drm_ioctl+0x2cb/0x550 [drm] amdgpu_drm_ioctl+0x5e/0xb0 [amdgpu] kfence-#167 [0x000000008e11c055-0x000000001f676b3e ttm_sys_man_alloc+0x35/0x80 [ttm] ttm_resource_alloc+0x39/0x50 [ttm] ttm_bo_swapout+0x252/0x5a0 [ttm] ttm_device_swapout+0x107/0x180 [ttm] ttm_global_swapout+0x6f/0x130 [ttm] ttm_tt_populate+0xb1/0x2a0 [ttm] ttm_bo_handle_move_mem+0x17e/0x1d0 [ttm] ttm_mem_evict_first+0x59d/0x9c0 [ttm] ttm_bo_mem_space+0x39f/0x400 [ttm] ttm_bo_validate+0x13c/0x340 [ttm] ttm_bo_init_reserved+0x269/0x540 [ttm] amdgpu_bo_create+0x1d1/0xa30 [amdgpu] amdgpu_bo_create_user+0x40/0x80 [amdgpu] amdgpu_gem_object_create+0x71/0xc0 [amdgpu] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x2f2/0xcd0 [amdgpu] kfd_ioctl_alloc_memory_of_gpu+0xe2/0x330 [amdgpu] kfd_ioctl+0x461/0x690 [amdgpu] Signed-off-by: xinhui pan Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index 59e0fefb15aa..acfa207cf970 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -54,11 +54,12 @@ static inline void amdgpu_res_first(struct ttm_resource *res, { struct drm_mm_node *node; - if (!res) { + if (!res || res->mem_type == TTM_PL_SYSTEM) { cur->start = start; cur->size = size; cur->remaining = size; cur->node = NULL; + WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT); return; } From 1c0539a6fc8a4a4b77278e35d763073890de96b9 Mon Sep 17 00:00:00 2001 From: Yifan Zhang Date: Thu, 10 Jun 2021 09:55:01 +0800 Subject: [PATCH 1107/1469] drm/amdgpu: fix the doorbell missing when in CGPG issue for renoir. If GC has entered CGPG, ringing doorbell > first page doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround this issue. Signed-off-by: Yifan Zhang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 044076ec1d03..6a23c6826e12 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1295,6 +1295,16 @@ static bool is_raven_kicker(struct amdgpu_device *adev) return false; } +static bool check_if_enlarge_doorbell_range(struct amdgpu_device *adev) +{ + if ((adev->asic_type == CHIP_RENOIR) && + (adev->gfx.me_fw_version >= 0x000000a5) && + (adev->gfx.me_feature_version >= 52)) + return true; + else + return false; +} + static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) { if (gfx_v9_0_should_disable_gfxoff(adev->pdev)) @@ -3675,7 +3685,16 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); - WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, + /* If GC has entered CGPG, ringing doorbell > first page + * doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to + * workaround this issue. And this change has to align with firmware + * update. + */ + if (check_if_enlarge_doorbell_range(adev)) + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, + (adev->doorbell.size - 4)); + else + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, (adev->doorbell_index.userqueue_end * 2) << 2); } From 2e6b836312a477d647a7920b56810a5a25f6c856 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 28 Jul 2021 13:23:50 +0200 Subject: [PATCH 1108/1469] ASoC: intel: atom: Fix reference to PCM buffer address PCM buffers might be allocated dynamically when the buffer preallocation failed or a larger buffer is requested, and it's not guaranteed that substream->dma_buffer points to the actually used buffer. The address should be retrieved from runtime->dma_addr, instead of substream->dma_buffer (and shouldn't use virt_to_phys). Also, remove the line overriding runtime->dma_area superfluously, which was already set up at the PCM buffer allocation. Cc: Cezary Rojewski Cc: Pierre-Louis Bossart Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20210728112353.6675-3-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/intel/atom/sst-mfld-platform-pcm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 4124aa2fc247..5db2f4865bbb 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -127,7 +127,7 @@ static void sst_fill_alloc_params(struct snd_pcm_substream *substream, snd_pcm_uframes_t period_size; ssize_t periodbytes; ssize_t buffer_bytes = snd_pcm_lib_buffer_bytes(substream); - u32 buffer_addr = virt_to_phys(substream->dma_buffer.area); + u32 buffer_addr = substream->runtime->dma_addr; channels = substream->runtime->channels; period_size = substream->runtime->period_size; @@ -233,7 +233,6 @@ static int sst_platform_alloc_stream(struct snd_pcm_substream *substream, /* set codec params and inform SST driver the same */ sst_fill_pcm_params(substream, ¶m); sst_fill_alloc_params(substream, &alloc_params); - substream->runtime->dma_area = substream->dma_buffer.area; str_params.sparams = param; str_params.aparams = alloc_params; str_params.codec = SST_CODEC_TYPE_PCM; From 42bc62c9f1d3d4880bdc27acb5ab4784209bb0b0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 28 Jul 2021 13:23:51 +0200 Subject: [PATCH 1109/1469] ASoC: xilinx: Fix reference to PCM buffer address PCM buffers might be allocated dynamically when the buffer preallocation failed or a larger buffer is requested, and it's not guaranteed that substream->dma_buffer points to the actually used buffer. The driver needs to refer to substream->runtime->dma_addr instead for the buffer address. Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20210728112353.6675-4-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/xilinx/xlnx_formatter_pcm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/xilinx/xlnx_formatter_pcm.c b/sound/soc/xilinx/xlnx_formatter_pcm.c index 1d59fb668c77..91afea9d5de6 100644 --- a/sound/soc/xilinx/xlnx_formatter_pcm.c +++ b/sound/soc/xilinx/xlnx_formatter_pcm.c @@ -452,8 +452,8 @@ static int xlnx_formatter_pcm_hw_params(struct snd_soc_component *component, stream_data->buffer_size = size; - low = lower_32_bits(substream->dma_buffer.addr); - high = upper_32_bits(substream->dma_buffer.addr); + low = lower_32_bits(runtime->dma_addr); + high = upper_32_bits(runtime->dma_addr); writel(low, stream_data->mmio + XLNX_AUD_BUFF_ADDR_LSB); writel(high, stream_data->mmio + XLNX_AUD_BUFF_ADDR_MSB); From 827f3164aaa579eee6fd50c6654861d54f282a11 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 28 Jul 2021 13:23:52 +0200 Subject: [PATCH 1110/1469] ASoC: uniphier: Fix reference to PCM buffer address Along with the transition to the managed PCM buffers, the driver now accepts the dynamically allocated buffer, while it still kept the reference to the old preallocated buffer address. This patch corrects to the right reference via runtime->dma_addr. (Although this might have been already buggy before the cleanup with the managed buffer, let's put Fixes tag to point that; it's a corner case, after all.) Fixes: d55894bc2763 ("ASoC: uniphier: Use managed buffer allocation") Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20210728112353.6675-5-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/uniphier/aio-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/uniphier/aio-dma.c b/sound/soc/uniphier/aio-dma.c index 3c1628a3a1ac..3d9736e7381f 100644 --- a/sound/soc/uniphier/aio-dma.c +++ b/sound/soc/uniphier/aio-dma.c @@ -198,7 +198,7 @@ static int uniphier_aiodma_mmap(struct snd_soc_component *component, vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, - substream->dma_buffer.addr >> PAGE_SHIFT, + substream->runtime->dma_addr >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot); } From bb6a40fc5a830cae45ddd5cd6cfa151b008522ed Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 28 Jul 2021 13:23:53 +0200 Subject: [PATCH 1111/1469] ASoC: kirkwood: Fix reference to PCM buffer address The transition to the managed PCM buffers allowed the dynamically buffer allocation, while the driver code still assumes the fixed preallocation buffer and sets up the DMA stuff at the open call. This needs to be moved to hw_params after the buffer allocation and setup. Also, the reference to the buffer address has to be corrected to runtime->dma_addr. Fixes: b3c0ae75f5d3 ("ASoC: kirkwood: Use managed DMA buffer allocation") Cc: Lars-Peter Clausen Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20210728112353.6675-6-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/kirkwood/kirkwood-dma.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index c2a5933bfcfc..700a18561a94 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -104,8 +104,6 @@ static int kirkwood_dma_open(struct snd_soc_component *component, int err; struct snd_pcm_runtime *runtime = substream->runtime; struct kirkwood_dma_data *priv = kirkwood_priv(substream); - const struct mbus_dram_target_info *dram; - unsigned long addr; snd_soc_set_runtime_hwparams(substream, &kirkwood_dma_snd_hw); @@ -142,20 +140,14 @@ static int kirkwood_dma_open(struct snd_soc_component *component, writel((unsigned int)-1, priv->io + KIRKWOOD_ERR_MASK); } - dram = mv_mbus_dram_info(); - addr = substream->dma_buffer.addr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (priv->substream_play) return -EBUSY; priv->substream_play = substream; - kirkwood_dma_conf_mbus_windows(priv->io, - KIRKWOOD_PLAYBACK_WIN, addr, dram); } else { if (priv->substream_rec) return -EBUSY; priv->substream_rec = substream; - kirkwood_dma_conf_mbus_windows(priv->io, - KIRKWOOD_RECORD_WIN, addr, dram); } return 0; @@ -182,6 +174,23 @@ static int kirkwood_dma_close(struct snd_soc_component *component, return 0; } +static int kirkwood_dma_hw_params(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + struct kirkwood_dma_data *priv = kirkwood_priv(substream); + const struct mbus_dram_target_info *dram = mv_mbus_dram_info(); + unsigned long addr = substream->runtime->dma_addr; + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + kirkwood_dma_conf_mbus_windows(priv->io, + KIRKWOOD_PLAYBACK_WIN, addr, dram); + else + kirkwood_dma_conf_mbus_windows(priv->io, + KIRKWOOD_RECORD_WIN, addr, dram); + return 0; +} + static int kirkwood_dma_prepare(struct snd_soc_component *component, struct snd_pcm_substream *substream) { @@ -246,6 +255,7 @@ const struct snd_soc_component_driver kirkwood_soc_component = { .name = DRV_NAME, .open = kirkwood_dma_open, .close = kirkwood_dma_close, + .hw_params = kirkwood_dma_hw_params, .prepare = kirkwood_dma_prepare, .pointer = kirkwood_dma_pointer, .pcm_construct = kirkwood_dma_new, From 028a71775f811e9d60664ba2c248ff95c6cf57cb Mon Sep 17 00:00:00 2001 From: Catherine Sullivan Date: Thu, 29 Jul 2021 08:52:58 -0700 Subject: [PATCH 1112/1469] gve: Update MAINTAINERS list The team maintaining the gve driver has undergone some changes, this updates the MAINTAINERS file accordingly. Signed-off-by: Catherine Sullivan Signed-off-by: Jon Olson Signed-off-by: David Awogbemila Signed-off-by: Jeroen de Borst Link: https://lore.kernel.org/r/20210729155258.442650-1-csully@google.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 58afeb12d3b3..17a873153eba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7858,9 +7858,9 @@ S: Maintained F: drivers/input/touchscreen/goodix.c GOOGLE ETHERNET DRIVERS -M: Catherine Sullivan -R: Sagi Shahar -R: Jon Olson +M: Jeroen de Borst +R: Catherine Sullivan +R: David Awogbemila L: netdev@vger.kernel.org S: Supported F: Documentation/networking/device_drivers/ethernet/google/gve.rst From b2ff70a01a7a8083e749e01e5d3ffda706fe3305 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 29 Jul 2021 14:53:35 -0700 Subject: [PATCH 1113/1469] lib/test_string.c: move string selftest in the Runtime Testing menu STRING_SELFTEST is presented in the "Library routines" menu. Move it in Kernel hacking > Kernel Testing and Coverage > Runtime Testing together with other similar tests found in lib/ --- Runtime Testing <*> Test functions located in the hexdump module at runtime <*> Test string functions (NEW) <*> Test functions located in the string_helpers module at runtime <*> Test strscpy*() family of functions at runtime <*> Test kstrto*() family of functions at runtime <*> Test printf() family of functions at runtime <*> Test scanf() family of functions at runtime Link: https://lkml.kernel.org/r/20210719185158.190371-1-mcroce@linux.microsoft.com Signed-off-by: Matteo Croce Cc: Peter Rosin Cc: Geert Uytterhoeven Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig | 3 --- lib/Kconfig.debug | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/Kconfig b/lib/Kconfig index d241fe476fda..5c9c0687f76d 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -683,9 +683,6 @@ config PARMAN config OBJAGG tristate "objagg" if COMPILE_TEST -config STRING_SELFTEST - tristate "Test string functions" - endmenu config GENERIC_IOREMAP diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 831212722924..5ddd575159fb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2180,6 +2180,9 @@ config ASYNC_RAID6_TEST config TEST_HEXDUMP tristate "Test functions located in the hexdump module at runtime" +config STRING_SELFTEST + tristate "Test string functions at runtime" + config TEST_STRING_HELPERS tristate "Test functions located in the string_helpers module at runtime" From f267aeb6dea5e468793e5b8eb6a9c72c0020d418 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 29 Jul 2021 14:53:38 -0700 Subject: [PATCH 1114/1469] ocfs2: fix zero out valid data If append-dio feature is enabled, direct-io write and fallocate could run in parallel to extend file size, fallocate used "orig_isize" to record i_size before taking "ip_alloc_sem", when ocfs2_zeroout_partial_cluster() zeroout EOF blocks, i_size maybe already extended by ocfs2_dio_end_io_write(), that will cause valid data zeroed out. Link: https://lkml.kernel.org/r/20210722054923.24389-1-junxiao.bi@oracle.com Fixes: 6bba4471f0cc ("ocfs2: fix data corruption by fallocate") Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Mark Fasheh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 775657943057..53bb46ce3cbb 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1935,7 +1935,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1943,7 +1942,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += orig_isize; + sr->l_start += i_size_read(inode); break; default: ret = -EINVAL; @@ -1998,6 +1997,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, ret = -EINVAL; } + orig_isize = i_size_read(inode); /* zeroout eof blocks in the cluster. */ if (!ret && change_size && orig_isize < size) { ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, From 9449ad33be8480f538b11a593e2dda2fb33ca06d Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 29 Jul 2021 14:53:41 -0700 Subject: [PATCH 1115/1469] ocfs2: issue zeroout to EOF blocks For punch holes in EOF blocks, fallocate used buffer write to zero the EOF blocks in last cluster. But since ->writepage will ignore EOF pages, those zeros will not be flushed. This "looks" ok as commit 6bba4471f0cc ("ocfs2: fix data corruption by fallocate") will zero the EOF blocks when extend the file size, but it isn't. The problem happened on those EOF pages, before writeback, those pages had DIRTY flag set and all buffer_head in them also had DIRTY flag set, when writeback run by write_cache_pages(), DIRTY flag on the page was cleared, but DIRTY flag on the buffer_head not. When next write happened to those EOF pages, since buffer_head already had DIRTY flag set, it would not mark page DIRTY again. That made writeback ignore them forever. That will cause data corruption. Even directio write can't work because it will fail when trying to drop pages caches before direct io, as it found the buffer_head for those pages still had DIRTY flag set, then it will fall back to buffer io mode. To make a summary of the issue, as writeback ingores EOF pages, once any EOF page is generated, any write to it will only go to the page cache, it will never be flushed to disk even file size extends and that page is not EOF page any more. The fix is to avoid zero EOF blocks with buffer write. The following code snippet from qemu-img could trigger the corruption. 656 open("6b3711ae-3306-4bdd-823c-cf1c0060a095.conv.2", O_RDWR|O_DIRECT|O_CLOEXEC) = 11 ... 660 fallocate(11, FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE, 2275868672, 327680 660 fallocate(11, 0, 2275868672, 327680) = 0 658 pwrite64(11, " Link: https://lkml.kernel.org/r/20210722054923.24389-2-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/file.c | 99 ++++++++++++++++++++++++++++++------------------- 1 file changed, 60 insertions(+), 39 deletions(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 53bb46ce3cbb..54d7843c0211 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1529,6 +1529,45 @@ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start, } } +/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { @@ -1538,6 +1577,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; + loff_t isize = i_size_read(inode); /* * The "start" and "end" values are NOT necessarily part of @@ -1558,6 +1598,26 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out; + /* No page cache for EOF blocks, issue zero out to disk. */ + if (end > isize) { + /* + * zeroout eof blocks in last cluster starting from + * "isize" even "start" > "isize" because it is + * complicated to zeroout just at "start" as "start" + * may be not aligned with block size, buffer write + * would be required to do that, but out of eof buffer + * write is not supported. + */ + ret = ocfs2_zeroout_partial_cluster(inode, isize, + end - isize); + if (ret) { + mlog_errno(ret); + goto out; + } + if (start >= isize) + goto out; + end = isize; + } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -1855,45 +1915,6 @@ out: return ret; } -/* - * zero out partial blocks of one cluster. - * - * start: file offset where zero starts, will be made upper block aligned. - * len: it will be trimmed to the end of current cluster if "start + len" - * is bigger than it. - */ -static int ocfs2_zeroout_partial_cluster(struct inode *inode, - u64 start, u64 len) -{ - int ret; - u64 start_block, end_block, nr_blocks; - u64 p_block, offset; - u32 cluster, p_cluster, nr_clusters; - struct super_block *sb = inode->i_sb; - u64 end = ocfs2_align_bytes_to_clusters(sb, start); - - if (start + len < end) - end = start + len; - - start_block = ocfs2_blocks_for_bytes(sb, start); - end_block = ocfs2_blocks_for_bytes(sb, end); - nr_blocks = end_block - start_block; - if (!nr_blocks) - return 0; - - cluster = ocfs2_bytes_to_clusters(sb, start); - ret = ocfs2_get_clusters(inode, cluster, &p_cluster, - &nr_clusters, NULL); - if (ret) - return ret; - if (!p_cluster) - return 0; - - offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); - p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; - return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); -} - /* * Parts of this function taken from xfs_change_file_space() */ From 30def93565e5ba08676aa2b9083f253fc586dbed Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 29 Jul 2021 14:53:44 -0700 Subject: [PATCH 1116/1469] mm: memcontrol: fix blocking rstat function called from atomic cgroup1 thresholding code Dan Carpenter reports: The patch 2d146aa3aa84: "mm: memcontrol: switch to rstat" from Apr 29, 2021, leads to the following static checker warning: kernel/cgroup/rstat.c:200 cgroup_rstat_flush() warn: sleeping in atomic context mm/memcontrol.c 3572 static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) 3573 { 3574 unsigned long val; 3575 3576 if (mem_cgroup_is_root(memcg)) { 3577 cgroup_rstat_flush(memcg->css.cgroup); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ This is from static analysis and potentially a false positive. The problem is that mem_cgroup_usage() is called from __mem_cgroup_threshold() which holds an rcu_read_lock(). And the cgroup_rstat_flush() function can sleep. 3578 val = memcg_page_state(memcg, NR_FILE_PAGES) + 3579 memcg_page_state(memcg, NR_ANON_MAPPED); 3580 if (swap) 3581 val += memcg_page_state(memcg, MEMCG_SWAP); 3582 } else { 3583 if (!swap) 3584 val = page_counter_read(&memcg->memory); 3585 else 3586 val = page_counter_read(&memcg->memsw); 3587 } 3588 return val; 3589 } __mem_cgroup_threshold() indeed holds the rcu lock. In addition, the thresholding code is invoked during stat changes, and those contexts have irqs disabled as well. If the lock breaking occurs inside the flush function, it will result in a sleep from an atomic context. Use the irqsafe flushing variant in mem_cgroup_usage() to fix this. Link: https://lkml.kernel.org/r/20210726150019.251820-1-hannes@cmpxchg.org Fixes: 2d146aa3aa84 ("mm: memcontrol: switch to rstat") Signed-off-by: Johannes Weiner Reported-by: Dan Carpenter Acked-by: Chris Down Reviewed-by: Rik van Riel Acked-by: Michal Hocko Reviewed-by: Shakeel Butt Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ae1f5d0cb581..eb8e87c4833f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3574,7 +3574,8 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - cgroup_rstat_flush(memcg->css.cgroup); + /* mem_cgroup_threshold() calls here from irqsafe context */ + cgroup_rstat_flush_irqsafe(memcg->css.cgroup); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) From b5916c025432b7c776b6bb13617485fbc0bd3ebd Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 29 Jul 2021 14:53:47 -0700 Subject: [PATCH 1117/1469] mm/migrate: fix NR_ISOLATED corruption on 64-bit Similar to commit 2da9f6305f30 ("mm/vmscan: fix NR_ISOLATED_FILE corruption on 64-bit") avoid using unsigned int for nr_pages. With unsigned int type the large unsigned int converts to a large positive signed long. Symptoms include CMA allocations hanging forever due to alloc_contig_range->...->isolate_migratepages_block waiting forever in "while (unlikely(too_many_isolated(pgdat)))". Link: https://lkml.kernel.org/r/20210728042531.359409-1-aneesh.kumar@linux.ibm.com Fixes: c5fc5c3ae0c8 ("mm: migrate: account THP NUMA migration counters correctly") Signed-off-by: Aneesh Kumar K.V Reported-by: Michael Ellerman Reported-by: Alexey Kardashevskiy Reviewed-by: Yang Shi Cc: Mel Gorman Cc: Nicholas Piggin Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index 34a9ad3e0a4f..7e240437e7d9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2068,7 +2068,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, LIST_HEAD(migratepages); new_page_t *new; bool compound; - unsigned int nr_pages = thp_nr_pages(page); + int nr_pages = thp_nr_pages(page); /* * PTE mapped THP or HugeTLB page can't reach here so the page could From f227f0faf63b46a113c4d1aca633c80195622dd2 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 29 Jul 2021 14:53:50 -0700 Subject: [PATCH 1118/1469] slub: fix unreclaimable slab stat for bulk free SLUB uses page allocator for higher order allocations and update unreclaimable slab stat for such allocations. At the moment, the bulk free for SLUB does not share code with normal free code path for these type of allocations and have missed the stat update. So, fix the stat update by common code. The user visible impact of the bug is the potential of inconsistent unreclaimable slab stat visible through meminfo and vmstat. Link: https://lkml.kernel.org/r/20210728155354.3440560-1-shakeelb@google.com Fixes: 6a486c0ad4dc ("mm, sl[ou]b: improve memory accounting") Signed-off-by: Shakeel Butt Acked-by: Michal Hocko Acked-by: Roman Gushchin Reviewed-by: Muchun Song Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 090fa14628f9..af984e4990e8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3236,6 +3236,16 @@ struct detached_freelist { struct kmem_cache *s; }; +static inline void free_nonslab_page(struct page *page) +{ + unsigned int order = compound_order(page); + + VM_BUG_ON_PAGE(!PageCompound(page), page); + kfree_hook(page_address(page)); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); + __free_pages(page, order); +} + /* * This function progressively scans the array with free objects (with * a limited look ahead) and extract objects belonging to the same @@ -3272,9 +3282,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - BUG_ON(!PageCompound(page)); - kfree_hook(object); - __free_pages(page, compound_order(page)); + free_nonslab_page(page); p[size] = NULL; /* mark object processed */ return size; } @@ -4250,13 +4258,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - unsigned int order = compound_order(page); - - BUG_ON(!PageCompound(page)); - kfree_hook(object); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - -(PAGE_SIZE << order)); - __free_pages(page, order); + free_nonslab_page(page); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); From 121dffe20b141c9b27f39d49b15882469cbebae7 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Thu, 29 Jul 2021 14:53:54 -0700 Subject: [PATCH 1119/1469] mm/memcg: fix NULL pointer dereference in memcg_slab_free_hook() When I use kfree_rcu() to free a large memory allocated by kmalloc_node(), the following dump occurs. BUG: kernel NULL pointer dereference, address: 0000000000000020 [...] Oops: 0000 [#1] SMP [...] Workqueue: events kfree_rcu_work RIP: 0010:__obj_to_index include/linux/slub_def.h:182 [inline] RIP: 0010:obj_to_index include/linux/slub_def.h:191 [inline] RIP: 0010:memcg_slab_free_hook+0x120/0x260 mm/slab.h:363 [...] Call Trace: kmem_cache_free_bulk+0x58/0x630 mm/slub.c:3293 kfree_bulk include/linux/slab.h:413 [inline] kfree_rcu_work+0x1ab/0x200 kernel/rcu/tree.c:3300 process_one_work+0x207/0x530 kernel/workqueue.c:2276 worker_thread+0x320/0x610 kernel/workqueue.c:2422 kthread+0x13d/0x160 kernel/kthread.c:313 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294 When kmalloc_node() a large memory, page is allocated, not slab, so when freeing memory via kfree_rcu(), this large memory should not be used by memcg_slab_free_hook(), because memcg_slab_free_hook() is is used for slab. Using page_objcgs_check() instead of page_objcgs() in memcg_slab_free_hook() to fix this bug. Link: https://lkml.kernel.org/r/20210728145655.274476-1-wanghai38@huawei.com Fixes: 270c6a71460e ("mm: memcontrol/slab: Use helpers to access slab page's memcg_data") Signed-off-by: Wang Hai Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Acked-by: Roman Gushchin Reviewed-by: Kefeng Wang Reviewed-by: Muchun Song Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Johannes Weiner Cc: Alexei Starovoitov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/slab.h b/mm/slab.h index f997fd5e42c8..58c01a34e5b8 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -346,7 +346,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, continue; page = virt_to_head_page(p[i]); - objcgs = page_objcgs(page); + objcgs = page_objcgs_check(page); if (!objcgs) continue; From 1d25684e22516f1cff77176d288b1da02fff57bb Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 29 Jul 2021 00:47:29 +0100 Subject: [PATCH 1120/1469] ASoC: nau8824: Fix open coded prefix handling As with the component layer code the nau8824 driver had been doing some open coded pin manipulation which will have been broken now the core is fixed to handle this properly, remove the open coding to avoid the issue. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210728234729.10135-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/nau8824.c | 42 ++++++-------------------------------- 1 file changed, 6 insertions(+), 36 deletions(-) diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index 15bd8335f667..db88be48c998 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -828,36 +828,6 @@ static void nau8824_int_status_clear_all(struct regmap *regmap) } } -static void nau8824_dapm_disable_pin(struct nau8824 *nau8824, const char *pin) -{ - struct snd_soc_dapm_context *dapm = nau8824->dapm; - const char *prefix = dapm->component->name_prefix; - char prefixed_pin[80]; - - if (prefix) { - snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", - prefix, pin); - snd_soc_dapm_disable_pin(dapm, prefixed_pin); - } else { - snd_soc_dapm_disable_pin(dapm, pin); - } -} - -static void nau8824_dapm_enable_pin(struct nau8824 *nau8824, const char *pin) -{ - struct snd_soc_dapm_context *dapm = nau8824->dapm; - const char *prefix = dapm->component->name_prefix; - char prefixed_pin[80]; - - if (prefix) { - snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", - prefix, pin); - snd_soc_dapm_force_enable_pin(dapm, prefixed_pin); - } else { - snd_soc_dapm_force_enable_pin(dapm, pin); - } -} - static void nau8824_eject_jack(struct nau8824 *nau8824) { struct snd_soc_dapm_context *dapm = nau8824->dapm; @@ -866,8 +836,8 @@ static void nau8824_eject_jack(struct nau8824 *nau8824) /* Clear all interruption status */ nau8824_int_status_clear_all(regmap); - nau8824_dapm_disable_pin(nau8824, "SAR"); - nau8824_dapm_disable_pin(nau8824, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SAR"); + snd_soc_dapm_disable_pin(dapm, "MICBIAS"); snd_soc_dapm_sync(dapm); /* Enable the insertion interruption, disable the ejection @@ -897,8 +867,8 @@ static void nau8824_jdet_work(struct work_struct *work) struct regmap *regmap = nau8824->regmap; int adc_value, event = 0, event_mask = 0; - nau8824_dapm_enable_pin(nau8824, "MICBIAS"); - nau8824_dapm_enable_pin(nau8824, "SAR"); + snd_soc_dapm_enable_pin(dapm, "MICBIAS"); + snd_soc_dapm_enable_pin(dapm, "SAR"); snd_soc_dapm_sync(dapm); msleep(100); @@ -909,8 +879,8 @@ static void nau8824_jdet_work(struct work_struct *work) if (adc_value < HEADSET_SARADC_THD) { event |= SND_JACK_HEADPHONE; - nau8824_dapm_disable_pin(nau8824, "SAR"); - nau8824_dapm_disable_pin(nau8824, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SAR"); + snd_soc_dapm_disable_pin(dapm, "MICBIAS"); snd_soc_dapm_sync(dapm); } else { event |= SND_JACK_HEADSET; From 852a8a97776a153be2e6c803218eced45f37a19c Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 30 Jul 2021 11:02:54 +0200 Subject: [PATCH 1121/1469] ALSA: pcm - fix mmap capability check for the snd-dummy driver The snd-dummy driver (fake_buffer configuration) uses the ops->page callback for the mmap operations. Allow mmap for this case, too. Cc: Fixes: c4824ae7db41 ("ALSA: pcm: Fix mmap capability check") Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20210730090254.612478-1-perex@perex.cz Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 6a2971a7e6a1..09c0e2a6489c 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -246,7 +246,7 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP)) return false; - if (substream->ops->mmap) + if (substream->ops->mmap || substream->ops->page) return true; switch (substream->dma_buffer.dev.type) { From 9bac1bd6e6d36459087a728a968e79e37ebcea1a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 30 Jul 2021 18:26:22 -0300 Subject: [PATCH 1122/1469] Revert "perf map: Fix dso->nsinfo refcounting" This makes 'perf top' abort in some cases, and the right fix will involve surgery that is too much to do at this stage, so revert for now and fix it in the next merge window. This reverts commit 2d6b74baa7147251c30a46c4996e8cc224aa2dc5. Cc: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Krister Johansen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 72e7f3616157..8af693d9678c 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -192,8 +192,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (!(prot & PROT_EXEC)) dso__set_loaded(dso); } - - nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; if (build_id__is_defined(bid)) From 3a34b13a88caeb2800ab44a4918f230041b37dd9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 30 Jul 2021 15:42:34 -0700 Subject: [PATCH 1123/1469] pipe: make pipe writes always wake up readers Since commit 1b6b26ae7053 ("pipe: fix and clarify pipe write wakeup logic") we have sanitized the pipe write logic, and would only try to wake up readers if they needed it. In particular, if the pipe already had data in it before the write, there was no point in trying to wake up a reader, since any existing readers must have been aware of the pre-existing data already. Doing extraneous wakeups will only cause potential thundering herd problems. However, it turns out that some Android libraries have misused the EPOLL interface, and expected "edge triggered" be to "any new write will trigger it". Even if there was no edge in sight. Quoting Sandeep Patil: "The commit 1b6b26ae7053 ('pipe: fix and clarify pipe write wakeup logic') changed pipe write logic to wakeup readers only if the pipe was empty at the time of write. However, there are libraries that relied upon the older behavior for notification scheme similar to what's described in [1] One such library 'realm-core'[2] is used by numerous Android applications. The library uses a similar notification mechanism as GNU Make but it never drains the pipe until it is full. When Android moved to v5.10 kernel, all applications using this library stopped working. The library has since been fixed[3] but it will be a while before all applications incorporate the updated library" Our regression rule for the kernel is that if applications break from new behavior, it's a regression, even if it was because the application did something patently wrong. Also note the original report [4] by Michal Kerrisk about a test for this epoll behavior - but at that point we didn't know of any actual broken use case. So add the extraneous wakeup, to approximate the old behavior. [ I say "approximate", because the exact old behavior was to do a wakeup not for each write(), but for each pipe buffer chunk that was filled in. The behavior introduced by this change is not that - this is just "every write will cause a wakeup, whether necessary or not", which seems to be sufficient for the broken library use. ] It's worth noting that this adds the extraneous wakeup only for the write side, while the read side still considers the "edge" to be purely about reading enough from the pipe to allow further writes. See commit f467a6a66419 ("pipe: fix and clarify pipe read wakeup logic") for the pipe read case, which remains that "only wake up if the pipe was full, and we read something from it". Link: https://lore.kernel.org/lkml/CAHk-=wjeG0q1vgzu4iJhW5juPkTsjTYmiqiMUYAebWW+0bam6w@mail.gmail.com/ [1] Link: https://github.com/realm/realm-core [2] Link: https://github.com/realm/realm-core/issues/4666 [3] Link: https://lore.kernel.org/lkml/CAKgNAkjMBGeAwF=2MKK758BhxvW58wYTgYKB2V-gY1PwXxrH+Q@mail.gmail.com/ [4] Link: https://lore.kernel.org/lkml/20210729222635.2937453-1-sspatil@android.com/ Reported-by: Sandeep Patil Cc: Michael Kerrisk Signed-off-by: Linus Torvalds --- fs/pipe.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index bfd946a9ad01..9ef4231cce61 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -429,20 +429,20 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) #endif /* - * Only wake up if the pipe started out empty, since - * otherwise there should be no readers waiting. + * Epoll nonsensically wants a wakeup whether the pipe + * was already empty or not. * * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also - * page-aligs the rest of the writes for large writes + * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; - was_empty = pipe_empty(head, pipe->tail); + was_empty = true; chars = total_len & (PAGE_SIZE-1); - if (chars && !was_empty) { + if (chars && !pipe_empty(head, pipe->tail)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; From ff41c28c4b54052942180d8b3f49e75f1445135a Mon Sep 17 00:00:00 2001 From: Kamal Agrawal Date: Fri, 30 Jul 2021 18:53:06 +0530 Subject: [PATCH 1124/1469] tracing: Fix NULL pointer dereference in start_creating The event_trace_add_tracer() can fail. In this case, it leads to a crash in start_creating with below call stack. Handle the error scenario properly in trace_array_create_dir. Call trace: down_write+0x7c/0x204 start_creating.25017+0x6c/0x194 tracefs_create_file+0xc4/0x2b4 init_tracer_tracefs+0x5c/0x940 trace_array_create_dir+0x58/0xb4 trace_array_create+0x1bc/0x2b8 trace_array_get_by_name+0xdc/0x18c Link: https://lkml.kernel.org/r/1627651386-21315-1-git-send-email-kamaagra@codeaurora.org Cc: stable@vger.kernel.org Fixes: 4114fbfd02f1 ("tracing: Enable creating new instance early boot") Signed-off-by: Kamal Agrawal Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c59dd35a6da5..33899a71fdc1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9135,8 +9135,10 @@ static int trace_array_create_dir(struct trace_array *tr) return -EINVAL; ret = event_trace_add_tracer(tr->dir, tr); - if (ret) + if (ret) { tracefs_remove(tr->dir); + return ret; + } init_tracer_tracefs(tr, tr->dir); __update_tracer_options(tr); From 567c39047dbee341244fe3bf79fea24ee0897ff9 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Mon, 5 Jul 2021 08:09:21 +0300 Subject: [PATCH 1125/1469] selftests/sgx: Fix Q1 and Q2 calculation in sigstruct.c Q1 and Q2 are numbers with *maximum* length of 384 bytes. If the calculated length of Q1 and Q2 is less than 384 bytes, things will go wrong. E.g. if Q2 is 383 bytes, then 1. The bytes of q2 are copied to sigstruct->q2 in calc_q1q2(). 2. The entire sigstruct->q2 is reversed, which results it being 256 * Q2, given that the last byte of sigstruct->q2 is added to before the bytes given by calc_q1q2(). Either change in key or measurement can trigger the bug. E.g. an unmeasured heap could cause a devastating change in Q1 or Q2. Reverse exactly the bytes of Q1 and Q2 in calc_q1q2() before returning to the caller. Fixes: 2adcba79e69d ("selftests/x86: Add a selftest for SGX") Link: https://lore.kernel.org/linux-sgx/20210301051836.30738-1-tianjia.zhang@linux.alibaba.com/ Signed-off-by: Tianjia Zhang Signed-off-by: Jarkko Sakkinen Signed-off-by: Shuah Khan --- tools/testing/selftests/sgx/sigstruct.c | 41 +++++++++++++------------ 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index dee7a3d6c5a5..92bbc5a15c39 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -55,10 +55,27 @@ static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, return true; } +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, uint8_t *q2) { struct q1q2_ctx ctx; + int len; if (!alloc_q1q2_ctx(s, m, &ctx)) { fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); @@ -89,8 +106,10 @@ static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, goto out; } - BN_bn2bin(ctx.q1, q1); - BN_bn2bin(ctx.q2, q2); + len = BN_bn2bin(ctx.q1, q1); + reverse_bytes(q1, len); + len = BN_bn2bin(ctx.q2, q2); + reverse_bytes(q2, len); free_q1q2_ctx(&ctx); return true; @@ -152,22 +171,6 @@ static RSA *gen_sign_key(void) return key; } -static void reverse_bytes(void *data, int length) -{ - int i = 0; - int j = length - 1; - uint8_t temp; - uint8_t *ptr = data; - - while (i < j) { - temp = ptr[i]; - ptr[i] = ptr[j]; - ptr[j] = temp; - i++; - j--; - } -} - enum mrtags { MRECREATE = 0x0045544145524345, MREADD = 0x0000000044444145, @@ -367,8 +370,6 @@ bool encl_measure(struct encl *encl) /* BE -> LE */ reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE); reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE); EVP_MD_CTX_destroy(ctx); RSA_free(key); From f828b0bcacef189edbd247e9f48864fc36bfbe33 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Jul 2021 19:59:50 -0700 Subject: [PATCH 1126/1469] clk: fix leak on devm_clk_bulk_get_all() unwind clk_bulk_get_all() allocates an array of struct clk_bulk data for us (unlike clk_bulk_get()), so we need to free it. Let's use the clk_bulk_put_all() helper. kmemleak complains, on an RK3399 Gru/Kevin system: unreferenced object 0xffffff80045def00 (size 128): comm "swapper/0", pid 1, jiffies 4294667682 (age 86.394s) hex dump (first 32 bytes): 44 32 60 fe fe ff ff ff 00 00 00 00 00 00 00 00 D2`............. 48 32 60 fe fe ff ff ff 00 00 00 00 00 00 00 00 H2`............. backtrace: [<00000000742860d6>] __kmalloc+0x22c/0x39c [<00000000b0493f2c>] clk_bulk_get_all+0x64/0x188 [<00000000325f5900>] devm_clk_bulk_get_all+0x58/0xa8 [<00000000175b9bc5>] dwc3_probe+0x8ac/0xb5c [<000000009169e2f9>] platform_drv_probe+0x9c/0xbc [<000000005c51e2ee>] really_probe+0x13c/0x378 [<00000000c47b1f24>] driver_probe_device+0x84/0xc0 [<00000000f870fcfb>] __device_attach_driver+0x94/0xb0 [<000000004d1b92ae>] bus_for_each_drv+0x8c/0xd8 [<00000000481d60c3>] __device_attach+0xc4/0x150 [<00000000a163bd36>] device_initial_probe+0x1c/0x28 [<00000000accb6bad>] bus_probe_device+0x3c/0x9c [<000000001a199f89>] device_add+0x218/0x3cc [<000000001bd84952>] of_device_add+0x40/0x50 [<000000009c658c29>] of_platform_device_create_pdata+0xac/0x100 [<0000000021c69ba4>] of_platform_bus_create+0x190/0x224 Fixes: f08c2e2865f6 ("clk: add managed version of clk_bulk_get_all") Cc: Dong Aisheng Cc: stable@vger.kernel.org Signed-off-by: Brian Norris Link: https://lore.kernel.org/r/20210731025950.2238582-1-briannorris@chromium.org Signed-off-by: Stephen Boyd --- drivers/clk/clk-devres.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index be160764911b..f9d5b7334341 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -92,13 +92,20 @@ int __must_check devm_clk_bulk_get_optional(struct device *dev, int num_clks, } EXPORT_SYMBOL_GPL(devm_clk_bulk_get_optional); +static void devm_clk_bulk_release_all(struct device *dev, void *res) +{ + struct clk_bulk_devres *devres = res; + + clk_bulk_put_all(devres->num_clks, devres->clks); +} + int __must_check devm_clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks) { struct clk_bulk_devres *devres; int ret; - devres = devres_alloc(devm_clk_bulk_release, + devres = devres_alloc(devm_clk_bulk_release_all, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; From 5afc1540f13804a31bb704b763308e17688369c5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 30 Jul 2021 08:16:51 +0100 Subject: [PATCH 1127/1469] iio: adc: Fix incorrect exit of for-loop Currently the for-loop that scans for the optimial adc_period iterates through all the possible adc_period levels because the exit logic in the loop is inverted. I believe the comparison should be swapped and the continue replaced with a break to exit the loop at the correct point. Addresses-Coverity: ("Continue has no effect") Fixes: e08e19c331fb ("iio:adc: add iio driver for Palmas (twl6035/7) gpadc") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20210730071651.17394-1-colin.king@canonical.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 6ef09609be9f..f9c8385c72d3 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -664,8 +664,8 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) adc_period = adc->auto_conversion_period; for (i = 0; i < 16; ++i) { - if (((1000 * (1 << i)) / 32) < adc_period) - continue; + if (((1000 * (1 << i)) / 32) >= adc_period) + break; } if (i > 0) i--; From c500bee1c5b2f1d59b1081ac879d73268ab0ff17 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 1 Aug 2021 17:04:17 -0700 Subject: [PATCH 1128/1469] Linux 5.14-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 6b555f64df06..27a072cffcb9 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Opossums on Parade # *DOCUMENTATION* From 7199ddede9f0f2f68d41e6928e1c6c4bca9c39c0 Mon Sep 17 00:00:00 2001 From: Juergen Borleis Date: Thu, 29 Jul 2021 09:18:21 +0200 Subject: [PATCH 1129/1469] dmaengine: imx-dma: configure the generic DMA type to make it work Commit dea7a9fbb009 ("dmaengine: imx-dma: remove dma_slave_config direction usage") changes the method from a "configuration when called" to an "configuration when used". Due to this, only the cyclic DMA type gets configured correctly, while the generic DMA type is left non-configured. Without this additional call, the struct imxdma_channel::word_size member is stuck at DMA_SLAVE_BUSWIDTH_UNDEFINED and imxdma_prep_slave_sg() always returns NULL. Signed-off-by: Juergen Borleis Fixes: dea7a9fbb009 ("dmaengine: imx-dma: remove dma_slave_config direction usage") Link: https://lore.kernel.org/r/20210729071821.9857-1-jbe@pengutronix.de Signed-off-by: Vinod Koul --- drivers/dma/imx-dma.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index 7f116bbcfad2..2ddc31e64db0 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -812,6 +812,8 @@ static struct dma_async_tx_descriptor *imxdma_prep_slave_sg( dma_length += sg_dma_len(sg); } + imxdma_config_write(chan, &imxdmac->config, direction); + switch (imxdmac->word_size) { case DMA_SLAVE_BUSWIDTH_4_BYTES: if (sg_dma_len(sgl) & 3 || sgl->dma_address & 3) From eda80d7c9c4db0f55f130e38c682e19b58d5add7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 1 Aug 2021 13:38:01 +0200 Subject: [PATCH 1130/1469] ALSA: memalloc: Fix regression with SNDRV_DMA_TYPE_CONTINUOUS The recent code refactoring made the mmap of continuous pages to be done via the own helper snd_dma_continuous_mmap() with remap_pfn_range(). There I overlooked that dmab->addr isn't set for the allocation with SNDRV_DMA_TYPE_CONTINUOUS. This resulted always in an error at mmap with this buffer type on the system such as Intel SST Baytrail driver. This patch fixes the regression by passing the correct address. Fixes: 30b7ba6972d5 ("ALSA: core: Add continuous and vmalloc mmap ops") Reported-by: Hans de Goede Link: https://lore.kernel.org/r/8d6674da-7d7b-803e-acc9-7de6cb1223fa@redhat.com Link: https://lore.kernel.org/r/20210801113801.31290-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/memalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 83b79edfa52d..439a358ecfe9 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -215,7 +215,7 @@ static int snd_dma_continuous_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return remap_pfn_range(area, area->vm_start, - dmab->addr >> PAGE_SHIFT, + page_to_pfn(virt_to_page(dmab->area)), area->vm_end - area->vm_start, area->vm_page_prot); } From 1159e25c137422bdc48ee96e3fb014bd942092c6 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Thu, 29 Jul 2021 14:43:06 +0300 Subject: [PATCH 1131/1469] qede: fix crash in rmmod qede while automatic debug collection A crash has been observed if rmmod is done while automatic debug collection in progress. It is due to a race condition between both of them. To fix stop the sp_task during unload to avoid running qede_sp_task even if they are schedule during removal process. Signed-off-by: Alok Prasad Signed-off-by: Shai Malin Signed-off-by: Ariel Elior Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qede/qede.h | 1 + drivers/net/ethernet/qlogic/qede/qede_main.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 2e62a2c4eb63..5630008f38b7 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -501,6 +501,7 @@ struct qede_fastpath { #define QEDE_SP_HW_ERR 4 #define QEDE_SP_ARFS_CONFIG 5 #define QEDE_SP_AER 7 +#define QEDE_SP_DISABLE 8 #ifdef CONFIG_RFS_ACCEL int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 01ac1e93d27a..7c6064baeba2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1009,6 +1009,13 @@ static void qede_sp_task(struct work_struct *work) struct qede_dev *edev = container_of(work, struct qede_dev, sp_task.work); + /* Disable execution of this deferred work once + * qede removal is in progress, this stop any future + * scheduling of sp_task. + */ + if (test_bit(QEDE_SP_DISABLE, &edev->sp_flags)) + return; + /* The locking scheme depends on the specific flag: * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to * ensure that ongoing flows are ended and new ones are not started. @@ -1300,6 +1307,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY)); if (mode != QEDE_REMOVE_RECOVERY) { + set_bit(QEDE_SP_DISABLE, &edev->sp_flags); unregister_netdev(ndev); cancel_delayed_work_sync(&edev->sp_task); From d51c5907e9809a803b276883d203f45849abd4d6 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 29 Jul 2021 15:48:20 +0200 Subject: [PATCH 1132/1469] net, gro: Set inner transport header offset in tcp/udp GRO hook GSO expects inner transport header offset to be valid when skb->encapsulation flag is set. GSO uses this value to calculate the length of an individual segment of a GSO packet in skb_gso_transport_seglen(). However, tcp/udp gro_complete callbacks don't update the skb->inner_transport_header when processing an encapsulated TCP/UDP segment. As a result a GRO skb has ->inner_transport_header set to a value carried over from earlier skb processing. This can have mild to tragic consequences. From miscalculating the GSO segment length to triggering a page fault [1], when trying to read TCP/UDP header at an address past the skb->data page. The latter scenario leads to an oops report like so: BUG: unable to handle page fault for address: ffff9fa7ec00d008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 123f201067 P4D 123f201067 PUD 123f209067 PMD 0 Oops: 0000 [#1] SMP NOPTI CPU: 44 PID: 0 Comm: swapper/44 Not tainted 5.4.53-cloudflare-2020.7.21 #1 Hardware name: HYVE EDGE-METAL-GEN10/HS-1811DLite1, BIOS V2.15 02/21/2020 RIP: 0010:skb_gso_transport_seglen+0x44/0xa0 Code: c0 41 83 e0 11 f6 87 81 00 00 00 20 74 30 0f b7 87 aa 00 00 00 0f [...] RSP: 0018:ffffad8640bacbb8 EFLAGS: 00010202 RAX: 000000000000feda RBX: ffff9fcc8d31bc00 RCX: ffff9fa7ec00cffc RDX: ffff9fa7ebffdec0 RSI: 000000000000feda RDI: 0000000000000122 RBP: 00000000000005c4 R08: 0000000000000001 R09: 0000000000000000 R10: ffff9fe588ae3800 R11: ffff9fe011fc92f0 R12: ffff9fcc8d31bc00 R13: ffff9fe0119d4300 R14: 00000000000005c4 R15: ffff9fba57d70900 FS: 0000000000000000(0000) GS:ffff9fe68df00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff9fa7ec00d008 CR3: 0000003e99b1c000 CR4: 0000000000340ee0 Call Trace: skb_gso_validate_network_len+0x11/0x70 __ip_finish_output+0x109/0x1c0 ip_sublist_rcv_finish+0x57/0x70 ip_sublist_rcv+0x2aa/0x2d0 ? ip_rcv_finish_core.constprop.0+0x390/0x390 ip_list_rcv+0x12b/0x14f __netif_receive_skb_list_core+0x2a9/0x2d0 netif_receive_skb_list_internal+0x1b5/0x2e0 napi_complete_done+0x93/0x140 veth_poll+0xc0/0x19f [veth] ? mlx5e_napi_poll+0x221/0x610 [mlx5_core] net_rx_action+0x1f8/0x790 __do_softirq+0xe1/0x2bf irq_exit+0x8e/0xc0 do_IRQ+0x58/0xe0 common_interrupt+0xf/0xf The bug can be observed in a simple setup where we send IP/GRE/IP/TCP packets into a netns over a veth pair. Inside the netns, packets are forwarded to dummy device: trafgen -> [veth A]--[veth B] -forward-> [dummy] For veth B to GRO aggregate packets on receive, it needs to have an XDP program attached (for example, a trivial XDP_PASS). Additionally, for UDP, we need to enable GSO_UDP_L4 feature on the device: ip netns exec A ethtool -K AB rx-udp-gro-forwarding on The last component is an artificial delay to increase the chances of GRO batching happening: ip netns exec A tc qdisc add dev AB root \ netem delay 200us slot 5ms 10ms packets 2 bytes 64k With such a setup in place, the bug can be observed by tracing the skb outer and inner offsets when GSO skb is transmitted from the dummy device: tcp: FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE ip_finish_output dumB 2830 270 290 1 294 254 1383 (tcpv4,gre,) ^^^ udp: FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE ip_finish_output dumB 2818 270 290 1 294 254 1383 (gre,udp_l4,) ^^^ Fix it by updating the inner transport header offset in tcp/udp gro_complete callbacks, similar to how {inet,ipv6}_gro_complete callbacks update the inner network header offset, when skb->encapsulation flag is set. [1] https://lore.kernel.org/netdev/CAKxSbF01cLpZem2GFaUaifh0S-5WYViZemTicAg7FCHOnh6kug@mail.gmail.com/ Fixes: bf296b125b21 ("tcp: Add GRO support") Fixes: f993bc25e519 ("net: core: handle encapsulation offloads when computing segment lengths") Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Reported-by: Alex Forster Signed-off-by: Jakub Sitnicki Signed-off-by: David S. Miller --- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index e09147ac9a99..fc61cd3fea65 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -298,6 +298,9 @@ int tcp_gro_complete(struct sk_buff *skb) if (th->cwr) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } EXPORT_SYMBOL(tcp_gro_complete); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 9dde1e5fb449..1380a6b6f4ff 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -624,6 +624,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb) skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } From 85b1ebfea2b0d8797266bcc6f04b6cc87e38290a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 30 Jul 2021 08:54:08 +0100 Subject: [PATCH 1133/1469] interconnect: Fix undersized devress_alloc allocation The expression sizeof(**ptr) for the void **ptr is just 1 rather than the size of a pointer. Fix this by using sizeof(*ptr). Addresses-Coverity: ("Wrong sizeof argument") Fixes: e145d9a184f2 ("interconnect: Add devm_of_icc_get() as exported API for users") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20210730075408.19945-1-colin.king@canonical.com Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 1b2c564eaa99..7887941730db 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -403,7 +403,7 @@ struct icc_path *devm_of_icc_get(struct device *dev, const char *name) { struct icc_path **ptr, *path; - ptr = devres_alloc(devm_icc_release, sizeof(**ptr), GFP_KERNEL); + ptr = devres_alloc(devm_icc_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); From ebca25ead0711729e0aeeec45062e7ac4df3e158 Mon Sep 17 00:00:00 2001 From: Yannick Vignon Date: Fri, 30 Jul 2021 18:53:21 +0200 Subject: [PATCH 1134/1469] net/sched: taprio: Fix init procedure Commit 13511704f8d759 ("net: taprio offload: enforce qdisc to netdev queue mapping") resulted in duplicate entries in the qdisc hash. While this did not impact the overall operation of the qdisc and taprio code paths, it did result in an infinite loop when dumping the qdisc properties, at least on one target (NXP LS1028 ARDB). Removing the duplicate call to qdisc_hash_add() solves the problem. Fixes: 13511704f8d759 ("net: taprio offload: enforce qdisc to netdev queue mapping") Signed-off-by: Yannick Vignon Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 07b30d0601d7..9c79374457a0 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1739,8 +1739,6 @@ static void taprio_attach(struct Qdisc *sch) if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); - if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc, false); } else { old = dev_graft_qdisc(qdisc->dev_queue, sch); qdisc_refcount_inc(sch); From 8b5d95313b6d30f642e4ed0125891984c446604e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 31 Jul 2021 10:43:31 +0200 Subject: [PATCH 1135/1469] ASoC: amd: Fix reference to PCM buffer address PCM buffers might be allocated dynamically when the buffer preallocation failed or a larger buffer is requested, and it's not guaranteed that substream->dma_buffer points to the actually used buffer. The driver needs to refer to substream->runtime->dma_addr instead for the buffer address. Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20210731084331.32225-1-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/amd/acp-pcm-dma.c | 2 +- sound/soc/amd/raven/acp3x-pcm-dma.c | 2 +- sound/soc/amd/renoir/acp3x-pdm-dma.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index 143155a840ac..cc1ce6f22caa 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -969,7 +969,7 @@ static int acp_dma_hw_params(struct snd_soc_component *component, acp_set_sram_bank_state(rtd->acp_mmio, 0, true); /* Save for runtime private data */ - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = runtime->dma_addr; rtd->order = get_order(size); /* Fill the page table entries in ACP SRAM */ diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index 8148b0d22e88..597d7c4b2a6b 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -286,7 +286,7 @@ static int acp3x_dma_hw_params(struct snd_soc_component *component, pr_err("pinfo failed\n"); } size = params_buffer_bytes(params); - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = substream->runtime->dma_addr; rtd->num_pages = (PAGE_ALIGN(size) >> PAGE_SHIFT); config_acp3x_dma(rtd, substream->stream); return 0; diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index bd20622b0933..0391c28dd078 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -242,7 +242,7 @@ static int acp_pdm_dma_hw_params(struct snd_soc_component *component, return -EINVAL; size = params_buffer_bytes(params); period_bytes = params_period_bytes(params); - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = substream->runtime->dma_addr; rtd->num_pages = (PAGE_ALIGN(size) >> PAGE_SHIFT); config_acp_dma(rtd, substream->stream); init_pdm_ring_buffer(MEM_WINDOW_START, size, period_bytes, From 0d5c3954b35eddff0da0436c31e8d721eceb7dc2 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 1 Aug 2021 20:00:23 -0700 Subject: [PATCH 1136/1469] spi: mediatek: Fix fifo transfer Commit 3a70dd2d0503 ("spi: mediatek: fix fifo rx mode") claims that fifo RX mode was never handled, and adds the presumably missing code to the FIFO transfer function. However, the claim that receive data was not handled is incorrect. It was handled as part of interrupt handling after the transfer was complete. The code added with the above mentioned commit reads data from the receive FIFO before the transfer is started, which is wrong. This results in an actual transfer error on a Hayato Chromebook. Remove the code trying to handle receive data before the transfer is started to fix the problem. Fixes: 3a70dd2d0503 ("spi: mediatek: fix fifo rx mode") Cc: Peter Hess Cc: Frank Wunderlich Cc: Tzung-Bi Shih Cc: Hsin-Yi Wang Signed-off-by: Guenter Roeck Tested-by: Hsin-Yi Wang Tested-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20210802030023.1748777-1-linux@roeck-us.net Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 68dca8ceb3ad..7914255521c3 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -426,24 +426,15 @@ static int mtk_spi_fifo_transfer(struct spi_master *master, mtk_spi_prepare_transfer(master, xfer); mtk_spi_setup_packet(master); - cnt = xfer->len / 4; - if (xfer->tx_buf) + if (xfer->tx_buf) { + cnt = xfer->len / 4; iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt); - - if (xfer->rx_buf) - ioread32_rep(mdata->base + SPI_RX_DATA_REG, xfer->rx_buf, cnt); - - remainder = xfer->len % 4; - if (remainder > 0) { - reg_val = 0; - if (xfer->tx_buf) { + remainder = xfer->len % 4; + if (remainder > 0) { + reg_val = 0; memcpy(®_val, xfer->tx_buf + (cnt * 4), remainder); writel(reg_val, mdata->base + SPI_TX_DATA_REG); } - if (xfer->rx_buf) { - reg_val = readl(mdata->base + SPI_RX_DATA_REG); - memcpy(xfer->rx_buf + (cnt * 4), ®_val, remainder); - } } mtk_spi_enable_transfer(master); From 40e159403896f7d55c98f858d0b20fee1d941fa4 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Aug 2021 12:21:30 +0100 Subject: [PATCH 1137/1469] mhi: Fix networking tree build. Signed-off-by: David S. Miller --- include/linux/mhi.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..5e08468854db 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,8 +719,13 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, + unsigned int flags); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. From 47091f473b364c98207c4def197a0ae386fc9af1 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Sat, 26 Jun 2021 02:01:03 +0200 Subject: [PATCH 1138/1469] ARM: dts: nomadik: Fix up interrupt controller node names Once the new schema interrupt-controller/arm,vic.yaml is added, we get the below warnings: arch/arm/boot/dts/ste-nomadik-nhk15.dt.yaml: intc@10140000: $nodename:0: 'intc@10140000' does not match '^interrupt-controller(@[0-9a-f,]+)*$' Fix the node names for the interrupt controller to conform to the standard node name interrupt-controller@.. Signed-off-by: Sudeep Holla Signed-off-by: Linus Walleij Cc: Linus Walleij Link: https://lore.kernel.org/r/20210617210825.3064367-2-sudeep.holla@arm.com Link: https://lore.kernel.org/r/20210626000103.830184-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/ste-nomadik-stn8815.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index c9b906432341..1815361fe73c 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -755,14 +755,14 @@ status = "disabled"; }; - vica: intc@10140000 { + vica: interrupt-controller@10140000 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; reg = <0x10140000 0x20>; }; - vicb: intc@10140020 { + vicb: interrupt-controller@10140020 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; From a4282f66d90e93aacfe1b19509fd5851bf95be68 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 22 Jul 2021 02:26:16 +0300 Subject: [PATCH 1139/1469] soc/tegra: Make regulator couplers depend on CONFIG_REGULATOR The regulator coupler drivers now use regulator-driver API function that isn't available during compile-testing. Make regulator coupler drivers dependent on CONFIG_REGULATOR in Kconfig. Fixes: 03978d42ed0d ("soc/tegra: regulators: Bump voltages on system reboot") Reported-by: kernel test robot Signed-off-by: Dmitry Osipenko Acked-by: Jon Hunter Signed-off-by: Arnd Bergmann --- drivers/soc/tegra/Kconfig | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/soc/tegra/Kconfig b/drivers/soc/tegra/Kconfig index 20ace654553a..8b53ed1cc67e 100644 --- a/drivers/soc/tegra/Kconfig +++ b/drivers/soc/tegra/Kconfig @@ -15,7 +15,7 @@ config ARCH_TEGRA_2x_SOC select PL310_ERRATA_769419 if CACHE_L2X0 select SOC_TEGRA_FLOWCTRL select SOC_TEGRA_PMC - select SOC_TEGRA20_VOLTAGE_COUPLER + select SOC_TEGRA20_VOLTAGE_COUPLER if REGULATOR select TEGRA_TIMER help Support for NVIDIA Tegra AP20 and T20 processors, based on the @@ -29,7 +29,7 @@ config ARCH_TEGRA_3x_SOC select PL310_ERRATA_769419 if CACHE_L2X0 select SOC_TEGRA_FLOWCTRL select SOC_TEGRA_PMC - select SOC_TEGRA30_VOLTAGE_COUPLER + select SOC_TEGRA30_VOLTAGE_COUPLER if REGULATOR select TEGRA_TIMER help Support for NVIDIA Tegra T30 processor family, based on the @@ -155,7 +155,9 @@ config SOC_TEGRA_POWERGATE_BPMP config SOC_TEGRA20_VOLTAGE_COUPLER bool "Voltage scaling support for Tegra20 SoCs" depends on ARCH_TEGRA_2x_SOC || COMPILE_TEST + depends on REGULATOR config SOC_TEGRA30_VOLTAGE_COUPLER bool "Voltage scaling support for Tegra30 SoCs" depends on ARCH_TEGRA_3x_SOC || COMPILE_TEST + depends on REGULATOR From 7f94b69ece515ac82defa60ef7cba2cf26180216 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 23:13:43 +0200 Subject: [PATCH 1140/1469] ARM: ixp4xx: fix compile-testing soc drivers Randconfig builds on the ixp4xx ethernet driver showed that the qmgr and npe drivers are not actually built even when compile testing is enabled: ERROR: modpost: "qmgr_stat_empty" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "qmgr_enable_irq" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "qmgr_set_irq" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "__qmgr_request_queue" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "npe_send_recv_message" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "npe_recv_message" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "npe_load_firmware" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "npe_running" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "qmgr_disable_irq" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! ERROR: modpost: "qmgr_stat_below_low_watermark" [drivers/net/ethernet/xscale/ixp4xx_eth.ko] undefined! Fix it by always entering the drivers/soc/ixp4xx/ directory, and fix the resulting compile test failures by removing the #include statements that prevent building on most other platforms. Fixes: 7a6c9dbb36a4 ("soc: ixp4xx: Protect IXP4xx SoC drivers by ARCH_IXP4XX || COMPILE_TEST") Fixes: fcf2d8978cd5 ("ARM: ixp4xx: Move NPE and QMGR to drivers/soc") Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210721211412.3537004-1-arnd@kernel.org' Signed-off-by: Arnd Bergmann --- drivers/soc/Makefile | 2 +- drivers/soc/ixp4xx/ixp4xx-npe.c | 1 - drivers/soc/ixp4xx/ixp4xx-qmgr.c | 1 - 3 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile index f678e4d9e585..a05e9fbcd3e0 100644 --- a/drivers/soc/Makefile +++ b/drivers/soc/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_MACH_DOVE) += dove/ obj-y += fsl/ obj-$(CONFIG_ARCH_GEMINI) += gemini/ obj-y += imx/ -obj-$(CONFIG_ARCH_IXP4XX) += ixp4xx/ +obj-y += ixp4xx/ obj-$(CONFIG_SOC_XWAY) += lantiq/ obj-$(CONFIG_LITEX_SOC_CONTROLLER) += litex/ obj-y += mediatek/ diff --git a/drivers/soc/ixp4xx/ixp4xx-npe.c b/drivers/soc/ixp4xx/ixp4xx-npe.c index 7bd19354982a..fea50e04d5a1 100644 --- a/drivers/soc/ixp4xx/ixp4xx-npe.c +++ b/drivers/soc/ixp4xx/ixp4xx-npe.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #define DEBUG_MSG 0 diff --git a/drivers/soc/ixp4xx/ixp4xx-qmgr.c b/drivers/soc/ixp4xx/ixp4xx-qmgr.c index 7149510b307e..c6bf6ef257c0 100644 --- a/drivers/soc/ixp4xx/ixp4xx-qmgr.c +++ b/drivers/soc/ixp4xx/ixp4xx-qmgr.c @@ -12,7 +12,6 @@ #include #include #include -#include #include static struct qmgr_regs __iomem *qmgr_regs; From 796a8c85b1216618258e08b463d3bef0d7123760 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Jul 2021 17:16:04 +0200 Subject: [PATCH 1141/1469] ARM: ixp4xx: goramo_mlr depends on old PCI driver When this driver is disabled, the board file fails to build, so add a dependency: arch/arm/mach-ixp4xx/goramo_mlr.c: In function 'gmlr_pci_preinit': arch/arm/mach-ixp4xx/goramo_mlr.c:472:9: error: implicit declaration of function 'ixp4xx_pci_preinit'; did you mean 'iop3xx_pci_preinit'? [-Werror=implicit-function-declaration] 472 | ixp4xx_pci_preinit(); | ^~~~~~~~~~~~~~~~~~ | iop3xx_pci_preinit arch/arm/mach-ixp4xx/goramo_mlr.c: In function 'gmlr_pci_postinit': arch/arm/mach-ixp4xx/goramo_mlr.c:481:22: error: implicit declaration of function 'ixp4xx_pci_read' [-Werror=implicit-function-declaration] 481 | if (!ixp4xx_pci_read(addr, NP_CMD_CONFIGREAD, &value)) { | ^~~~~~~~~~~~~~~ arch/arm/mach-ixp4xx/goramo_mlr.c:231:35: error: 'IXP4XX_UART1_BASE_PHYS' undeclared here (not in a function) 231 | .start = IXP4XX_UART1_BASE_PHYS, | ^~~~~~~~~~~~~~~~~~~~~~ arch/arm/mach-ixp4xx/goramo_mlr.c: In function 'gmlr_init': arch/arm/mach-ixp4xx/goramo_mlr.c:376:9: error: implicit declaration of function 'ixp4xx_sys_init' [-Werror=implicit-function-declaration] 376 | ixp4xx_sys_init(); | ^~~~~~~~~~~~~~~ Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Cc: Linus Walleij Cc: soc@kernel.org Link: https://lore.kernel.org/r/20210721151620.2373500-1-arnd@kernel.org' Signed-off-by: Arnd Bergmann --- arch/arm/mach-ixp4xx/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig index bf14d65120b9..34a1c7742088 100644 --- a/arch/arm/mach-ixp4xx/Kconfig +++ b/arch/arm/mach-ixp4xx/Kconfig @@ -91,6 +91,7 @@ config MACH_IXDP465 config MACH_GORAMO_MLR bool "GORAMO Multi Link Router" + depends on IXP4XX_PCI_LEGACY help Say 'Y' here if you want your kernel to support GORAMO MultiLink router. From cb81698fddbcc9a3ee75857e99dfc29caa96135b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:10 +0300 Subject: [PATCH 1142/1469] net: dsa: sja1105: fix static FDB writes for SJA1110 The blamed commit made FDB access on SJA1110 functional only as far as dumping the existing entries goes, but anything having to do with an entry's index (adding, deleting) is still broken. There are in fact 2 problems, all caused by improperly inheriting the code from SJA1105P/Q/R/S: - An entry size is SJA1110_SIZE_L2_LOOKUP_ENTRY (24) bytes and not SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY (20) bytes - The "index" field within an FDB entry is at bits 10:1 for SJA1110 and not 15:6 as in SJA1105P/Q/R/S This patch moves the packing function for the cmd->index outside of sja1105pqrs_common_l2_lookup_cmd_packing() and into the device specific functions sja1105pqrs_l2_lookup_cmd_packing and sja1110_l2_lookup_cmd_packing. Fixes: 74e7feff0e22 ("net: dsa: sja1105: fix dynamic access to L2 Address Lookup table for SJA1110") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/dsa/sja1105/sja1105_dynamic_config.c | 27 ++++++++++--------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 56fead68ea9f..147709131c13 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -304,6 +304,15 @@ sja1105pqrs_common_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, hostcmd = SJA1105_HOSTCMD_INVALIDATE; } sja1105_packing(p, &hostcmd, 25, 23, size, op); +} + +static void +sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + int entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + + sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size); /* Hack - The hardware takes the 'index' field within * struct sja1105_l2_lookup_entry as the index on which this command @@ -313,26 +322,18 @@ sja1105pqrs_common_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, * such that our API doesn't need to ask for a full-blown entry * structure when e.g. a delete is requested. */ - sja1105_packing(buf, &cmd->index, 15, 6, - SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op); -} - -static void -sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, - enum packing_op op) -{ - int size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; - - return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size); + sja1105_packing(buf, &cmd->index, 15, 6, entry_size, op); } static void sja1110_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) { - int size = SJA1110_SIZE_L2_LOOKUP_ENTRY; + int entry_size = SJA1110_SIZE_L2_LOOKUP_ENTRY; - return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size); + sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size); + + sja1105_packing(buf, &cmd->index, 10, 1, entry_size, op); } /* The switch is so retarded that it makes our command/entry abstraction From e11e865bf84e3c6ea91563ff3e858cfe0e184bd2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:11 +0300 Subject: [PATCH 1143/1469] net: dsa: sja1105: overwrite dynamic FDB entries with static ones in .port_fdb_add The SJA1105 switch family leaves it up to software to decide where within the FDB to install a static entry, and to concatenate destination ports for already existing entries (the FDB is also used for multicast entries), it is not as simple as just saying "please add this entry". This means we first need to search for an existing FDB entry before adding a new one. The driver currently manages to fool itself into thinking that if an FDB entry already exists, there is nothing to be done. But that FDB entry might be dynamically learned, case in which it should be replaced with a static entry, but instead it is left alone. This patch checks the LOCKEDS ("locked/static") bit from found FDB entries, and lets the code "goto skip_finding_an_index;" if the FDB entry was not static. So we also need to move the place where we set LOCKEDS = true, to cover the new case where a dynamic FDB entry existed but was dynamic. Fixes: 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management") Fixes: 1da73821343c ("net: dsa: sja1105: Add FDB operations for P/Q/R/S series") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index e2dc997580a8..cc4a22ee1474 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1333,7 +1333,7 @@ int sja1105et_fdb_add(struct dsa_switch *ds, int port, * mask? If yes, we need to do nothing. If not, we need * to rewrite the entry by adding this port to it. */ - if (l2_lookup.destports & BIT(port)) + if ((l2_lookup.destports & BIT(port)) && l2_lookup.lockeds) return 0; l2_lookup.destports |= BIT(port); } else { @@ -1364,6 +1364,7 @@ int sja1105et_fdb_add(struct dsa_switch *ds, int port, index, NULL, false); } } + l2_lookup.lockeds = true; l2_lookup.index = sja1105et_fdb_index(bin, way); rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, @@ -1434,10 +1435,10 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, SJA1105_SEARCH, &l2_lookup); if (rc == 0) { - /* Found and this port is already in the entry's + /* Found a static entry and this port is already in the entry's * port mask => job done */ - if (l2_lookup.destports & BIT(port)) + if ((l2_lookup.destports & BIT(port)) && l2_lookup.lockeds) return 0; /* l2_lookup.index is populated by the switch in case it * found something. @@ -1460,10 +1461,11 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, dev_err(ds->dev, "FDB is full, cannot add entry.\n"); return -EINVAL; } - l2_lookup.lockeds = true; l2_lookup.index = i; skip_finding_an_index: + l2_lookup.lockeds = true; + rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, l2_lookup.index, &l2_lookup, true); From 6c5fc159e0927531707895709eee1f8bfa04289f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:12 +0300 Subject: [PATCH 1144/1469] net: dsa: sja1105: invalidate dynamic FDB entries learned concurrently with statically added ones The procedure to add a static FDB entry in sja1105 is concurrent with dynamic learning performed on all bridge ports and the CPU port. The switch looks up the FDB from left to right, and also learns dynamically from left to right, so it is possible that between the moment when we pick up a free slot to install an FDB entry, another slot to the left of that one becomes free due to an address ageing out, and that other slot is then immediately used by the switch to learn dynamically the same address as we're trying to add statically. The result is that we succeeded to add our static FDB entry, but it is being shadowed by a dynamic FDB entry to its left, and the switch will behave as if our static FDB entry did not exist. We cannot really prevent this from happening unless we make the entire process to add a static FDB entry a huge critical section where address learning is temporarily disabled on _all_ ports, and then re-enabled according to the configuration done by sja1105_port_set_learning. However, that is kind of disruptive for the operation of the network. What we can do alternatively is to simply read back the FDB for dynamic entries located before our newly added static one, and delete them. This will guarantee that our static FDB entry is now operational. It will still not guarantee that there aren't dynamic FDB entries to the _right_ of that static FDB entry, but at least those entries will age out by themselves since they aren't hit, and won't bother anyone. Fixes: 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management") Fixes: 1da73821343c ("net: dsa: sja1105: Add FDB operations for P/Q/R/S series") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 57 +++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index cc4a22ee1474..5a4c7789ca43 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1318,10 +1318,11 @@ static int sja1105et_is_fdb_entry_in_bin(struct sja1105_private *priv, int bin, int sja1105et_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { - struct sja1105_l2_lookup_entry l2_lookup = {0}; + struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp; struct sja1105_private *priv = ds->priv; struct device *dev = ds->dev; int last_unused = -1; + int start, end, i; int bin, way, rc; bin = sja1105et_fdb_hash(priv, addr, vid); @@ -1373,6 +1374,29 @@ int sja1105et_fdb_add(struct dsa_switch *ds, int port, if (rc < 0) return rc; + /* Invalidate a dynamically learned entry if that exists */ + start = sja1105et_fdb_index(bin, 0); + end = sja1105et_fdb_index(bin, way); + + for (i = start; i < end; i++) { + rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, + i, &tmp); + if (rc == -ENOENT) + continue; + if (rc) + return rc; + + if (tmp.macaddr != ether_addr_to_u64(addr) || tmp.vlanid != vid) + continue; + + rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, + i, NULL, false); + if (rc) + return rc; + + break; + } + return sja1105_static_fdb_change(priv, port, &l2_lookup, true); } @@ -1414,7 +1438,7 @@ int sja1105et_fdb_del(struct dsa_switch *ds, int port, int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { - struct sja1105_l2_lookup_entry l2_lookup = {0}; + struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp; struct sja1105_private *priv = ds->priv; int rc, i; @@ -1472,6 +1496,35 @@ skip_finding_an_index: if (rc < 0) return rc; + /* The switch learns dynamic entries and looks up the FDB left to + * right. It is possible that our addition was concurrent with the + * dynamic learning of the same address, so now that the static entry + * has been installed, we are certain that address learning for this + * particular address has been turned off, so the dynamic entry either + * is in the FDB at an index smaller than the static one, or isn't (it + * can also be at a larger index, but in that case it is inactive + * because the static FDB entry will match first, and the dynamic one + * will eventually age out). Search for a dynamically learned address + * prior to our static one and invalidate it. + */ + tmp = l2_lookup; + + rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, + SJA1105_SEARCH, &tmp); + if (rc < 0) { + dev_err(ds->dev, + "port %d failed to read back entry for %pM vid %d: %pe\n", + port, addr, vid, ERR_PTR(rc)); + return rc; + } + + if (tmp.index < l2_lookup.index) { + rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, + tmp.index, NULL, false); + if (rc < 0) + return rc; + } + return sja1105_static_fdb_change(priv, port, &l2_lookup, true); } From 728db843df88753aeb7224314807a203afa8eb32 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:13 +0300 Subject: [PATCH 1145/1469] net: dsa: sja1105: ignore the FDB entry for unknown multicast when adding a new address Currently, when sja1105pqrs_fdb_add() is called for a host-joined IPv6 MDB entry such as 33:33:00:00:00:6a, the search for that address will return the FDB entry for SJA1105_UNKNOWN_MULTICAST, which has a destination MAC of 01:00:00:00:00:00 and a mask of 01:00:00:00:00:00. It returns that entry because, well, it matches, in the sense that unknown multicast is supposed by design to match it... But the issue is that we then proceed to overwrite this entry with the one for our precise host-joined multicast address, and the unknown multicast entry is no longer there - unknown multicast is now flooded to the same group of ports as broadcast, which does not look up the FDB. To solve this problem, we should ignore searches that return the unknown multicast address as the match, and treat them as "no match" which will result in the entry being installed to hardware. For this to work properly, we need to put the result of the FDB search in a temporary variable in order to avoid overwriting the l2_lookup entry we want to program. The l2_lookup entry returned by the search might not have the same set of DESTPORTS and not even the same MACADDR as the entry we're trying to add. Fixes: 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to device") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 5a4c7789ca43..5d8739b30d8c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1456,14 +1456,19 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, } l2_lookup.destports = BIT(port); + tmp = l2_lookup; + rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, - SJA1105_SEARCH, &l2_lookup); - if (rc == 0) { + SJA1105_SEARCH, &tmp); + if (rc == 0 && tmp.index != SJA1105_MAX_L2_LOOKUP_COUNT - 1) { /* Found a static entry and this port is already in the entry's * port mask => job done */ - if ((l2_lookup.destports & BIT(port)) && l2_lookup.lockeds) + if ((tmp.destports & BIT(port)) && tmp.lockeds) return 0; + + l2_lookup = tmp; + /* l2_lookup.index is populated by the switch in case it * found something. */ From 589918df93226a1e5f104306c185b6dcf2bd8051 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:14 +0300 Subject: [PATCH 1146/1469] net: dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too Similar but not quite the same with what was done in commit b11f0a4c0c81 ("net: dsa: sja1105: be stateless when installing FDB entries") for SJA1105E/T, it is desirable to drop the priv->vlan_aware check and simply go ahead and install FDB entries in the VLAN that was given by the bridge. As opposed to SJA1105E/T, in SJA1105P/Q/R/S and SJA1110, the FDB is a maskable TCAM, and we are installing VLAN-unaware FDB entries with the VLAN ID masked off. However, such FDB entries might completely obscure VLAN-aware entries where the VLAN ID is included in the search mask, because the switch looks up the FDB from left to right and picks the first entry which results in a masked match. So it depends on whether the bridge installs first the VLAN-unaware or the VLAN-aware FDB entries. Anyway, if we had a VLAN-unaware FDB entry towards one set of DESTPORTS and a VLAN-aware one towards other set of DESTPORTS, the result is that the packets in VLAN-aware mode will be forwarded towards the DESTPORTS specified by the VLAN-unaware entry. To solve this, simply do not use the masked matching ability of the FDB for VLAN ID, and always match precisely on it. In VLAN-unaware mode, we configure the switch for shared VLAN learning, so the VLAN ID will be ignored anyway during lookup, so it is redundant to mask it off in the TCAM. This patch conflicts with net-next commit 0fac6aa098ed ("net: dsa: sja1105: delete the best_effort_vlan_filtering mode") which changed this line: if (priv->vlan_state != SJA1105_VLAN_UNAWARE) { into: if (priv->vlan_aware) { When merging with net-next, the lines added by this patch should take precedence in the conflict resolution (i.e. the "if" condition should be deleted in both cases). Fixes: 1da73821343c ("net: dsa: sja1105: Add FDB operations for P/Q/R/S series") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 5d8739b30d8c..335b608bad11 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1447,13 +1447,8 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - if (priv->vlan_state != SJA1105_VLAN_UNAWARE) { - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); - } else { - l2_lookup.mask_vlanid = 0; - l2_lookup.mask_iotag = 0; - } + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); l2_lookup.destports = BIT(port); tmp = l2_lookup; @@ -1545,13 +1540,8 @@ int sja1105pqrs_fdb_del(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - if (priv->vlan_state != SJA1105_VLAN_UNAWARE) { - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); - } else { - l2_lookup.mask_vlanid = 0; - l2_lookup.mask_iotag = 0; - } + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, From 47c2c0c2312118a478f738503781de1d1a6020d2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jul 2021 20:18:15 +0300 Subject: [PATCH 1147/1469] net: dsa: sja1105: match FDB entries regardless of inner/outer VLAN tag On SJA1105P/Q/R/S and SJA1110, the L2 Lookup Table entries contain a maskable "inner/outer tag" bit which means: - when set to 1: match single-outer and double tagged frames - when set to 0: match untagged and single-inner tagged frames - when masked off: match all frames regardless of the type of tag This driver does not make any meaningful distinction between inner tags (matches on TPID) and outer tags (matches on TPID2). In fact, all VLAN table entries are installed as SJA1110_VLAN_D_TAG, which means that they match on both inner and outer tags. So it does not make sense that we install FDB entries with the IOTAG bit set to 1. In VLAN-unaware mode, we set both TPID and TPID2 to 0xdadb, so the switch will see frames as outer-tagged or double-tagged (never inner). So the FDB entries will match if IOTAG is set to 1. In VLAN-aware mode, we set TPID to 0x8100 and TPID2 to 0x88a8. So the switch will see untagged and 802.1Q-tagged packets as inner-tagged, and 802.1ad-tagged packets as outer-tagged. So untagged and 802.1Q-tagged packets will not match FDB entries if IOTAG is set to 1, but 802.1ad tagged packets will. Strange. To fix this, simply mask off the IOTAG bit from FDB entries, and make them match regardless of whether the VLAN tag is inner or outer. Fixes: 1da73821343c ("net: dsa: sja1105: Add FDB operations for P/Q/R/S series") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 335b608bad11..8667c9754330 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1445,10 +1445,8 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, /* Search for an existing entry in the FDB table */ l2_lookup.macaddr = ether_addr_to_u64(addr); l2_lookup.vlanid = vid; - l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); l2_lookup.destports = BIT(port); tmp = l2_lookup; @@ -1538,10 +1536,8 @@ int sja1105pqrs_fdb_del(struct dsa_switch *ds, int port, l2_lookup.macaddr = ether_addr_to_u64(addr); l2_lookup.vlanid = vid; - l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, From 4c156084daa8ee70978e4b150b5eb5fc7b1f15be Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Thu, 29 Jul 2021 11:16:44 +0800 Subject: [PATCH 1148/1469] selinux: correct the return value when loads initial sids It should not return 0 when SID 0 is assigned to isids. This patch fixes it. Cc: stable@vger.kernel.org Fixes: e3e0b582c321a ("selinux: remove unused initial SIDs and improve handling") Signed-off-by: Xiu Jianfeng [PM: remove changelog from description] Signed-off-by: Paul Moore --- security/selinux/ss/policydb.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index defc5ef35c66..0ae1b718194a 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -874,7 +874,7 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s) rc = sidtab_init(s); if (rc) { pr_err("SELinux: out of memory on SID table init\n"); - goto out; + return rc; } head = p->ocontexts[OCON_ISID]; @@ -885,7 +885,7 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s) if (sid == SECSID_NULL) { pr_err("SELinux: SID 0 was assigned a context.\n"); sidtab_destroy(s); - goto out; + return -EINVAL; } /* Ignore initial SIDs unused by this kernel. */ @@ -897,12 +897,10 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s) pr_err("SELinux: unable to load initial SID %s.\n", name); sidtab_destroy(s); - goto out; + return rc; } } - rc = 0; -out: - return rc; + return 0; } int policydb_class_isvalid(struct policydb *p, unsigned int class) From a5e63c7d38d548b8dab6c6205e0b6af76899dbf5 Mon Sep 17 00:00:00 2001 From: Steve Bennett Date: Sat, 31 Jul 2021 08:57:50 +1000 Subject: [PATCH 1149/1469] net: phy: micrel: Fix detection of ksz87xx switch The logic for discerning between KSZ8051 and KSZ87XX PHYs is incorrect such that the that KSZ87XX switch is not identified correctly. ksz8051_ksz8795_match_phy_device() uses the parameter ksz_phy_id to discriminate whether it was called from ksz8051_match_phy_device() or from ksz8795_match_phy_device() but since PHY_ID_KSZ87XX is the same value as PHY_ID_KSZ8051, this doesn't work. Instead use a bool to discriminate the caller. Without this patch, the KSZ8795 switch port identifies as: ksz8795-switch spi3.1 ade1 (uninitialized): PHY [dsa-0.1:03] driver [Generic PHY] With the patch, it identifies correctly: ksz8795-switch spi3.1 ade1 (uninitialized): PHY [dsa-0.1:03] driver [Micrel KSZ87XX Switch] Fixes: 8b95599c55ed24b36cf4 ("net: phy: micrel: Discern KSZ8051 and KSZ8795 PHYs") Signed-off-by: Steve Bennett Reviewed-by: Marek Vasut Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 4d53886f7d51..53bdd673ae56 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -401,11 +401,11 @@ static int ksz8041_config_aneg(struct phy_device *phydev) } static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev, - const u32 ksz_phy_id) + const bool ksz_8051) { int ret; - if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id) + if ((phydev->phy_id & MICREL_PHY_ID_MASK) != PHY_ID_KSZ8051) return 0; ret = phy_read(phydev, MII_BMSR); @@ -418,7 +418,7 @@ static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev, * the switch does not. */ ret &= BMSR_ERCAP; - if (ksz_phy_id == PHY_ID_KSZ8051) + if (ksz_8051) return ret; else return !ret; @@ -426,7 +426,7 @@ static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev, static int ksz8051_match_phy_device(struct phy_device *phydev) { - return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051); + return ksz8051_ksz8795_match_phy_device(phydev, true); } static int ksz8081_config_init(struct phy_device *phydev) @@ -535,7 +535,7 @@ static int ksz8061_config_init(struct phy_device *phydev) static int ksz8795_match_phy_device(struct phy_device *phydev) { - return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX); + return ksz8051_ksz8795_match_phy_device(phydev, false); } static int ksz9021_load_values_from_of(struct phy_device *phydev, From 7fe74dfd41c428afb24e2e615470832fa997ff14 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Sat, 31 Jul 2021 14:38:01 +0800 Subject: [PATCH 1150/1469] net: natsemi: Fix missing pci_disable_device() in probe and remove Replace pci_enable_device() with pcim_enable_device(), pci_disable_device() and pci_release_regions() will be called in release automatically. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot Signed-off-by: Wang Hai Signed-off-by: David S. Miller --- drivers/net/ethernet/natsemi/natsemi.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index 51b4b25d15ad..84f7dbe9edff 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -819,7 +819,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) printk(version); #endif - i = pci_enable_device(pdev); + i = pcim_enable_device(pdev); if (i) return i; /* natsemi has a non-standard PM control register @@ -852,7 +852,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) ioaddr = ioremap(iostart, iosize); if (!ioaddr) { i = -ENOMEM; - goto err_ioremap; + goto err_pci_request_regions; } /* Work around the dropped serial bit. */ @@ -974,9 +974,6 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) err_register_netdev: iounmap(ioaddr); - err_ioremap: - pci_release_regions(pdev); - err_pci_request_regions: free_netdev(dev); return i; @@ -3241,7 +3238,6 @@ static void natsemi_remove1(struct pci_dev *pdev) NATSEMI_REMOVE_FILE(pdev, dspcfg_workaround); unregister_netdev (dev); - pci_release_regions (pdev); iounmap(ioaddr); free_netdev (dev); } From 6387f65e2acb9a63044bd64464401771b8cf1acc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 31 Jul 2021 07:39:17 -0700 Subject: [PATCH 1151/1469] net: sparx5: fix compiletime_assert for GCC 4.9 Stephen reports sparx5 broke GCC 4.9 build. Move the compiletime_assert() out of the static function. Compile-tested only, no object code changes. Reported-by: Stephen Rothwell Fixes: f3cad2611a77 ("net: sparx5: add hostmode with phylink support") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../ethernet/microchip/sparx5/sparx5_netdev.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index 9d485a9d1f1f..1a240e6bddd0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -13,7 +13,19 @@ */ #define VSTAX 73 -static void ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width) +#define ifh_encode_bitfield(ifh, value, pos, _width) \ + ({ \ + u32 width = (_width); \ + \ + /* Max width is 5 bytes - 40 bits. In worst case this will + * spread over 6 bytes - 48 bits + */ \ + compiletime_assert(width <= 40, \ + "Unsupported width, must be <= 40"); \ + __ifh_encode_bitfield((ifh), (value), (pos), width); \ + }) + +static void __ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width) { u8 *ifh_hdr = ifh; /* Calculate the Start IFH byte position of this IFH bit position */ @@ -22,11 +34,6 @@ static void ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width) u32 bit = (pos % 8); u64 encode = GENMASK(bit + width - 1, bit) & (value << bit); - /* Max width is 5 bytes - 40 bits. In worst case this will - * spread over 6 bytes - 48 bits - */ - compiletime_assert(width <= 40, "Unsupported width, must be <= 40"); - /* The b0-b7 goes into the start IFH byte */ if (encode & 0xFF) ifh_hdr[byte] |= (u8)((encode & 0xFF)); From 66e0da21728343bd3e75230a53d909e045fb9dd7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 31 Jul 2021 07:40:07 -0700 Subject: [PATCH 1152/1469] docs: operstates: fix typo TVL -> TLV Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/operstates.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/operstates.rst b/Documentation/networking/operstates.rst index 9c918f7cb0e8..f6b9cce5b201 100644 --- a/Documentation/networking/operstates.rst +++ b/Documentation/networking/operstates.rst @@ -111,7 +111,7 @@ it as lower layer. Note that for certain kind of soft-devices, which are not managing any real hardware, it is possible to set this bit from userspace. One -should use TVL IFLA_CARRIER to do so. +should use TLV IFLA_CARRIER to do so. netif_carrier_ok() can be used to query that bit. From 7a7b8635b622add64d98cff84bf3ee71eac36237 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 31 Jul 2021 07:40:52 -0700 Subject: [PATCH 1153/1469] docs: operstates: document IF_OPER_TESTING IF_OPER_TESTING is in fact used today. Signed-off-by: Jakub Kicinski Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/networking/operstates.rst | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/operstates.rst b/Documentation/networking/operstates.rst index f6b9cce5b201..1ee2141e8ef1 100644 --- a/Documentation/networking/operstates.rst +++ b/Documentation/networking/operstates.rst @@ -73,7 +73,9 @@ IF_OPER_LOWERLAYERDOWN (3): state (f.e. VLAN). IF_OPER_TESTING (4): - Unused in current kernel. + Interface is in testing mode, for example executing driver self-tests + or media (cable) test. It can't be used for normal traffic until tests + complete. IF_OPER_DORMANT (5): Interface is L1 up, but waiting for an external event, f.e. for a From 1c69d7cf4a8b6b6cfd920a1e809f1cd33ae4369c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Aug 2021 07:30:29 -0700 Subject: [PATCH 1154/1469] Revert "mhi: Fix networking tree build." This reverts commit 40e159403896f7d55c98f858d0b20fee1d941fa4. Looks like this commit breaks the build for me. Signed-off-by: Jakub Kicinski --- include/linux/mhi.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 5e08468854db..944aa3aa3035 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,13 +719,8 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels - * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, - unsigned int flags); - -/* Automatically allocate and queue inbound buffers */ -#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. From 9b87f43537acfa24b95c236beba0f45901356eb2 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 16 Jul 2021 12:00:47 +0200 Subject: [PATCH 1155/1469] gpio: tqmx86: really make IRQ optional The tqmx86 MFD driver was passing IRQ 0 for "no IRQ" in the past. This causes warnings with newer kernels. Prepare the gpio-tqmx86 driver for the fixed MFD driver by handling a missing IRQ properly. Fixes: b868db94a6a7 ("gpio: tqmx86: Add GPIO from for this IO controller") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-tqmx86.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 5022e0ad0fae..0f5d17f343f1 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -238,8 +238,8 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) struct resource *res; int ret, irq; - irq = platform_get_irq(pdev, 0); - if (irq < 0) + irq = platform_get_irq_optional(pdev, 0); + if (irq < 0 && irq != -ENXIO) return irq; res = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -278,7 +278,7 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); - if (irq) { + if (irq > 0) { struct irq_chip *irq_chip = &gpio->irq_chip; u8 irq_status; From d6793ca97b76642b77629dd0783ec64782a50bdb Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 27 Jul 2021 10:16:06 +0300 Subject: [PATCH 1156/1469] RDMA/mlx5: Delay emptying a cache entry when a new MR is added to it recently Fixing a typo that causes a cache entry to shrink immediately after adding to it new MRs if the entry size exceeds the high limit. In doing so, the cache misses its purpose to prevent the creation of new mkeys on the runtime by using the cached ones. Fixes: b9358bdbc713 ("RDMA/mlx5: Fix locking in MR cache work queue") Link: https://lore.kernel.org/r/fcb546986be346684a016f5ca23a0567399145fa.1627370131.git.leonro@nvidia.com Signed-off-by: Aharon Landau Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 3263851ea574..3f1c5a4f158b 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -531,8 +531,8 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) */ spin_unlock_irq(&ent->lock); need_delay = need_resched() || someone_adding(cache) || - time_after(jiffies, - READ_ONCE(cache->last_add) + 300 * HZ); + !time_after(jiffies, + READ_ONCE(cache->last_add) + 300 * HZ); spin_lock_irq(&ent->lock); if (ent->disabled) goto out; From db4657afd10e45855ac1d8437fcc9a86bd3d741d Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Thu, 29 Jul 2021 14:26:22 -0400 Subject: [PATCH 1157/1469] RDMA/cma: Revert INIT-INIT patch The net/sunrpc/xprtrdma module creates its QP using rdma_create_qp() and immediately post receives, implicitly assuming the QP is in the INIT state and thus valid for ib_post_recv(). The patch noted in Fixes: removed the RESET->INIT modifiy from rdma_create_qp(), breaking NFS rdma for verbs providers that fail the ib_post_recv() for a bad state. This situation was proven using kprobes in rvt_post_recv() and rvt_modify_qp(). The traces showed that the rvt_post_recv() failed before ANY modify QP and that the current state was RESET. Fix by reverting the patch below. Fixes: dc70f7c3ed34 ("RDMA/cma: Remove unnecessary INIT->INIT transition") Link: https://lore.kernel.org/r/1627583182-81330-1-git-send-email-mike.marciniszyn@cornelisnetworks.com Cc: Haakon Bugge Cc: Chuck Lever III Signed-off-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 515a7e95a421..5d3b8b8d163d 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -926,12 +926,25 @@ static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) return ret; } +static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) +{ + struct ib_qp_attr qp_attr; + int qp_attr_mask, ret; + + qp_attr.qp_state = IB_QPS_INIT; + ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); + if (ret) + return ret; + + return ib_modify_qp(qp, &qp_attr, qp_attr_mask); +} + int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; - int ret = 0; + int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { @@ -948,6 +961,8 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); + else + ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; From e2a05339fa1188b6b37540f4611893ac4c534fa2 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 29 Jul 2021 17:00:38 -0500 Subject: [PATCH 1158/1469] RDMA/rxe: Use the correct size of wqe when processing SRQ The memcpy() that copies a WQE from a SRQ the QP uses an incorrect size. The size should have been the size of the rxe_send_wqe struct not the size of a pointer to it. The result is that IO operations using a SRQ on the responder side will fail. Fixes: ec0fa2445c18 ("RDMA/rxe: Fix over copying in get_srq_wqe") Link: https://lore.kernel.org/r/20210729220039.18549-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_resp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 3743dc39b60c..360ec67cb9e1 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -318,7 +318,7 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp) pr_warn("%s: invalid num_sge in SRQ entry\n", __func__); return RESPST_ERR_MALFORMED_WQE; } - size = sizeof(wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge); + size = sizeof(*wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge); memcpy(&qp->resp.srq_wqe, wqe, size); qp->resp.wqe = &qp->resp.srq_wqe.wqe; From ef4b96a5773d7f6568363b3d0c3c3f371fb690bd Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Thu, 29 Jul 2021 17:00:39 -0500 Subject: [PATCH 1159/1469] RDMA/rxe: Restore setting tot_len in the IPv4 header An earlier patch removed setting of tot_len in IPv4 headers because it was also set in ip_local_out. However, this change resulted in an incorrect ICRC being computed because the tot_len field is not masked out. This patch restores that line. This fixes the bug reported by Zhu Yanjun. This bug affects anyone using rxe which is currently broken. Fixes: 230bb836ee88 ("RDMA/rxe: Fix redundant call to ip_send_check") Link: https://lore.kernel.org/r/20210729220039.18549-3-rpearsonhpe@gmail.com Reported-by: Zhu Yanjun Signed-off-by: Bob Pearson Reviewed-and-tested-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_net.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index dec92928a1cd..5ac27f28ace1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -259,6 +259,7 @@ static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, iph->version = IPVERSION; iph->ihl = sizeof(struct iphdr) >> 2; + iph->tot_len = htons(skb->len); iph->frag_off = df; iph->protocol = proto; iph->tos = tos; From e89afb51f97ae03ee246c1fd0b47e3e491266aef Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Tue, 15 Jun 2021 14:23:34 -0400 Subject: [PATCH 1160/1469] drm/vmwgfx: Fix a 64bit regression on svga3 Register accesses are always 4bytes, accidently this was changed to a void pointer whwqich badly breaks 64bit archs when running on top of svga3. Fixes: 2cd80dbd3551 ("drm/vmwgfx: Add basic support for SVGA3") Signed-off-by: Zack Rusin Reviewed-by: Martin Krastev Link: https://patchwork.freedesktop.org/patch/msgid/20210615182336.995192-3-zackr@vmware.com (cherry picked from commit 87360168759879d68550b0c052bbcc2a0339ff74) Signed-off-by: Thomas Zimmermann --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index d1cef3b69e9d..5652d982b1ce 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -492,7 +492,7 @@ struct vmw_private { resource_size_t vram_start; resource_size_t vram_size; resource_size_t prim_bb_mem; - void __iomem *rmmio; + u32 __iomem *rmmio; u32 *fifo_mem; resource_size_t fifo_mem_size; uint32_t fb_max_width; From 0541a6293298fb52789de389dfb27ef54df81f73 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 2 Aug 2021 02:17:30 +0300 Subject: [PATCH 1161/1469] net: bridge: validate the NUD_PERMANENT bit when adding an extern_learn FDB entry Currently it is possible to add broken extern_learn FDB entries to the bridge in two ways: 1. Entries pointing towards the bridge device that are not local/permanent: ip link add br0 type bridge bridge fdb add 00:01:02:03:04:05 dev br0 self extern_learn static 2. Entries pointing towards the bridge device or towards a port that are marked as local/permanent, however the bridge does not process the 'permanent' bit in any way, therefore they are recorded as though they aren't permanent: ip link add br0 type bridge bridge fdb add 00:01:02:03:04:05 dev br0 self extern_learn permanent Since commit 52e4bec15546 ("net: bridge: switchdev: treat local FDBs the same as entries towards the bridge"), these incorrect FDB entries can even trigger NULL pointer dereferences inside the kernel. This is because that commit made the assumption that all FDB entries that are not local/permanent have a valid destination port. For context, local / permanent FDB entries either have fdb->dst == NULL, and these point towards the bridge device and are therefore local and not to be used for forwarding, or have fdb->dst == a net_bridge_port structure (but are to be treated in the same way, i.e. not for forwarding). That assumption _is_ correct as long as things are working correctly in the bridge driver, i.e. we cannot logically have fdb->dst == NULL under any circumstance for FDB entries that are not local. However, the extern_learn code path where FDB entries are managed by a user space controller show that it is possible for the bridge kernel driver to misinterpret the NUD flags of an entry transmitted by user space, and end up having fdb->dst == NULL while not being a local entry. This is invalid and should be rejected. Before, the two commands listed above both crashed the kernel in this check from br_switchdev_fdb_notify: struct net_device *dev = info.is_local ? br->dev : dst->dev; info.is_local == false, dst == NULL. After this patch, the invalid entry added by the first command is rejected: ip link add br0 type bridge && bridge fdb add 00:01:02:03:04:05 dev br0 self extern_learn static; ip link del br0 Error: bridge: FDB entry towards bridge must be permanent. and the valid entry added by the second command is properly treated as a local address and does not crash br_switchdev_fdb_notify anymore: ip link add br0 type bridge && bridge fdb add 00:01:02:03:04:05 dev br0 self extern_learn permanent; ip link del br0 Fixes: eb100e0e24a2 ("net: bridge: allow to add externally learned entries from user-space") Reported-by: syzbot+9ba1174359adba5a5b7c@syzkaller.appspotmail.com Signed-off-by: Vladimir Oltean Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20210801231730.7493-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- net/bridge/br.c | 3 ++- net/bridge/br_fdb.c | 30 ++++++++++++++++++++++++------ net/bridge/br_private.h | 2 +- 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/net/bridge/br.c b/net/bridge/br.c index ef743f94254d..bbab9984f24e 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,7 +166,8 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, false); + fdb_info->vid, + fdb_info->is_local, false); if (err) { err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index a16191dcaed1..835cec1e5a03 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1019,7 +1019,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, - u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[]) + u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[], + struct netlink_ext_ack *extack) { int err = 0; @@ -1038,7 +1039,15 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { - err = br_fdb_external_learn_add(br, p, addr, vid, true); + if (!p && !(ndm->ndm_state & NUD_PERMANENT)) { + NL_SET_ERR_MSG_MOD(extack, + "FDB entry towards bridge must be permanent"); + return -EINVAL; + } + + err = br_fdb_external_learn_add(br, p, addr, vid, + ndm->ndm_state & NUD_PERMANENT, + true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1110,9 +1119,11 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb, + extack); } else { - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb, + extack); if (err || !vg || !vg->num_vlans) goto out; @@ -1124,7 +1135,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (!br_vlan_should_use(v)) continue; err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid, - nfea_tb); + nfea_tb, extack); if (err) goto out; } @@ -1264,7 +1275,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, + const unsigned char *addr, u16 vid, bool is_local, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1281,6 +1292,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); + + if (is_local) + flags |= BIT(BR_FDB_LOCAL); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1307,6 +1322,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); + if (is_local) + set_bit(BR_FDB_LOCAL, &fdb->flags); + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2b48b204205e..aa64d8d63ca3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -711,7 +711,7 @@ int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, + const unsigned char *addr, u16 vid, bool is_local, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, From 6b994c554ebc4c065427f510db333081cbd7228d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 2 Aug 2021 10:16:28 -0500 Subject: [PATCH 1162/1469] ASoC: SOF: Intel: Kconfig: fix SoundWire dependencies The previous Kconfig cleanup added simplifications but also introduced a new one by moving a boolean to a tristate. This leads to randconfig problems. This patch moves the select operations in the SOUNDWIRE_LINK_BASELINE option. The INTEL_SOUNDWIRE config remains a tristate for backwards compatibility with older configurations but is essentially an on/off switch. Fixes: cf5807f5f814f ('ASoC: SOF: Intel: SoundWire: simplify Kconfig') Reported-by: Arnd Bergmann Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Bard Liao Tested-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210802151628.15291-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/intel/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index 4bce89b5ea40..4447f515e8b1 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -278,6 +278,8 @@ config SND_SOC_SOF_HDA config SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE tristate + select SOUNDWIRE_INTEL if SND_SOC_SOF_INTEL_SOUNDWIRE + select SND_INTEL_SOUNDWIRE_ACPI if SND_SOC_SOF_INTEL_SOUNDWIRE config SND_SOC_SOF_INTEL_SOUNDWIRE tristate "SOF support for SoundWire" @@ -285,8 +287,6 @@ config SND_SOC_SOF_INTEL_SOUNDWIRE depends on SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE depends on ACPI && SOUNDWIRE depends on !(SOUNDWIRE=m && SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE=y) - select SOUNDWIRE_INTEL - select SND_INTEL_SOUNDWIRE_ACPI help This adds support for SoundWire with Sound Open Firmware for Intel(R) platforms. From 973b393fdf073a4ebd8d82ef6edea99fedc74af9 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Mon, 2 Aug 2021 10:17:49 -0500 Subject: [PATCH 1163/1469] ASoC: SOF: Intel: hda-ipc: fix reply size checking Checking that two values don't have common bits makes no sense, strict equality is meant. Fixes: f3b433e4699f ("ASoC: SOF: Implement Probe IPC API") Reviewed-by: Ranjani Sridharan Signed-off-by: Guennadi Liakhovetski Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210802151749.15417-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/intel/hda-ipc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/sof/intel/hda-ipc.c b/sound/soc/sof/intel/hda-ipc.c index c91aa951df22..acfeca42604c 100644 --- a/sound/soc/sof/intel/hda-ipc.c +++ b/sound/soc/sof/intel/hda-ipc.c @@ -107,8 +107,8 @@ void hda_dsp_ipc_get_reply(struct snd_sof_dev *sdev) } else { /* reply correct size ? */ if (reply.hdr.size != msg->reply_size && - /* getter payload is never known upfront */ - !(reply.hdr.cmd & SOF_IPC_GLB_PROBE)) { + /* getter payload is never known upfront */ + ((reply.hdr.cmd & SOF_GLB_TYPE_MASK) != SOF_IPC_GLB_PROBE)) { dev_err(sdev->dev, "error: reply expected %zu got %u bytes\n", msg->reply_size, reply.hdr.size); ret = -EINVAL; From 5b94046efb4706b3429c9c8e7377bd8d1621d588 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 26 Jul 2021 11:38:41 +0200 Subject: [PATCH 1164/1469] efi/libstub: arm64: Force Image reallocation if BSS was not reserved Distro versions of GRUB replace the usual LoadImage/StartImage calls used to load the kernel image with some local code that fails to honor the allocation requirements described in the PE/COFF header, as it does not account for the image's BSS section at all: it fails to allocate space for it, and fails to zero initialize it. Since the EFI stub itself is allocated in the .init segment, which is in the middle of the image, its BSS section is not impacted by this, and the main consequence of this omission is that the BSS section may overlap with memory regions that are already used by the firmware. So let's warn about this condition, and force image reallocation to occur in this case, which works around the problem. Fixes: 82046702e288 ("efi/libstub/arm64: Replace 'preferred' offset with alignment check") Signed-off-by: Ard Biesheuvel Tested-by: Benjamin Herrenschmidt --- drivers/firmware/efi/libstub/arm64-stub.c | 49 ++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 7bf0a7acae5e..3698c1ce2940 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -34,6 +34,51 @@ efi_status_t check_platform_features(void) return EFI_SUCCESS; } +/* + * Distro versions of GRUB may ignore the BSS allocation entirely (i.e., fail + * to provide space, and fail to zero it). Check for this condition by double + * checking that the first and the last byte of the image are covered by the + * same EFI memory map entry. + */ +static bool check_image_region(u64 base, u64 size) +{ + unsigned long map_size, desc_size, buff_size; + efi_memory_desc_t *memory_map; + struct efi_boot_memmap map; + efi_status_t status; + bool ret = false; + int map_offset; + + map.map = &memory_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = NULL; + map.key_ptr = NULL; + map.buff_size = &buff_size; + + status = efi_get_memory_map(&map); + if (status != EFI_SUCCESS) + return false; + + for (map_offset = 0; map_offset < map_size; map_offset += desc_size) { + efi_memory_desc_t *md = (void *)memory_map + map_offset; + u64 end = md->phys_addr + md->num_pages * EFI_PAGE_SIZE; + + /* + * Find the region that covers base, and return whether + * it covers base+size bytes. + */ + if (base >= md->phys_addr && base < end) { + ret = (base + size) <= end; + break; + } + } + + efi_bs_call(free_pool, memory_map); + + return ret; +} + /* * Although relocatable kernels can fix up the misalignment with respect to * MIN_KIMG_ALIGN, the resulting virtual text addresses are subtly out of @@ -92,7 +137,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, } if (status != EFI_SUCCESS) { - if (IS_ALIGNED((u64)_text, min_kimg_align())) { + if (!check_image_region((u64)_text, kernel_memsize)) { + efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); + } else if (IS_ALIGNED((u64)_text, min_kimg_align())) { /* * Just execute from wherever we were loaded by the * UEFI PE/COFF loader if the alignment is suitable. From 3a262423755b83a5f85009ace415d6e7f572dfe8 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 22 Jul 2021 12:10:31 +0200 Subject: [PATCH 1165/1469] efi/libstub: arm64: Relax 2M alignment again for relocatable kernels Commit 82046702e288 ("efi/libstub/arm64: Replace 'preferred' offset with alignment check") simplified the way the stub moves the kernel image around in memory before booting it, given that a relocatable image does not need to be copied to a 2M aligned offset if it was loaded on a 64k boundary by EFI. Commit d32de9130f6c ("efi/arm64: libstub: Deal gracefully with EFI_RNG_PROTOCOL failure") inadvertently defeated this logic by overriding the value of efi_nokaslr if EFI_RNG_PROTOCOL is not available, which was mistaken by the loader logic as an explicit request on the part of the user to disable KASLR and any associated relocation of an Image not loaded on a 2M boundary. So let's reinstate this functionality, by capturing the value of efi_nokaslr at function entry to choose the minimum alignment. Fixes: d32de9130f6c ("efi/arm64: libstub: Deal gracefully with EFI_RNG_PROTOCOL failure") Signed-off-by: Ard Biesheuvel Tested-by: Benjamin Herrenschmidt --- drivers/firmware/efi/libstub/arm64-stub.c | 28 +++++++++++------------ 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 3698c1ce2940..6f214c9c303e 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -79,18 +79,6 @@ static bool check_image_region(u64 base, u64 size) return ret; } -/* - * Although relocatable kernels can fix up the misalignment with respect to - * MIN_KIMG_ALIGN, the resulting virtual text addresses are subtly out of - * sync with those recorded in the vmlinux when kaslr is disabled but the - * image required relocation anyway. Therefore retain 2M alignment unless - * KASLR is in use. - */ -static u64 min_kimg_align(void) -{ - return efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; -} - efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, @@ -101,6 +89,16 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long kernel_size, kernel_memsize = 0; u32 phys_seed = 0; + /* + * Although relocatable kernels can fix up the misalignment with + * respect to MIN_KIMG_ALIGN, the resulting virtual text addresses are + * subtly out of sync with those recorded in the vmlinux when kaslr is + * disabled but the image required relocation anyway. Therefore retain + * 2M alignment if KASLR was explicitly disabled, even if it was not + * going to be activated to begin with. + */ + u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { if (!efi_nokaslr) { status = efi_get_random_bytes(sizeof(phys_seed), @@ -130,7 +128,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, * If KASLR is enabled, and we have some randomness available, * locate the kernel at a randomized offset in physical memory. */ - status = efi_random_alloc(*reserve_size, min_kimg_align(), + status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed); } else { status = EFI_OUT_OF_RESOURCES; @@ -139,7 +137,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (status != EFI_SUCCESS) { if (!check_image_region((u64)_text, kernel_memsize)) { efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); - } else if (IS_ALIGNED((u64)_text, min_kimg_align())) { + } else if (IS_ALIGNED((u64)_text, min_kimg_align)) { /* * Just execute from wherever we were loaded by the * UEFI PE/COFF loader if the alignment is suitable. @@ -150,7 +148,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, - ULONG_MAX, min_kimg_align()); + ULONG_MAX, min_kimg_align); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); From ff80ef5bf5bd59e5eab82d1d846acc613ebbf6c4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 26 Jul 2021 16:24:01 +0200 Subject: [PATCH 1166/1469] efi/libstub: arm64: Warn when efi_random_alloc() fails Randomization of the physical load address of the kernel image relies on efi_random_alloc() returning successfully, and currently, we ignore any failures and just carry on, using the ordinary, non-randomized page allocator routine. This means we never find out if a failure occurs, which could harm security, so let's at least warn about this condition. Signed-off-by: Ard Biesheuvel Tested-by: Benjamin Herrenschmidt --- drivers/firmware/efi/libstub/arm64-stub.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 6f214c9c303e..010564f8bbc4 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -130,6 +130,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, */ status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed); + if (status != EFI_SUCCESS) + efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { status = EFI_OUT_OF_RESOURCES; } From c32ac11da3f83bb42b986702a9b92f0a14ed4182 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 26 Jul 2021 16:31:44 +0200 Subject: [PATCH 1167/1469] efi/libstub: arm64: Double check image alignment at entry On arm64, the stub only moves the kernel image around in memory if needed, which is typically only for KASLR, given that relocatable kernels (which is the default) can run from any 64k aligned address, which is also the minimum alignment communicated to EFI via the PE/COFF header. Unfortunately, some loaders appear to ignore this header, and load the kernel at some arbitrary offset in memory. We can deal with this, but let's check for this condition anyway, so non-compliant code can be spotted and fixed. Cc: # v5.10+ Signed-off-by: Ard Biesheuvel Tested-by: Benjamin Herrenschmidt --- drivers/firmware/efi/libstub/arm64-stub.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 010564f8bbc4..2363fee9211c 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -119,6 +119,10 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (image->image_base != _text) efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n"); + if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) + efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", + EFI_KIMG_ALIGN >> 10); + kernel_size = _edata - _text; kernel_memsize = kernel_size + (_end - _edata); *reserve_size = kernel_memsize; From 8861452b2097bb0b5d0081a1c137fb3870b0a31f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 8 Nov 2019 09:43:06 +0100 Subject: [PATCH 1168/1469] soc: ixp4xx: fix printing resources When compile-testing with 64-bit resource_size_t, gcc reports an invalid printk format string: In file included from include/linux/dma-mapping.h:7, from drivers/soc/ixp4xx/ixp4xx-npe.c:15: drivers/soc/ixp4xx/ixp4xx-npe.c: In function 'ixp4xx_npe_probe': drivers/soc/ixp4xx/ixp4xx-npe.c:694:18: error: format '%x' expects argument of type 'unsigned int', but argument 4 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] dev_info(dev, "NPE%d at 0x%08x-0x%08x not available\n", Use the special %pR format string to print the resources. Fixes: 0b458d7b10f8 ("soc: ixp4xx: npe: Pass addresses as resources") Signed-off-by: Arnd Bergmann --- drivers/soc/ixp4xx/ixp4xx-npe.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/soc/ixp4xx/ixp4xx-npe.c b/drivers/soc/ixp4xx/ixp4xx-npe.c index fea50e04d5a1..f490c4ca51f5 100644 --- a/drivers/soc/ixp4xx/ixp4xx-npe.c +++ b/drivers/soc/ixp4xx/ixp4xx-npe.c @@ -693,8 +693,8 @@ static int ixp4xx_npe_probe(struct platform_device *pdev) if (!(ixp4xx_read_feature_bits() & (IXP4XX_FEATURE_RESET_NPEA << i))) { - dev_info(dev, "NPE%d at 0x%08x-0x%08x not available\n", - i, res->start, res->end); + dev_info(dev, "NPE%d at %pR not available\n", + i, res); continue; /* NPE already disabled or not present */ } npe->regs = devm_ioremap_resource(dev, res); @@ -702,13 +702,12 @@ static int ixp4xx_npe_probe(struct platform_device *pdev) return PTR_ERR(npe->regs); if (npe_reset(npe)) { - dev_info(dev, "NPE%d at 0x%08x-0x%08x does not reset\n", - i, res->start, res->end); + dev_info(dev, "NPE%d at %pR does not reset\n", + i, res); continue; } npe->valid = 1; - dev_info(dev, "NPE%d at 0x%08x-0x%08x registered\n", - i, res->start, res->end); + dev_info(dev, "NPE%d at %pR registered\n", i, res); found++; } From a8eee86317f11e97990d755d4615c1c0db203d08 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Aug 2021 10:12:34 +0200 Subject: [PATCH 1169/1469] soc: ixp4xx/qmgr: fix invalid __iomem access Sparse reports a compile time warning when dereferencing an __iomem pointer: drivers/soc/ixp4xx/ixp4xx-qmgr.c:149:37: warning: dereference of noderef expression drivers/soc/ixp4xx/ixp4xx-qmgr.c:153:40: warning: dereference of noderef expression drivers/soc/ixp4xx/ixp4xx-qmgr.c:154:40: warning: dereference of noderef expression drivers/soc/ixp4xx/ixp4xx-qmgr.c:174:38: warning: dereference of noderef expression drivers/soc/ixp4xx/ixp4xx-qmgr.c:174:44: warning: dereference of noderef expression Use __raw_readl() here for consistency with the rest of the file. This should really get converted to some proper accessor, as the __raw functions are not meant to be used in drivers, but the driver has used these since the start, so for the moment, let's only fix the warning. Reported-by: kernel test robot Fixes: d4c9e9fc9751 ("IXP42x: Add QMgr support for IXP425 rev. A0 processors.") Signed-off-by: Arnd Bergmann --- drivers/soc/ixp4xx/ixp4xx-qmgr.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/soc/ixp4xx/ixp4xx-qmgr.c b/drivers/soc/ixp4xx/ixp4xx-qmgr.c index c6bf6ef257c0..9154c7029b05 100644 --- a/drivers/soc/ixp4xx/ixp4xx-qmgr.c +++ b/drivers/soc/ixp4xx/ixp4xx-qmgr.c @@ -146,12 +146,12 @@ static irqreturn_t qmgr_irq1_a0(int irq, void *pdev) /* ACK - it may clear any bits so don't rely on it */ __raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[0]); - en_bitmap = qmgr_regs->irqen[0]; + en_bitmap = __raw_readl(&qmgr_regs->irqen[0]); while (en_bitmap) { i = __fls(en_bitmap); /* number of the last "low" queue */ en_bitmap &= ~BIT(i); - src = qmgr_regs->irqsrc[i >> 3]; - stat = qmgr_regs->stat1[i >> 3]; + src = __raw_readl(&qmgr_regs->irqsrc[i >> 3]); + stat = __raw_readl(&qmgr_regs->stat1[i >> 3]); if (src & 4) /* the IRQ condition is inverted */ stat = ~stat; if (stat & BIT(src & 3)) { @@ -171,7 +171,8 @@ static irqreturn_t qmgr_irq2_a0(int irq, void *pdev) /* ACK - it may clear any bits so don't rely on it */ __raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[1]); - req_bitmap = qmgr_regs->irqen[1] & qmgr_regs->statne_h; + req_bitmap = __raw_readl(&qmgr_regs->irqen[1]) & + __raw_readl(&qmgr_regs->statne_h); while (req_bitmap) { i = __fls(req_bitmap); /* number of the last "high" queue */ req_bitmap &= ~BIT(i); From e30e8d46cf605d216a799a28c77b8a41c328613a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 2 Aug 2021 11:42:00 +0100 Subject: [PATCH 1170/1469] arm64: fix compat syscall return truncation Due to inconsistencies in the way we manipulate compat GPRs, we have a few issues today: * For audit and tracing, where error codes are handled as a (native) long, negative error codes are expected to be sign-extended to the native 64-bits, or they may fail to be matched correctly. Thus a syscall which fails with an error may erroneously be identified as failing. * For ptrace, *all* compat return values should be sign-extended for consistency with 32-bit arm, but we currently only do this for negative return codes. * As we may transiently set the upper 32 bits of some compat GPRs while in the kernel, these can be sampled by perf, which is somewhat confusing. This means that where a syscall returns a pointer above 2G, this will be sign-extended, but will not be mistaken for an error as error codes are constrained to the inclusive range [-4096, -1] where no user pointer can exist. To fix all of these, we must consistently use helpers to get/set the compat GPRs, ensuring that we never write the upper 32 bits of the return code, and always sign-extend when reading the return code. This patch does so, with the following changes: * We re-organise syscall_get_return_value() to always sign-extend for compat tasks, and reimplement syscall_get_error() atop. We update syscall_trace_exit() to use syscall_get_return_value(). * We consistently use syscall_set_return_value() to set the return value, ensureing the upper 32 bits are never set unexpectedly. * As the core audit code currently uses regs_return_value() rather than syscall_get_return_value(), we special-case this for compat_user_mode(regs) such that this will do the right thing. Going forward, we should try to move the core audit code over to syscall_get_return_value(). Cc: Reported-by: He Zhe Reported-by: weiyuchen Cc: Catalin Marinas Cc: Will Deacon Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20210802104200.21390-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/ptrace.h | 12 +++++++++++- arch/arm64/include/asm/syscall.h | 21 +++++++++++---------- arch/arm64/kernel/ptrace.c | 2 +- arch/arm64/kernel/signal.c | 3 ++- arch/arm64/kernel/syscall.c | 9 +++------ 5 files changed, 28 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index e58bca832dff..41b332c054ab 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -320,7 +320,17 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) static inline unsigned long regs_return_value(struct pt_regs *regs) { - return regs->regs[0]; + unsigned long val = regs->regs[0]; + + /* + * Audit currently uses regs_return_value() instead of + * syscall_get_return_value(). Apply the same sign-extension here until + * audit is updated to use syscall_get_return_value(). + */ + if (compat_user_mode(regs)) + val = sign_extend64(val, 31); + + return val; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index cfc0672013f6..03e20895453a 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -29,24 +29,25 @@ static inline void syscall_rollback(struct task_struct *task, regs->regs[0] = regs->orig_x0; } +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + unsigned long val = regs->regs[0]; + + if (is_compat_thread(task_thread_info(task))) + val = sign_extend64(val, 31); + + return val; +} static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - unsigned long error = regs->regs[0]; - - if (is_compat_thread(task_thread_info(task))) - error = sign_extend64(error, 31); + unsigned long error = syscall_get_return_value(task, regs); return IS_ERR_VALUE(error) ? error : 0; } -static inline long syscall_get_return_value(struct task_struct *task, - struct pt_regs *regs) -{ - return regs->regs[0]; -} - static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 499b6b2f9757..b381a1ee9ea7 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1862,7 +1862,7 @@ void syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(regs); if (flags & _TIF_SYSCALL_TRACEPOINT) - trace_sys_exit(regs, regs_return_value(regs)); + trace_sys_exit(regs, syscall_get_return_value(current, regs)); if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f8192f4ae0b8..23036334f4dc 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -890,7 +891,7 @@ static void do_signal(struct pt_regs *regs) retval == -ERESTART_RESTARTBLOCK || (retval == -ERESTARTSYS && !(ksig.ka.sa.sa_flags & SA_RESTART)))) { - regs->regs[0] = -EINTR; + syscall_set_return_value(current, regs, -EINTR, 0); regs->pc = continue_addr; } diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 263d6c1a525f..50a0f1a38e84 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -54,10 +54,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, ret = do_ni_syscall(regs, scno); } - if (is_compat_task()) - ret = lower_32_bits(ret); - - regs->regs[0] = ret; + syscall_set_return_value(current, regs, 0, ret); /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), @@ -115,7 +112,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * syscall. do_notify_resume() will send a signal to userspace * before the syscall is restarted. */ - regs->regs[0] = -ERESTARTNOINTR; + syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0); return; } @@ -136,7 +133,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * anyway. */ if (scno == NO_SYSCALL) - regs->regs[0] = -ENOSYS; + syscall_set_return_value(current, regs, -ENOSYS, 0); scno = syscall_trace_enter(regs); if (scno == NO_SYSCALL) goto trace_exit; From 64ee84c75b5f75132eec97f2c7a201a056d53698 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 1 Aug 2021 14:35:25 +0900 Subject: [PATCH 1171/1469] arm64: move warning about toolchains to archprepare Commit 987fdfec2410 ("arm64: move --fix-cortex-a53-843419 linker test to Kconfig") fixed the false-positive warning in the installation step. Yet, there are some cases where this false-positive is shown. For example, you can see it when you cross 987fdfec2410 during git-bisect. $ git checkout 987fdfec2410^ [ snip ] $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- defconfig all [ snip ] $ git checkout v5.13 [ snip] $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- defconfig all [ snip ] arch/arm64/Makefile:25: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum In the stale include/config/auto.config, CONFIG_ARM64_ERRATUM_843419=y is set without CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419, so the warning is displayed while parsing the Makefiles. Make will restart with the updated include/config/auto.config, hence CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419 will be set eventually, but this warning is a surprise for users. Commit 25896d073d8a ("x86/build: Fix compiler support check for CONFIG_RETPOLINE") addressed a similar issue. Move $(warning ...) out of the parse stage of Makefiles. The same applies to CONFIG_ARM64_USE_LSE_ATOMICS. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20210801053525.105235-1-masahiroy@kernel.org Signed-off-by: Will Deacon --- arch/arm64/Makefile | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7bc37d0a1b68..7b668db43261 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -21,19 +21,11 @@ LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \ endif ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) - ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y) -$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum) - else + ifeq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y) LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif endif -ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y) - ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y) -$(warning LSE atomics not supported by binutils) - endif -endif - cc_has_k_constraint := $(call try-run,echo \ 'int main(void) { \ asm volatile("and w0, w0, %w0" :: "K" (4294967295)); \ @@ -176,6 +168,17 @@ vdso_install: archprepare: $(Q)$(MAKE) $(build)=arch/arm64/tools kapi +ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) + ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y) + @echo "warning: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum" >&2 + endif +endif +ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS),y) + ifneq ($(CONFIG_ARM64_LSE_ATOMICS),y) + @echo "warning: LSE atomics not supported by binutils" >&2 + endif +endif + # We use MRPROPER_FILES and CLEAN_FILES now archclean: From f9c4ff2ab9fe433d44ebbc2e3c2368a49df44798 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 31 Jul 2021 00:51:31 +1200 Subject: [PATCH 1172/1469] arm64: fix the doc of RANDOMIZE_MODULE_REGION_FULL Obviously kaslr is setting the module region to 2GB rather than 4GB since commit b2eed9b588112 ("arm64/kernel: kaslr: reduce module randomization range to 2 GB"). So fix the size of region in Kconfig. On the other hand, even though RANDOMIZE_MODULE_REGION_FULL is not set, module_alloc() can fall back to a 2GB window if ARM64_MODULE_PLTS is set. In this case, veneers are still needed. !RANDOMIZE_MODULE_REGION_FULL doesn't necessarily mean veneers are not needed. So fix the doc to be more precise to avoid any confusion to the readers of the code. Cc: Masami Hiramatsu Cc: Ard Biesheuvel Cc: Qi Liu Signed-off-by: Barry Song Reviewed-by: Masami Hiramatsu Link: https://lore.kernel.org/r/20210730125131.13724-1-song.bao.hua@hisilicon.com Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 9 ++++++--- arch/arm64/kernel/kaslr.c | 4 +++- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index b5b13a932561..fdcd54d39c1e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1800,11 +1800,11 @@ config RANDOMIZE_BASE If unsure, say N. config RANDOMIZE_MODULE_REGION_FULL - bool "Randomize the module region over a 4 GB range" + bool "Randomize the module region over a 2 GB range" depends on RANDOMIZE_BASE default y help - Randomizes the location of the module region inside a 4 GB window + Randomizes the location of the module region inside a 2 GB window covering the core kernel. This way, it is less likely for modules to leak information about the location of core kernel data structures but it does imply that function calls between modules and the core @@ -1812,7 +1812,10 @@ config RANDOMIZE_MODULE_REGION_FULL When this option is not set, the module region will be randomized over a limited range that contains the [_stext, _etext] interval of the - core kernel, so branch relocations are always in range. + core kernel, so branch relocations are almost always in range unless + ARM64_MODULE_PLTS is enabled and the region is exhausted. In this + particular case of region exhaustion, modules might be able to fall + back to a larger 2GB area. config CC_HAVE_STACKPROTECTOR_SYSREG def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index cfa2cfde3019..418b2bba1521 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -162,7 +162,9 @@ u64 __init kaslr_early_init(void) * a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE, * _stext) . This guarantees that the resulting region still * covers [_stext, _etext], and that all relative branches can - * be resolved without veneers. + * be resolved without veneers unless this region is exhausted + * and we fall back to a larger 2GB window in module_alloc() + * when ARM64_MODULE_PLTS is enabled. */ module_range = MODULES_VSIZE - (u64)(_etext - _stext); module_alloc_base = (u64)_etext + offset - MODULES_VSIZE; From 8d5903f457145e3fcd858578b065d667822d99ac Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 2 Aug 2021 17:48:44 +0100 Subject: [PATCH 1173/1469] arm64: stacktrace: fix comment Due to a copy-paste error, we describe struct stackframe::pc as a snapshot of the `fp` field rather than the `lr` field. Fix the comment. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Madhavan T. Venkataraman Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20210802164845.45506-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/stacktrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 1801399204d7..8aebc00c1718 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -35,7 +35,7 @@ struct stack_info { * accounting information necessary for robust unwinding. * * @fp: The fp value in the frame record (or the real fp) - * @pc: The fp value in the frame record (or the real lr) + * @pc: The lr value in the frame record (or the real lr) * * @stacks_done: Stacks which have been entirely unwound, for which it is no * longer valid to unwind to. From 0c32706dac1b0a72713184246952ab0f54327c21 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 2 Aug 2021 17:48:45 +0100 Subject: [PATCH 1174/1469] arm64: stacktrace: avoid tracing arch_stack_walk() When the function_graph tracer is in use, arch_stack_walk() may unwind the stack incorrectly, erroneously reporting itself, missing the final entry which is being traced, and reporting all traced entries between these off-by-one from where they should be. When ftrace hooks a function return, the original return address is saved to the fgraph ret_stack, and the return address in the LR (or the function's frame record) is replaced with `return_to_handler`. When arm64's unwinder encounter frames returning to `return_to_handler`, it finds the associated original return address from the fgraph ret stack, assuming the most recent `ret_to_hander` entry on the stack corresponds to the most recent entry in the fgraph ret stack, and so on. When arch_stack_walk() is used to dump the current task's stack, it starts from the caller of arch_stack_walk(). However, arch_stack_walk() can be traced, and so may push an entry on to the fgraph ret stack, leaving the fgraph ret stack offset by one from the expected position. This can be seen when dumping the stack via /proc/self/stack, where enabling the graph tracer results in an unexpected `stack_trace_save_tsk` entry at the start of the trace, and `el0_svc` missing form the end of the trace. This patch fixes this by marking arch_stack_walk() as notrace, as we do for all other functions on the path to ftrace_graph_get_ret_stack(). While a few helper functions are not marked notrace, their calls/returns are balanced, and will have no observable effect when examining the fgraph ret stack. It is possible for an exeption boundary to cause a similar offset if the return address of the interrupted context was in the LR. Fixing those cases will require some more substantial rework, and is left for subsequent patches. Before: | # cat /proc/self/stack | [<0>] proc_pid_stack+0xc4/0x140 | [<0>] proc_single_show+0x6c/0x120 | [<0>] seq_read_iter+0x240/0x4e0 | [<0>] seq_read+0xe8/0x140 | [<0>] vfs_read+0xb8/0x1e4 | [<0>] ksys_read+0x74/0x100 | [<0>] __arm64_sys_read+0x28/0x3c | [<0>] invoke_syscall+0x50/0x120 | [<0>] el0_svc_common.constprop.0+0xc4/0xd4 | [<0>] do_el0_svc+0x30/0x9c | [<0>] el0_svc+0x2c/0x54 | [<0>] el0t_64_sync_handler+0x1a8/0x1b0 | [<0>] el0t_64_sync+0x198/0x19c | # echo function_graph > /sys/kernel/tracing/current_tracer | # cat /proc/self/stack | [<0>] stack_trace_save_tsk+0xa4/0x110 | [<0>] proc_pid_stack+0xc4/0x140 | [<0>] proc_single_show+0x6c/0x120 | [<0>] seq_read_iter+0x240/0x4e0 | [<0>] seq_read+0xe8/0x140 | [<0>] vfs_read+0xb8/0x1e4 | [<0>] ksys_read+0x74/0x100 | [<0>] __arm64_sys_read+0x28/0x3c | [<0>] invoke_syscall+0x50/0x120 | [<0>] el0_svc_common.constprop.0+0xc4/0xd4 | [<0>] do_el0_svc+0x30/0x9c | [<0>] el0t_64_sync_handler+0x1a8/0x1b0 | [<0>] el0t_64_sync+0x198/0x19c After: | # cat /proc/self/stack | [<0>] proc_pid_stack+0xc4/0x140 | [<0>] proc_single_show+0x6c/0x120 | [<0>] seq_read_iter+0x240/0x4e0 | [<0>] seq_read+0xe8/0x140 | [<0>] vfs_read+0xb8/0x1e4 | [<0>] ksys_read+0x74/0x100 | [<0>] __arm64_sys_read+0x28/0x3c | [<0>] invoke_syscall+0x50/0x120 | [<0>] el0_svc_common.constprop.0+0xc4/0xd4 | [<0>] do_el0_svc+0x30/0x9c | [<0>] el0_svc+0x2c/0x54 | [<0>] el0t_64_sync_handler+0x1a8/0x1b0 | [<0>] el0t_64_sync+0x198/0x19c | # echo function_graph > /sys/kernel/tracing/current_tracer | # cat /proc/self/stack | [<0>] proc_pid_stack+0xc4/0x140 | [<0>] proc_single_show+0x6c/0x120 | [<0>] seq_read_iter+0x240/0x4e0 | [<0>] seq_read+0xe8/0x140 | [<0>] vfs_read+0xb8/0x1e4 | [<0>] ksys_read+0x74/0x100 | [<0>] __arm64_sys_read+0x28/0x3c | [<0>] invoke_syscall+0x50/0x120 | [<0>] el0_svc_common.constprop.0+0xc4/0xd4 | [<0>] do_el0_svc+0x30/0x9c | [<0>] el0_svc+0x2c/0x54 | [<0>] el0t_64_sync_handler+0x1a8/0x1b0 | [<0>] el0t_64_sync+0x198/0x19c Cc: Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Madhavan T. Venkataraman Cc: Mark Brown Cc: Will Deacon Reviwed-by: Mark Brown Link: https://lore.kernel.org/r/20210802164845.45506-3-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/stacktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index b83c8d911930..8982a2b78acf 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -218,7 +218,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) #ifdef CONFIG_STACKTRACE -noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, +noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { From ce78ffa3ef1681065ba451cfd545da6126f5ca88 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 3 Aug 2021 11:14:03 +0100 Subject: [PATCH 1175/1469] net: really fix the build... Signed-off-by: David S. Miller --- drivers/bus/mhi/core/internal.h | 2 +- drivers/bus/mhi/core/main.c | 9 ++++++--- drivers/net/mhi/net.c | 2 +- drivers/net/wwan/mhi_wwan_ctrl.c | 2 +- include/linux/mhi.h | 7 ++++++- net/qrtr/mhi.c | 16 +++++++++++++++- 6 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5b9ea66b92dc..bc239a11aa69 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan); + struct mhi_chan *mhi_chan, unsigned int flags); int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index fc9196f11cb7..84448233f64c 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan) + struct mhi_chan *mhi_chan, unsigned int flags) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,6 +1455,9 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; + if (mhi_chan->dir == DMA_FROM_DEVICE) + mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); + /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1610,7 +1613,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) } /* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1621,7 +1624,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); if (ret) goto error_open_chan; } diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index e60e38c1f09d..11be6bcdd551 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -335,7 +335,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, u64_stats_init(&mhi_netdev->stats.tx_syncp); /* Start MHI channels */ - err = mhi_prepare_for_transfer(mhi_dev); + err = mhi_prepare_for_transfer(mhi_dev, 0); if (err) goto out_err; diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index 1bc6b69aa530..1e18420ce404 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -110,7 +110,7 @@ static int mhi_wwan_ctrl_start(struct wwan_port *port) int ret; /* Start mhi device's channel(s) */ - ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev); + ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0); if (ret) return ret; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..5e08468854db 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -719,8 +719,13 @@ void mhi_device_put(struct mhi_device *mhi_dev); * host and device execution environments match and * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * @flags: MHI channel flags */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, + unsigned int flags); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index fa611678af05..1dc955ca57d3 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -15,6 +15,7 @@ struct qrtr_mhi_dev { struct qrtr_endpoint ep; struct mhi_device *mhi_dev; struct device *dev; + struct completion ready; }; /* From MHI to QRTR */ @@ -50,6 +51,10 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep); int rc; + rc = wait_for_completion_interruptible(&qdev->ready); + if (rc) + goto free_skb; + if (skb->sk) sock_hold(skb->sk); @@ -79,7 +84,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev); + rc = mhi_prepare_for_transfer(mhi_dev, 0); if (rc) return rc; @@ -96,6 +101,15 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; + /* start channels */ + rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); + if (rc) { + qrtr_endpoint_unregister(&qdev->ep); + dev_set_drvdata(&mhi_dev->dev, NULL); + return rc; + } + + complete_all(&qdev->ready); dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; From 2e2f1e8d0450c561c0c936b4b67e8b5a95975fb7 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 30 Jul 2021 14:26:22 +0200 Subject: [PATCH 1176/1469] KVM: x86: hyper-v: Check access to hypercall before reading XMM registers In case guest doesn't have access to the particular hypercall we can avoid reading XMM registers. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Siddharth Chandrasekaran Signed-off-by: Paolo Bonzini Message-Id: <20210730122625.112848-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index b07592ca92f0..cb7e045905a5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2173,9 +2173,6 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; hc.rep = !!(hc.rep_cnt || hc.rep_idx); - if (hc.fast && is_xmm_fast_hypercall(&hc)) - kvm_hv_hypercall_read_xmm(&hc); - trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx, hc.ingpa, hc.outgpa); @@ -2184,6 +2181,9 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) goto hypercall_complete; } + if (hc.fast && is_xmm_fast_hypercall(&hc)) + kvm_hv_hypercall_read_xmm(&hc); + switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: if (unlikely(hc.rep)) { From f5714bbb5b3120b33dfbf3d81ffc0b98ae4cd4c1 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 30 Jul 2021 14:26:23 +0200 Subject: [PATCH 1177/1469] KVM: x86: Introduce trace_kvm_hv_hypercall_done() Hypercall failures are unusual with potentially far going consequences so it would be useful to see their results when tracing. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Siddharth Chandrasekaran Signed-off-by: Paolo Bonzini Message-Id: <20210730122625.112848-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 1 + arch/x86/kvm/trace.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index cb7e045905a5..2945b93dbadd 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2016,6 +2016,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { + trace_kvm_hv_hypercall_done(result); kvm_hv_hypercall_set_result(vcpu, result); ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b484141ea15b..03ebe368333e 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -92,6 +92,21 @@ TRACE_EVENT(kvm_hv_hypercall, __entry->outgpa) ); +TRACE_EVENT(kvm_hv_hypercall_done, + TP_PROTO(u64 result), + TP_ARGS(result), + + TP_STRUCT__entry( + __field(__u64, result) + ), + + TP_fast_assign( + __entry->result = result; + ), + + TP_printk("result 0x%llx", __entry->result) +); + /* * Tracepoint for Xen hypercall. */ From 4e62aa96d6e55c1b2a4e841f1f8601eae81e81ae Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 30 Jul 2021 14:26:24 +0200 Subject: [PATCH 1178/1469] KVM: x86: hyper-v: Check if guest is allowed to use XMM registers for hypercall input MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TLFS states that "Availability of the XMM fast hypercall interface is indicated via the “Hypervisor Feature Identification” CPUID Leaf (0x40000003, see section 2.4.4) ... Any attempt to use this interface when the hypervisor does not indicate availability will result in a #UD fault." Implement the check for 'strict' mode (KVM_CAP_HYPERV_ENFORCE_CPUID). Signed-off-by: Vitaly Kuznetsov Reviewed-by: Siddharth Chandrasekaran Signed-off-by: Paolo Bonzini Message-Id: <20210730122625.112848-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2945b93dbadd..0b38f944c6b6 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2140,6 +2140,7 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_hv_hcall hc; u64 ret = HV_STATUS_SUCCESS; @@ -2177,13 +2178,21 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx, hc.ingpa, hc.outgpa); - if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) { + if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) { ret = HV_STATUS_ACCESS_DENIED; goto hypercall_complete; } - if (hc.fast && is_xmm_fast_hypercall(&hc)) + if (hc.fast && is_xmm_fast_hypercall(&hc)) { + if (unlikely(hv_vcpu->enforce_cpuid && + !(hv_vcpu->cpuid_cache.features_edx & + HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + kvm_hv_hypercall_read_xmm(&hc); + } switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: From 2476b5a1b16ced78a80629da8ff87538d5c95073 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 30 Jul 2021 14:26:25 +0200 Subject: [PATCH 1179/1469] KVM: selftests: Test access to XMM fast hypercalls Check that #UD is raised if bit 16 is clear in HYPERV_CPUID_FEATURES.EDX and an 'XMM fast' hypercall is issued. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Siddharth Chandrasekaran Signed-off-by: Paolo Bonzini Message-Id: <20210730122625.112848-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- .../selftests/kvm/include/x86_64/hyperv.h | 5 ++- .../selftests/kvm/x86_64/hyperv_features.c | 41 +++++++++++++++++-- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index 412eaee7884a..b66910702c0a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -117,7 +117,7 @@ #define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) #define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) #define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) #define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) #define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) @@ -182,4 +182,7 @@ #define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 +/* hypercall options */ +#define HV_HYPERCALL_FAST_BIT BIT(16) + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index af27c7e829c1..91d88aaa9899 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -47,6 +47,7 @@ static void do_wrmsr(u32 idx, u64 val) } static int nr_gp; +static int nr_ud; static inline u64 hypercall(u64 control, vm_vaddr_t input_address, vm_vaddr_t output_address) @@ -80,6 +81,12 @@ static void guest_gp_handler(struct ex_regs *regs) regs->rip = (uint64_t)&wrmsr_end; } +static void guest_ud_handler(struct ex_regs *regs) +{ + nr_ud++; + regs->rip += 3; +} + struct msr_data { uint32_t idx; bool available; @@ -90,6 +97,7 @@ struct msr_data { struct hcall_data { uint64_t control; uint64_t expect; + bool ud_expected; }; static void guest_msr(struct msr_data *msr) @@ -117,13 +125,26 @@ static void guest_msr(struct msr_data *msr) static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) { int i = 0; + u64 res, input, output; wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); while (hcall->control) { - GUEST_ASSERT(hypercall(hcall->control, pgs_gpa, - pgs_gpa + 4096) == hcall->expect); + nr_ud = 0; + if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { + input = pgs_gpa; + output = pgs_gpa + 4096; + } else { + input = output = 0; + } + + res = hypercall(hcall->control, input, output); + if (hcall->ud_expected) + GUEST_ASSERT(nr_ud == 1); + else + GUEST_ASSERT(res == hcall->expect); + GUEST_SYNC(i++); } @@ -552,8 +573,18 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall recomm.ebx = 0xfff; hcall->expect = HV_STATUS_SUCCESS; break; - case 17: + /* XMM fast hypercall */ + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; + hcall->ud_expected = true; + break; + case 18: + feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + hcall->ud_expected = false; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 19: /* END */ hcall->control = 0; break; @@ -625,6 +656,10 @@ int main(void) /* Test hypercalls */ vm = vm_create_default(VCPU_ID, 0, guest_hcall); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); From ae954bbc451d267f7d60d7b49db811d5a68ebd7b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Aug 2021 02:25:31 -0400 Subject: [PATCH 1180/1469] sctp: move the active_key update after sh_keys is added In commit 58acd1009226 ("sctp: update active_key for asoc when old key is being replaced"), sctp_auth_asoc_init_active_key() is called to update the active_key right after the old key is deleted and before the new key is added, and it caused that the active_key could be found with the key_id. In Ying Xu's testing, the BUG_ON in sctp_auth_asoc_init_active_key() was triggered: [ ] kernel BUG at net/sctp/auth.c:416! [ ] RIP: 0010:sctp_auth_asoc_init_active_key.part.8+0xe7/0xf0 [sctp] [ ] Call Trace: [ ] sctp_auth_set_key+0x16d/0x1b0 [sctp] [ ] sctp_setsockopt.part.33+0x1ba9/0x2bd0 [sctp] [ ] __sys_setsockopt+0xd6/0x1d0 [ ] __x64_sys_setsockopt+0x20/0x30 [ ] do_syscall_64+0x5b/0x1a0 So fix it by moving the active_key update after sh_keys is added. Fixes: 58acd1009226 ("sctp: update active_key for asoc when old key is being replaced") Reported-by: Ying Xu Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/auth.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index fe74c5f95630..db6b7373d16c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -857,14 +857,18 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength); cur_key->key = key; - if (replace) { - list_del_init(&shkey->key_list); - sctp_auth_shkey_release(shkey); - if (asoc && asoc->active_key_id == auth_key->sca_keynumber) - sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + if (!replace) { + list_add(&cur_key->key_list, sh_keys); + return 0; } + + list_del_init(&shkey->key_list); + sctp_auth_shkey_release(shkey); list_add(&cur_key->key_list, sh_keys); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber) + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + return 0; } From f41e57af926ad840d114439d34cafc0533bf25f0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Aug 2021 17:21:53 +0200 Subject: [PATCH 1181/1469] net: sparx5: fix bitmask on 32-bit targets I saw the build failure that was fixed in commit 6387f65e2acb ("net: sparx5: fix compiletime_assert for GCC 4.9") and noticed another issue that was introduced in the same patch: Using GENMASK() to create a 64-bit mask does not work on 32-bit architectures. This probably won't ever happen on this driver since it's specific to a 64-bit SoC, but it's better to write it portably, so use GENMASK_ULL() instead. Fixes: f3cad2611a77 ("net: sparx5: add hostmode with phylink support") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index 1a240e6bddd0..cb68eaaac881 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -32,7 +32,7 @@ static void __ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width) u32 byte = (35 - (pos / 8)); /* Calculate the Start bit position in the Start IFH byte */ u32 bit = (pos % 8); - u64 encode = GENMASK(bit + width - 1, bit) & (value << bit); + u64 encode = GENMASK_ULL(bit + width - 1, bit) & (value << bit); /* The b0-b7 goes into the start IFH byte */ if (encode & 0xFF) From 9c9c6d0ab08acfe41c9f7efa72c4ad3f133a266b Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 28 Jul 2021 16:34:11 -0700 Subject: [PATCH 1182/1469] drm/i915: Correct SFC_DONE register offset The register offset for SFC_DONE was missing a '0' at the end, causing us to read from a non-existent register address. We only use this register in error state dumps so the mistake hasn't caused any real problems, but fixing it will hopefully make the error state dumps a bit more useful for debugging. Fixes: e50dbdbfd9fb ("drm/i915/tgl: Add SFC instdone to error state") Cc: Mika Kuoppala Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210728233411.2365788-1-matthew.d.roper@intel.com Reviewed-by: Mika Kuoppala (cherry picked from commit 82929a2140eb99f1f1d21855f3f580e70d7abdd8) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 94fde5ca26ae..41186c1f771e 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -422,7 +422,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN12_HCP_SFC_LOCK_ACK_BIT REG_BIT(1) #define GEN12_HCP_SFC_USAGE_BIT REG_BIT(0) -#define GEN12_SFC_DONE(n) _MMIO(0x1cc00 + (n) * 0x100) +#define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000) #define GEN12_SFC_DONE_MAX 4 #define RING_PP_DIR_BASE(base) _MMIO((base) + 0x228) From 1354d830cb8f9be966cc07fc61368af27ffb7c4a Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 21 Jul 2021 10:23:54 -0500 Subject: [PATCH 1183/1469] drm/i915: Call i915_globals_exit() if pci_register_device() fails In the unlikely event that pci_register_device() fails, we were tearing down our PMU setup but not globals. This leaves a bunch of memory slabs lying around. Signed-off-by: Jason Ekstrand Fixes: 32eb6bcfdda9 ("drm/i915: Make request allocation caches global") [danvet: Fix conflicts against removal of the globals_flush infrastructure.] Reviewed-by: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210721152358.2893314-3-jason@jlekstrand.net (cherry picked from commit db484889d1ff0645e07e360d3e3ad306c0515821) Signed-off-by: Rodrigo Vivi [Fixed small conflict while cherry picking] --- drivers/gpu/drm/i915/i915_globals.c | 2 +- drivers/gpu/drm/i915/i915_pci.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c index 77f1911c463b..2db90e770616 100644 --- a/drivers/gpu/drm/i915/i915_globals.c +++ b/drivers/gpu/drm/i915/i915_globals.c @@ -148,7 +148,7 @@ static void __exit __i915_globals_flush(void) atomic_dec(&active); } -void __exit i915_globals_exit(void) +void i915_globals_exit(void) { GEM_BUG_ON(atomic_read(&active)); diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 83b500bb170c..2880ec57c97d 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1195,6 +1195,7 @@ static int __init i915_init(void) err = pci_register_driver(&i915_pci_driver); if (err) { i915_pmu_exit(); + i915_globals_exit(); return err; } From 97367c97226aab8b298ada954ce12659ee3ad2a4 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 3 Aug 2021 13:43:12 +0200 Subject: [PATCH 1184/1469] ALSA: seq: Fix racy deletion of subscriber It turned out that the current implementation of the port subscription is racy. The subscription contains two linked lists, and we have to add to or delete from both lists. Since both connection and disconnection procedures perform the same order for those two lists (i.e. src list, then dest list), when a deletion happens during a connection procedure, the src list may be deleted before the dest list addition completes, and this may lead to a use-after-free or an Oops, even though the access to both lists are protected via mutex. The simple workaround for this race is to change the access order for the disconnection, namely, dest list, then src list. This assures that the connection has been established when disconnecting, and also the concurrent deletion can be avoided. Reported-and-tested-by: folkert Cc: Link: https://lore.kernel.org/r/20210801182754.GP890690@belle.intranet.vanheusden.com Link: https://lore.kernel.org/r/20210803114312.2536-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/seq/seq_ports.c | 39 ++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index b9c2ce2b8d5a..84d78630463e 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -514,10 +514,11 @@ static int check_and_subscribe_port(struct snd_seq_client *client, return err; } -static void delete_and_unsubscribe_port(struct snd_seq_client *client, - struct snd_seq_client_port *port, - struct snd_seq_subscribers *subs, - bool is_src, bool ack) +/* called with grp->list_mutex held */ +static void __delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; struct list_head *list; @@ -525,7 +526,6 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, grp = is_src ? &port->c_src : &port->c_dest; list = is_src ? &subs->src_list : &subs->dest_list; - down_write(&grp->list_mutex); write_lock_irq(&grp->list_lock); empty = list_empty(list); if (!empty) @@ -535,6 +535,18 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, if (!empty) unsubscribe_port(client, port, grp, &subs->info, ack); +} + +static void delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack) +{ + struct snd_seq_port_subs_info *grp; + + grp = is_src ? &port->c_src : &port->c_dest; + down_write(&grp->list_mutex); + __delete_and_unsubscribe_port(client, port, subs, is_src, ack); up_write(&grp->list_mutex); } @@ -590,27 +602,30 @@ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_client_port *dest_port, struct snd_seq_port_subscribe *info) { - struct snd_seq_port_subs_info *src = &src_port->c_src; + struct snd_seq_port_subs_info *dest = &dest_port->c_dest; struct snd_seq_subscribers *subs; int err = -ENOENT; - down_write(&src->list_mutex); + /* always start from deleting the dest port for avoiding concurrent + * deletions + */ + down_write(&dest->list_mutex); /* look for the connection */ - list_for_each_entry(subs, &src->list_head, src_list) { + list_for_each_entry(subs, &dest->list_head, dest_list) { if (match_subs_info(info, &subs->info)) { - atomic_dec(&subs->ref_count); /* mark as not ready */ + __delete_and_unsubscribe_port(dest_client, dest_port, + subs, false, + connector->number != dest_client->number); err = 0; break; } } - up_write(&src->list_mutex); + up_write(&dest->list_mutex); if (err < 0) return err; delete_and_unsubscribe_port(src_client, src_port, subs, true, connector->number != src_client->number); - delete_and_unsubscribe_port(dest_client, dest_port, subs, false, - connector->number != dest_client->number); kfree(subs); return 0; } From c87a4c542b5a796f795fec2b7a909c7d3067b11c Mon Sep 17 00:00:00 2001 From: Bijie Xu Date: Tue, 3 Aug 2021 11:40:18 +0200 Subject: [PATCH 1185/1469] net: flow_offload: correct comments mismatch with code Correct mismatch between the name of flow_offload_has_one_action() and its kdoc entry. Found using ./scripts/kernel-doc -Werror -none include/net/flow_offload.h Signed-off-by: Bijie Xu Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/net/flow_offload.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 69c9eabf8325..f3c2841566a0 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -293,7 +293,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action) } /** - * flow_action_has_one_action() - check if exactly one action is present + * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * * Returns true if exactly one action is present. From 0161d151f3e36306219f5aa6f5f6b3877038afd3 Mon Sep 17 00:00:00 2001 From: Bijie Xu Date: Tue, 3 Aug 2021 11:40:19 +0200 Subject: [PATCH 1186/1469] net: sched: provide missing kdoc for tcf_pkt_info and tcf_ematch_ops Provide missing kdoc of fields of struct tcf_pkt_info and tcf_ematch_ops. Found using ./scripts/kernel-doc -none -Werror include/net/pkt_cls.h Signed-off-by: Bijie Xu Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index ec7823921bd2..298a8d10168b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -337,6 +337,9 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** * struct tcf_pkt_info - packet information + * + * @ptr: start of the pkt data + * @nexthdr: offset of the next header */ struct tcf_pkt_info { unsigned char * ptr; @@ -355,6 +358,7 @@ struct tcf_ematch_ops; * @ops: the operations lookup table of the corresponding ematch module * @datalen: length of the ematch specific configuration data * @data: ematch specific data + * @net: the network namespace */ struct tcf_ematch { struct tcf_ematch_ops * ops; From 9fdc5d85a8fe684cdf24dc31c6bc4a727decfe87 Mon Sep 17 00:00:00 2001 From: Fei Qin Date: Tue, 3 Aug 2021 12:39:11 +0200 Subject: [PATCH 1187/1469] nfp: update ethtool reporting of pauseframe control Pauseframe control is set to symmetric mode by default on the NFP. Pause frames can not be configured through ethtool now, but ethtool can report the supported mode. Fixes: 265aeb511bd5 ("nfp: add support for .get_link_ksettings()") Signed-off-by: Fei Qin Signed-off-by: Louis Peens Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1b482446536d..8803faadd302 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -286,6 +286,8 @@ nfp_net_get_link_ksettings(struct net_device *netdev, /* Init to unknowns */ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; cmd->base.duplex = DUPLEX_UNKNOWN; From 4039146777a91e1576da2bf38e0d8a1061a1ae47 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 3 Aug 2021 12:00:16 +0200 Subject: [PATCH 1188/1469] net: ipv6: fix returned variable type in ip6_skb_dst_mtu The patch fixing the returned value of ip6_skb_dst_mtu (int -> unsigned int) was rebased between its initial review and the version applied. In the meantime fade56410c22 was applied, which added a new variable (int) used as the returned value. This lead to a mismatch between the function prototype and the variable used as the return value. Fixes: 40fc3054b458 ("net: ipv6: fix return value of ip6_skb_dst_mtu") Cc: Vadim Fedorenko Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 625a38ccb5d9..0bf09a9bca4e 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -265,7 +265,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb) { - int mtu; + unsigned int mtu; struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; From ecd92e2167c30faa18df21e3ec3dbec510ddebaa Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 31 Jul 2021 13:13:40 +0200 Subject: [PATCH 1189/1469] s390: update defconfigs Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 2 +- arch/s390/configs/defconfig | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7de253f766e8..b88184019af9 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -335,7 +335,7 @@ CONFIG_L2TP_DEBUGFS=m CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m -CONFIG_BRIDGE=m +CONFIG_BRIDGE=y CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b671642967ba..1667a3cdcf0a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -325,7 +325,7 @@ CONFIG_L2TP_DEBUGFS=m CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m -CONFIG_BRIDGE=m +CONFIG_BRIDGE=y CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y From c2ec772b87408259cb01209a22fb4e1ae7d346de Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 30 Jul 2021 16:38:07 +0200 Subject: [PATCH 1190/1469] cpuidle: teo: Fix alternative idle state lookup There are three mistakes in the loop in teo_select() that is looking for an alternative candidate idle state. First, it should walk all of the idle states shallower than the current candidate one, including all of the disabled ones, but it terminates after the first enabled idle state. Second, it should not terminate its last step if idle state 0 is disabled (which is related to the first issue). Finally, it may return the current alternative candidate idle state prematurely if the time span criterion is not met by the idle state under consideration at the moment. To address the issues mentioned above, make the loop in question walk all of the idle states shallower than the current candidate idle state all the way down to idle state 0 and rearrange the checks in it. Fixes: 77577558f25d ("cpuidle: teo: Rework most recent idle duration values treatment") Reported-by: Doug Smythies Tested-by: Doug Smythies Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/governors/teo.c | 44 ++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 15 deletions(-) diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 7b91060e82f6..8c59050ba419 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -397,32 +397,46 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, intercept_sum = 0; recent_sum = 0; - for (i = idx - 1; i >= idx0; i--) { + for (i = idx - 1; i >= 0; i--) { struct teo_bin *bin = &cpu_data->state_bins[i]; s64 span_ns; intercept_sum += bin->intercepts; recent_sum += bin->recent; - if (dev->states_usage[i].disable) - continue; - span_ns = teo_middle_of_bin(i, drv); - if (!teo_time_ok(span_ns)) { - /* - * The current state is too shallow, so select - * the first enabled deeper state. - */ - duration_ns = last_enabled_span_ns; - idx = last_enabled_idx; - break; - } if ((!alt_recent || 2 * recent_sum > idx_recent_sum) && (!alt_intercepts || 2 * intercept_sum > idx_intercept_sum)) { - idx = i; - duration_ns = span_ns; + if (teo_time_ok(span_ns) && + !dev->states_usage[i].disable) { + idx = i; + duration_ns = span_ns; + } else { + /* + * The current state is too shallow or + * disabled, so take the first enabled + * deeper state with suitable time span. + */ + idx = last_enabled_idx; + duration_ns = last_enabled_span_ns; + } + break; + } + + if (dev->states_usage[i].disable) + continue; + + if (!teo_time_ok(span_ns)) { + /* + * The current state is too shallow, but if an + * alternative candidate state has been found, + * it may still turn out to be a better choice. + */ + if (last_enabled_idx != idx) + continue; + break; } From 4adae7dd10db10f20f51833dc11b3cf7a342ad38 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 30 Jul 2021 16:38:52 +0200 Subject: [PATCH 1191/1469] cpuidle: teo: Rename two local variables in teo_select() Rename two local variables in teo_select() so that their names better reflect their purpose. No functional impact. Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/governors/teo.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 8c59050ba419..d9262db79cae 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -382,8 +382,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, alt_intercepts = 2 * idx_intercept_sum > cpu_data->total - idx_hit_sum; alt_recent = idx_recent_sum > NR_RECENT / 2; if (alt_recent || alt_intercepts) { - s64 last_enabled_span_ns = duration_ns; - int last_enabled_idx = idx; + s64 first_suitable_span_ns = duration_ns; + int first_suitable_idx = idx; /* * Look for the deepest idle state whose target residency had @@ -419,8 +419,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * disabled, so take the first enabled * deeper state with suitable time span. */ - idx = last_enabled_idx; - duration_ns = last_enabled_span_ns; + idx = first_suitable_idx; + duration_ns = first_suitable_span_ns; } break; } @@ -434,14 +434,14 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * alternative candidate state has been found, * it may still turn out to be a better choice. */ - if (last_enabled_idx != idx) + if (first_suitable_idx != idx) continue; break; } - last_enabled_span_ns = span_ns; - last_enabled_idx = i; + first_suitable_span_ns = span_ns; + first_suitable_idx = i; } } From 6511a8b5b7a65037340cd8ee91a377811effbc83 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 3 Aug 2021 18:14:44 +0200 Subject: [PATCH 1192/1469] Revert "ACPICA: Fix memory leak caused by _CID repair function" Revert commit c27bac0314131 ("ACPICA: Fix memory leak caused by _CID repair function") which is reported to cause a boot issue on Acer Swift 3 (SF314-51). Reported-by: Adrien Precigout Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/nsrepair2.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 38e10ab976e6..14b71b41e845 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -379,13 +379,6 @@ acpi_ns_repair_CID(struct acpi_evaluate_info *info, (*element_ptr)->common.reference_count = original_ref_count; - - /* - * The original_element holds a reference from the package object - * that represents _HID. Since a new element was created by _HID, - * remove the reference from the _CID package. - */ - acpi_ut_remove_reference(original_element); } element_ptr++; From 8b436a99cd708bd158231a0630ffa49b1d6175e4 Mon Sep 17 00:00:00 2001 From: Yangyang Li Date: Mon, 2 Aug 2021 14:56:14 +0800 Subject: [PATCH 1193/1469] RDMA/hns: Fix the double unlock problem of poll_sem If hns_roce_cmd_use_events() fails then it means that the poll_sem is not obtained, but the poll_sem is released in hns_roce_cmd_use_polling(), this will cause an unlock problem. This is the static checker warning: drivers/infiniband/hw/hns/hns_roce_main.c:926 hns_roce_init() error: double unlocked '&hr_dev->cmd.poll_sem' (orig line 879) Event mode and polling mode are mutually exclusive and resources are separated, so there is no need to process polling mode resources in event mode. The initial mode of cmd is polling mode, so even if cmd fails to switch to event mode, it is not necessary to switch to polling mode. Fixes: a389d016c030 ("RDMA/hns: Enable all CMDQ context") Fixes: 3d50503b3b33 ("RDMA/hns: Optimize cmd init and mode selection for hip08") Link: https://lore.kernel.org/r/1627887374-20019-1-git-send-email-liangwenpeng@huawei.com Reported-by: Dan Carpenter Signed-off-by: Yangyang Li Signed-off-by: Wenpeng Liang Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_cmd.c | 7 +++---- drivers/infiniband/hw/hns/hns_roce_main.c | 4 +--- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c index 8f68cc3ff193..84f3f2b5f097 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.c +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c @@ -213,8 +213,10 @@ int hns_roce_cmd_use_events(struct hns_roce_dev *hr_dev) hr_cmd->context = kcalloc(hr_cmd->max_cmds, sizeof(*hr_cmd->context), GFP_KERNEL); - if (!hr_cmd->context) + if (!hr_cmd->context) { + hr_dev->cmd_mod = 0; return -ENOMEM; + } for (i = 0; i < hr_cmd->max_cmds; ++i) { hr_cmd->context[i].token = i; @@ -228,7 +230,6 @@ int hns_roce_cmd_use_events(struct hns_roce_dev *hr_dev) spin_lock_init(&hr_cmd->context_lock); hr_cmd->use_events = 1; - down(&hr_cmd->poll_sem); return 0; } @@ -239,8 +240,6 @@ void hns_roce_cmd_use_polling(struct hns_roce_dev *hr_dev) kfree(hr_cmd->context); hr_cmd->use_events = 0; - - up(&hr_cmd->poll_sem); } struct hns_roce_cmd_mailbox * diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 078a97193f0e..cc6eab14a222 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -873,11 +873,9 @@ int hns_roce_init(struct hns_roce_dev *hr_dev) if (hr_dev->cmd_mod) { ret = hns_roce_cmd_use_events(hr_dev); - if (ret) { + if (ret) dev_warn(dev, "Cmd event mode failed, set back to poll!\n"); - hns_roce_cmd_use_polling(hr_dev); - } } ret = hns_roce_init_hem(hr_dev); From 30615bd21b4cc3c3bb5ae8bd70e2a915cc5f75c7 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 3 Aug 2021 17:08:33 +0100 Subject: [PATCH 1194/1469] ASoC: cs42l42: Fix inversion of ADC Notch Switch control The underlying register field has inverted sense (0 = enabled) so the control definition must be marked as inverted. Signed-off-by: Richard Fitzgerald Fixes: 2c394ca79604 ("ASoC: Add support for CS42L42 codec") Link: https://lore.kernel.org/r/20210803160834.9005-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 08ca05bfbeb3..2db87e3a4dc3 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -437,7 +437,7 @@ static SOC_ENUM_SINGLE_DECL(cs42l42_wnf05_freq_enum, CS42L42_ADC_WNF_HPF_CTL, static const struct snd_kcontrol_new cs42l42_snd_controls[] = { /* ADC Volume and Filter Controls */ SOC_SINGLE("ADC Notch Switch", CS42L42_ADC_CTL, - CS42L42_ADC_NOTCH_DIS_SHIFT, true, false), + CS42L42_ADC_NOTCH_DIS_SHIFT, true, true), SOC_SINGLE("ADC Weak Force Switch", CS42L42_ADC_CTL, CS42L42_ADC_FORCE_WEAK_VCM_SHIFT, true, false), SOC_SINGLE("ADC Invert Switch", CS42L42_ADC_CTL, From 8b353bbeae20e2214c9d9d88bcb2fda4ba145d83 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 3 Aug 2021 17:08:34 +0100 Subject: [PATCH 1195/1469] ASoC: cs42l42: Remove duplicate control for WNF filter frequency The driver was defining two ALSA controls that both change the same register field for the wind noise filter corner frequency. The filter response has two corners, at different frequencies, and the duplicate controls most likely were an attempt to be able to set the value using either of the frequencies. However, having two controls changing the same field can be problematic and it is unnecessary. Both frequencies are related to each other so setting one implies exactly what the other would be. Removing a control affects user-side code, but there is currently no known use of the removed control so it would be best to remove it now before it becomes a problem. Signed-off-by: Richard Fitzgerald Fixes: 2c394ca79604 ("ASoC: Add support for CS42L42 codec") Link: https://lore.kernel.org/r/20210803160834.9005-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 2db87e3a4dc3..a00dc3c65549 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -425,15 +425,6 @@ static SOC_ENUM_SINGLE_DECL(cs42l42_wnf3_freq_enum, CS42L42_ADC_WNF_HPF_CTL, CS42L42_ADC_WNF_CF_SHIFT, cs42l42_wnf3_freq_text); -static const char * const cs42l42_wnf05_freq_text[] = { - "280Hz", "315Hz", "350Hz", "385Hz", - "420Hz", "455Hz", "490Hz", "525Hz" -}; - -static SOC_ENUM_SINGLE_DECL(cs42l42_wnf05_freq_enum, CS42L42_ADC_WNF_HPF_CTL, - CS42L42_ADC_WNF_CF_SHIFT, - cs42l42_wnf05_freq_text); - static const struct snd_kcontrol_new cs42l42_snd_controls[] = { /* ADC Volume and Filter Controls */ SOC_SINGLE("ADC Notch Switch", CS42L42_ADC_CTL, @@ -451,7 +442,6 @@ static const struct snd_kcontrol_new cs42l42_snd_controls[] = { CS42L42_ADC_HPF_EN_SHIFT, true, false), SOC_ENUM("HPF Corner Freq", cs42l42_hpf_freq_enum), SOC_ENUM("WNF 3dB Freq", cs42l42_wnf3_freq_enum), - SOC_ENUM("WNF 05dB Freq", cs42l42_wnf05_freq_enum), /* DAC Volume and Filter Controls */ SOC_SINGLE("DACA Invert Switch", CS42L42_DAC_CTL1, From abc7285d89ffd089739a1a3059ddd843dd019637 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 2 Aug 2021 16:19:14 -0700 Subject: [PATCH 1196/1469] mptcp: drop unused rcu member in mptcp_pm_addr_entry kfree_rcu() had been removed from pm_netlink.c, so this rcu field in struct mptcp_pm_addr_entry became useless. Let's drop it. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20210802231914.54709-1-mathew.j.martineau@linux.intel.com Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d2591ebf01d9..56263c2c4014 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry { struct mptcp_addr_info addr; u8 flags; int ifindex; - struct rcu_head rcu; struct socket *lsk; }; From e3ea110d6e796146920e1be0108464ebcf283ef7 Mon Sep 17 00:00:00 2001 From: Harshavardhan Unnibhavi Date: Mon, 2 Aug 2021 19:35:06 +0200 Subject: [PATCH 1197/1469] VSOCK: handle VIRTIO_VSOCK_OP_CREDIT_REQUEST The original implementation of the virtio-vsock driver does not handle a VIRTIO_VSOCK_OP_CREDIT_REQUEST as required by the virtio-vsock specification. The vsock device emulated by vhost-vsock and the virtio-vsock driver never uses this request, which was probably why nobody noticed it. However, another implementation of the device may use this request type. Hence, this commit introduces a way to handle an explicit credit request by responding with a corresponding credit update as required by the virtio-vsock specification. Fixes: 06a8fc78367d ("VSOCK: Introduce virtio_vsock_common.ko") Signed-off-by: Harshavardhan Unnibhavi Reviewed-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20210802173506.2383-1-harshanavkis@gmail.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/virtio_transport_common.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 169ba8b72a63..081e7ae93cb1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1079,6 +1079,9 @@ virtio_transport_recv_connected(struct sock *sk, virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; + case VIRTIO_VSOCK_OP_CREDIT_REQUEST: + virtio_transport_send_credit_update(vsk); + break; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: sk->sk_write_space(sk); break; From d1a58c013a5837451e3213e7a426d350fa524ead Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 3 Aug 2021 08:37:46 +0200 Subject: [PATCH 1198/1469] net: dsa: qca: ar9331: reorder MDIO write sequence In case of this switch we work with 32bit registers on top of 16bit bus. Some registers (for example access to forwarding database) have trigger bit on the first 16bit half of request and the result + configuration of request in the second half. Without this patch, we would trigger database operation and overwrite result in one run. To make it work properly, we should do the second part of transfer before the first one is done. So far, this rule seems to work for all registers on this switch. Fixes: ec6698c272de ("net: dsa: add support for Atheros AR9331 built-in switch") Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210803063746.3600-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/dsa/qca/ar9331.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index ca2ad77b71f1..6686192e1883 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -837,16 +837,24 @@ static int ar9331_mdio_write(void *ctx, u32 reg, u32 val) return 0; } - ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val); - if (ret < 0) - goto error; - + /* In case of this switch we work with 32bit registers on top of 16bit + * bus. Some registers (for example access to forwarding database) have + * trigger bit on the first 16bit half of request, the result and + * configuration of request in the second half. + * To make it work properly, we should do the second part of transfer + * before the first one is done. + */ ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg + 2, val >> 16); if (ret < 0) goto error; + ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val); + if (ret < 0) + goto error; + return 0; + error: dev_err_ratelimited(&sbus->dev, "Bus error. Failed to write register.\n"); return ret; From d4067395519b40d4ee9b7c26347233e4ae59f900 Mon Sep 17 00:00:00 2001 From: Jinchao Wang Date: Sat, 26 Jun 2021 13:58:28 +0800 Subject: [PATCH 1199/1469] arc: Prefer unsigned int to bare use of unsigned Fix checkpatch warnings: WARNING: Prefer 'unsigned int' to bare use of 'unsigned' Signed-off-by: Jinchao Wang Signed-off-by: Vineet Gupta --- arch/arc/include/asm/checksum.h | 2 +- arch/arc/include/asm/perf_event.h | 2 +- arch/arc/kernel/unwind.c | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h index 69debd77cd04..0b485800a392 100644 --- a/arch/arc/include/asm/checksum.h +++ b/arch/arc/include/asm/checksum.h @@ -24,7 +24,7 @@ */ static inline __sum16 csum_fold(__wsum s) { - unsigned r = s << 16 | s >> 16; /* ror */ + unsigned int r = s << 16 | s >> 16; /* ror */ s = ~s; s -= r; return s >> 16; diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 30b9ae511ea9..e1971d34ef30 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -123,7 +123,7 @@ static const char * const arc_pmu_ev_hw_map[] = { #define C(_x) PERF_COUNT_HW_CACHE_##_x #define CACHE_OP_UNSUPPORTED 0xffff -static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { [C(OP_READ)] = { [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 47bab67f8649..9e28058cdba8 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -260,7 +260,7 @@ static void init_unwind_hdr(struct unwind_table *table, { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; - unsigned n; + unsigned int n; const u32 *fde; struct { u8 version; @@ -462,7 +462,7 @@ static uleb128_t get_uleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; uleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -483,7 +483,7 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; sleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -609,7 +609,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, static signed fde_pointer_type(const u32 *cie) { const u8 *ptr = (const u8 *)(cie + 2); - unsigned version = *ptr; + unsigned int version = *ptr; if (*++ptr) { const char *aug; @@ -904,7 +904,7 @@ int arc_unwind(struct unwind_frame_info *frame) const u8 *ptr = NULL, *end = NULL; unsigned long pc = UNW_PC(frame) - frame->call_frame; unsigned long startLoc = 0, endLoc = 0, cfa; - unsigned i; + unsigned int i; signed ptrType = -1; uleb128_t retAddrReg = 0; const struct unwind_table *table; From 81e82fa58098b13af206c8ba4edb690bf5b7d5d5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 4 Jul 2021 10:28:24 +0100 Subject: [PATCH 1200/1469] arc: Fix spelling mistake and grammar in Kconfig There is a spelling mistake and incorrect grammar in the Kconfig text. Fix them. Signed-off-by: Colin Ian King Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index d8f51eb8963b..b5bf68e74732 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -409,7 +409,7 @@ choice help Depending on the configuration, CPU can contain DSP registers (ACC0_GLO, ACC0_GHI, DSP_BFLY0, DSP_CTRL, DSP_FFT_CTRL). - Bellow is options describing how to handle these registers in + Below are options describing how to handle these registers in interrupt entry / exit and in context switch. config ARC_DSP_NONE From bf79167fd86f3b97390fe2e70231d383526bd9cc Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 10 Jul 2021 07:50:33 -0700 Subject: [PATCH 1201/1469] ARC: Fix CONFIG_STACKDEPOT Enabling CONFIG_STACKDEPOT results in the following build error. arc-elf-ld: lib/stackdepot.o: in function `filter_irq_stacks': stackdepot.c:(.text+0x456): undefined reference to `__irqentry_text_start' arc-elf-ld: stackdepot.c:(.text+0x456): undefined reference to `__irqentry_text_start' arc-elf-ld: stackdepot.c:(.text+0x476): undefined reference to `__irqentry_text_end' arc-elf-ld: stackdepot.c:(.text+0x476): undefined reference to `__irqentry_text_end' arc-elf-ld: stackdepot.c:(.text+0x484): undefined reference to `__softirqentry_text_start' arc-elf-ld: stackdepot.c:(.text+0x484): undefined reference to `__softirqentry_text_start' arc-elf-ld: stackdepot.c:(.text+0x48c): undefined reference to `__softirqentry_text_end' arc-elf-ld: stackdepot.c:(.text+0x48c): undefined reference to `__softirqentry_text_end' Other architectures address this problem by adding IRQENTRY_TEXT and SOFTIRQENTRY_TEXT to the text segment, so do the same here. Signed-off-by: Guenter Roeck Signed-off-by: Vineet Gupta --- arch/arc/kernel/vmlinux.lds.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index e2146a8da195..529ae50f9fe2 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -88,6 +88,8 @@ SECTIONS CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) } From 3a715e80400f452b247caa55344f4f60250ffbcf Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 8 Jul 2021 17:13:48 -0700 Subject: [PATCH 1202/1469] ARC: fp: set FPU_STATUS.FWE to enable FPU_STATUS update on context switch FPU_STATUS register contains FP exception flags bits which are updated by core as side-effect of FP instructions but can also be manually wiggled such as by glibc C99 functions fe{raise,clear,test}except() etc. To effect the update, the programming model requires OR'ing FWE bit (31). This bit is write-only and RAZ, meaning it is effectively auto-cleared after write and thus needs to be set everytime: which is how glibc implements this. However there's another usecase of FPU_STATUS update, at the time of Linux task switch when incoming task value needs to be programmed into the register. This was added as part of f45ba2bd6da0dc ("ARCv2: fpu: preserve userspace fpu state") which missed OR'ing FWE bit, meaning the new value is effectively not being written at all. This patch remedies that. Interestingly, this snafu was not caught in interm glibc testing as the race window which relies on a specific exception bit to be set/clear is really small specially when it nvolves context switch. Fortunately this was caught by glibc's math/test-fenv-tls test which repeatedly set/clear exception flags in a big loop, concurrently in main program and also in a thread. Fixes: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/54 Fixes: f45ba2bd6da0dc ("ARCv2: fpu: preserve userspace fpu state") Cc: stable@vger.kernel.org #5.6+ Signed-off-by: Vineet Gupta --- arch/arc/kernel/fpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c index c67c0f0f5f77..ec640219d989 100644 --- a/arch/arc/kernel/fpu.c +++ b/arch/arc/kernel/fpu.c @@ -57,23 +57,26 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next) void fpu_init_task(struct pt_regs *regs) { + const unsigned int fwe = 0x80000000; + /* default rounding mode */ write_aux_reg(ARC_REG_FPU_CTRL, 0x100); - /* set "Write enable" to allow explicit write to exception flags */ - write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000); + /* Initialize to zero: setting requires FWE be set */ + write_aux_reg(ARC_REG_FPU_STATUS, fwe); } void fpu_save_restore(struct task_struct *prev, struct task_struct *next) { struct arc_fpu *save = &prev->thread.fpu; struct arc_fpu *restore = &next->thread.fpu; + const unsigned int fwe = 0x80000000; save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL); save->status = read_aux_reg(ARC_REG_FPU_STATUS); write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl); - write_aux_reg(ARC_REG_FPU_STATUS, restore->status); + write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status)); } #endif From d09560435cb712c9ec1e62b8a43a79b0af69fe77 Mon Sep 17 00:00:00 2001 From: Qiu Wenbo Date: Sun, 4 Jul 2021 16:34:41 +0800 Subject: [PATCH 1203/1469] riscv: dts: fix memory size for the SiFive HiFive Unmatched The production version of HiFive Unmatched have 16GB memory. Signed-off-by: Qiu Wenbo Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index b1c3c596578f..2e4ea84f27e7 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -24,7 +24,7 @@ memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x2 0x00000000>; + reg = <0x0 0x80000000 0x4 0x00000000>; }; soc { From a18b14d8886614b3c7d290c4cfc33389822b0535 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 6 Jul 2021 09:26:21 -0700 Subject: [PATCH 1204/1469] riscv: Disable STACKPROTECTOR_PER_TASK if GCC_PLUGIN_RANDSTRUCT is enabled riscv uses the value of TSK_STACK_CANARY to set stack-protector-guard-offset. With GCC_PLUGIN_RANDSTRUCT enabled, that value is non-deterministic, and with riscv:allmodconfig often results in build errors such as cc1: error: '8120' is not a valid offset in '-mstack-protector-guard-offset=' Enable STACKPROTECTOR_PER_TASK only if GCC_PLUGIN_RANDSTRUCT is disabled to fix the problem. Fixes: fea2fed201ee5 ("riscv: Enable per-task stack canaries") Signed-off-by: Guenter Roeck Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 8fcceb8eda07..31f9e92f1402 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -492,6 +492,7 @@ config CC_HAVE_STACKPROTECTOR_TLS config STACKPROTECTOR_PER_TASK def_bool y + depends on !GCC_PLUGIN_RANDSTRUCT depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS config PHYS_RAM_BASE From 5648c073c33d33a0a19d0cb1194a4eb88efe2b71 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Tue, 3 Aug 2021 21:47:11 +0200 Subject: [PATCH 1205/1469] USB: serial: option: add Telit FD980 composition 0x1056 Add the following Telit FD980 composition 0x1056: Cfg #1: mass storage Cfg #2: rndis, tty, adb, tty, tty, tty, tty Signed-off-by: Daniele Palmas Link: https://lore.kernel.org/r/20210803194711.3036-1-dnlplm@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 0fbe253dc570..039450069ca4 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1203,6 +1203,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff), /* Telit FN980 (PCIe) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), From 5f7b51bf09baca8e4f80cbe879536842bafb5f31 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 28 Jul 2021 17:01:15 +0200 Subject: [PATCH 1206/1469] netfilter: ipset: Limit the maximal range of consecutive elements to add/delete The range size of consecutive elements were not limited. Thus one could define a huge range which may result soft lockup errors due to the long execution time. Now the range size is limited to 2^20 entries. Reported-by: Brad Spengler Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 3 +++ net/netfilter/ipset/ip_set_hash_ip.c | 9 ++++++++- net/netfilter/ipset/ip_set_hash_ipmark.c | 10 +++++++++- net/netfilter/ipset/ip_set_hash_ipport.c | 3 +++ net/netfilter/ipset/ip_set_hash_ipportip.c | 3 +++ net/netfilter/ipset/ip_set_hash_ipportnet.c | 3 +++ net/netfilter/ipset/ip_set_hash_net.c | 11 ++++++++++- net/netfilter/ipset/ip_set_hash_netiface.c | 10 +++++++++- net/netfilter/ipset/ip_set_hash_netnet.c | 16 +++++++++++++++- net/netfilter/ipset/ip_set_hash_netport.c | 11 ++++++++++- net/netfilter/ipset/ip_set_hash_netportnet.c | 16 +++++++++++++++- 11 files changed, 88 insertions(+), 7 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 10279c4830ac..ada1296c87d5 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -196,6 +196,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* Max range where every element is added/deleted in one step */ +#define IPSET_MAX_RANGE (1<<20) + /* The max revision number supported by any set type + 1 */ #define IPSET_REVISION_MAX 9 diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d1bef23fd4f5..dd30c03d5a23 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) { ip = ntohl(h->next.ip); e.ip = htonl(ip); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 18346d18aa16..153de3457423 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e1ca11196515..7303138e46be 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index ab179e064597..334fb1ad0e86 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f075b44cf64..7df94f437f60 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c1a11f041ac6..1422739d9aa2 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ddd51c2e1cb3..9810f5bf63f5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6532f0505e66..3d09eefe998a 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ec1564a1cb5a..09cf72eb37f8 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0e91d1e82f1c..19bcdb3141f6 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); From 38ea9def5b62f9193f6bad96c5d108e2830ecbde Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Thu, 29 Jul 2021 16:20:21 +0800 Subject: [PATCH 1207/1469] netfilter: nf_conntrack_bridge: Fix memory leak when error It should be added kfree_skb_list() when err is not equal to zero in nf_br_ip_fragment(). v2: keep this aligned with IPv6. v3: modify iter.frag_list to iter.frag. Fixes: 3c171f496ef5 ("netfilter: bridge: add connection tracking system") Signed-off-by: Yajun Deng Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/nf_conntrack_bridge.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8d033a75a766..fdbed3158555 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -88,6 +88,12 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, skb = ip_fraglist_next(&iter); } + + if (!err) + return 0; + + kfree_skb_list(iter.frag); + return err; } slow_path: From 06f5553e0f0c2182268179b93856187d9cb86dd5 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Tue, 3 Aug 2021 18:58:21 +0800 Subject: [PATCH 1208/1469] net: sched: fix lockdep_set_class() typo error for sch->seqlock According to comment in qdisc_alloc(), sch->seqlock's lockdep class key should be set to qdisc_tx_busylock, due to possible type error, sch->busylock's lockdep class key is set to qdisc_tx_busylock, which is duplicated because sch->busylock's lockdep class key is already set in qdisc_alloc(). So fix it by replacing sch->busylock with sch->seqlock. Fixes: 96009c7d500e ("sched: replace __QDISC_STATE_RUNNING bit with a spin lock") Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d9ac60ffe927..a8dd06c74e31 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -913,7 +913,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, + lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); seqcount_init(&sch->running); From 13a9c4ac319a23c792e2e03ac73777b6710132c3 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 3 Aug 2021 15:00:43 +0300 Subject: [PATCH 1209/1469] net/prestera: Fix devlink groups leakage in error flow Devlink trap group is registered but not released in error flow, add the missing devlink_trap_groups_unregister() call. Fixes: 0a9003f45e91 ("net: marvell: prestera: devlink: add traps/groups implementation") Signed-off-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/prestera/prestera_devlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index d12e21db9fd6..fa7a0682ad1e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -530,6 +530,8 @@ err_trap_register: prestera_trap = &prestera_trap_items_arr[i]; devlink_traps_unregister(devlink, &prestera_trap->trap, 1); } + devlink_trap_groups_unregister(devlink, prestera_trap_groups_arr, + groups_count); err_groups_register: kfree(trap_data->trap_items_arr); err_trap_items_alloc: From 3212a99349cee5fb611d3ffcf0e65bc3cd6dcf2f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 4 Aug 2021 11:31:00 +0200 Subject: [PATCH 1210/1469] USB: serial: pl2303: fix GT type detection At least some PL2303GT have a bcdDevice of 0x305 instead of 0x100 as the datasheet claims. Add it to the list of known release numbers for the HXN (G) type. Fixes: 894758d0571d ("USB: serial: pl2303: tighten type HXN (G) detection") Reported-by: Vasily Khoruzhick Tested-by: Vasily Khoruzhick Cc: stable@vger.kernel.org # 5.13 Link: https://lore.kernel.org/r/20210804093100.24811-1-johan@kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/pl2303.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 17601e32083e..930b3d50a330 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -432,6 +432,7 @@ static int pl2303_detect_type(struct usb_serial *serial) case 0x200: switch (bcdDevice) { case 0x100: + case 0x305: /* * Assume it's an HXN-type if the device doesn't * support the old read request value. From 8a160e2e9aeb8318159b48701ad8a6e22274372d Mon Sep 17 00:00:00 2001 From: Petko Manolov Date: Tue, 3 Aug 2021 20:25:23 +0300 Subject: [PATCH 1211/1469] net: usb: pegasus: Check the return value of get_geristers() and friends; Certain call sites of get_geristers() did not do proper error handling. This could be a problem as get_geristers() typically return the data via pointer to a buffer. If an error occurred the code is carelessly manipulating the wrong data. Signed-off-by: Petko Manolov Reviewed-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/usb/pegasus.c | 108 ++++++++++++++++++++++++++------------ 1 file changed, 75 insertions(+), 33 deletions(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 9a907182569c..22353bab76c8 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -132,9 +132,15 @@ static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data) static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, const void *data) { - return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS, + int ret; + + ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0, indx, data, size, 1000, GFP_NOIO); + if (ret < 0) + netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret); + + return ret; } /* @@ -145,10 +151,15 @@ static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data) { void *buf = &data; + int ret; - return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG, + ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data, indx, buf, 1, 1000, GFP_NOIO); + if (ret < 0) + netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret); + + return ret; } static int update_eth_regs_async(pegasus_t *pegasus) @@ -188,10 +199,9 @@ static int update_eth_regs_async(pegasus_t *pegasus) static int __mii_op(pegasus_t *p, __u8 phy, __u8 indx, __u16 *regd, __u8 cmd) { - int i; - __u8 data[4] = { phy, 0, 0, indx }; + int i, ret; __le16 regdi; - int ret = -ETIMEDOUT; + __u8 data[4] = { phy, 0, 0, indx }; if (cmd & PHY_WRITE) { __le16 *t = (__le16 *) & data[1]; @@ -207,12 +217,15 @@ static int __mii_op(pegasus_t *p, __u8 phy, __u8 indx, __u16 *regd, __u8 cmd) if (data[0] & PHY_DONE) break; } - if (i >= REG_TIMEOUT) + if (i >= REG_TIMEOUT) { + ret = -ETIMEDOUT; goto fail; + } if (cmd & PHY_READ) { ret = get_registers(p, PhyData, 2, ®di); + if (ret < 0) + goto fail; *regd = le16_to_cpu(regdi); - return ret; } return 0; fail: @@ -235,9 +248,13 @@ static int write_mii_word(pegasus_t *pegasus, __u8 phy, __u8 indx, __u16 *regd) static int mdio_read(struct net_device *dev, int phy_id, int loc) { pegasus_t *pegasus = netdev_priv(dev); + int ret; u16 res; - read_mii_word(pegasus, phy_id, loc, &res); + ret = read_mii_word(pegasus, phy_id, loc, &res); + if (ret < 0) + return ret; + return (int)res; } @@ -251,10 +268,9 @@ static void mdio_write(struct net_device *dev, int phy_id, int loc, int val) static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata) { - int i; - __u8 tmp = 0; + int ret, i; __le16 retdatai; - int ret; + __u8 tmp = 0; set_register(pegasus, EpromCtrl, 0); set_register(pegasus, EpromOffset, index); @@ -262,21 +278,25 @@ static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata) for (i = 0; i < REG_TIMEOUT; i++) { ret = get_registers(pegasus, EpromCtrl, 1, &tmp); + if (ret < 0) + goto fail; if (tmp & EPROM_DONE) break; - if (ret == -ESHUTDOWN) - goto fail; } - if (i >= REG_TIMEOUT) + if (i >= REG_TIMEOUT) { + ret = -ETIMEDOUT; goto fail; + } ret = get_registers(pegasus, EpromData, 2, &retdatai); + if (ret < 0) + goto fail; *retdata = le16_to_cpu(retdatai); return ret; fail: - netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__); - return -ETIMEDOUT; + netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__); + return ret; } #ifdef PEGASUS_WRITE_EEPROM @@ -324,10 +344,10 @@ static int write_eprom_word(pegasus_t *pegasus, __u8 index, __u16 data) return ret; fail: - netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__); + netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__); return -ETIMEDOUT; } -#endif /* PEGASUS_WRITE_EEPROM */ +#endif /* PEGASUS_WRITE_EEPROM */ static inline int get_node_id(pegasus_t *pegasus, u8 *id) { @@ -367,19 +387,21 @@ static void set_ethernet_addr(pegasus_t *pegasus) return; err: eth_hw_addr_random(pegasus->net); - dev_info(&pegasus->intf->dev, "software assigned MAC address.\n"); + netif_dbg(pegasus, drv, pegasus->net, "software assigned MAC address.\n"); return; } static inline int reset_mac(pegasus_t *pegasus) { + int ret, i; __u8 data = 0x8; - int i; set_register(pegasus, EthCtrl1, data); for (i = 0; i < REG_TIMEOUT; i++) { - get_registers(pegasus, EthCtrl1, 1, &data); + ret = get_registers(pegasus, EthCtrl1, 1, &data); + if (ret < 0) + goto fail; if (~data & 0x08) { if (loopback) break; @@ -402,22 +424,29 @@ static inline int reset_mac(pegasus_t *pegasus) } if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_ELCON) { __u16 auxmode; - read_mii_word(pegasus, 3, 0x1b, &auxmode); + ret = read_mii_word(pegasus, 3, 0x1b, &auxmode); + if (ret < 0) + goto fail; auxmode |= 4; write_mii_word(pegasus, 3, 0x1b, &auxmode); } return 0; +fail: + netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__); + return ret; } static int enable_net_traffic(struct net_device *dev, struct usb_device *usb) { - __u16 linkpart; - __u8 data[4]; pegasus_t *pegasus = netdev_priv(dev); int ret; + __u16 linkpart; + __u8 data[4]; - read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart); + ret = read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart); + if (ret < 0) + goto fail; data[0] = 0xc8; /* TX & RX enable, append status, no CRC */ data[1] = 0; if (linkpart & (ADVERTISE_100FULL | ADVERTISE_10FULL)) @@ -435,11 +464,16 @@ static int enable_net_traffic(struct net_device *dev, struct usb_device *usb) usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS2 || usb_dev_id[pegasus->dev_index].vendor == VENDOR_DLINK) { u16 auxmode; - read_mii_word(pegasus, 0, 0x1b, &auxmode); + ret = read_mii_word(pegasus, 0, 0x1b, &auxmode); + if (ret < 0) + goto fail; auxmode |= 4; write_mii_word(pegasus, 0, 0x1b, &auxmode); } + return 0; +fail: + netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__); return ret; } @@ -447,9 +481,9 @@ static void read_bulk_callback(struct urb *urb) { pegasus_t *pegasus = urb->context; struct net_device *net; + u8 *buf = urb->transfer_buffer; int rx_status, count = urb->actual_length; int status = urb->status; - u8 *buf = urb->transfer_buffer; __u16 pkt_len; if (!pegasus) @@ -998,8 +1032,7 @@ static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd) data[0] = pegasus->phy; fallthrough; case SIOCDEVPRIVATE + 1: - read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]); - res = 0; + res = read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]); break; case SIOCDEVPRIVATE + 2: if (!capable(CAP_NET_ADMIN)) @@ -1033,22 +1066,25 @@ static void pegasus_set_multicast(struct net_device *net) static __u8 mii_phy_probe(pegasus_t *pegasus) { - int i; + int i, ret; __u16 tmp; for (i = 0; i < 32; i++) { - read_mii_word(pegasus, i, MII_BMSR, &tmp); + ret = read_mii_word(pegasus, i, MII_BMSR, &tmp); + if (ret < 0) + goto fail; if (tmp == 0 || tmp == 0xffff || (tmp & BMSR_MEDIA) == 0) continue; else return i; } - +fail: return 0xff; } static inline void setup_pegasus_II(pegasus_t *pegasus) { + int ret; __u8 data = 0xa5; set_register(pegasus, Reg1d, 0); @@ -1060,7 +1096,9 @@ static inline void setup_pegasus_II(pegasus_t *pegasus) set_register(pegasus, Reg7b, 2); set_register(pegasus, 0x83, data); - get_registers(pegasus, 0x83, 1, &data); + ret = get_registers(pegasus, 0x83, 1, &data); + if (ret < 0) + goto fail; if (data == 0xa5) pegasus->chip = 0x8513; @@ -1075,6 +1113,10 @@ static inline void setup_pegasus_II(pegasus_t *pegasus) set_register(pegasus, Reg81, 6); else set_register(pegasus, Reg81, 2); + + return; +fail: + netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__); } static void check_carrier(struct work_struct *work) From bc65bacf239d0bc1d00d92cd535a4031921dd78a Mon Sep 17 00:00:00 2001 From: Petko Manolov Date: Tue, 3 Aug 2021 20:25:24 +0300 Subject: [PATCH 1212/1469] net: usb: pegasus: Remove the changelog and DRIVER_VERSION. These are now deemed redundant. Signed-off-by: Petko Manolov Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/usb/pegasus.c | 30 ++---------------------------- 1 file changed, 2 insertions(+), 28 deletions(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 22353bab76c8..f18b03be1b87 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -1,31 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 1999-2013 Petko Manolov (petkan@nucleusys.com) + * Copyright (c) 1999-2021 Petko Manolov (petkan@nucleusys.com) * - * ChangeLog: - * .... Most of the time spent on reading sources & docs. - * v0.2.x First official release for the Linux kernel. - * v0.3.0 Beutified and structured, some bugs fixed. - * v0.3.x URBifying bulk requests and bugfixing. First relatively - * stable release. Still can touch device's registers only - * from top-halves. - * v0.4.0 Control messages remained unurbified are now URBs. - * Now we can touch the HW at any time. - * v0.4.9 Control urbs again use process context to wait. Argh... - * Some long standing bugs (enable_net_traffic) fixed. - * Also nasty trick about resubmiting control urb from - * interrupt context used. Please let me know how it - * behaves. Pegasus II support added since this version. - * TODO: suppressing HCD warnings spewage on disconnect. - * v0.4.13 Ethernet address is now set at probe(), not at open() - * time as this seems to break dhcpd. - * v0.5.0 branch to 2.5.x kernels - * v0.5.1 ethtool support added - * v0.5.5 rx socket buffers are in a pool and the their allocation - * is out of the interrupt routine. - * ... - * v0.9.3 simplified [get|set]_register(s), async update registers - * logic revisited, receive skb_pool removed. */ #include @@ -45,7 +21,6 @@ /* * Version Information */ -#define DRIVER_VERSION "v0.9.3 (2013/04/25)" #define DRIVER_AUTHOR "Petko Manolov " #define DRIVER_DESC "Pegasus/Pegasus II USB Ethernet driver" @@ -914,7 +889,6 @@ static void pegasus_get_drvinfo(struct net_device *dev, pegasus_t *pegasus = netdev_priv(dev); strlcpy(info->driver, driver_name, sizeof(info->driver)); - strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); usb_make_path(pegasus->usb, info->bus_info, sizeof(info->bus_info)); } @@ -1338,7 +1312,7 @@ static void __init parse_id(char *id) static int __init pegasus_init(void) { - pr_info("%s: %s, " DRIVER_DESC "\n", driver_name, DRIVER_VERSION); + pr_info("%s: " DRIVER_DESC "\n", driver_name); if (devid) parse_id(devid); return usb_register(&pegasus_driver); From 85cd39af14f498f791d8aab3fbd64cd175787f1a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 4 Aug 2021 05:28:52 -0400 Subject: [PATCH 1213/1469] KVM: Do not leak memory for duplicate debugfs directories KVM creates a debugfs directory for each VM in order to store statistics about the virtual machine. The directory name is built from the process pid and a VM fd. While generally unique, it is possible to keep a file descriptor alive in a way that causes duplicate directories, which manifests as these messages: [ 471.846235] debugfs: Directory '20245-4' with parent 'kvm' already present! Even though this should not happen in practice, it is more or less expected in the case of KVM for testcases that call KVM_CREATE_VM and close the resulting file descriptor repeatedly and in parallel. When this happens, debugfs_create_dir() returns an error but kvm_create_vm_debugfs() goes on to allocate stat data structs which are later leaked. The slow memory leak was spotted by syzkaller, where it caused OOM reports. Since the issue only affects debugfs, do a lookup before calling debugfs_create_dir, so that the message is downgraded and rate-limited. While at it, ensure kvm->debugfs_dentry is NULL rather than an error if it is not created. This fixes kvm_destroy_vm_debugfs, which was not checking IS_ERR_OR_NULL correctly. Cc: stable@vger.kernel.org Fixes: 536a6f88c49d ("KVM: Create debugfs dir and stat files for each VM") Reported-by: Alexey Kardashevskiy Suggested-by: Greg Kroah-Hartman Acked-by: Greg Kroah-Hartman Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d20fba0fc290..b50dbe269f4b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -892,6 +892,8 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm) static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) { + static DEFINE_MUTEX(kvm_debugfs_lock); + struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; const struct _kvm_stats_desc *pdesc; @@ -903,8 +905,20 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) return 0; snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd); - kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir); + mutex_lock(&kvm_debugfs_lock); + dent = debugfs_lookup(dir_name, kvm_debugfs_dir); + if (dent) { + pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); + dput(dent); + mutex_unlock(&kvm_debugfs_lock); + return 0; + } + dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); + mutex_unlock(&kvm_debugfs_lock); + if (IS_ERR(dent)) + return 0; + kvm->debugfs_dentry = dent; kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), GFP_KERNEL_ACCOUNT); @@ -5201,7 +5215,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) } add_uevent_var(env, "PID=%d", kvm->userspace_pid); - if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) { + if (kvm->debugfs_dentry) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); if (p) { From 179c6c27bf487273652efc99acd3ba512a23c137 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 3 Aug 2021 09:27:46 -0700 Subject: [PATCH 1214/1469] KVM: SVM: Fix off-by-one indexing when nullifying last used SEV VMCB Use the raw ASID, not ASID-1, when nullifying the last used VMCB when freeing an SEV ASID. The consumer, pre_sev_run(), indexes the array by the raw ASID, thus KVM could get a false negative when checking for a different VMCB if KVM manages to reallocate the same ASID+VMCB combo for a new VM. Note, this cannot cause a functional issue _in the current code_, as pre_sev_run() also checks which pCPU last did VMRUN for the vCPU, and last_vmentry_cpu is initialized to -1 during vCPU creation, i.e. is guaranteed to mismatch on the first VMRUN. However, prior to commit 8a14fe4f0c54 ("kvm: x86: Move last_cpu into kvm_vcpu_arch as last_vmentry_cpu"), SVM tracked pCPU on its own and zero-initialized the last_cpu variable. Thus it's theoretically possible that older versions of KVM could miss a TLB flush if the first VMRUN is on pCPU0 and the ASID and VMCB exactly match those of a prior VM. Fixes: 70cd94e60c73 ("KVM: SVM: VMRUN should use associated ASID when SEV is enabled") Cc: Tom Lendacky Cc: Brijesh Singh Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6710d9ee2e4b..4d0aba185412 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -189,7 +189,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); - sd->sev_vmcbs[pos] = NULL; + sd->sev_vmcbs[sev->asid] = NULL; } mutex_unlock(&sev_bitmap_lock); From 396492b4c5f249f616002bb5de787d060d2b2974 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 3 Aug 2021 16:14:15 -0700 Subject: [PATCH 1215/1469] docs: networking: netdevsim rules There are aspects of netdevsim which are commonly misunderstood and pointed out in review. Cong suggest we document them. Suggested-by: Cong Wang Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/netdev-FAQ.rst | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index 91b2cf712801..e26532f49760 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -228,6 +228,23 @@ before posting to the mailing list. The patchwork build bot instance gets overloaded very easily and netdev@vger really doesn't need more traffic if we can help it. +netdevsim is great, can I extend it for my out-of-tree tests? +------------------------------------------------------------- + +No, `netdevsim` is a test vehicle solely for upstream tests. +(Please add your tests under tools/testing/selftests/.) + +We also give no guarantees that `netdevsim` won't change in the future +in a way which would break what would normally be considered uAPI. + +Is netdevsim considered a "user" of an API? +------------------------------------------- + +Linux kernel has a long standing rule that no API should be added unless +it has a real, in-tree user. Mock-ups and tests based on `netdevsim` are +strongly encouraged when adding new APIs, but `netdevsim` in itself +is **not** considered a use case/user. + Any other tips to help ensure my net/net-next patch gets OK'd? -------------------------------------------------------------- Attention to detail. Re-read your own work as if you were the From 6b67d4d63edece1033972214704c04f36c5be89a Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Wed, 4 Aug 2021 11:13:39 +0300 Subject: [PATCH 1216/1469] net: usb: lan78xx: don't modify phy_device state concurrently Currently phy_device state could be left in inconsistent state shown by following alert message[1]. This is because phy_read_status could be called concurrently from lan78xx_delayedwork, phy_state_machine and __ethtool_get_link. Fix this by making sure that phy_device state is updated atomically. [1] lan78xx 1-1.1.1:1.0 eth0: No phy led trigger registered for speed(-1) Signed-off-by: Ivan T. Ivanov Signed-off-by: David S. Miller --- drivers/net/usb/lan78xx.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 25489389ea49..6d092d78e0cb 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1154,7 +1154,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) { struct phy_device *phydev = dev->net->phydev; struct ethtool_link_ksettings ecmd; - int ladv, radv, ret; + int ladv, radv, ret, link; u32 buf; /* clear LAN78xx interrupt status */ @@ -1162,9 +1162,12 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (unlikely(ret < 0)) return -EIO; + mutex_lock(&phydev->lock); phy_read_status(phydev); + link = phydev->link; + mutex_unlock(&phydev->lock); - if (!phydev->link && dev->link_on) { + if (!link && dev->link_on) { dev->link_on = false; /* reset MAC */ @@ -1177,7 +1180,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) return -EIO; del_timer(&dev->stat_monitor); - } else if (phydev->link && !dev->link_on) { + } else if (link && !dev->link_on) { dev->link_on = true; phy_ethtool_ksettings_get(phydev, &ecmd); @@ -1466,9 +1469,14 @@ static int lan78xx_set_eee(struct net_device *net, struct ethtool_eee *edata) static u32 lan78xx_get_link(struct net_device *net) { - phy_read_status(net->phydev); + u32 link; - return net->phydev->link; + mutex_lock(&net->phydev->lock); + phy_read_status(net->phydev); + link = net->phydev->link; + mutex_unlock(&net->phydev->lock); + + return link; } static void lan78xx_get_drvinfo(struct net_device *net, From f558c2b834ec27e75d37b1c860c139e7b7c3a8e4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 Aug 2021 12:45:01 +0200 Subject: [PATCH 1217/1469] sched/rt: Fix double enqueue caused by rt_effective_prio Double enqueues in rt runqueues (list) have been reported while running a simple test that spawns a number of threads doing a short sleep/run pattern while being concurrently setscheduled between rt and fair class. WARNING: CPU: 3 PID: 2825 at kernel/sched/rt.c:1294 enqueue_task_rt+0x355/0x360 CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:enqueue_task_rt+0x355/0x360 Call Trace: __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae list_add double add: new=ffff9867cb629b40, prev=ffff9867cb629b40, next=ffff98679fc67ca0. kernel BUG at lib/list_debug.c:31! invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:__list_add_valid+0x41/0x50 Call Trace: enqueue_task_rt+0x291/0x360 __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae __sched_setscheduler() uses rt_effective_prio() to handle proper queuing of priority boosted tasks that are setscheduled while being boosted. rt_effective_prio() is however called twice per each __sched_setscheduler() call: first directly by __sched_setscheduler() before dequeuing the task and then by __setscheduler() to actually do the priority change. If the priority of the pi_top_task is concurrently being changed however, it might happen that the two calls return different results. If, for example, the first call returned the same rt priority the task was running at and the second one a fair priority, the task won't be removed by the rt list (on_list still set) and then enqueued in the fair runqueue. When eventually setscheduled back to rt it will be seen as enqueued already and the WARNING/BUG be issued. Fix this by calling rt_effective_prio() only once and then reusing the return value. While at it refactor code as well for clarity. Concurrent priority inheritance handling is still safe and will eventually converge to a new state by following the inheritance chain(s). Fixes: 0782e63bc6fe ("sched: Handle priority boosted tasks proper in setscheduler()") [squashed Peterz changes; added changelog] Reported-by: Mark Simmons Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210803104501.38333-1-juri.lelli@redhat.com --- kernel/sched/core.c | 90 ++++++++++++++++++--------------------------- 1 file changed, 35 insertions(+), 55 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2d9ff40f4661..20ffcc044134 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1981,12 +1981,18 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -/* - * __normal_prio - return the priority that is based on the static prio - */ -static inline int __normal_prio(struct task_struct *p) +static inline int __normal_prio(int policy, int rt_prio, int nice) { - return p->static_prio; + int prio; + + if (dl_policy(policy)) + prio = MAX_DL_PRIO - 1; + else if (rt_policy(policy)) + prio = MAX_RT_PRIO - 1 - rt_prio; + else + prio = NICE_TO_PRIO(nice); + + return prio; } /* @@ -1998,15 +2004,7 @@ static inline int __normal_prio(struct task_struct *p) */ static inline int normal_prio(struct task_struct *p) { - int prio; - - if (task_has_dl_policy(p)) - prio = MAX_DL_PRIO-1; - else if (task_has_rt_policy(p)) - prio = MAX_RT_PRIO-1 - p->rt_priority; - else - prio = __normal_prio(p); - return prio; + return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); } /* @@ -4099,7 +4097,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0); - p->prio = p->normal_prio = __normal_prio(p); + p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false); /* @@ -6341,6 +6339,18 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag } EXPORT_SYMBOL(default_wake_function); +static void __setscheduler_prio(struct task_struct *p, int prio) +{ + if (dl_prio(prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; + + p->prio = prio; +} + #ifdef CONFIG_RT_MUTEXES static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) @@ -6456,22 +6466,19 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) } else { p->dl.pi_se = &p->dl; } - p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; - p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; - p->sched_class = &fair_sched_class; } - p->prio = prio; + __setscheduler_prio(p, prio); if (queued) enqueue_task(rq, p, queue_flag); @@ -6824,35 +6831,6 @@ static void __setscheduler_params(struct task_struct *p, set_load_weight(p, true); } -/* Actually do priority change: must hold pi & rq lock. */ -static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr, bool keep_boost) -{ - /* - * If params can't change scheduling class changes aren't allowed - * either. - */ - if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) - return; - - __setscheduler_params(p, attr); - - /* - * Keep a potential priority boosting if called from - * sched_setscheduler(). - */ - p->prio = normal_prio(p); - if (keep_boost) - p->prio = rt_effective_prio(p, p->prio); - - if (dl_prio(p->prio)) - p->sched_class = &dl_sched_class; - else if (rt_prio(p->prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -6873,10 +6851,8 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) { - int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : - MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, queued, running; - int new_effective_prio, policy = attr->sched_policy; + int oldpolicy = -1, policy = attr->sched_policy; + int retval, oldprio, newprio, queued, running; const struct sched_class *prev_class; struct callback_head *head; struct rq_flags rf; @@ -7074,6 +7050,7 @@ change: p->sched_reset_on_fork = reset_on_fork; oldprio = p->prio; + newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); if (pi) { /* * Take priority boosted tasks into account. If the new @@ -7082,8 +7059,8 @@ change: * the runqueue. This will be done when the task deboost * itself. */ - new_effective_prio = rt_effective_prio(p, newprio); - if (new_effective_prio == oldprio) + newprio = rt_effective_prio(p, newprio); + if (newprio == oldprio) queue_flags &= ~DEQUEUE_MOVE; } @@ -7096,7 +7073,10 @@ change: prev_class = p->sched_class; - __setscheduler(rq, p, attr, pi); + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + __setscheduler_prio(p, newprio); + } __setscheduler_uclamp(p, attr); if (queued) { From f4b4b45652578357031fbbef7f7a1b04f6fa2dc3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 29 Jul 2021 11:14:57 +0200 Subject: [PATCH 1218/1469] perf/x86: Fix out of bound MSR access On Wed, Jul 28, 2021 at 12:49:43PM -0400, Vince Weaver wrote: > [32694.087403] unchecked MSR access error: WRMSR to 0x318 (tried to write 0x0000000000000000) at rIP: 0xffffffff8106f854 (native_write_msr+0x4/0x20) > [32694.101374] Call Trace: > [32694.103974] perf_clear_dirty_counters+0x86/0x100 The problem being that it doesn't filter out all fake counters, in specific the above (erroneously) tries to use FIXED_BTS. Limit the fixed counters indexes to the hardware supplied number. Reported-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Tested-by: Vince Weaver Tested-by: Like Xu Link: https://lkml.kernel.org/r/YQJxka3dxgdIdebG@hirez.programming.kicks-ass.net --- arch/x86/events/core.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1eb45139fcc6..3092fbf9dbe4 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2489,13 +2489,15 @@ void perf_clear_dirty_counters(void) return; for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) { - /* Metrics and fake events don't have corresponding HW counters. */ - if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR)) - continue; - else if (i >= INTEL_PMC_IDX_FIXED) + if (i >= INTEL_PMC_IDX_FIXED) { + /* Metrics and fake events don't have corresponding HW counters. */ + if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed)) + continue; + wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0); - else + } else { wrmsrl(x86_pmu_event_addr(i), 0); + } } bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX); From df51fe7ea1c1c2c3bfdb81279712fdd2e4ea6c27 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 2 Aug 2021 15:08:50 +0800 Subject: [PATCH 1219/1469] perf/x86/amd: Don't touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest If we use "perf record" in an AMD Milan guest, dmesg reports a #GP warning from an unchecked MSR access error on MSR_F15H_PERF_CTLx: [] unchecked MSR access error: WRMSR to 0xc0010200 (tried to write 0x0000020000110076) at rIP: 0xffffffff8106ddb4 (native_write_msr+0x4/0x20) [] Call Trace: [] amd_pmu_disable_event+0x22/0x90 [] x86_pmu_stop+0x4c/0xa0 [] x86_pmu_del+0x3a/0x140 The AMD64_EVENTSEL_HOSTONLY bit is defined and used on the host, while the guest perf driver should avoid such use. Fixes: 1018faa6cf23 ("perf/x86/kvm: Fix Host-Only/Guest-Only counting with SVM disabled") Signed-off-by: Like Xu Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Liam Merwick Tested-by: Kim Phillips Tested-by: Liam Merwick Link: https://lkml.kernel.org/r/20210802070850.35295-1-likexu@tencent.com --- arch/x86/events/perf_event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2bf1c7ea2758..2938c902ffbe 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1115,9 +1115,10 @@ void x86_pmu_stop(struct perf_event *event, int flags); static inline void x86_pmu_disable_event(struct perf_event *event) { + u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask); struct hw_perf_event *hwc = &event->hw; - wrmsrl(hwc->config_base, hwc->config); + wrmsrl(hwc->config_base, hwc->config & ~disable_mask); if (is_counter_pair(hwc)) wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0); From bb2baeb214a71cda47d50dce80414016117ddda0 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Mon, 2 Aug 2021 11:09:03 -0700 Subject: [PATCH 1220/1469] KVM: SVM: improve the code readability for ASID management KVM SEV code uses bitmaps to manage ASID states. ASID 0 was always skipped because it is never used by VM. Thus, in existing code, ASID value and its bitmap postion always has an 'offset-by-1' relationship. Both SEV and SEV-ES shares the ASID space, thus KVM uses a dynamic range [min_asid, max_asid] to handle SEV and SEV-ES ASIDs separately. Existing code mixes the usage of ASID value and its bitmap position by using the same variable called 'min_asid'. Fix the min_asid usage: ensure that its usage is consistent with its name; allocate extra size for ASID 0 to ensure that each ASID has the same value with its bitmap position. Add comments on ASID bitmap allocation to clarify the size change. Signed-off-by: Mingwei Zhang Cc: Tom Lendacky Cc: Marc Orr Cc: David Rientjes Cc: Alper Gun Cc: Dionna Glaze Cc: Sean Christopherson Cc: Vipin Sharma Cc: Peter Gonda Cc: Joerg Roedel Message-Id: <20210802180903.159381-1-mizhang@google.com> [Fix up sev_asid_free to also index by ASID, as suggested by Sean Christopherson, and use nr_asids in sev_cpu_init. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 43 +++++++++++++++++++++++------------------- 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4d0aba185412..7fbce342eec4 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -64,6 +64,7 @@ static DEFINE_MUTEX(sev_bitmap_lock); unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long sev_me_mask; +static unsigned int nr_asids; static unsigned long *sev_asid_bitmap; static unsigned long *sev_reclaim_asid_bitmap; @@ -78,11 +79,11 @@ struct enc_region { /* Called with the sev_bitmap_lock held, or on shutdown */ static int sev_flush_asids(int min_asid, int max_asid) { - int ret, pos, error = 0; + int ret, asid, error = 0; /* Check if there are any ASIDs to reclaim before performing a flush */ - pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid); - if (pos >= max_asid) + asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); + if (asid > max_asid) return -EBUSY; /* @@ -115,15 +116,15 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */ bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, - max_sev_asid); - bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + nr_asids); + bitmap_zero(sev_reclaim_asid_bitmap, nr_asids); return true; } static int sev_asid_new(struct kvm_sev_info *sev) { - int pos, min_asid, max_asid, ret; + int asid, min_asid, max_asid, ret; bool retry = true; enum misc_res_type type; @@ -143,11 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev) * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. */ - min_asid = sev->es_active ? 0 : min_sev_asid - 1; + min_asid = sev->es_active ? 1 : min_sev_asid; max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: - pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid); - if (pos >= max_asid) { + asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); + if (asid > max_asid) { if (retry && __sev_recycle_asids(min_asid, max_asid)) { retry = false; goto again; @@ -157,11 +158,11 @@ again: goto e_uncharge; } - __set_bit(pos, sev_asid_bitmap); + __set_bit(asid, sev_asid_bitmap); mutex_unlock(&sev_bitmap_lock); - return pos + 1; + return asid; e_uncharge: misc_cg_uncharge(type, sev->misc_cg, 1); put_misc_cg(sev->misc_cg); @@ -179,13 +180,12 @@ static int sev_get_asid(struct kvm *kvm) static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; - int cpu, pos; + int cpu; enum misc_res_type type; mutex_lock(&sev_bitmap_lock); - pos = sev->asid - 1; - __set_bit(pos, sev_reclaim_asid_bitmap); + __set_bit(sev->asid, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); @@ -1857,12 +1857,17 @@ void __init sev_hardware_setup(void) min_sev_asid = edx; sev_me_mask = 1UL << (ebx & 0x3f); - /* Initialize SEV ASID bitmaps */ - sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + /* + * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap, + * even though it's never used, so that the bitmap is indexed by the + * actual ASID. + */ + nr_asids = max_sev_asid + 1; + sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); if (!sev_asid_bitmap) goto out; - sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); if (!sev_reclaim_asid_bitmap) { bitmap_free(sev_asid_bitmap); sev_asid_bitmap = NULL; @@ -1907,7 +1912,7 @@ void sev_hardware_teardown(void) return; /* No need to take sev_bitmap_lock, all VMs have been destroyed. */ - sev_flush_asids(0, max_sev_asid); + sev_flush_asids(1, max_sev_asid); bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); @@ -1921,7 +1926,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) if (!sev_enabled) return 0; - sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); + sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) return -ENOMEM; From 13c2c3cfe01952575b1dd5e24d450fcccff93bc0 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 4 Aug 2021 14:20:57 +0300 Subject: [PATCH 1221/1469] KVM: selftests: fix hyperv_clock test The test was mistakenly using addr_gpa2hva on a gva and that happened to work accidentally. Commit 106a2e766eae ("KVM: selftests: Lower the min virtual address for misc page allocations") revealed this bug. Fixes: 2c7f76b4c42b ("selftests: kvm: Add basic Hyper-V clocksources tests", 2021-03-18) Signed-off-by: Maxim Levitsky Message-Id: <20210804112057.409498-1-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/hyperv_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index bab10ae787b6..e0b2bb1339b1 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -215,7 +215,7 @@ int main(void) vcpu_set_hv_cpuid(vm, VCPU_ID); tsc_page_gva = vm_vaddr_alloc_page(vm); - memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize()); + memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned\n"); vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); From 952835edb4fdad49361d5330da918be8b765b787 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Wed, 4 Aug 2021 17:18:00 +0200 Subject: [PATCH 1222/1469] s390/dasd: fix use after free in dasd path handling When new configuration data is obtained after a path event it is stored in the per path array. The old data needs to be freed. The first valid configuration data is also referenced in the device private structure to identify the device. When the old per path configuration data was freed the device still pointed to the already freed data leading to a use after free. Fix by replacing also the device configuration data with the newly obtained one before the old data gets freed. Fixes: 460181217a24 ("s390/dasd: Store path configuration data during path handling") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20210804151800.4031761-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 0de1a463c509..fb5d8152652d 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1004,15 +1004,23 @@ static unsigned char dasd_eckd_path_access(void *conf_data, int conf_len) static void dasd_eckd_store_conf_data(struct dasd_device *device, struct dasd_conf_data *conf_data, int chp) { + struct dasd_eckd_private *private = device->private; struct channel_path_desc_fmt0 *chp_desc; struct subchannel_id sch_id; + void *cdp; - ccw_device_get_schid(device->cdev, &sch_id); /* * path handling and read_conf allocate data * free it before replacing the pointer + * also replace the old private->conf_data pointer + * with the new one if this points to the same data */ - kfree(device->path[chp].conf_data); + cdp = device->path[chp].conf_data; + if (private->conf_data == cdp) { + private->conf_data = (void *)conf_data; + dasd_eckd_identify_conf_parts(private); + } + ccw_device_get_schid(device->cdev, &sch_id); device->path[chp].conf_data = conf_data; device->path[chp].cssid = sch_id.cssid; device->path[chp].ssid = sch_id.ssid; @@ -1020,6 +1028,7 @@ static void dasd_eckd_store_conf_data(struct dasd_device *device, if (chp_desc) device->path[chp].chpid = chp_desc->chpid; kfree(chp_desc); + kfree(cdp); } static void dasd_eckd_clear_conf_data(struct dasd_device *device) From 2f658f7a3953f6d70bab90e117aff8d0ad44e200 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Aug 2021 14:21:41 +0300 Subject: [PATCH 1223/1469] pinctrl: tigerlake: Fix GPIO mapping for newer version of software The software mapping for GPIO, which initially comes from Microsoft, is subject to change by respective Windows and firmware developers. Due to the above the driver had been written and published way ahead of the schedule, and thus the numbering schema used in it is outdated. Fix the numbering schema in accordance with the real products on market. Fixes: 653d96455e1e ("pinctrl: tigerlake: Add support for Tiger Lake-H") Reported-and-tested-by: Kai-Heng Feng Reported-by: Riccardo Mori Reported-and-tested-by: Lovesh BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213463 BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213579 BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213857 Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg --- drivers/pinctrl/intel/pinctrl-tigerlake.c | 26 +++++++++++------------ 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c index 3e4ef2b87526..0bcd19597e4a 100644 --- a/drivers/pinctrl/intel/pinctrl-tigerlake.c +++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c @@ -701,32 +701,32 @@ static const struct pinctrl_pin_desc tglh_pins[] = { static const struct intel_padgroup tglh_community0_gpps[] = { TGL_GPP(0, 0, 24, 0), /* GPP_A */ - TGL_GPP(1, 25, 44, 128), /* GPP_R */ - TGL_GPP(2, 45, 70, 32), /* GPP_B */ - TGL_GPP(3, 71, 78, INTEL_GPIO_BASE_NOMAP), /* vGPIO_0 */ + TGL_GPP(1, 25, 44, 32), /* GPP_R */ + TGL_GPP(2, 45, 70, 64), /* GPP_B */ + TGL_GPP(3, 71, 78, 96), /* vGPIO_0 */ }; static const struct intel_padgroup tglh_community1_gpps[] = { - TGL_GPP(0, 79, 104, 96), /* GPP_D */ - TGL_GPP(1, 105, 128, 64), /* GPP_C */ - TGL_GPP(2, 129, 136, 160), /* GPP_S */ - TGL_GPP(3, 137, 153, 192), /* GPP_G */ - TGL_GPP(4, 154, 180, 224), /* vGPIO */ + TGL_GPP(0, 79, 104, 128), /* GPP_D */ + TGL_GPP(1, 105, 128, 160), /* GPP_C */ + TGL_GPP(2, 129, 136, 192), /* GPP_S */ + TGL_GPP(3, 137, 153, 224), /* GPP_G */ + TGL_GPP(4, 154, 180, 256), /* vGPIO */ }; static const struct intel_padgroup tglh_community3_gpps[] = { - TGL_GPP(0, 181, 193, 256), /* GPP_E */ - TGL_GPP(1, 194, 217, 288), /* GPP_F */ + TGL_GPP(0, 181, 193, 288), /* GPP_E */ + TGL_GPP(1, 194, 217, 320), /* GPP_F */ }; static const struct intel_padgroup tglh_community4_gpps[] = { - TGL_GPP(0, 218, 241, 320), /* GPP_H */ + TGL_GPP(0, 218, 241, 352), /* GPP_H */ TGL_GPP(1, 242, 251, 384), /* GPP_J */ - TGL_GPP(2, 252, 266, 352), /* GPP_K */ + TGL_GPP(2, 252, 266, 416), /* GPP_K */ }; static const struct intel_padgroup tglh_community5_gpps[] = { - TGL_GPP(0, 267, 281, 416), /* GPP_I */ + TGL_GPP(0, 267, 281, 448), /* GPP_I */ TGL_GPP(1, 282, 290, INTEL_GPIO_BASE_NOMAP), /* JTAG */ }; From 402e0b8cd00284a25c6eb8c0a43319bc8430b1c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Aug 2021 11:49:58 +0200 Subject: [PATCH 1224/1469] n64cart: fix the dma address in n64cart_do_bvec dma_map_bvec already takes bv_offset into account. Fixes: 9b2a2bbbb4d0 ("block: Add n64 cart driver") Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/n64cart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 7b4dd10af9ec..c84be0028f63 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -74,7 +74,7 @@ static bool n64cart_do_bvec(struct device *dev, struct bio_vec *bv, u32 pos) n64cart_wait_dma(); - n64cart_write_reg(PI_DRAM_REG, dma_addr + bv->bv_offset); + n64cart_write_reg(PI_DRAM_REG, dma_addr); n64cart_write_reg(PI_CART_REG, (bstart | CART_DOMAIN) & CART_MAX); n64cart_write_reg(PI_WRITE_REG, bv->bv_len - 1); From bf2ba432213fade50dd39f2e348085b758c0726e Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Tue, 6 Jul 2021 14:52:41 +0100 Subject: [PATCH 1225/1469] ceph: reduce contention in ceph_check_delayed_caps() Function ceph_check_delayed_caps() is called from the mdsc->delayed_work workqueue and it can be kept looping for quite some time if caps keep being added back to the mdsc->cap_delay_list. This may result in the watchdog tainting the kernel with the softlockup flag. This patch breaks this loop if the caps have been recently (i.e. during the loop execution). Any new caps added to the list will be handled in the next run. Also, allow schedule_delayed() callers to explicitly set the delay value instead of defaulting to 5s, so we can ensure that it runs soon afterward if it looks like there is more work. Cc: stable@vger.kernel.org URL: https://tracker.ceph.com/issues/46284 Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 17 ++++++++++++++++- fs/ceph/mds_client.c | 25 ++++++++++++++++--------- fs/ceph/super.h | 2 +- 3 files changed, 33 insertions(+), 11 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7bdefd0c789a..2a2900903f8c 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4150,11 +4150,19 @@ bad: /* * Delayed work handler to process end of delayed cap release LRU list. + * + * If new caps are added to the list while processing it, these won't get + * processed in this run. In this case, the ci->i_hold_caps_max will be + * returned so that the work can be scheduled accordingly. */ -void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) +unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { struct inode *inode; struct ceph_inode_info *ci; + struct ceph_mount_options *opt = mdsc->fsc->mount_options; + unsigned long delay_max = opt->caps_wanted_delay_max * HZ; + unsigned long loop_start = jiffies; + unsigned long delay = 0; dout("check_delayed_caps\n"); spin_lock(&mdsc->cap_delay_lock); @@ -4162,6 +4170,11 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) ci = list_first_entry(&mdsc->cap_delay_list, struct ceph_inode_info, i_cap_delay_list); + if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) { + dout("%s caps added recently. Exiting loop", __func__); + delay = ci->i_hold_caps_max; + break; + } if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 && time_before(jiffies, ci->i_hold_caps_max)) break; @@ -4177,6 +4190,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) } } spin_unlock(&mdsc->cap_delay_lock); + + return delay; } /* diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9db1b39df773..afdc20213876 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4490,22 +4490,29 @@ void inc_session_sequence(struct ceph_mds_session *s) } /* - * delayed work -- periodically trim expired leases, renew caps with mds + * delayed work -- periodically trim expired leases, renew caps with mds. If + * the @delay parameter is set to 0 or if it's more than 5 secs, the default + * workqueue delay value of 5 secs will be used. */ -static void schedule_delayed(struct ceph_mds_client *mdsc) +static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay) { - int delay = 5; - unsigned hz = round_jiffies_relative(HZ * delay); - schedule_delayed_work(&mdsc->delayed_work, hz); + unsigned long max_delay = HZ * 5; + + /* 5 secs default delay */ + if (!delay || (delay > max_delay)) + delay = max_delay; + schedule_delayed_work(&mdsc->delayed_work, + round_jiffies_relative(delay)); } static void delayed_work(struct work_struct *work) { - int i; struct ceph_mds_client *mdsc = container_of(work, struct ceph_mds_client, delayed_work.work); + unsigned long delay; int renew_interval; int renew_caps; + int i; dout("mdsc delayed_work\n"); @@ -4545,7 +4552,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex); - ceph_check_delayed_caps(mdsc); + delay = ceph_check_delayed_caps(mdsc); ceph_queue_cap_reclaim_work(mdsc); @@ -4553,7 +4560,7 @@ static void delayed_work(struct work_struct *work) maybe_recover_session(mdsc); - schedule_delayed(mdsc); + schedule_delayed(mdsc, delay); } int ceph_mdsc_init(struct ceph_fs_client *fsc) @@ -5030,7 +5037,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) mdsc->mdsmap->m_epoch); mutex_unlock(&mdsc->mutex); - schedule_delayed(mdsc); + schedule_delayed(mdsc, 0); return; bad_unlock: diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6b6332a5c113..9215a2f4535c 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1167,7 +1167,7 @@ extern void ceph_flush_snaps(struct ceph_inode_info *ci, extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); -extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); +extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, From 8434ffe71c874b9c4e184b88d25de98c2bf5fe3f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 3 Aug 2021 12:47:34 -0400 Subject: [PATCH 1226/1469] ceph: take snap_empty_lock atomically with snaprealm refcount change There is a race in ceph_put_snap_realm. The change to the nref and the spinlock acquisition are not done atomically, so you could decrement nref, and before you take the spinlock, the nref is incremented again. At that point, you end up putting it on the empty list when it shouldn't be there. Eventually __cleanup_empty_realms runs and frees it when it's still in-use. Fix this by protecting the 1->0 transition with atomic_dec_and_lock, and just drop the spinlock if we can get the rwsem. Because these objects can also undergo a 0->1 refcount transition, we must protect that change as well with the spinlock. Increment locklessly unless the value is at 0, in which case we take the spinlock, increment and then take it off the empty list if it did the 0->1 transition. With these changes, I'm removing the dout() messages from these functions, as well as in __put_snap_realm. They've always been racy, and it's better to not print values that may be misleading. Cc: stable@vger.kernel.org URL: https://tracker.ceph.com/issues/46419 Reported-by: Mark Nelson Signed-off-by: Jeff Layton Reviewed-by: Luis Henriques Signed-off-by: Ilya Dryomov --- fs/ceph/snap.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 4ac0606dcbd4..4c6bd1042c94 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -67,19 +67,19 @@ void ceph_get_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held(&mdsc->snap_rwsem); - dout("get_realm %p %d -> %d\n", realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)+1); /* - * since we _only_ increment realm refs or empty the empty - * list with snap_rwsem held, adjusting the empty list here is - * safe. we do need to protect against concurrent empty list - * additions, however. + * The 0->1 and 1->0 transitions must take the snap_empty_lock + * atomically with the refcount change. Go ahead and bump the + * nref here, unless it's 0, in which case we take the spinlock + * and then do the increment and remove it from the list. */ - if (atomic_inc_return(&realm->nref) == 1) { - spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_not_zero(&realm->nref)) + return; + + spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_return(&realm->nref) == 1) list_del_init(&realm->empty_item); - spin_unlock(&mdsc->snap_empty_lock); - } + spin_unlock(&mdsc->snap_empty_lock); } static void __insert_snap_realm(struct rb_root *root, @@ -208,28 +208,28 @@ static void __put_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held_write(&mdsc->snap_rwsem); - dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); + /* + * We do not require the snap_empty_lock here, as any caller that + * increments the value must hold the snap_rwsem. + */ if (atomic_dec_and_test(&realm->nref)) __destroy_snap_realm(mdsc, realm); } /* - * caller needn't hold any locks + * See comments in ceph_get_snap_realm. Caller needn't hold any locks. */ void ceph_put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { - dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); - if (!atomic_dec_and_test(&realm->nref)) + if (!atomic_dec_and_lock(&realm->nref, &mdsc->snap_empty_lock)) return; if (down_write_trylock(&mdsc->snap_rwsem)) { + spin_unlock(&mdsc->snap_empty_lock); __destroy_snap_realm(mdsc, realm); up_write(&mdsc->snap_rwsem); } else { - spin_lock(&mdsc->snap_empty_lock); list_add(&realm->empty_item, &mdsc->snap_empty); spin_unlock(&mdsc->snap_empty_lock); } From 83d6c39310b6d11199179f6384c2b0a415389597 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 3 Aug 2021 09:14:35 -0600 Subject: [PATCH 1227/1469] io-wq: fix race between worker exiting and activating free worker Nadav correctly reports that we have a race between a worker exiting, and new work being queued. This can lead to work being queued behind an existing worker that could be sleeping on an event before it can run to completion, and hence introducing potential big latency gaps if we hit this race condition: cpu0 cpu1 ---- ---- io_wqe_worker() schedule_timeout() // timed out io_wqe_enqueue() io_wqe_wake_worker() // work_flags & IO_WQ_WORK_CONCURRENT io_wqe_activate_free_worker() io_worker_exit() Fix this by having the exiting worker go through the normal decrement of a running worker, which will spawn a new one if needed. The free worker activation is modified to only return success if we were able to find a sleeping worker - if not, we keep looking through the list. If we fail, we create a new worker as per usual. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/io-uring/BFF746C0-FEDE-4646-A253-3021C57C26C9@gmail.com/ Reported-by: Nadav Amit Tested-by: Nadav Amit Signed-off-by: Jens Axboe --- fs/io-wq.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index cf086b01c6c6..50dc93ffc153 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -130,6 +130,7 @@ struct io_cb_cancel_data { }; static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void io_wqe_dec_running(struct io_worker *worker); static bool io_worker_get(struct io_worker *worker) { @@ -168,26 +169,21 @@ static void io_worker_exit(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; struct io_wqe_acct *acct = io_wqe_get_acct(worker); - unsigned flags; if (refcount_dec_and_test(&worker->ref)) complete(&worker->ref_done); wait_for_completion(&worker->ref_done); - preempt_disable(); - current->flags &= ~PF_IO_WORKER; - flags = worker->flags; - worker->flags = 0; - if (flags & IO_WORKER_F_RUNNING) - atomic_dec(&acct->nr_running); - worker->flags = 0; - preempt_enable(); - raw_spin_lock_irq(&wqe->lock); - if (flags & IO_WORKER_F_FREE) + if (worker->flags & IO_WORKER_F_FREE) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); acct->nr_workers--; + preempt_disable(); + io_wqe_dec_running(worker); + worker->flags = 0; + current->flags &= ~PF_IO_WORKER; + preempt_enable(); raw_spin_unlock_irq(&wqe->lock); kfree_rcu(worker, rcu); @@ -214,15 +210,19 @@ static bool io_wqe_activate_free_worker(struct io_wqe *wqe) struct hlist_nulls_node *n; struct io_worker *worker; - n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list)); - if (is_a_nulls(n)) - return false; - - worker = hlist_nulls_entry(n, struct io_worker, nulls_node); - if (io_worker_get(worker)) { - wake_up_process(worker->task); + /* + * Iterate free_list and see if we can find an idle worker to + * activate. If a given worker is on the free_list but in the process + * of exiting, keep trying. + */ + hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) { + if (!io_worker_get(worker)) + continue; + if (wake_up_process(worker->task)) { + io_worker_release(worker); + return true; + } io_worker_release(worker); - return true; } return false; From a07296453bf2778952a09b6244a695bf7607babb Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 4 Aug 2021 13:41:47 -0700 Subject: [PATCH 1228/1469] drm/i915: fix i915_globals_exit() section mismatch error Fix modpost Section mismatch error in i915_globals_exit(). Since both an __init function and an __exit function can call i915_globals_exit(), any function that i915_globals_exit() calls should not be marked as __init or __exit. I.e., it needs to be available for either of them. WARNING: modpost: vmlinux.o(.text+0x8b796a): Section mismatch in reference from the function i915_globals_exit() to the function .exit.text:__i915_globals_flush() The function i915_globals_exit() references a function in an exit section. Often the function __i915_globals_flush() has valid usage outside the exit section and the fix is to remove the __exit annotation of __i915_globals_flush. ERROR: modpost: Section mismatches detected. Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them. Fixes: 1354d830cb8f ("drm/i915: Call i915_globals_exit() if pci_register_device() fails") Signed-off-by: Randy Dunlap Cc: Jason Ekstrand Cc: Daniel Vetter Cc: Rodrigo Vivi Cc: Jani Nikula Cc: Joonas Lahtinen Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20210804204147.2070-1-rdunlap@infradead.org --- drivers/gpu/drm/i915/i915_globals.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c index 2db90e770616..3acb0b6be284 100644 --- a/drivers/gpu/drm/i915/i915_globals.c +++ b/drivers/gpu/drm/i915/i915_globals.c @@ -138,7 +138,7 @@ void i915_globals_unpark(void) atomic_inc(&active); } -static void __exit __i915_globals_flush(void) +static void __i915_globals_flush(void) { atomic_inc(&active); /* skip shrinking */ From 2c05caa7ba8803209769b9e4fe02c38d77ae88d0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 30 Jul 2021 17:19:51 -0400 Subject: [PATCH 1229/1469] tracing / histogram: Give calculation hist_fields a size When working on my user space applications, I found a bug in the synthetic event code where the automated synthetic event field was not matching the event field calculation it was attached to. Looking deeper into it, it was because the calculation hist_field was not given a size. The synthetic event fields are matched to their hist_fields either by having the field have an identical string type, or if that does not match, then the size and signed values are used to match the fields. The problem arose when I tried to match a calculation where the fields were "unsigned int". My tool created a synthetic event of type "u32". But it failed to match. The string was: diff=field1-field2:onmatch(event).trace(synth,$diff) Adding debugging into the kernel, I found that the size of "diff" was 0. And since it was given "unsigned int" as a type, the histogram fallback code used size and signed. The signed matched, but the size of u32 (4) did not match zero, and the event failed to be created. This can be worse if the field you want to match is not one of the acceptable fields for a synthetic event. As event fields can have any type that is supported in Linux, this can cause an issue. For example, if a type is an enum. Then there's no way to use that with any calculations. Have the calculation field simply take on the size of what it is calculating. Link: https://lkml.kernel.org/r/20210730171951.59c7743f@oasis.local.home Cc: Tom Zanussi Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Ingo Molnar Cc: Andrew Morton Cc: stable@vger.kernel.org Fixes: 100719dcef447 ("tracing: Add simple expression support to hist triggers") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 34325f41ebc0..362db9b81b8d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2287,6 +2287,10 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr->operands[0] = operand1; expr->operands[1] = operand2; + + /* The operand sizes should be the same, so just pick one */ + expr->size = operand1->size; + expr->operator = field_op; expr->name = expr_str(expr, 0); expr->type = kstrdup(operand1->type, GFP_KERNEL); From a9d10ca4986571bffc19778742d508cc8dd13e02 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 28 Jul 2021 07:55:43 +0900 Subject: [PATCH 1230/1469] tracing: Reject string operand in the histogram expression Since the string type can not be the target of the addition / subtraction operation, it must be rejected. Without this fix, the string type silently converted to digits. Link: https://lkml.kernel.org/r/162742654278.290973.1523000673366456634.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: 100719dcef447 ("tracing: Add simple expression support to hist triggers") Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 362db9b81b8d..949ef09dc537 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -65,7 +65,8 @@ C(INVALID_SORT_MODIFIER,"Invalid sort modifier"), \ C(EMPTY_SORT_FIELD, "Empty sort field"), \ C(TOO_MANY_SORT_FIELDS, "Too many sort fields (Max = 2)"), \ - C(INVALID_SORT_FIELD, "Sort field must be a key or a val"), + C(INVALID_SORT_FIELD, "Sort field must be a key or a val"), \ + C(INVALID_STR_OPERAND, "String type can not be an operand in expression"), #undef C #define C(a, b) HIST_ERR_##a @@ -2156,6 +2157,13 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data, ret = PTR_ERR(operand1); goto free; } + if (operand1->flags & HIST_FIELD_FL_STRING) { + /* String type can not be the operand of unary operator. */ + hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str)); + destroy_hist_field(operand1, 0); + ret = -EINVAL; + goto free; + } expr->flags |= operand1->flags & (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS); @@ -2257,6 +2265,11 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, operand1 = NULL; goto free; } + if (operand1->flags & HIST_FIELD_FL_STRING) { + hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str)); + ret = -EINVAL; + goto free; + } /* rest of string could be another expression e.g. b+c in a+b+c */ operand_flags = 0; @@ -2266,6 +2279,11 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, operand2 = NULL; goto free; } + if (operand2->flags & HIST_FIELD_FL_STRING) { + hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str)); + ret = -EINVAL; + goto free; + } ret = check_expr_operands(file->tr, operand1, operand2); if (ret) From b18b851ba85a5855cb53865fcff3cd2c17b44b0b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 2 Aug 2021 14:03:07 -0700 Subject: [PATCH 1231/1469] scripts/recordmcount.pl: Remove check_objcopy() and $can_use_local When building ARCH=riscv allmodconfig with llvm-objcopy, the objcopy version warning from this script appears: WARNING: could not find objcopy version or version is less than 2.17. Local function references are disabled. The check_objcopy() function in scripts/recordmcount.pl is set up to parse GNU objcopy's version string, not llvm-objcopy's, which triggers the warning. Commit 799c43415442 ("kbuild: thin archives make default for all archs") made binutils 2.20 mandatory and commit ba64beb17493 ("kbuild: check the minimum assembler version in Kconfig") enforces this at configuration time so just remove check_objcopy() and $can_use_local instead, assuming --globalize-symbol is always available. llvm-objcopy has supported --globalize-symbol since LLVM 7.0.0 in 2018 and the minimum version for building the kernel with LLVM is 10.0.1 so there is no issue introduced: Link: https://github.com/llvm/llvm-project/commit/ee5be798dae30d5f9414b01f76ff807edbc881aa Link: https://lkml.kernel.org/r/20210802210307.3202472-1-nathan@kernel.org Reviewed-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Steven Rostedt (VMware) --- Makefile | 1 - scripts/recordmcount.pl | 40 ---------------------------------------- 2 files changed, 41 deletions(-) diff --git a/Makefile b/Makefile index e4f5895badb5..d6915f361aa4 100644 --- a/Makefile +++ b/Makefile @@ -546,7 +546,6 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \ PHONY += scripts_basic scripts_basic: $(Q)$(MAKE) $(build)=scripts/basic - $(Q)rm -f .tmp_quiet_recordmcount PHONY += outputmakefile ifdef building_out_of_srctree diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index c17e48020ec3..8f6b13ae46bf 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -173,39 +173,6 @@ my $mcount_regex; # Find the call site to mcount (return offset) my $mcount_adjust; # Address adjustment to mcount offset my $alignment; # The .align value to use for $mcount_section my $section_type; # Section header plus possible alignment command -my $can_use_local = 0; # If we can use local function references - -# Shut up recordmcount if user has older objcopy -my $quiet_recordmcount = ".tmp_quiet_recordmcount"; -my $print_warning = 1; -$print_warning = 0 if ( -f $quiet_recordmcount); - -## -# check_objcopy - whether objcopy supports --globalize-symbols -# -# --globalize-symbols came out in 2.17, we must test the version -# of objcopy, and if it is less than 2.17, then we can not -# record local functions. -sub check_objcopy -{ - open (IN, "$objcopy --version |") or die "error running $objcopy"; - while () { - if (/objcopy.*\s(\d+)\.(\d+)/) { - $can_use_local = 1 if ($1 > 2 || ($1 == 2 && $2 >= 17)); - last; - } - } - close (IN); - - if (!$can_use_local && $print_warning) { - print STDERR "WARNING: could not find objcopy version or version " . - "is less than 2.17.\n" . - "\tLocal function references are disabled.\n"; - open (QUIET, ">$quiet_recordmcount"); - printf QUIET "Disables the warning from recordmcount.pl\n"; - close QUIET; - } -} if ($arch =~ /(x86(_64)?)|(i386)/) { if ($bits == 64) { @@ -434,8 +401,6 @@ if ($filename =~ m,^(.*)(\.\S),) { my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s"; my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o"; -check_objcopy(); - # # Step 1: find all the local (static functions) and weak symbols. # 't' is local, 'w/W' is weak @@ -473,11 +438,6 @@ sub update_funcs # is this function static? If so, note this fact. if (defined $locals{$ref_func}) { - - # only use locals if objcopy supports globalize-symbols - if (!$can_use_local) { - return; - } $convert{$ref_func} = 1; } From 1c0cec64a7cc545eb49f374a43e9f7190a14defa Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 11 Jun 2021 10:21:07 +0800 Subject: [PATCH 1232/1469] scripts/tracing: fix the bug that can't parse raw_trace_func Since commit 77271ce4b2c0 ("tracing: Add irq, preempt-count and need resched info to default trace output"), the default trace output format has been changed to: -0 [009] d.h. 22420.068695: _raw_spin_lock_irqsave <-hrtimer_interrupt -0 [000] ..s. 22420.068695: _nohz_idle_balance <-run_rebalance_domains -0 [011] d.h. 22420.068695: account_process_tick <-update_process_times origin trace output format:(before v3.2.0) # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | migration/0-6 [000] 50.025810: rcu_note_context_switch <-__schedule migration/0-6 [000] 50.025812: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025813: rcu_sched_qs <-rcu_note_context_switch migration/0-6 [000] 50.025815: rcu_preempt_qs <-rcu_note_context_switch migration/0-6 [000] 50.025817: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025818: debug_lockdep_rcu_enabled <-__schedule migration/0-6 [000] 50.025820: debug_lockdep_rcu_enabled <-__schedule The draw_functrace.py(introduced in v2.6.28) can't parse the new version format trace_func, So we need modify draw_functrace.py to adapt the new version trace output format. Link: https://lkml.kernel.org/r/20210611022107.608787-1-suhui@zeku.com Cc: stable@vger.kernel.org Fixes: 77271ce4b2c0 tracing: Add irq, preempt-count and need resched info to default trace output Signed-off-by: Hui Su Signed-off-by: Steven Rostedt (VMware) --- scripts/tracing/draw_functrace.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py index 74f8aadfd4cb..7011fbe003ff 100755 --- a/scripts/tracing/draw_functrace.py +++ b/scripts/tracing/draw_functrace.py @@ -17,7 +17,7 @@ Usage: $ cat /sys/kernel/debug/tracing/trace_pipe > ~/raw_trace_func Wait some times but not too much, the script is a bit slow. Break the pipe (Ctrl + Z) - $ scripts/draw_functrace.py < raw_trace_func > draw_functrace + $ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace Then you have your drawn trace in draw_functrace """ @@ -103,10 +103,10 @@ def parseLine(line): line = line.strip() if line.startswith("#"): raise CommentLineException - m = re.match("[^]]+?\\] +([0-9.]+): (\\w+) <-(\\w+)", line) + m = re.match("[^]]+?\\] +([a-z.]+) +([0-9.]+): (\\w+) <-(\\w+)", line) if m is None: raise BrokenLineException - return (m.group(1), m.group(2), m.group(3)) + return (m.group(2), m.group(3), m.group(4)) def main(): From d5aaad6f83420efb8357ac8e11c868708b22d0a9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 4 Aug 2021 14:46:09 -0700 Subject: [PATCH 1233/1469] KVM: x86/mmu: Fix per-cpu counter corruption on 32-bit builds Take a signed 'long' instead of an 'unsigned long' for the number of pages to add/subtract to the total number of pages used by the MMU. This fixes a zero-extension bug on 32-bit kernels that effectively corrupts the per-cpu counter used by the shrinker. Per-cpu counters take a signed 64-bit value on both 32-bit and 64-bit kernels, whereas kvm_mod_used_mmu_pages() takes an unsigned long and thus an unsigned 32-bit value on 32-bit kernels. As a result, the value used to adjust the per-cpu counter is zero-extended (unsigned -> signed), not sign-extended (signed -> signed), and so KVM's intended -1 gets morphed to 4294967295 and effectively corrupts the counter. This was found by a staggering amount of sheer dumb luck when running kvm-unit-tests on a 32-bit KVM build. The shrinker just happened to kick in while running tests and do_shrink_slab() logged an error about trying to free a negative number of objects. The truly lucky part is that the kernel just happened to be a slightly stale build, as the shrinker no longer yells about negative objects as of commit 18bb473e5031 ("mm: vmscan: shrink deferred objects proportional to priority"). vmscan: shrink_slab: mmu_shrink_scan+0x0/0x210 [kvm] negative objects to delete nr=-858993460 Fixes: bc8a3d8925a8 ("kvm: mmu: Fix overflow on kvm mmu page limit calculation") Cc: stable@vger.kernel.org Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210804214609.1096003-1-seanjc@google.com> Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 66f7f5bc3482..c4f4fa23320e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1644,7 +1644,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); From 8da0e55c7988ef9f08a708c38e5c75ecd8862cf8 Mon Sep 17 00:00:00 2001 From: David Bauer Date: Thu, 5 Aug 2021 01:25:22 +0200 Subject: [PATCH 1234/1469] USB: serial: ftdi_sio: add device ID for Auto-M3 OP-COM v2 The Auto-M3 OP-COM v2 is a OBD diagnostic device using a FTD232 for the USB connection. Signed-off-by: David Bauer Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/ftdi_sio.c | 1 + drivers/usb/serial/ftdi_sio_ids.h | 3 +++ 2 files changed, 4 insertions(+) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 4a1f3a95d017..33bbb3470ca3 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -219,6 +219,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_MTXORB_6_PID) }, { USB_DEVICE(FTDI_VID, FTDI_R2000KU_TRUE_RNG) }, { USB_DEVICE(FTDI_VID, FTDI_VARDAAN_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_AUTO_M3_OP_COM_V2_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0100_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0101_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0102_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index add602bebd82..755858ca20ba 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -159,6 +159,9 @@ /* Vardaan Enterprises Serial Interface VEUSB422R3 */ #define FTDI_VARDAAN_PID 0xF070 +/* Auto-M3 Ltd. - OP-COM USB V2 - OBD interface Adapter */ +#define FTDI_AUTO_M3_OP_COM_V2_PID 0x4f50 + /* * Xsens Technologies BV products (http://www.xsens.com). */ From d25d85061bd856d6be221626605319154f9b5043 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Thu, 29 Jul 2021 00:33:14 -0700 Subject: [PATCH 1235/1469] usb: dwc3: gadget: Use list_replace_init() before traversing lists The list_for_each_entry_safe() macro saves the current item (n) and the item after (n+1), so that n can be safely removed without corrupting the list. However, when traversing the list and removing items using gadget giveback, the DWC3 lock is briefly released, allowing other routines to execute. There is a situation where, while items are being removed from the cancelled_list using dwc3_gadget_ep_cleanup_cancelled_requests(), the pullup disable routine is running in parallel (due to UDC unbind). As the cleanup routine removes n, and the pullup disable removes n+1, once the cleanup retakes the DWC3 lock, it references a request who was already removed/handled. With list debug enabled, this leads to a panic. Ensure all instances of the macro are replaced where gadget giveback is used. Example call stack: Thread#1: __dwc3_gadget_ep_set_halt() - CLEAR HALT -> dwc3_gadget_ep_cleanup_cancelled_requests() ->list_for_each_entry_safe() ->dwc3_gadget_giveback(n) ->dwc3_gadget_del_and_unmap_request()- n deleted[cancelled_list] ->spin_unlock ->Thread#2 executes ... ->dwc3_gadget_giveback(n+1) ->Already removed! Thread#2: dwc3_gadget_pullup() ->waiting for dwc3 spin_lock ... ->Thread#1 released lock ->dwc3_stop_active_transfers() ->dwc3_remove_requests() ->fetches n+1 item from cancelled_list (n removed by Thread#1) ->dwc3_gadget_giveback() ->dwc3_gadget_del_and_unmap_request()- n+1 deleted[cancelled_list] ->spin_unlock Fix this condition by utilizing list_replace_init(), and traversing through a local copy of the current elements in the endpoint lists. This will also set the parent list as empty, so if another thread is also looping through the list, it will be empty on the next iteration. Fixes: d4f1afe5e896 ("usb: dwc3: gadget: move requests to cancelled_list") Cc: stable Acked-by: Felipe Balbi Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1627543994-20327-1-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 45f2bc0807e8..a1b262669574 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1741,9 +1741,13 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) { struct dwc3_request *req; struct dwc3_request *tmp; + struct list_head local; struct dwc3 *dwc = dep->dwc; - list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) { +restart: + list_replace_init(&dep->cancelled_list, &local); + + list_for_each_entry_safe(req, tmp, &local, list) { dwc3_gadget_ep_skip_trbs(dep, req); switch (req->status) { case DWC3_REQUEST_STATUS_DISCONNECTED: @@ -1761,6 +1765,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) break; } } + + if (!list_empty(&dep->cancelled_list)) + goto restart; } static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, @@ -2958,8 +2965,12 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, { struct dwc3_request *req; struct dwc3_request *tmp; + struct list_head local; - list_for_each_entry_safe(req, tmp, &dep->started_list, list) { +restart: + list_replace_init(&dep->started_list, &local); + + list_for_each_entry_safe(req, tmp, &local, list) { int ret; ret = dwc3_gadget_ep_cleanup_completed_request(dep, event, @@ -2967,6 +2978,9 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, if (ret) break; } + + if (!list_empty(&dep->started_list)) + goto restart; } static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep) From cb10f68ad8150f243964b19391711aaac5e8ff42 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Tue, 3 Aug 2021 23:24:05 -0700 Subject: [PATCH 1236/1469] usb: dwc3: gadget: Avoid runtime resume if disabling pullup If the device is already in the runtime suspended state, any call to the pullup routine will issue a runtime resume on the DWC3 core device. If the USB gadget is disabling the pullup, then avoid having to issue a runtime resume, as DWC3 gadget has already been halted/stopped. This fixes an issue where the following condition occurs: usb_gadget_remove_driver() -->usb_gadget_disconnect() -->dwc3_gadget_pullup(0) -->pm_runtime_get_sync() -> ret = 0 -->pm_runtime_put() [async] -->usb_gadget_udc_stop() -->dwc3_gadget_stop() -->dwc->gadget_driver = NULL ... dwc3_suspend_common() -->dwc3_gadget_suspend() -->DWC3 halt/stop routine skipped, driver_data == NULL This leads to a situation where the DWC3 gadget is not properly stopped, as the runtime resume would have re-enabled EP0 and event interrupts, and since we avoided the DWC3 gadget suspend, these resources were never disabled. Fixes: 77adb8bdf422 ("usb: dwc3: gadget: Allow runtime suspend if UDC unbinded") Cc: stable Acked-by: Felipe Balbi Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1628058245-30692-1-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index a1b262669574..b8d4b2d327b2 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2256,6 +2256,17 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) } } + /* + * Avoid issuing a runtime resume if the device is already in the + * suspended state during gadget disconnect. DWC3 gadget was already + * halted/stopped during runtime suspend. + */ + if (!is_on) { + pm_runtime_barrier(dwc->dev); + if (pm_runtime_suspended(dwc->dev)) + return 0; + } + /* * Check the return value for successful resume, or error. For a * successful resume, the DWC3 runtime PM resume routine will handle From 6aa32467299e9e12280a6aec9dbc21bf2db830b0 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Wed, 21 Jul 2021 17:30:45 +0800 Subject: [PATCH 1237/1469] MIPS: check return value of pgtable_pmd_page_ctor +. According to Documentation/vm/split_page_table_lock, handle failure of pgtable_pmd_page_ctor +. Use GFP_KERNEL_ACCOUNT instead of GFP_KERNEL|__GFP_ACCOUNT +. Adjust coding style Fixes: ed914d48b6a1 ("MIPS: add PMD table accounting into MIPS') Reported-by: Joshua Kinard Signed-off-by: Huang Pei Reviewed-by: Joshua Kinard Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/pgalloc.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 4b2567d6b2df..c7925d0e9874 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -58,15 +58,20 @@ do { \ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *pmd = NULL; + pmd_t *pmd; struct page *pg; - pg = alloc_pages(GFP_KERNEL | __GFP_ACCOUNT, PMD_ORDER); - if (pg) { - pgtable_pmd_page_ctor(pg); - pmd = (pmd_t *)page_address(pg); - pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); + pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_ORDER); + if (!pg) + return NULL; + + if (!pgtable_pmd_page_ctor(pg)) { + __free_pages(pg, PMD_ORDER); + return NULL; } + + pmd = (pmd_t *)page_address(pg); + pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); return pmd; } From 43ad944cd73f2360ec8ff31d29ea44830b3119af Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Tue, 3 Aug 2021 17:13:14 +0800 Subject: [PATCH 1238/1469] usb: typec: tcpm: Keep other events when receiving FRS and Sourcing_vbus events When receiving FRS and Sourcing_Vbus events from low-level drivers, keep other events which come a bit earlier so that they will not be ignored in the event handler. Fixes: 8dc4bd073663 ("usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS)") Cc: stable Cc: Badhri Jagan Sridharan Reviewed-by: Guenter Roeck Reviewed-by: Badhri Jagan Sridharan Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210803091314.3051302-1-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 5b22a1c931a9..b9bb63d749ec 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5369,7 +5369,7 @@ EXPORT_SYMBOL_GPL(tcpm_pd_hard_reset); void tcpm_sink_frs(struct tcpm_port *port) { spin_lock(&port->pd_event_lock); - port->pd_events = TCPM_FRS_EVENT; + port->pd_events |= TCPM_FRS_EVENT; spin_unlock(&port->pd_event_lock); kthread_queue_work(port->wq, &port->event_work); } @@ -5378,7 +5378,7 @@ EXPORT_SYMBOL_GPL(tcpm_sink_frs); void tcpm_sourcing_vbus(struct tcpm_port *port) { spin_lock(&port->pd_event_lock); - port->pd_events = TCPM_SOURCING_VBUS; + port->pd_events |= TCPM_SOURCING_VBUS; spin_unlock(&port->pd_event_lock); kthread_queue_work(port->wq, &port->event_work); } From 5a7c1b2a5bb4461967b15f3484a0ff75d3199719 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Wed, 4 Aug 2021 21:39:49 +0530 Subject: [PATCH 1239/1469] net: wwan: iosm: fix lkp buildbot warning Correct td buffer type casting & format specifier to fix lkp buildbot warning. Reported-by: kernel test robot Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c index 91109e27efd3..35d590743d3a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c @@ -412,8 +412,8 @@ struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol, } if (p_td->buffer.address != IPC_CB(skb)->mapping) { - dev_err(ipc_protocol->dev, "invalid buf=%p or skb=%p", - (void *)p_td->buffer.address, skb->data); + dev_err(ipc_protocol->dev, "invalid buf=%llx or skb=%p", + (unsigned long long)p_td->buffer.address, skb->data); ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); skb = NULL; goto ret; From b46c5795d641b759eb0f001ab21852fe5df5ef92 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Wed, 4 Aug 2021 21:39:50 +0530 Subject: [PATCH 1240/1469] net: wwan: iosm: endianness type correction Endianness type correction for nr_of_bytes. This field is exchanged as part of host-device protocol communication. Signed-off-by: M Chetan Kumar Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_mux_codec.c | 4 ++-- drivers/net/wwan/iosm/iosm_ipc_mux_codec.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index 562de275797a..bdb2d32cdb6d 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -320,7 +320,7 @@ static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux, return; } - ul_credits = fct->vfl.nr_of_bytes; + ul_credits = le32_to_cpu(fct->vfl.nr_of_bytes); dev_dbg(ipc_mux->dev, "Flow_Credit:: if_id[%d] Old: %d Grants: %d", if_id, ipc_mux->session[if_id].ul_flow_credits, ul_credits); @@ -586,7 +586,7 @@ static bool ipc_mux_lite_send_qlt(struct iosm_mux *ipc_mux) qlt->reserved[0] = 0; qlt->reserved[1] = 0; - qlt->vfl.nr_of_bytes = session->ul_list.qlen; + qlt->vfl.nr_of_bytes = cpu_to_le32(session->ul_list.qlen); /* Add QLT to the transfer list. */ skb_queue_tail(&ipc_mux->channel->ul_list, diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h index 4a74e3c9457f..aae83db5cbb8 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h @@ -106,7 +106,7 @@ struct mux_lite_cmdh { * @nr_of_bytes: Number of bytes available to transmit in the queue. */ struct mux_lite_vfl { - u32 nr_of_bytes; + __le32 nr_of_bytes; }; /** From c98f5220e9703db2d73b4e89c07879dc61eeab14 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Wed, 4 Aug 2021 21:39:51 +0530 Subject: [PATCH 1241/1469] net: wwan: iosm: correct data protocol mask bit Correct ul/dl data protocol mask bit to know which protocol capability does device implement. Signed-off-by: M Chetan Kumar Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_mmio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.h b/drivers/net/wwan/iosm/iosm_ipc_mmio.h index 45e6923da78f..f861994a6d90 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.h @@ -10,10 +10,10 @@ #define IOSM_CP_VERSION 0x0100UL /* DL dir Aggregation support mask */ -#define DL_AGGR BIT(23) +#define DL_AGGR BIT(9) /* UL dir Aggregation support mask */ -#define UL_AGGR BIT(22) +#define UL_AGGR BIT(8) /* UL flow credit support mask */ #define UL_FLOW_CREDIT BIT(21) From 679505baaaabed98359c1dfb78f81600e299af21 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Wed, 4 Aug 2021 21:39:52 +0530 Subject: [PATCH 1242/1469] net: wwan: iosm: fix recursive lock acquire in unregister Calling unregister_netdevice() inside wwan del link is trying to acquire the held lock in ndo_stop_cb(). Instead, queue net dev to be unregistered later. Signed-off-by: M Chetan Kumar Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index b2357ad5d517..b571d9cedba4 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -228,7 +228,7 @@ static void ipc_wwan_dellink(void *ctxt, struct net_device *dev, RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL); /* unregistering includes synchronize_net() */ - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); unlock: mutex_unlock(&ipc_wwan->if_mutex); From fa953adfad7cf9c7e30d9ea0e4ccfd38cfb5495d Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 8 Jul 2021 10:57:09 +0200 Subject: [PATCH 1243/1469] x86/tools/relocs: Fix non-POSIX regexp Trying to run a cross-compiled x86 relocs tool on a BSD based HOSTCC leads to errors like VOFFSET arch/x86/boot/compressed/../voffset.h - due to: vmlinux CC arch/x86/boot/compressed/misc.o - due to: arch/x86/boot/compressed/../voffset.h OBJCOPY arch/x86/boot/compressed/vmlinux.bin - due to: vmlinux RELOCS arch/x86/boot/compressed/vmlinux.relocs - due to: vmlinux empty (sub)expressionarch/x86/boot/compressed/Makefile:118: recipe for target 'arch/x86/boot/compressed/vmlinux.relocs' failed make[3]: *** [arch/x86/boot/compressed/vmlinux.relocs] Error 1 It turns out that relocs.c uses patterns like "something(|_end)" This is not valid syntax or gives undefined results according to POSIX 9.5.3 ERE Grammar https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html It seems to be silently accepted by the Linux regexp() implementation while a BSD host complains. Such patterns can be replaced by a transformation like "(|p1|p2)" -> "(p1|p2)?" Fixes: fd952815307f ("x86-32, relocs: Whitelist more symbols for ld bug workaround") Signed-off-by: H. Nikolaus Schaller Signed-off-by: Masahiro Yamada --- arch/x86/tools/relocs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 04c5a44b9682..9ba700dc47de 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -57,12 +57,12 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { [S_REL] = "^(__init_(begin|end)|" "__x86_cpu_dev_(start|end)|" - "(__parainstructions|__alt_instructions)(|_end)|" - "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" + "(__parainstructions|__alt_instructions)(_end)?|" + "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" "__(start|end)_builtin_fw|" - "__(start|stop)___ksymtab(|_gpl)|" - "__(start|stop)___kcrctab(|_gpl)|" + "__(start|stop)___ksymtab(_gpl)?|" + "__(start|stop)___kcrctab(_gpl)?|" "__(start|stop)___param|" "__(start|stop)___modver|" "__(start|stop)___bug_table|" From 28bbbb9875a35975904e46f9b06fa689d051b290 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 8 Jul 2021 10:57:10 +0200 Subject: [PATCH 1244/1469] mips: Fix non-POSIX regexp When cross compiling a MIPS kernel on a BSD based HOSTCC leads to errors like SYNC include/config/auto.conf.cmd - due to: .config egrep: empty (sub)expression UPD include/config/kernel.release HOSTCC scripts/dtc/dtc.o - due to target missing It turns out that egrep uses this egrep pattern: (|MINOR_|PATCHLEVEL_) This is not valid syntax or gives undefined results according to POSIX 9.5.3 ERE Grammar https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html It seems to be silently accepted by the Linux egrep implementation while a BSD host complains. Such patterns can be replaced by a transformation like "(|p1|p2)" -> "(p1|p2)?" Fixes: 48c35b2d245f ("[MIPS] There is no __GNUC_MAJOR__") Signed-off-by: H. Nikolaus Schaller Signed-off-by: Masahiro Yamada --- arch/mips/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 4e942b7ef022..653befc1b176 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -321,7 +321,7 @@ KBUILD_LDFLAGS += -m $(ld-emul) ifdef CONFIG_MIPS CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ - egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \ + egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g') endif From 54eacba0e3bbda9777788b44b45a5186918569f2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 26 Jul 2021 19:57:37 -0700 Subject: [PATCH 1245/1469] scripts: checkversion: modernize linux/version.h search strings Update scripts/checkversion.pl to recognize the current contents of and both of its current locations. Also update my email address. Signed-off-by: Randy Dunlap Signed-off-by: Masahiro Yamada --- scripts/checkversion.pl | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/scripts/checkversion.pl b/scripts/checkversion.pl index f67b125c5269..94cd49eff605 100755 --- a/scripts/checkversion.pl +++ b/scripts/checkversion.pl @@ -1,10 +1,10 @@ #! /usr/bin/env perl # SPDX-License-Identifier: GPL-2.0 # -# checkversion find uses of LINUX_VERSION_CODE or KERNEL_VERSION -# without including , or cases of -# including that don't need it. -# Copyright (C) 2003, Randy Dunlap +# checkversion finds uses of all macros in +# where the source files do not #include ; or cases +# of including where it is not needed. +# Copyright (C) 2003, Randy Dunlap use strict; @@ -13,7 +13,8 @@ $| = 1; my $debugging; foreach my $file (@ARGV) { - next if $file =~ "include/linux/version\.h"; + next if $file =~ "include/generated/uapi/linux/version\.h"; + next if $file =~ "usr/include/linux/version\.h"; # Open this file. open( my $f, '<', $file ) or die "Can't open $file: $!\n"; @@ -41,8 +42,11 @@ foreach my $file (@ARGV) { $iLinuxVersion = $. if m/^\s*#\s*include\s*/o; } - # Look for uses: LINUX_VERSION_CODE, KERNEL_VERSION, UTS_RELEASE - if (($_ =~ /LINUX_VERSION_CODE/) || ($_ =~ /\WKERNEL_VERSION/)) { + # Look for uses: LINUX_VERSION_CODE, KERNEL_VERSION, + # LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, LINUX_VERSION_SUBLEVEL + if (($_ =~ /LINUX_VERSION_CODE/) || ($_ =~ /\WKERNEL_VERSION/) || + ($_ =~ /LINUX_VERSION_MAJOR/) || ($_ =~ /LINUX_VERSION_PATCHLEVEL/) || + ($_ =~ /LINUX_VERSION_SUBLEVEL/)) { $fUseVersion = 1; last if $iLinuxVersion; } From 14ccc638b02f9ec500c17d9e39efe979145a4b61 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 29 Jul 2021 09:12:54 +0900 Subject: [PATCH 1246/1469] kbuild: cancel sub_make_done for the install target to fix DKMS Since commit bcf637f54f6d ("kbuild: parse C= and M= before changing the working directory"), external module builds invoked by DKMS fail because M= option is not parsed. I wanted to add 'unset sub_make_done' in install.sh but similar scripts, arch/*/boot/install.sh, are duplicated, so I set sub_make_done empty in the top Makefile. Fixes: bcf637f54f6d ("kbuild: parse C= and M= before changing the working directory") Reported-by: John S Gruber Signed-off-by: Masahiro Yamada Tested-by: John S Gruber --- Makefile | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/Makefile b/Makefile index 27a072cffcb9..efb294568f28 100644 --- a/Makefile +++ b/Makefile @@ -1317,6 +1317,16 @@ PHONY += scripts_unifdef scripts_unifdef: scripts_basic $(Q)$(MAKE) $(build)=scripts scripts/unifdef +# --------------------------------------------------------------------------- +# Install + +# Many distributions have the custom install script, /sbin/installkernel. +# If DKMS is installed, 'make install' will eventually recuses back +# to the this Makefile to build and install external modules. +# Cancel sub_make_done so that options such as M=, V=, etc. are parsed. + +install: sub_make_done := + # --------------------------------------------------------------------------- # Tools From fb653827c758725b149b5c924a5eb50ab4812750 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 5 Aug 2021 13:38:26 +0300 Subject: [PATCH 1247/1469] bnx2x: fix an error code in bnx2x_nic_load() Set the error code if bnx2x_alloc_fw_stats_mem() fails. The current code returns success. Fixes: ad5afc89365e ("bnx2x: Separate VF and PF logic") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 1a6ec1a12d53..b5d954cb409a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2669,7 +2669,8 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) } /* Allocated memory for FW statistics */ - if (bnx2x_alloc_fw_stats_mem(bp)) + rc = bnx2x_alloc_fw_stats_mem(bp); + if (rc) LOAD_ERROR_EXIT(bp, load_error0); /* request pf to initialize status blocks */ From ae03d189bae306e1e00aa631feee090ebda6cf63 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 5 Aug 2021 13:14:09 +0300 Subject: [PATCH 1248/1469] net: ethernet: ti: am65-cpsw: fix crash in am65_cpsw_port_offload_fwd_mark_update() The am65_cpsw_port_offload_fwd_mark_update() causes NULL exception crash when there is at least one disabled port and any other port added to the bridge first time. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000858 pc : am65_cpsw_port_offload_fwd_mark_update+0x54/0x68 lr : am65_cpsw_netdevice_event+0x8c/0xf0 Call trace: am65_cpsw_port_offload_fwd_mark_update+0x54/0x68 notifier_call_chain+0x54/0x98 raw_notifier_call_chain+0x14/0x20 call_netdevice_notifiers_info+0x34/0x78 __netdev_upper_dev_link+0x1c8/0x290 netdev_master_upper_dev_link+0x1c/0x28 br_add_if+0x3f0/0x6d0 [bridge] Fix it by adding proper check for port->ndev != NULL. Fixes: 2934db9bcb30 ("net: ti: am65-cpsw-nuss: Add netdevice notifiers") Signed-off-by: Grygorii Strashko Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 718539cdd2f2..67a08cbba859 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2060,8 +2060,12 @@ static void am65_cpsw_port_offload_fwd_mark_update(struct am65_cpsw_common *comm for (i = 1; i <= common->port_num; i++) { struct am65_cpsw_port *port = am65_common_get_port(common, i); - struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(port->ndev); + struct am65_cpsw_ndev_priv *priv; + if (!port->ndev) + continue; + + priv = am65_ndev_to_priv(port->ndev); priv->offload_fwd_mark = set_val; } } From 51397dc6f283bb570e1cf8226017d300d8ea1f5b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 4 Aug 2021 14:18:48 -0400 Subject: [PATCH 1249/1469] tracing: Quiet smp_processor_id() use in preemptable warning in hwlat The hardware latency detector (hwlat) has a mode that it runs one thread across CPUs. The logic to move from the currently running CPU to the next one in the list does a smp_processor_id() to find where it currently is. Unfortunately, it's done with preemption enabled, and this triggers a warning for using smp_processor_id() in a preempt enabled section. As it is only using smp_processor_id() to get information on where it currently is in order to simply move it to the next CPU, it doesn't really care if it got moved in the mean time. It will simply balance out later if such a case arises. Switch smp_processor_id() to raw_smp_processor_id() to quiet that warning. Link: https://lkml.kernel.org/r/20210804141848.79edadc0@oasis.local.home Acked-by: Daniel Bristot de Oliveira Fixes: 8fa826b7344d ("trace/hwlat: Implement the mode config option") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_hwlat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index a6c0cdaf4b87..14f46aae1981 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -327,7 +327,7 @@ static void move_to_next_cpu(void) get_online_cpus(); cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); - next_cpu = cpumask_next(smp_processor_id(), current_mask); + next_cpu = cpumask_next(raw_smp_processor_id(), current_mask); put_online_cpus(); if (next_cpu >= nr_cpu_ids) From af35fc37354cda3c9c8cc4961b1d24bdc9d27903 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 4 Aug 2021 17:30:05 +0300 Subject: [PATCH 1250/1469] net: pegasus: fix uninit-value in get_interrupt_interval Syzbot reported uninit value pegasus_probe(). The problem was in missing error handling. get_interrupt_interval() internally calls read_eprom_word() which can fail in some cases. For example: failed to receive usb control message. These cases should be handled to prevent uninit value bug, since read_eprom_word() will not initialize passed stack variable in case of internal failure. Fail log: BUG: KMSAN: uninit-value in get_interrupt_interval drivers/net/usb/pegasus.c:746 [inline] BUG: KMSAN: uninit-value in pegasus_probe+0x10e7/0x4080 drivers/net/usb/pegasus.c:1152 CPU: 1 PID: 825 Comm: kworker/1:1 Not tainted 5.12.0-rc6-syzkaller #0 ... Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x24c/0x2e0 lib/dump_stack.c:120 kmsan_report+0xfb/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x5c/0xa0 mm/kmsan/kmsan_instr.c:197 get_interrupt_interval drivers/net/usb/pegasus.c:746 [inline] pegasus_probe+0x10e7/0x4080 drivers/net/usb/pegasus.c:1152 .... Local variable ----data.i@pegasus_probe created at: get_interrupt_interval drivers/net/usb/pegasus.c:1151 [inline] pegasus_probe+0xe57/0x4080 drivers/net/usb/pegasus.c:1152 get_interrupt_interval drivers/net/usb/pegasus.c:1151 [inline] pegasus_probe+0xe57/0x4080 drivers/net/usb/pegasus.c:1152 Reported-and-tested-by: syzbot+02c9f70f3afae308464a@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/20210804143005.439-1-paskripkin@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/pegasus.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f18b03be1b87..652e9fcf0b77 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -744,12 +744,16 @@ static inline void disable_net_traffic(pegasus_t *pegasus) set_registers(pegasus, EthCtrl0, sizeof(tmp), &tmp); } -static inline void get_interrupt_interval(pegasus_t *pegasus) +static inline int get_interrupt_interval(pegasus_t *pegasus) { u16 data; u8 interval; + int ret; + + ret = read_eprom_word(pegasus, 4, &data); + if (ret < 0) + return ret; - read_eprom_word(pegasus, 4, &data); interval = data >> 8; if (pegasus->usb->speed != USB_SPEED_HIGH) { if (interval < 0x80) { @@ -764,6 +768,8 @@ static inline void get_interrupt_interval(pegasus_t *pegasus) } } pegasus->intr_interval = interval; + + return 0; } static void set_carrier(struct net_device *net) @@ -1165,7 +1171,9 @@ static int pegasus_probe(struct usb_interface *intf, | NETIF_MSG_PROBE | NETIF_MSG_LINK); pegasus->features = usb_dev_id[dev_index].private; - get_interrupt_interval(pegasus); + res = get_interrupt_interval(pegasus); + if (res) + goto out2; if (reset_mac(pegasus)) { dev_err(&intf->dev, "can't reset MAC\n"); res = -EIO; From 44712965bf12ae1758cec4de53816ed4b914ca1a Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 4 Aug 2021 18:51:51 +0300 Subject: [PATCH 1251/1469] net: fec: fix use-after-free in fec_drv_remove Smatch says: drivers/net/ethernet/freescale/fec_main.c:3994 fec_drv_remove() error: Using fep after free_{netdev,candev}(ndev); drivers/net/ethernet/freescale/fec_main.c:3995 fec_drv_remove() error: Using fep after free_{netdev,candev}(ndev); Since fep pointer is netdev private data, accessing it after free_netdev() call can cause use-after-free bug. Fix it by moving free_netdev() call at the end of the function Reported-by: Dan Carpenter Fixes: a31eda65ba21 ("net: fec: fix clock count mis-match") Signed-off-by: Pavel Skripkin Reviewed-by: Joakim Zhang Reviewed-by: Jesse Brandeburg Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8aea707a65a7..7e4c4980ced7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3843,13 +3843,13 @@ fec_drv_remove(struct platform_device *pdev) if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - free_netdev(ndev); clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_ipg); pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + free_netdev(ndev); return 0; } From 942e560a3d3862dd5dee1411dbdd7097d29b8416 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Wed, 4 Aug 2021 18:52:20 +0300 Subject: [PATCH 1252/1469] net: vxge: fix use-after-free in vxge_device_unregister Smatch says: drivers/net/ethernet/neterion/vxge/vxge-main.c:3518 vxge_device_unregister() error: Using vdev after free_{netdev,candev}(dev); drivers/net/ethernet/neterion/vxge/vxge-main.c:3518 vxge_device_unregister() error: Using vdev after free_{netdev,candev}(dev); drivers/net/ethernet/neterion/vxge/vxge-main.c:3520 vxge_device_unregister() error: Using vdev after free_{netdev,candev}(dev); drivers/net/ethernet/neterion/vxge/vxge-main.c:3520 vxge_device_unregister() error: Using vdev after free_{netdev,candev}(dev); Since vdev pointer is netdev private data accessing it after free_netdev() call can cause use-after-free bug. Fix it by moving free_netdev() call at the end of the function Fixes: 6cca200362b4 ("vxge: cleanup probe error paths") Reported-by: Dan Carpenter Signed-off-by: Pavel Skripkin Reviewed-by: Jesse Brandeburg Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/neterion/vxge/vxge-main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 82eef4c72f01..7abd13e69471 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -3512,13 +3512,13 @@ static void vxge_device_unregister(struct __vxge_hw_device *hldev) kfree(vdev->vpaths); - /* we are safe to free it now */ - free_netdev(dev); - vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered", buf); vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d Exiting...", buf, __func__, __LINE__); + + /* we are safe to free it now */ + free_netdev(dev); } /* From 8d75d0eff6887bcac7225e12b9c75595e523d92d Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 5 Aug 2021 20:46:45 +0800 Subject: [PATCH 1253/1469] blk-iolatency: error out if blk_get_queue() failed in iolatency_set_limit() If queue is dying while iolatency_set_limit() is in progress, blk_get_queue() won't increment the refcount of the queue. However, blk_put_queue() will still decrement the refcount later, which will cause the refcout to be unbalanced. Thus error out in such case to fix the problem. Fixes: 8c772a9bfc7c ("blk-iolatency: fix IO hang due to negative inflight counter") Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210805124645.543797-1-yukuai3@huawei.com Signed-off-by: Jens Axboe --- block/blk-iolatency.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 81be0096411d..d8b0d8bd132b 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -833,7 +833,11 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, enable = iolatency_set_min_lat_nsec(blkg, lat_val); if (enable) { - WARN_ON_ONCE(!blk_get_queue(blkg->q)); + if (!blk_get_queue(blkg->q)) { + ret = -ENODEV; + goto out; + } + blkg_get(blkg); } From 46c4c9d1beb7f5b4cec4dd90e7728720583ee348 Mon Sep 17 00:00:00 2001 From: "Alex Xu (Hello71)" Date: Thu, 5 Aug 2021 10:40:47 -0400 Subject: [PATCH 1254/1469] pipe: increase minimum default pipe size to 2 pages This program always prints 4096 and hangs before the patch, and always prints 8192 and exits successfully after: int main() { int pipefd[2]; for (int i = 0; i < 1025; i++) if (pipe(pipefd) == -1) return 1; size_t bufsz = fcntl(pipefd[1], F_GETPIPE_SZ); printf("%zd\n", bufsz); char *buf = calloc(bufsz, 1); write(pipefd[1], buf, bufsz); read(pipefd[0], buf, bufsz-1); write(pipefd[1], buf, 1); } Note that you may need to increase your RLIMIT_NOFILE before running the program. Fixes: 759c01142a ("pipe: limit the per-user amount of pages allocated in pipes") Cc: Link: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/ Link: https://lore.kernel.org/lkml/1628127094.lxxn016tj7.none@localhost/ Signed-off-by: Alex Xu (Hello71) Signed-off-by: Linus Torvalds --- fs/pipe.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index 9ef4231cce61..8e6ef62aeb1c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -31,6 +31,21 @@ #include "internal.h" +/* + * New pipe buffers will be restricted to this size while the user is exceeding + * their pipe buffer quota. The general pipe use case needs at least two + * buffers: one for data yet to be read, and one for new data. If this is less + * than two, then a write to a non-empty pipe may block even if the pipe is not + * full. This can occur with GNU make jobserver or similar uses of pipes as + * semaphores: multiple processes may be waiting to write tokens back to the + * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. + * + * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their + * own risk, namely: pipe writes to non-full pipes may block until the pipe is + * emptied. + */ +#define PIPE_MIN_DEF_BUFFERS 2 + /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size @@ -781,8 +796,8 @@ struct pipe_inode_info *alloc_pipe_info(void) user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { - user_bufs = account_pipe_buffers(user, pipe_bufs, 1); - pipe_bufs = 1; + user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); + pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) From 7d3fc01796fc895e5fcce45c994c5a8db8120a8d Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Wed, 4 Aug 2021 18:37:22 +0000 Subject: [PATCH 1255/1469] cifs: create sd context must be a multiple of 8 We used to follow the rule earlier that the create SD context always be a multiple of 8. However, with the change: cifs: refactor create_sd_buf() and and avoid corrupting the buffer ...we recompute the length, and we failed that rule. Fixing that with this change. Cc: # v5.10+ Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 781d14e5f2af..b6d2e3591927 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2426,7 +2426,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) memcpy(aclptr, &acl, sizeof(struct cifs_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); - *len = ptr - (__u8 *)buf; + *len = roundup(ptr - (__u8 *)buf, 8); return buf; } From 2e9fb2c11e0ec3113fcf0e8e052c99ecd82fcd4e Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 5 Aug 2021 10:34:47 -0700 Subject: [PATCH 1256/1469] block/partitions/ldm.c: Fix a kernel-doc warning Fix the following kernel-doc warning that appears when building with W=1: block/partitions/ldm.c:31: warning: expecting prototype for ldm(). Prototype was for ldm_debug() instead Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20210805173447.3249906-1-bvanassche@acm.org Signed-off-by: Jens Axboe --- block/partitions/ldm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index d333786b5c7e..14b124cdacfc 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * ldm - Support for Windows Logical Disk Manager (Dynamic Disks) * * Copyright (C) 2001,2002 Richard Russon From e04480920d1eec9c061841399aa6f35b6f987d8b Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 4 Aug 2021 19:26:56 +0900 Subject: [PATCH 1257/1469] Bluetooth: defer cleanup of resources in hci_unregister_dev() syzbot is hitting might_sleep() warning at hci_sock_dev_event() due to calling lock_sock() with rw spinlock held [1]. It seems that history of this locking problem is a trial and error. Commit b40df5743ee8 ("[PATCH] bluetooth: fix socket locking in hci_sock_dev_event()") in 2.6.21-rc4 changed bh_lock_sock() to lock_sock() as an attempt to fix lockdep warning. Then, commit 4ce61d1c7a8e ("[BLUETOOTH]: Fix locking in hci_sock_dev_event().") in 2.6.22-rc2 changed lock_sock() to local_bh_disable() + bh_lock_sock_nested() as an attempt to fix the sleep in atomic context warning. Then, commit 4b5dd696f81b ("Bluetooth: Remove local_bh_disable() from hci_sock.c") in 3.3-rc1 removed local_bh_disable(). Then, commit e305509e678b ("Bluetooth: use correct lock to prevent UAF of hdev object") in 5.13-rc5 again changed bh_lock_sock_nested() to lock_sock() as an attempt to fix CVE-2021-3573. This difficulty comes from current implementation that hci_sock_dev_event(HCI_DEV_UNREG) is responsible for dropping all references from sockets because hci_unregister_dev() immediately reclaims resources as soon as returning from hci_sock_dev_event(HCI_DEV_UNREG). But the history suggests that hci_sock_dev_event(HCI_DEV_UNREG) was not doing what it should do. Therefore, instead of trying to detach sockets from device, let's accept not detaching sockets from device at hci_sock_dev_event(HCI_DEV_UNREG), by moving actual cleanup of resources from hci_unregister_dev() to hci_cleanup_dev() which is called by bt_host_release() when all references to this unregistered device (which is a kobject) are gone. Since hci_sock_dev_event(HCI_DEV_UNREG) no longer resets hci_pi(sk)->hdev, we need to check whether this device was unregistered and return an error based on HCI_UNREGISTER flag. There might be subtle behavioral difference in "monitor the hdev" functionality; please report if you found something went wrong due to this patch. Link: https://syzkaller.appspot.com/bug?extid=a5df189917e79d5e59c9 [1] Reported-by: syzbot Suggested-by: Linus Torvalds Signed-off-by: Tetsuo Handa Fixes: e305509e678b ("Bluetooth: use correct lock to prevent UAF of hdev object") Acked-by: Luiz Augusto von Dentz Signed-off-by: Linus Torvalds --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 16 +++++------ net/bluetooth/hci_sock.c | 49 +++++++++++++++++++++----------- net/bluetooth/hci_sysfs.c | 3 ++ 4 files changed, 45 insertions(+), 24 deletions(-) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a53e94459ecd..db4312e44d47 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1230,6 +1230,7 @@ struct hci_dev *hci_alloc_dev(void); void hci_free_dev(struct hci_dev *hdev); int hci_register_dev(struct hci_dev *hdev); void hci_unregister_dev(struct hci_dev *hdev); +void hci_cleanup_dev(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2560ed2f144d..e1a545c8a69f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3996,14 +3996,10 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int id; - BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hci_dev_set_flag(hdev, HCI_UNREGISTER); - id = hdev->id; - write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -4038,7 +4034,14 @@ void hci_unregister_dev(struct hci_dev *hdev) } device_del(&hdev->dev); + /* Actual cleanup is deferred until hci_cleanup_dev(). */ + hci_dev_put(hdev); +} +EXPORT_SYMBOL(hci_unregister_dev); +/* Cleanup HCI device */ +void hci_cleanup_dev(struct hci_dev *hdev) +{ debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); @@ -4063,11 +4066,8 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_blocked_keys_clear(hdev); hci_dev_unlock(hdev); - hci_dev_put(hdev); - - ida_simple_remove(&hci_index_ida, id); + ida_simple_remove(&hci_index_ida, hdev->id); } -EXPORT_SYMBOL(hci_unregister_dev); /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index b04a5a02ecf3..f1128c2134f0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -59,6 +59,17 @@ struct hci_pinfo { char comm[TASK_COMM_LEN]; }; +static struct hci_dev *hci_hdev_from_sock(struct sock *sk) +{ + struct hci_dev *hdev = hci_pi(sk)->hdev; + + if (!hdev) + return ERR_PTR(-EBADFD); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return ERR_PTR(-EPIPE); + return hdev; +} + void hci_sock_set_flag(struct sock *sk, int nr) { set_bit(nr, &hci_pi(sk)->flags); @@ -759,19 +770,13 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - /* Detach sockets from device */ + /* Wake up sockets using this dead device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { - lock_sock(sk); if (hci_pi(sk)->hdev == hdev) { - hci_pi(sk)->hdev = NULL; sk->sk_err = EPIPE; - sk->sk_state = BT_OPEN; sk->sk_state_change(sk); - - hci_dev_put(hdev); } - release_sock(sk); } read_unlock(&hci_sk_list.lock); } @@ -930,10 +935,10 @@ static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { - struct hci_dev *hdev = hci_pi(sk)->hdev; + struct hci_dev *hdev = hci_hdev_from_sock(sk); - if (!hdev) - return -EBADFD; + if (IS_ERR(hdev)) + return PTR_ERR(hdev); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; @@ -1103,6 +1108,18 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, lock_sock(sk); + /* Allow detaching from dead device and attaching to alive device, if + * the caller wants to re-bind (instead of close) this socket in + * response to hci_sock_dev_event(HCI_DEV_UNREG) notification. + */ + hdev = hci_pi(sk)->hdev; + if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + hci_pi(sk)->hdev = NULL; + sk->sk_state = BT_OPEN; + hci_dev_put(hdev); + } + hdev = NULL; + if (sk->sk_state == BT_BOUND) { err = -EALREADY; goto done; @@ -1379,9 +1396,9 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } @@ -1743,9 +1760,9 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, goto done; } - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 9874844a95a9..b69d88b88d2e 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -83,6 +83,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn) static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); + + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + hci_cleanup_dev(hdev); kfree(hdev); module_put(THIS_MODULE); } From f1040e86f83b0f7d5f45724500a6a441731ff4b7 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 5 Aug 2021 17:11:04 +0100 Subject: [PATCH 1258/1469] ASoC: cs42l42: PLL must be running when changing MCLK_SRC_SEL Both SCLK and PLL clocks must be running to drive the glitch-free mux behind MCLK_SRC_SEL and complete the switchover. This patch moves the writing of MCLK_SRC_SEL to when the PLL is started and stopped, so that it only transitions while the PLL is running. The unconditional write MCLK_SRC_SEL=0 in cs42l42_mute_stream() is safe because if the PLL is not running MCLK_SRC_SEL is already 0. Signed-off-by: Richard Fitzgerald Fixes: 43fc357199f9 ("ASoC: cs42l42: Set clock source for both ways of stream") Link: https://lore.kernel.org/r/20210805161111.10410-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 25 ++++++++++++++++++------- sound/soc/codecs/cs42l42.h | 1 + 2 files changed, 19 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index a00dc3c65549..c96549fe6ab2 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -619,6 +619,8 @@ static int cs42l42_pll_config(struct snd_soc_component *component) for (i = 0; i < ARRAY_SIZE(pll_ratio_table); i++) { if (pll_ratio_table[i].sclk == clk) { + cs42l42->pll_config = i; + /* Configure the internal sample rate */ snd_soc_component_update_bits(component, CS42L42_MCLK_CTL, CS42L42_INTERNAL_FS_MASK, @@ -627,14 +629,9 @@ static int cs42l42_pll_config(struct snd_soc_component *component) (pll_ratio_table[i].mclk_int != 24000000)) << CS42L42_INTERNAL_FS_SHIFT); - /* Set the MCLK src (PLL or SCLK) and the divide - * ratio - */ + snd_soc_component_update_bits(component, CS42L42_MCLK_SRC_SEL, - CS42L42_MCLK_SRC_SEL_MASK | CS42L42_MCLKDIV_MASK, - (pll_ratio_table[i].mclk_src_sel - << CS42L42_MCLK_SRC_SEL_SHIFT) | (pll_ratio_table[i].mclk_div << CS42L42_MCLKDIV_SHIFT)); /* Set up the LRCLK */ @@ -892,13 +889,21 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) */ regmap_multi_reg_write(cs42l42->regmap, cs42l42_to_osc_seq, ARRAY_SIZE(cs42l42_to_osc_seq)); + + /* Must disconnect PLL before stopping it */ + snd_soc_component_update_bits(component, + CS42L42_MCLK_SRC_SEL, + CS42L42_MCLK_SRC_SEL_MASK, + 0); + usleep_range(100, 200); + snd_soc_component_update_bits(component, CS42L42_PLL_CTL1, CS42L42_PLL_START_MASK, 0); } } else { if (!cs42l42->stream_use) { /* SCLK must be running before codec unmute */ - if ((cs42l42->bclk < 11289600) && (cs42l42->sclk < 11289600)) { + if (pll_ratio_table[cs42l42->pll_config].mclk_src_sel) { snd_soc_component_update_bits(component, CS42L42_PLL_CTL1, CS42L42_PLL_START_MASK, 1); @@ -919,6 +924,12 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) CS42L42_PLL_LOCK_TIMEOUT_US); if (ret < 0) dev_warn(component->dev, "PLL failed to lock: %d\n", ret); + + /* PLL must be running to drive glitchless switch logic */ + snd_soc_component_update_bits(component, + CS42L42_MCLK_SRC_SEL, + CS42L42_MCLK_SRC_SEL_MASK, + CS42L42_MCLK_SRC_SEL_MASK); } /* Mark SCLK as present, turn off internal oscillator */ diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h index 7bf05ff05f74..3dfeaf6611d1 100644 --- a/sound/soc/codecs/cs42l42.h +++ b/sound/soc/codecs/cs42l42.h @@ -775,6 +775,7 @@ struct cs42l42_private { struct gpio_desc *reset_gpio; struct completion pdn_done; struct snd_soc_jack *jack; + int pll_config; int bclk; u32 sclk; u32 srate; From 0c2f2ad4f16a58879463d0979a54293f8f296d6f Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 5 Aug 2021 17:11:05 +0100 Subject: [PATCH 1259/1469] ASoC: cs42l42: Fix LRCLK frame start edge An I2S frame starts on the falling edge of LRCLK so ASP_STP must be 0. At the same time, move other format settings in the same register from cs42l42_pll_config() to cs42l42_set_dai_fmt() where you'd expect to find them, and merge into a single write. Signed-off-by: Richard Fitzgerald Fixes: 2c394ca79604 ("ASoC: Add support for CS42L42 codec") Link: https://lore.kernel.org/r/20210805161111.10410-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index c96549fe6ab2..02486329a570 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -667,15 +667,6 @@ static int cs42l42_pll_config(struct snd_soc_component *component) CS42L42_FSYNC_PULSE_WIDTH_MASK, CS42L42_FRAC1_VAL(fsync - 1) << CS42L42_FSYNC_PULSE_WIDTH_SHIFT); - snd_soc_component_update_bits(component, - CS42L42_ASP_FRM_CFG, - CS42L42_ASP_5050_MASK, - CS42L42_ASP_5050_MASK); - /* Set the frame delay to 1.0 SCLK clocks */ - snd_soc_component_update_bits(component, CS42L42_ASP_FRM_CFG, - CS42L42_ASP_FSD_MASK, - CS42L42_ASP_FSD_1_0 << - CS42L42_ASP_FSD_SHIFT); /* Set the sample rates (96k or lower) */ snd_soc_component_update_bits(component, CS42L42_FS_RATE_EN, CS42L42_FS_EN_MASK, @@ -775,6 +766,18 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) /* interface format */ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: + /* + * 5050 mode, frame starts on falling edge of LRCLK, + * frame delayed by 1.0 SCLKs + */ + snd_soc_component_update_bits(component, + CS42L42_ASP_FRM_CFG, + CS42L42_ASP_STP_MASK | + CS42L42_ASP_5050_MASK | + CS42L42_ASP_FSD_MASK, + CS42L42_ASP_5050_MASK | + (CS42L42_ASP_FSD_1_0 << + CS42L42_ASP_FSD_SHIFT)); break; default: return -EINVAL; From 3a5d89a9c6fe306d35dce4496abbb464c1454da0 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 5 Aug 2021 17:11:06 +0100 Subject: [PATCH 1260/1469] ASoC: cs42l42: Constrain sample rate to prevent illegal SCLK The lowest valid SCLK corresponds to 44.1 kHz at 16-bit. Sample rates less than this would produce SCLK below the minimum when using a normal I2S frame. A constraint must be applied to prevent this. The constraint is not applied if the machine driver sets SCLK, to allow setups where the host generates additional bits per LRCLK phase to increase the SCLK frequency. In these cases the machine driver would always have to inform this driver of the actual SCLK, and it must select a legal SCLK. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20210805161111.10410-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 02486329a570..29e0c8dc8466 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -807,6 +807,25 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return 0; } +static int cs42l42_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) +{ + struct snd_soc_component *component = dai->component; + struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component); + + /* + * Sample rates < 44.1 kHz would produce an out-of-range SCLK with + * a standard I2S frame. If the machine driver sets SCLK it must be + * legal. + */ + if (cs42l42->sclk) + return 0; + + /* Machine driver has not set a SCLK, limit bottom end to 44.1 kHz */ + return snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 44100, 192000); +} + static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -966,8 +985,8 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) SNDRV_PCM_FMTBIT_S24_LE |\ SNDRV_PCM_FMTBIT_S32_LE ) - static const struct snd_soc_dai_ops cs42l42_ops = { + .startup = cs42l42_dai_startup, .hw_params = cs42l42_pcm_hw_params, .set_fmt = cs42l42_set_dai_fmt, .set_sysclk = cs42l42_set_sysclk, From e5ada3f6787a4d6234adc6f2f3ae35c6d5b71ba0 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 5 Aug 2021 17:11:07 +0100 Subject: [PATCH 1261/1469] ASoC: cs42l42: Fix mono playback I2S always has two LRCLK phases and both CH1 and CH2 of the RX must be enabled (corresponding to the low and high phases of LRCLK.) The selection of the valid data channels is done by setting the DAC CHA_SEL and CHB_SEL. CHA_SEL is always the first (left) channel, CHB_SEL depends on the number of active channels. Previously for mono ASP CH2 was not enabled, the result was playing mono data would not produce any audio output. Signed-off-by: Richard Fitzgerald Fixes: 621d65f3b868 ("ASoC: cs42l42: Provide finer control on playback path") Link: https://lore.kernel.org/r/20210805161111.10410-4-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l42.c | 15 +++++++++++++-- sound/soc/codecs/cs42l42.h | 2 ++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 29e0c8dc8466..99c022be94a6 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -460,8 +460,8 @@ static const struct snd_soc_dapm_widget cs42l42_dapm_widgets[] = { SND_SOC_DAPM_OUTPUT("HP"), SND_SOC_DAPM_DAC("DAC", NULL, CS42L42_PWR_CTL1, CS42L42_HP_PDN_SHIFT, 1), SND_SOC_DAPM_MIXER("MIXER", CS42L42_PWR_CTL1, CS42L42_MIXER_PDN_SHIFT, 1, NULL, 0), - SND_SOC_DAPM_AIF_IN("SDIN1", NULL, 0, CS42L42_ASP_RX_DAI0_EN, CS42L42_ASP_RX0_CH1_SHIFT, 0), - SND_SOC_DAPM_AIF_IN("SDIN2", NULL, 1, CS42L42_ASP_RX_DAI0_EN, CS42L42_ASP_RX0_CH2_SHIFT, 0), + SND_SOC_DAPM_AIF_IN("SDIN1", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SDIN2", NULL, 1, SND_SOC_NOPM, 0, 0), /* Playback Requirements */ SND_SOC_DAPM_SUPPLY("ASP DAI0", CS42L42_PWR_CTL1, CS42L42_ASP_DAI_PDN_SHIFT, 1, NULL, 0), @@ -866,6 +866,17 @@ static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH2_AP_RES, CS42L42_ASP_RX_CH_AP_MASK | CS42L42_ASP_RX_CH_RES_MASK, val); + + /* Channel B comes from the last active channel */ + snd_soc_component_update_bits(component, CS42L42_SP_RX_CH_SEL, + CS42L42_SP_RX_CHB_SEL_MASK, + (channels - 1) << CS42L42_SP_RX_CHB_SEL_SHIFT); + + /* Both LRCLK slots must be enabled */ + snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_EN, + CS42L42_ASP_RX0_CH_EN_MASK, + BIT(CS42L42_ASP_RX0_CH1_SHIFT) | + BIT(CS42L42_ASP_RX0_CH2_SHIFT)); break; default: break; diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h index 3dfeaf6611d1..112ffcf938c3 100644 --- a/sound/soc/codecs/cs42l42.h +++ b/sound/soc/codecs/cs42l42.h @@ -653,6 +653,8 @@ /* Page 0x25 Audio Port Registers */ #define CS42L42_SP_RX_CH_SEL (CS42L42_PAGE_25 + 0x01) +#define CS42L42_SP_RX_CHB_SEL_SHIFT 2 +#define CS42L42_SP_RX_CHB_SEL_MASK (3 << CS42L42_SP_RX_CHB_SEL_SHIFT) #define CS42L42_SP_RX_ISOC_CTL (CS42L42_PAGE_25 + 0x02) #define CS42L42_SP_RX_RSYNC_SHIFT 6 From 0395be967b067d99494113d78470574e86a02ed4 Mon Sep 17 00:00:00 2001 From: Apurva Nandan Date: Fri, 16 Jul 2021 23:25:03 +0000 Subject: [PATCH 1262/1469] spi: cadence-quadspi: Fix check condition for DTR ops buswidth and dtr fields in spi_mem_op are only valid when the corresponding spi_mem_op phase has a non-zero length. For example, SPI NAND core doesn't set buswidth when using SPI_MEM_OP_NO_ADDR phase. Fix the dtr checks in set_protocol() and suppports_mem_op() to ignore empty spi_mem_op phases, as checking for dtr field in empty phase will result in false negatives. Signed-off-by: Apurva Nandan Link: https://lore.kernel.org/r/20210716232504.182-3-a-nandan@ti.com Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-quadspi.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index a2de23516553..101cc71bffa7 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -325,7 +325,15 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->dtr = op->data.dtr && op->cmd.dtr && op->addr.dtr; + + /* + * For an op to be DTR, cmd phase along with every other non-empty + * phase should have dtr field set to 1. If an op phase has zero + * nbytes, ignore its dtr field; otherwise, check its dtr field. + */ + f_pdata->dtr = op->cmd.dtr && + (!op->addr.nbytes || op->addr.dtr) && + (!op->data.nbytes || op->data.dtr); switch (op->data.buswidth) { case 0: @@ -1228,8 +1236,15 @@ static bool cqspi_supports_mem_op(struct spi_mem *mem, { bool all_true, all_false; - all_true = op->cmd.dtr && op->addr.dtr && op->dummy.dtr && - op->data.dtr; + /* + * op->dummy.dtr is required for converting nbytes into ncycles. + * Also, don't check the dtr field of the op phase having zero nbytes. + */ + all_true = op->cmd.dtr && + (!op->addr.nbytes || op->addr.dtr) && + (!op->dummy.nbytes || op->dummy.dtr) && + (!op->data.nbytes || op->data.dtr); + all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr && !op->data.dtr; From f7ec4121256393e1d03274acdca73eb18958f27e Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 5 Aug 2021 09:27:15 -0400 Subject: [PATCH 1263/1469] tracepoint: static call: Compare data on transition from 2->1 callees On transition from 2->1 callees, we should be comparing .data rather than .func, because the same callback can be registered twice with different data, and what we care about here is that the data of array element 0 is unchanged to skip rcu sync. Link: https://lkml.kernel.org/r/20210805132717.23813-2-mathieu.desnoyers@efficios.com Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/ Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrew Morton Cc: "Paul E. McKenney" Cc: Stefan Metzmacher Fixes: 547305a64632 ("tracepoint: Fix out of sync data passing by static caller") Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- kernel/tracepoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index fc32821f8240..133b6454b287 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -338,7 +338,7 @@ static int tracepoint_remove_func(struct tracepoint *tp, } else { rcu_assign_pointer(tp->funcs, tp_funcs); tracepoint_update_call(tp, tp_funcs, - tp_funcs[0].func != old[0].func); + tp_funcs[0].data != old[0].data); } release_probes(old); return 0; From 231264d6927f6740af36855a622d0e240be9d94c Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 5 Aug 2021 09:27:16 -0400 Subject: [PATCH 1264/1469] tracepoint: Fix static call function vs data state mismatch On a 1->0->1 callbacks transition, there is an issue with the new callback using the old callback's data. Considering __DO_TRACE_CALL: do { \ struct tracepoint_func *it_func_ptr; \ void *__data; \ it_func_ptr = \ rcu_dereference_raw((&__tracepoint_##name)->funcs); \ if (it_func_ptr) { \ __data = (it_func_ptr)->data; \ ----> [ delayed here on one CPU (e.g. vcpu preempted by the host) ] static_call(tp_func_##name)(__data, args); \ } \ } while (0) It has loaded the tp->funcs of the old callback, so it will try to use the old data. This can be fixed by adding a RCU sync anywhere in the 1->0->1 transition chain. On a N->2->1 transition, we need an rcu-sync because you may have a sequence of 3->2->1 (or 1->2->1) where the element 0 data is unchanged between 2->1, but was changed from 3->2 (or from 1->2), which may be observed by the static call. This can be fixed by adding an unconditional RCU sync in transition 2->1. Note, this fixes a correctness issue at the cost of adding a tremendous performance regression to the disabling of tracepoints. Before this commit: # trace-cmd start -e all # time trace-cmd start -p nop real 0m0.778s user 0m0.000s sys 0m0.061s After this commit: # trace-cmd start -e all # time trace-cmd start -p nop real 0m10.593s user 0m0.017s sys 0m0.259s A follow up fix will introduce a more lightweight scheme based on RCU get_state and cond_sync, that will return the performance back to what it was. As both this change and the lightweight versions are complex on their own, for bisecting any issues that this may cause, they are kept as two separate changes. Link: https://lkml.kernel.org/r/20210805132717.23813-3-mathieu.desnoyers@efficios.com Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/ Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrew Morton Cc: "Paul E. McKenney" Cc: Stefan Metzmacher Fixes: d25e37d89dd2 ("tracepoint: Optimize using static_call()") Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- kernel/tracepoint.c | 102 +++++++++++++++++++++++++++++++++++--------- 1 file changed, 82 insertions(+), 20 deletions(-) diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 133b6454b287..8d772bd6894d 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -15,6 +15,13 @@ #include #include +enum tp_func_state { + TP_FUNC_0, + TP_FUNC_1, + TP_FUNC_2, + TP_FUNC_N, +}; + extern tracepoint_ptr_t __start___tracepoints_ptrs[]; extern tracepoint_ptr_t __stop___tracepoints_ptrs[]; @@ -246,26 +253,29 @@ static void *func_remove(struct tracepoint_func **funcs, return old; } -static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs, bool sync) +/* + * Count the number of functions (enum tp_func_state) in a tp_funcs array. + */ +static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs) +{ + if (!tp_funcs) + return TP_FUNC_0; + if (!tp_funcs[1].func) + return TP_FUNC_1; + if (!tp_funcs[2].func) + return TP_FUNC_2; + return TP_FUNC_N; /* 3 or more */ +} + +static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs) { void *func = tp->iterator; /* Synthetic events do not have static call sites */ if (!tp->static_call_key) return; - - if (!tp_funcs[1].func) { + if (nr_func_state(tp_funcs) == TP_FUNC_1) func = tp_funcs[0].func; - /* - * If going from the iterator back to a single caller, - * we need to synchronize with __DO_TRACE to make sure - * that the data passed to the callback is the one that - * belongs to that callback. - */ - if (sync) - tracepoint_synchronize_unregister(); - } - __static_call_update(tp->static_call_key, tp->static_call_tramp, func); } @@ -299,9 +309,31 @@ static int tracepoint_add_func(struct tracepoint *tp, * a pointer to it. This array is referenced by __DO_TRACE from * include/linux/tracepoint.h using rcu_dereference_sched(). */ - tracepoint_update_call(tp, tp_funcs, false); - rcu_assign_pointer(tp->funcs, tp_funcs); - static_key_enable(&tp->key); + switch (nr_func_state(tp_funcs)) { + case TP_FUNC_1: /* 0->1 */ + /* Set static call to first function */ + tracepoint_update_call(tp, tp_funcs); + /* Both iterator and static call handle NULL tp->funcs */ + rcu_assign_pointer(tp->funcs, tp_funcs); + static_key_enable(&tp->key); + break; + case TP_FUNC_2: /* 1->2 */ + /* Set iterator static call */ + tracepoint_update_call(tp, tp_funcs); + /* + * Iterator callback installed before updating tp->funcs. + * Requires ordering between RCU assign/dereference and + * static call update/call. + */ + rcu_assign_pointer(tp->funcs, tp_funcs); + break; + case TP_FUNC_N: /* N->N+1 (N>1) */ + rcu_assign_pointer(tp->funcs, tp_funcs); + break; + default: + WARN_ON_ONCE(1); + break; + } release_probes(old); return 0; @@ -328,17 +360,47 @@ static int tracepoint_remove_func(struct tracepoint *tp, /* Failed allocating new tp_funcs, replaced func with stub */ return 0; - if (!tp_funcs) { + switch (nr_func_state(tp_funcs)) { + case TP_FUNC_0: /* 1->0 */ /* Removed last function */ if (tp->unregfunc && static_key_enabled(&tp->key)) tp->unregfunc(); static_key_disable(&tp->key); + /* Set iterator static call */ + tracepoint_update_call(tp, tp_funcs); + /* Both iterator and static call handle NULL tp->funcs */ + rcu_assign_pointer(tp->funcs, NULL); + /* + * Make sure new func never uses old data after a 1->0->1 + * transition sequence. + * Considering that transition 0->1 is the common case + * and don't have rcu-sync, issue rcu-sync after + * transition 1->0 to break that sequence by waiting for + * readers to be quiescent. + */ + tracepoint_synchronize_unregister(); + break; + case TP_FUNC_1: /* 2->1 */ rcu_assign_pointer(tp->funcs, tp_funcs); - } else { + /* + * On 2->1 transition, RCU sync is needed before setting + * static call to first callback, because the observer + * may have loaded any prior tp->funcs after the last one + * associated with an rcu-sync. + */ + tracepoint_synchronize_unregister(); + /* Set static call to first function */ + tracepoint_update_call(tp, tp_funcs); + break; + case TP_FUNC_2: /* N->N-1 (N>2) */ + fallthrough; + case TP_FUNC_N: rcu_assign_pointer(tp->funcs, tp_funcs); - tracepoint_update_call(tp, tp_funcs, - tp_funcs[0].data != old[0].data); + break; + default: + WARN_ON_ONCE(1); + break; } release_probes(old); return 0; From 23c0ebac20de19e3f54e5e81f4c3fa0caf2f8395 Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Thu, 29 Jul 2021 15:44:39 +0800 Subject: [PATCH 1265/1469] drm/amd/pm: update yellow carp pmfw interface version Correct yellow carp driver-PMFW interface version to v4. Signed-off-by: Xiaomeng Hou Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/smu_v13_0.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index 3fea2430dec0..dc91eb608791 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -26,7 +26,7 @@ #include "amdgpu_smu.h" #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x03 +#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04 #define SMU13_DRIVER_IF_VERSION_ALDE 0x07 /* MP Apertures */ From 5706cb3c910cc8283f344bc37a889a8d523a2c6d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 29 Jul 2021 20:03:47 -0700 Subject: [PATCH 1266/1469] drm/amdgpu: fix checking pmops when PM_SLEEP is not enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'pm_suspend_target_state' is only available when CONFIG_PM_SLEEP is set/enabled. OTOH, when both SUSPEND and HIBERNATION are not set, PM_SLEEP is not set, so this variable cannot be used. ../drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c: In function ‘amdgpu_acpi_is_s0ix_active’: ../drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:1046:11: error: ‘pm_suspend_target_state’ undeclared (first use in this function); did you mean ‘__KSYM_pm_suspend_target_state’? return pm_suspend_target_state == PM_SUSPEND_TO_IDLE; ^~~~~~~~~~~~~~~~~~~~~~~ __KSYM_pm_suspend_target_state Also use shorter IS_ENABLED(CONFIG_foo) notation for checking the 2 config symbols. Fixes: 91e273712ab8dd ("drm/amdgpu: Check pmops for desired suspend state") Signed-off-by: Randy Dunlap Cc: Alex Deucher Cc: Christian König Cc: "Pan, Xinhui" Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: linux-next@vger.kernel.org Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 6cc0d4fa4d0a..4137e848f6a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1040,7 +1040,7 @@ void amdgpu_acpi_detect(void) */ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { -#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE) +#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_PM_SLEEP) if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { if (adev->flags & AMD_IS_APU) return pm_suspend_target_state == PM_SUSPEND_TO_IDLE; From ffb9ee8eb272ba2b5a7325e69bb98118869637db Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Mon, 19 Jul 2021 13:13:33 -0400 Subject: [PATCH 1267/1469] drm/amd/display: Assume LTTPR interop for DCN31+ [WHY] For DCN31 onward, LTTPR is to be enabled and set to Transparent by VBIOS. Driver is to assume that VBIOS has done this without needing to check the VBIOS interop bit. [HOW] Add LTTPR enable and interop VBIOS bits into dc->caps, and force-set the interop bit to true for DCN31+. Reviewed-by: Jun Lei Acked-by: Aurabindo Pillai Signed-off-by: Wesley Chalmers Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/core/dc_link_dp.c | 21 ++----------------- drivers/gpu/drm/amd/display/dc/dc.h | 2 ++ .../drm/amd/display/dc/dcn30/dcn30_resource.c | 20 ++++++++++++++++++ .../drm/amd/display/dc/dcn31/dcn31_resource.c | 16 ++++++++++++++ 4 files changed, 40 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 9fb8c46dc606..a6d0fd24fd02 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -3602,29 +3602,12 @@ static bool dpcd_read_sink_ext_caps(struct dc_link *link) bool dp_retrieve_lttpr_cap(struct dc_link *link) { uint8_t lttpr_dpcd_data[6]; - bool vbios_lttpr_enable = false; - bool vbios_lttpr_interop = false; - struct dc_bios *bios = link->dc->ctx->dc_bios; + bool vbios_lttpr_enable = link->dc->caps.vbios_lttpr_enable; + bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware; enum dc_status status = DC_ERROR_UNEXPECTED; bool is_lttpr_present = false; memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data)); - /* Query BIOS to determine if LTTPR functionality is forced on by system */ - if (bios->funcs->get_lttpr_caps) { - enum bp_result bp_query_result; - uint8_t is_vbios_lttpr_enable = 0; - - bp_query_result = bios->funcs->get_lttpr_caps(bios, &is_vbios_lttpr_enable); - vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable; - } - - if (bios->funcs->get_lttpr_interop) { - enum bp_result bp_query_result; - uint8_t is_vbios_interop_enabled = 0; - - bp_query_result = bios->funcs->get_lttpr_interop(bios, &is_vbios_interop_enabled); - vbios_lttpr_interop = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled; - } /* * Logic to determine LTTPR mode diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 8dcea8ff5c5a..af7b60108e9d 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -183,6 +183,8 @@ struct dc_caps { unsigned int cursor_cache_size; struct dc_plane_cap planes[MAX_PLANES]; struct dc_color_caps color; + bool vbios_lttpr_aware; + bool vbios_lttpr_enable; }; struct dc_bug_wa { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 596c97dce67e..253654d605c2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -2617,6 +2617,26 @@ static bool dcn30_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + /* read VBIOS LTTPR caps */ + { + if (ctx->dc_bios->funcs->get_lttpr_caps) { + enum bp_result bp_query_result; + uint8_t is_vbios_lttpr_enable = 0; + + bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable); + dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable; + } + + if (ctx->dc_bios->funcs->get_lttpr_interop) { + enum bp_result bp_query_result; + uint8_t is_vbios_interop_enabled = 0; + + bp_query_result = ctx->dc_bios->funcs->get_lttpr_interop(ctx->dc_bios, + &is_vbios_interop_enabled); + dc->caps.vbios_lttpr_aware = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled; + } + } + if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV) dc->debug = debug_defaults_drv; else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 38c010afade1..cd3248dc31d8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -1968,6 +1968,22 @@ static bool dcn31_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + /* read VBIOS LTTPR caps */ + { + if (ctx->dc_bios->funcs->get_lttpr_caps) { + enum bp_result bp_query_result; + uint8_t is_vbios_lttpr_enable = 0; + + bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable); + dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable; + } + + /* interop bit is implicit */ + { + dc->caps.vbios_lttpr_aware = true; + } + } + if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV) dc->debug = debug_defaults_drv; else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) { From 06050a0f01dbac2ca33145ef19a72041206ea983 Mon Sep 17 00:00:00 2001 From: Bing Guo Date: Mon, 19 Jul 2021 18:24:06 -0400 Subject: [PATCH 1268/1469] drm/amd/display: Fix Dynamic bpp issue with 8K30 with Navi 1X Why: In DCN2x, HW doesn't automatically divide MASTER_UPDATE_LOCK_DB_X by the number of pipes ODM Combined. How: Set MASTER_UPDATE_LOCK_DB_X to the value that is adjusted by the number of pipes ODM Combined. Reviewed-by: Martin Leung Acked-by: Aurabindo Pillai Signed-off-by: Bing Guo Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 7fa9fc656b0c..f6e747f25ebe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -464,7 +464,7 @@ void optc2_lock_doublebuffer_enable(struct timing_generator *optc) REG_UPDATE_2(OTG_GLOBAL_CONTROL1, MASTER_UPDATE_LOCK_DB_X, - h_blank_start - 200 - 1, + (h_blank_start - 200 - 1) / optc1->opp_count, MASTER_UPDATE_LOCK_DB_Y, v_blank_start - 1); } From cd7b0531a61811429e7907c875e864ab918f3e62 Mon Sep 17 00:00:00 2001 From: Bing Guo Date: Tue, 20 Jul 2021 15:13:38 -0400 Subject: [PATCH 1269/1469] drm/amd/display: Increase stutter watermark for dcn303 [Why&How] Hardware team suggested to use SRExitTime= 35.5us as w/a to prevent underflow in certain modes. Reviewed-by: Martin Leung Acked-by: Aurabindo Pillai Signed-off-by: Bing Guo Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 833ab13fa834..dc7823d23ba8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -146,8 +146,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc = { .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ .num_states = 1, - .sr_exit_time_us = 26.5, - .sr_enter_plus_exit_time_us = 31, + .sr_exit_time_us = 35.5, + .sr_enter_plus_exit_time_us = 40, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, From d5c5ac3a7bca35261eb599204cbf1efee0af22cc Mon Sep 17 00:00:00 2001 From: Jude Shih Date: Tue, 6 Jul 2021 18:04:11 +0800 Subject: [PATCH 1270/1469] drm/amd/display: Fix resetting DCN3.1 HW when resuming from S4 [Why] On S4 resume we also need to fix detection of when to reload DMCUB firmware because we're currently using the VBIOS version which isn't compatible with the driver version. [How] Update the hardware init check for DCN31 since it's the ASIC that has this issue. Reviewed-by: Nicholas Kazlauskas Acked-by: Aurabindo Pillai Signed-off-by: Jude Shih Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index 973de346410d..27c7fa3110c8 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -267,11 +267,13 @@ void dmub_dcn31_set_outbox1_rptr(struct dmub_srv *dmub, uint32_t rptr_offset) bool dmub_dcn31_is_hw_init(struct dmub_srv *dmub) { - uint32_t is_hw_init; + union dmub_fw_boot_status status; + uint32_t is_enable; - REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_hw_init); + status.all = REG_READ(DMCUB_SCRATCH0); + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enable); - return is_hw_init != 0; + return is_enable != 0 && status.bits.dal_fw; } bool dmub_dcn31_is_supported(struct dmub_srv *dmub) From c4152b297d56d3696ad0a9003169bc5b98ad7b72 Mon Sep 17 00:00:00 2001 From: Qingqing Zhuo Date: Thu, 22 Jul 2021 14:48:54 -0400 Subject: [PATCH 1271/1469] drm/amd/display: workaround for hard hang on HPD on native DP [Why] HPD disable and enable sequences are not mutually exclusive on Linux. For HPDs that spans over 1s (i.e. HPD low = 1s), part of the disable sequence (specifically, a request to SMU to lower refclk) could come right before the call to PHY enable, causing DMUB to access an unresponsive PHY and thus a hard hang on the system. [How] Disable 48mhz refclk off on native DP. Reviewed-by: Hersen Wu Acked-by: Aurabindo Pillai Signed-off-by: Qingqing Zhuo Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index c6f494f0dcea..6185f9475fa2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -66,9 +66,11 @@ int rn_get_active_display_cnt_wa( for (i = 0; i < context->stream_count; i++) { const struct dc_stream_state *stream = context->streams[i]; + /* Extend the WA to DP for Linux*/ if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A || stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK || - stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK) + stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT) tmds_present = true; } From 0e99e960ce6d5ff586fc0733bc393c087f52c27b Mon Sep 17 00:00:00 2001 From: Shirish S Date: Tue, 3 Aug 2021 14:03:44 +0530 Subject: [PATCH 1272/1469] drm/amdgpu/display: fix DMUB firmware version info DMUB firmware info is printed before it gets initialized. Correct this order to ensure true value is conveyed. Signed-off-by: Shirish S Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b53f49a23ddc..c0ae73b0691c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1548,6 +1548,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) } hdr = (const struct dmcub_firmware_header_v1_0 *)adev->dm.dmub_fw->data; + adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version); if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].ucode_id = @@ -1561,7 +1562,6 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) adev->dm.dmcub_fw_version); } - adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version); adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL); dmub_srv = adev->dm.dmub_srv; From e00f543d3596c71201438d967877138ab33bb3de Mon Sep 17 00:00:00 2001 From: Chengming Gui Date: Wed, 24 Feb 2021 11:48:23 +0800 Subject: [PATCH 1273/1469] drm/amdgpu: add DID for beige goby Add device ids. Signed-off-by: Chengming Gui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 361b86b71b56..5ed8381ae0f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1213,6 +1213,13 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x740F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT}, {0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT}, + /* BEIGE_GOBY */ + {0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY}, + {0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY}, + {0x1002, 0x7422, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY}, + {0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY}, + {0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY}, + {0, 0, 0} }; From 2638a32348bbb1c384dbbd515fd2b12c155f0188 Mon Sep 17 00:00:00 2001 From: Dakshaja Uppalapati Date: Thu, 5 Aug 2021 18:13:32 +0530 Subject: [PATCH 1274/1469] RDMA/iw_cxgb4: Fix refcount underflow while destroying cqs. Previous atomic increment/decrement logic expects the atomic count to be '0' after the final decrement. Replacing atomic count with refcount does not allow that, as refcount_dec() considers count of 1 as underflow and triggers a kernel splat. Fix the current refcount logic by using the usual pattern of decrementing the refcount and test if it is '0' on the final deref in c4iw_destroy_cq(). Use wait_for_completion() instead of wait_event(). Fixes: 7183451f846d ("RDMA/cxgb4: Use refcount_t instead of atomic_t for reference counting") Link: https://lore.kernel.org/r/1628167412-12114-1-git-send-email-dakshaja@chelsio.com Signed-off-by: Dakshaja Uppalapati Reviewed-by: Potnuri Bharat Teja Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/cxgb4/cq.c | 12 +++++++++--- drivers/infiniband/hw/cxgb4/ev.c | 6 ++---- drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 3 ++- 3 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 6c8c910f4e86..c7e8d7b3baa1 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -967,6 +967,12 @@ int c4iw_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return !err || err == -ENODATA ? npolled : err; } +void c4iw_cq_rem_ref(struct c4iw_cq *chp) +{ + if (refcount_dec_and_test(&chp->refcnt)) + complete(&chp->cq_rel_comp); +} + int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) { struct c4iw_cq *chp; @@ -976,8 +982,8 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) chp = to_c4iw_cq(ib_cq); xa_erase_irq(&chp->rhp->cqs, chp->cq.cqid); - refcount_dec(&chp->refcnt); - wait_event(chp->wait, !refcount_read(&chp->refcnt)); + c4iw_cq_rem_ref(chp); + wait_for_completion(&chp->cq_rel_comp); ucontext = rdma_udata_to_drv_context(udata, struct c4iw_ucontext, ibucontext); @@ -1081,7 +1087,7 @@ int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, spin_lock_init(&chp->lock); spin_lock_init(&chp->comp_handler_lock); refcount_set(&chp->refcnt, 1); - init_waitqueue_head(&chp->wait); + init_completion(&chp->cq_rel_comp); ret = xa_insert_irq(&rhp->cqs, chp->cq.cqid, chp, GFP_KERNEL); if (ret) goto err_destroy_cq; diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c index 7798d090888b..34211a533d5c 100644 --- a/drivers/infiniband/hw/cxgb4/ev.c +++ b/drivers/infiniband/hw/cxgb4/ev.c @@ -213,8 +213,7 @@ void c4iw_ev_dispatch(struct c4iw_dev *dev, struct t4_cqe *err_cqe) break; } done: - if (refcount_dec_and_test(&chp->refcnt)) - wake_up(&chp->wait); + c4iw_cq_rem_ref(chp); c4iw_qp_rem_ref(&qhp->ibqp); out: return; @@ -234,8 +233,7 @@ int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid) spin_lock_irqsave(&chp->comp_handler_lock, flag); (*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context); spin_unlock_irqrestore(&chp->comp_handler_lock, flag); - if (refcount_dec_and_test(&chp->refcnt)) - wake_up(&chp->wait); + c4iw_cq_rem_ref(chp); } else { pr_debug("unknown cqid 0x%x\n", qid); xa_unlock_irqrestore(&dev->cqs, flag); diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 3883af3d2312..ac5f581aff4c 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -428,7 +428,7 @@ struct c4iw_cq { spinlock_t lock; spinlock_t comp_handler_lock; refcount_t refcnt; - wait_queue_head_t wait; + struct completion cq_rel_comp; struct c4iw_wr_wait *wr_waitp; }; @@ -979,6 +979,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc); int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata); int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata); +void c4iw_cq_rem_ref(struct c4iw_cq *chp); int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags); From aff51c5da3208bd164381e1488998667269c6cf4 Mon Sep 17 00:00:00 2001 From: DENG Qingfang Date: Fri, 6 Aug 2021 12:05:27 +0800 Subject: [PATCH 1275/1469] net: dsa: mt7530: add the missing RxUnicast MIB counter Add the missing RxUnicast counter. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: DENG Qingfang Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 69f21b71614c..632f0fcc5aa7 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -47,6 +47,7 @@ static const struct mt7530_mib_desc mt7530_mib[] = { MIB_DESC(2, 0x48, "TxBytes"), MIB_DESC(1, 0x60, "RxDrop"), MIB_DESC(1, 0x64, "RxFiltering"), + MIB_DESC(1, 0x68, "RxUnicast"), MIB_DESC(1, 0x6c, "RxMulticast"), MIB_DESC(1, 0x70, "RxBroadcast"), MIB_DESC(1, 0x74, "RxAlignErr"), From 704e624f7b3e8a4fc1ce43fb564746d1d07b20c0 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 5 Aug 2021 23:53:30 -0700 Subject: [PATCH 1276/1469] net: mvvp2: fix short frame size on s390 On s390, the following build warning occurs: drivers/net/ethernet/marvell/mvpp2/mvpp2.h:844:2: warning: overflow in conversion from 'long unsigned int' to 'int' changes value from '18446744073709551584' to '-32' [-Woverflow] 844 | ((total_size) - MVPP2_SKB_HEADROOM - MVPP2_SKB_SHINFO_SIZE) This happens because MVPP2_SKB_SHINFO_SIZE, which is 320 bytes (which is already 64-byte aligned) on some architectures, actually gets ALIGN'd up to 512 bytes in the s390 case. So then, when this is invoked: MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_SHORT_FRAME_SIZE) ...that turns into: 704 - 224 - 512 == -32 ...which is not a good frame size to end up with! The warning above is a bit lucky: it notices a signed/unsigned bad behavior here, which leads to the real problem of a frame that is too short for its contents. Increase MVPP2_BM_SHORT_FRAME_SIZE by 32 (from 704 to 736), which is just exactly big enough. (The other values can't readily be changed without causing a lot of other problems.) Fixes: 07dd0a7aae7f ("mvpp2: add basic XDP support") Cc: Sven Auhagen Cc: Matteo Croce Cc: David S. Miller Signed-off-by: John Hubbard Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index b9fbc9f000f2..cf8acabb90ac 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -938,7 +938,7 @@ enum mvpp22_ptp_packet_format { #define MVPP2_BM_COOKIE_POOL_OFFS 8 #define MVPP2_BM_COOKIE_CPU_OFFS 24 -#define MVPP2_BM_SHORT_FRAME_SIZE 704 /* frame size 128 */ +#define MVPP2_BM_SHORT_FRAME_SIZE 736 /* frame size 128 */ #define MVPP2_BM_LONG_FRAME_SIZE 2240 /* frame size 1664 */ #define MVPP2_BM_JUMBO_FRAME_SIZE 10432 /* frame size 9856 */ /* BM short pool packet size From 085fc31f81765e061c78cdcab0e5516fd672bff7 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 2 Aug 2021 16:10:00 +0200 Subject: [PATCH 1277/1469] platform/x86: Make dual_accel_detect() KIOX010A + KIOX020A detect more robust 360 degree hinges devices with dual KIOX010A + KIOX020A accelerometers always have both a KIOX010A and a KIOX020A ACPI device (one for each accel). Theoretical some vendor may re-use some DSDT for a non-convertible stripping out just the KIOX020A ACPI device from the DSDT. Check that both ACPI devices are present to make the check more robust. Fixes: 153cca9caa81 ("platform/x86: Add and use a dual_accel_detect() helper") Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210802141000.978035-1-hdegoede@redhat.com --- drivers/platform/x86/dual_accel_detect.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/dual_accel_detect.h b/drivers/platform/x86/dual_accel_detect.h index 1a069159da91..a9eae17cc43d 100644 --- a/drivers/platform/x86/dual_accel_detect.h +++ b/drivers/platform/x86/dual_accel_detect.h @@ -60,7 +60,8 @@ static bool dual_accel_detect_bosc0200(void) static bool dual_accel_detect(void) { /* Systems which use a pair of accels with KIOX010A / KIOX020A ACPI ids */ - if (acpi_dev_present("KIOX010A", NULL, -1)) + if (acpi_dev_present("KIOX010A", NULL, -1) && + acpi_dev_present("KIOX020A", NULL, -1)) return true; /* Systems which use a single DUAL250E ACPI device to model 2 accels */ From 9d7b132e62e41b7d49bf157aeaf9147c27492e0f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 6 Aug 2021 13:55:15 +0200 Subject: [PATCH 1278/1469] platform/x86: pcengines-apuv2: Add missing terminating entries to gpio-lookup tables The gpiod_lookup_table.table passed to gpiod_add_lookup_table() must be terminated with an empty entry, add this. Note we have likely been getting away with this not being present because the GPIO lookup code first matches on the dev_id, causing most lookups to skip checking the table and the lookups which do check the table will find a matching entry before reaching the end. With that said, terminating these tables properly still is obviously the correct thing to do. Fixes: f8eb0235f659 ("x86: pcengines apuv2 gpio/leds/keys platform driver") Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210806115515.12184-1-hdegoede@redhat.com --- drivers/platform/x86/pcengines-apuv2.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index c37349f97bb8..d063d91db9bc 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -94,6 +94,7 @@ static struct gpiod_lookup_table gpios_led_table = { NULL, 1, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_LED3, NULL, 2, GPIO_ACTIVE_LOW), + {} /* Terminating entry */ } }; @@ -123,6 +124,7 @@ static struct gpiod_lookup_table gpios_key_table = { .table = { GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_MODESW, NULL, 0, GPIO_ACTIVE_LOW), + {} /* Terminating entry */ } }; From acade6379930dfa7987f4bd9b26d1a701cc1b542 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 3 Aug 2021 06:25:28 -0700 Subject: [PATCH 1279/1469] perf/x86/intel: Apply mid ACK for small core A warning as below may be occasionally triggered in an ADL machine when these conditions occur: - Two perf record commands run one by one. Both record a PEBS event. - Both runs on small cores. - They have different adaptive PEBS configuration (PEBS_DATA_CFG). [ ] WARNING: CPU: 4 PID: 9874 at arch/x86/events/intel/ds.c:1743 setup_pebs_adaptive_sample_data+0x55e/0x5b0 [ ] RIP: 0010:setup_pebs_adaptive_sample_data+0x55e/0x5b0 [ ] Call Trace: [ ] [ ] intel_pmu_drain_pebs_icl+0x48b/0x810 [ ] perf_event_nmi_handler+0x41/0x80 [ ] [ ] __perf_event_task_sched_in+0x2c2/0x3a0 Different from the big core, the small core requires the ACK right before re-enabling counters in the NMI handler, otherwise a stale PEBS record may be dumped into the later NMI handler, which trigger the warning. Add a new mid_ack flag to track the case. Add all PMI handler bits in the struct x86_hybrid_pmu to track the bits for different types of PMUs. Apply mid ACK for the small cores on an Alder Lake machine. The existing hybrid() macro has a compile error when taking address of a bit-field variable. Add a new macro hybrid_bit() to get the bit-field value of a given PMU. Fixes: f83d2f91d259 ("perf/x86/intel: Add Alder Lake Hybrid support") Reported-by: Ammy Yi Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andi Kleen Tested-by: Ammy Yi Link: https://lkml.kernel.org/r/1627997128-57891-1-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 23 +++++++++++++++-------- arch/x86/events/perf_event.h | 15 +++++++++++++++ 2 files changed, 30 insertions(+), 8 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fca7a6e2242f..ac6fd2dabf6a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2904,24 +2904,28 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ static int intel_pmu_handle_irq(struct pt_regs *regs) { - struct cpu_hw_events *cpuc; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + bool late_ack = hybrid_bit(cpuc->pmu, late_ack); + bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack); int loops; u64 status; int handled; int pmu_enabled; - cpuc = this_cpu_ptr(&cpu_hw_events); - /* * Save the PMU state. * It needs to be restored when leaving the handler. */ pmu_enabled = cpuc->enabled; /* - * No known reason to not always do late ACK, - * but just in case do it opt-in. + * In general, the early ACK is only applied for old platforms. + * For the big core starts from Haswell, the late ACK should be + * applied. + * For the small core after Tremont, we have to do the ACK right + * before re-enabling counters, which is in the middle of the + * NMI handler. */ - if (!x86_pmu.late_ack) + if (!late_ack && !mid_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); cpuc->enabled = 0; @@ -2958,6 +2962,8 @@ again: goto again; done: + if (mid_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); /* Only restore PMU state when it's active. See x86_pmu_disable(). */ cpuc->enabled = pmu_enabled; if (pmu_enabled) @@ -2969,7 +2975,7 @@ done: * have been reset. This avoids spurious NMIs on * Haswell CPUs. */ - if (x86_pmu.late_ack) + if (late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); return handled; } @@ -6129,7 +6135,6 @@ __init int intel_pmu_init(void) static_branch_enable(&perf_is_hybrid); x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS; - x86_pmu.late_ack = true; x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; @@ -6167,6 +6172,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX]; pmu->name = "cpu_core"; pmu->cpu_type = hybrid_big; + pmu->late_ack = true; if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) { pmu->num_counters = x86_pmu.num_counters + 2; pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1; @@ -6192,6 +6198,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; pmu->name = "cpu_atom"; pmu->cpu_type = hybrid_small; + pmu->mid_ack = true; pmu->num_counters = x86_pmu.num_counters; pmu->num_counters_fixed = x86_pmu.num_counters_fixed; pmu->max_pebs_events = x86_pmu.max_pebs_events; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2938c902ffbe..e3ac05c97b5e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -656,6 +656,10 @@ struct x86_hybrid_pmu { struct event_constraint *event_constraints; struct event_constraint *pebs_constraints; struct extra_reg *extra_regs; + + unsigned int late_ack :1, + mid_ack :1, + enabled_ack :1; }; static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu) @@ -686,6 +690,16 @@ extern struct static_key_false perf_is_hybrid; __Fp; \ })) +#define hybrid_bit(_pmu, _field) \ +({ \ + bool __Fp = x86_pmu._field; \ + \ + if (is_hybrid() && (_pmu)) \ + __Fp = hybrid_pmu(_pmu)->_field; \ + \ + __Fp; \ +}) + enum hybrid_pmu_type { hybrid_big = 0x40, hybrid_small = 0x20, @@ -755,6 +769,7 @@ struct x86_pmu { /* PMI handler bits */ unsigned int late_ack :1, + mid_ack :1, enabled_ack :1; /* * sysfs attrs From 3d4e4face9c1548752a2891e98b38b100feee336 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Thu, 5 Aug 2021 18:05:37 +0800 Subject: [PATCH 1280/1469] io-wq: fix no lock protection of acct->nr_worker There is an acct->nr_worker visit without lock protection. Think about the case: two callers call io_wqe_wake_worker(), one is the original context and the other one is an io-worker(by calling io_wqe_enqueue(wqe, linked)), on two cpus paralelly, this may cause nr_worker to be larger than max_worker. Let's fix it by adding lock for it, and let's do nr_workers++ before create_io_worker. There may be a edge cause that the first caller fails to create an io-worker, but the second caller doesn't know it and then quit creating io-worker as well: say nr_worker = max_worker - 1 cpu 0 cpu 1 io_wqe_wake_worker() io_wqe_wake_worker() nr_worker < max_worker nr_worker++ create_io_worker() nr_worker == max_worker failed return return But the chance of this case is very slim. Fixes: 685fe7feedb9 ("io-wq: eliminate the need for a manager thread") Signed-off-by: Hao Xu [axboe: fix unconditional create_io_worker() call] Signed-off-by: Jens Axboe --- fs/io-wq.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 50dc93ffc153..64d904ce4f2d 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -247,10 +247,19 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) ret = io_wqe_activate_free_worker(wqe); rcu_read_unlock(); - if (!ret && acct->nr_workers < acct->max_workers) { - atomic_inc(&acct->nr_running); - atomic_inc(&wqe->wq->worker_refs); - create_io_worker(wqe->wq, wqe, acct->index); + if (!ret) { + bool do_create = false; + + raw_spin_lock_irq(&wqe->lock); + if (acct->nr_workers < acct->max_workers) { + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + acct->nr_workers++; + do_create = true; + } + raw_spin_unlock_irq(&wqe->lock); + if (do_create) + create_io_worker(wqe->wq, wqe, acct->index); } } @@ -635,6 +644,9 @@ static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) kfree(worker); fail: atomic_dec(&acct->nr_running); + raw_spin_lock_irq(&wqe->lock); + acct->nr_workers--; + raw_spin_unlock_irq(&wqe->lock); io_worker_ref_put(wq); return; } @@ -650,9 +662,8 @@ fail: worker->flags |= IO_WORKER_F_FREE; if (index == IO_WQ_ACCT_BOUND) worker->flags |= IO_WORKER_F_BOUND; - if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) + if ((acct->nr_workers == 1) && (worker->flags & IO_WORKER_F_BOUND)) worker->flags |= IO_WORKER_F_FIXED; - acct->nr_workers++; raw_spin_unlock_irq(&wqe->lock); wake_up_new_task(tsk); } From 21698274da5b6fc724b005bc7ec3e6b9fbcfaa06 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Thu, 5 Aug 2021 18:05:38 +0800 Subject: [PATCH 1281/1469] io-wq: fix lack of acct->nr_workers < acct->max_workers judgement There should be this judgement before we create an io-worker Fixes: 685fe7feedb9 ("io-wq: eliminate the need for a manager thread") Signed-off-by: Hao Xu Signed-off-by: Jens Axboe --- fs/io-wq.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 64d904ce4f2d..12fc19353bb0 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -280,9 +280,17 @@ static void create_worker_cb(struct callback_head *cb) { struct create_worker_data *cwd; struct io_wq *wq; + struct io_wqe *wqe; + struct io_wqe_acct *acct; cwd = container_of(cb, struct create_worker_data, work); - wq = cwd->wqe->wq; + wqe = cwd->wqe; + wq = wqe->wq; + acct = &wqe->acct[cwd->index]; + raw_spin_lock_irq(&wqe->lock); + if (acct->nr_workers < acct->max_workers) + acct->nr_workers++; + raw_spin_unlock_irq(&wqe->lock); create_io_worker(wq, cwd->wqe, cwd->index); kfree(cwd); } From 7b40066c97ec66a44e388f82fcf694987451768f Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 5 Aug 2021 15:29:54 -0400 Subject: [PATCH 1282/1469] tracepoint: Use rcu get state and cond sync for static call updates State transitions from 1->0->1 and N->2->1 callbacks require RCU synchronization. Rather than performing the RCU synchronization every time the state change occurs, which is quite slow when many tracepoints are registered in batch, instead keep a snapshot of the RCU state on the most recent transitions which belong to a chain, and conditionally wait for a grace period on the last transition of the chain if one g.p. has not elapsed since the last snapshot. This applies to both RCU and SRCU. This brings the performance regression caused by commit 231264d6927f ("Fix: tracepoint: static call function vs data state mismatch") back to what it was originally. Before this commit: # trace-cmd start -e all # time trace-cmd start -p nop real 0m10.593s user 0m0.017s sys 0m0.259s After this commit: # trace-cmd start -e all # time trace-cmd start -p nop real 0m0.878s user 0m0.000s sys 0m0.103s Link: https://lkml.kernel.org/r/20210805192954.30688-1-mathieu.desnoyers@efficios.com Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/ Cc: stable@vger.kernel.org Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrew Morton Cc: "Paul E. McKenney" Cc: Stefan Metzmacher Fixes: 231264d6927f ("Fix: tracepoint: static call function vs data state mismatch") Signed-off-by: Mathieu Desnoyers Reviewed-by: Paul E. McKenney Signed-off-by: Steven Rostedt (VMware) --- kernel/tracepoint.c | 81 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 67 insertions(+), 14 deletions(-) diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 8d772bd6894d..efd14c79fab4 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -28,6 +28,44 @@ extern tracepoint_ptr_t __stop___tracepoints_ptrs[]; DEFINE_SRCU(tracepoint_srcu); EXPORT_SYMBOL_GPL(tracepoint_srcu); +enum tp_transition_sync { + TP_TRANSITION_SYNC_1_0_1, + TP_TRANSITION_SYNC_N_2_1, + + _NR_TP_TRANSITION_SYNC, +}; + +struct tp_transition_snapshot { + unsigned long rcu; + unsigned long srcu; + bool ongoing; +}; + +/* Protected by tracepoints_mutex */ +static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC]; + +static void tp_rcu_get_state(enum tp_transition_sync sync) +{ + struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; + + /* Keep the latest get_state snapshot. */ + snapshot->rcu = get_state_synchronize_rcu(); + snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu); + snapshot->ongoing = true; +} + +static void tp_rcu_cond_sync(enum tp_transition_sync sync) +{ + struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; + + if (!snapshot->ongoing) + return; + cond_synchronize_rcu(snapshot->rcu); + if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu)) + synchronize_srcu(&tracepoint_srcu); + snapshot->ongoing = false; +} + /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; @@ -311,6 +349,11 @@ static int tracepoint_add_func(struct tracepoint *tp, */ switch (nr_func_state(tp_funcs)) { case TP_FUNC_1: /* 0->1 */ + /* + * Make sure new static func never uses old data after a + * 1->0->1 transition sequence. + */ + tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); /* Both iterator and static call handle NULL tp->funcs */ @@ -325,10 +368,15 @@ static int tracepoint_add_func(struct tracepoint *tp, * Requires ordering between RCU assign/dereference and * static call update/call. */ - rcu_assign_pointer(tp->funcs, tp_funcs); - break; + fallthrough; case TP_FUNC_N: /* N->N+1 (N>1) */ rcu_assign_pointer(tp->funcs, tp_funcs); + /* + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>1) transition sequence. + */ + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1); @@ -372,24 +420,23 @@ static int tracepoint_remove_func(struct tracepoint *tp, /* Both iterator and static call handle NULL tp->funcs */ rcu_assign_pointer(tp->funcs, NULL); /* - * Make sure new func never uses old data after a 1->0->1 - * transition sequence. - * Considering that transition 0->1 is the common case - * and don't have rcu-sync, issue rcu-sync after - * transition 1->0 to break that sequence by waiting for - * readers to be quiescent. + * Make sure new static func never uses old data after a + * 1->0->1 transition sequence. */ - tracepoint_synchronize_unregister(); + tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1); break; case TP_FUNC_1: /* 2->1 */ rcu_assign_pointer(tp->funcs, tp_funcs); /* - * On 2->1 transition, RCU sync is needed before setting - * static call to first callback, because the observer - * may have loaded any prior tp->funcs after the last one - * associated with an rcu-sync. + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>2) transition sequence. If the first + * element's data has changed, then force the synchronization + * to prevent current readers that have loaded the old data + * from calling the new function. */ - tracepoint_synchronize_unregister(); + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); + tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); break; @@ -397,6 +444,12 @@ static int tracepoint_remove_func(struct tracepoint *tp, fallthrough; case TP_FUNC_N: rcu_assign_pointer(tp->funcs, tp_funcs); + /* + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>2) transition sequence. + */ + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1); From 4608fdfc07e116f9fc0895beb40abad7cdb5ee3d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 27 Jul 2021 00:29:19 +0200 Subject: [PATCH 1283/1469] netfilter: conntrack: collect all entries in one cycle Michal Kubecek reports that conntrack gc is responsible for frequent wakeups (every 125ms) on idle systems. On busy systems, timed out entries are evicted during lookup. The gc worker is only needed to remove entries after system becomes idle after a busy period. To resolve this, always scan the entire table. If the scan is taking too long, reschedule so other work_structs can run and resume from next bucket. After a completed scan, wait for 2 minutes before the next cycle. Heuristics for faster re-schedule are removed. GC_SCAN_INTERVAL could be exposed as a sysctl in the future to allow tuning this as-needed or even turn the gc worker off. Reported-by: Michal Kubecek Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 71 ++++++++++--------------------- 1 file changed, 22 insertions(+), 49 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5c03e5106751..d31dbccbe7bd 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,22 +66,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash); struct conntrack_gc_work { struct delayed_work dwork; - u32 last_bucket; + u32 next_bucket; bool exiting; bool early_drop; - long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; -/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 128u -/* upper bound of full table scan */ -#define GC_MAX_SCAN_JIFFIES (16u * HZ) -/* desired ratio of entries found to be expired */ -#define GC_EVICT_RATIO 50u +#define GC_SCAN_INTERVAL (120u * HZ) +#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) static struct conntrack_gc_work conntrack_gc_work; @@ -1363,17 +1358,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) static void gc_worker(struct work_struct *work) { - unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); - unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned int nf_conntrack_max95 = 0; + unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION; + unsigned int i, hashsz, nf_conntrack_max95 = 0; + unsigned long next_run = GC_SCAN_INTERVAL; struct conntrack_gc_work *gc_work; - unsigned int ratio, scanned = 0; - unsigned long next_run; - gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; - i = gc_work->last_bucket; + i = gc_work->next_bucket; if (gc_work->early_drop) nf_conntrack_max95 = nf_conntrack_max / 100u * 95u; @@ -1381,15 +1372,15 @@ static void gc_worker(struct work_struct *work) struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int hashsz; struct nf_conn *tmp; - i++; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hashsz); - if (i >= hashsz) - i = 0; + if (i >= hashsz) { + rcu_read_unlock(); + break; + } hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { struct nf_conntrack_net *cnet; @@ -1397,7 +1388,6 @@ static void gc_worker(struct work_struct *work) tmp = nf_ct_tuplehash_to_ctrack(h); - scanned++; if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); continue; @@ -1405,7 +1395,6 @@ static void gc_worker(struct work_struct *work) if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); - expired_count++; continue; } @@ -1438,7 +1427,14 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched(); - } while (++buckets < goal); + i++; + + if (time_after(jiffies, end_time) && i < hashsz) { + gc_work->next_bucket = i; + next_run = 0; + break; + } + } while (i < hashsz); if (gc_work->exiting) return; @@ -1449,40 +1445,17 @@ static void gc_worker(struct work_struct *work) * * This worker is only here to reap expired entries when system went * idle after a busy period. - * - * The heuristics below are supposed to balance conflicting goals: - * - * 1. Minimize time until we notice a stale entry - * 2. Maximize scan intervals to not waste cycles - * - * Normally, expire ratio will be close to 0. - * - * As soon as a sizeable fraction of the entries have expired - * increase scan frequency. */ - ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio > GC_EVICT_RATIO) { - gc_work->next_gc_run = min_interval; - } else { - unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - - BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); - - gc_work->next_gc_run += min_interval; - if (gc_work->next_gc_run > max) - gc_work->next_gc_run = max; + if (next_run) { + gc_work->early_drop = false; + gc_work->next_bucket = 0; } - - next_run = gc_work->next_gc_run; - gc_work->last_bucket = i; - gc_work->early_drop = false; queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = HZ; gc_work->exiting = false; } From 61e0c2bc555a194ada2632fadac73f2bdb5df9cb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Aug 2021 00:15:53 +0200 Subject: [PATCH 1284/1469] netfilter: nfnetlink_hook: strip off module name from hookfn NFNLA_HOOK_FUNCTION_NAME should include the hook function name only, the module name is already provided by NFNLA_HOOK_MODULE_NAME. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_hook.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 202f57d17bab..ca453c61dbdf 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -135,6 +135,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, if (module_name) { char *end; + *module_name = '\0'; module_name += 2; end = strchr(module_name, ']'); if (end) { From a6e57c4af12bbacf927d7321c3aa894948653688 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Aug 2021 00:15:54 +0200 Subject: [PATCH 1285/1469] netfilter: nfnetlink_hook: missing chain family The family is relevant for pseudo-families like NFPROTO_INET otherwise the user needs to rely on the hook function name to differentiate it from NFPROTO_IPV4 and NFPROTO_IPV6 names. Add nfnl_hook_chain_desc_attributes instead of using the existing NFTA_CHAIN_* attributes, since these do not provide a family number. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_hook.h | 9 +++++++++ net/netfilter/nfnetlink_hook.c | 8 ++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h index 912ec60b26b0..bbcd285b22e1 100644 --- a/include/uapi/linux/netfilter/nfnetlink_hook.h +++ b/include/uapi/linux/netfilter/nfnetlink_hook.h @@ -43,6 +43,15 @@ enum nfnl_hook_chain_info_attributes { }; #define NFNLA_HOOK_INFO_MAX (__NFNLA_HOOK_INFO_MAX - 1) +enum nfnl_hook_chain_desc_attributes { + NFNLA_CHAIN_UNSPEC, + NFNLA_CHAIN_TABLE, + NFNLA_CHAIN_FAMILY, + NFNLA_CHAIN_NAME, + __NFNLA_CHAIN_MAX, +}; +#define NFNLA_CHAIN_MAX (__NFNLA_CHAIN_MAX - 1) + /** * enum nfnl_hook_chaintype - chain type * diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index ca453c61dbdf..e0ff2973fd14 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -89,11 +89,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, if (!nest2) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name); if (ret) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family); if (ret) goto cancel_nest; From 3d9bbaf6c5416bfc50f014ce5879c8c440aaa511 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 4 Aug 2021 01:27:19 +0200 Subject: [PATCH 1286/1469] netfilter: nfnetlink_hook: use the sequence number of the request message The sequence number allows to correlate the netlink reply message (as part of the dump) with the original request message. The cb->seq field is internally used to detect an interference (update) of the hook list during the netlink dump, do not use it as sequence number in the netlink dump header. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_hook.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index e0ff2973fd14..7b0d4a317457 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -264,7 +264,8 @@ static int nfnl_hook_dump(struct sk_buff *nlskb, ops = nf_hook_entries_get_hook_ops(e); for (; i < e->num_hook_entries; i++) { - err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], + cb->nlh->nlmsg_seq); if (err) break; } From 69311e7c997451dd40942b6b27b522cc3b659cef Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 4 Aug 2021 01:27:20 +0200 Subject: [PATCH 1287/1469] netfilter: nfnetlink_hook: Use same family as request message Use the same family as the request message, for consistency. The netlink payload provides sufficient information to describe the hook object, including the family. This makes it easier to userspace to correlate the hooks are that visited by the packets for a certain family. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_hook.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 7b0d4a317457..32eea785ae25 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -113,7 +113,7 @@ cancel_nest: static int nfnl_hook_dump_one(struct sk_buff *nlskb, const struct nfnl_dump_hook_data *ctx, const struct nf_hook_ops *ops, - unsigned int seq) + int family, unsigned int seq) { u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); unsigned int portid = NETLINK_CB(nlskb).portid; @@ -124,7 +124,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, char *module_name; #endif nlh = nfnl_msg_put(nlskb, portid, seq, event, - NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + NLM_F_MULTI, family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; @@ -264,7 +264,7 @@ static int nfnl_hook_dump(struct sk_buff *nlskb, ops = nf_hook_entries_get_hook_ops(e); for (; i < e->num_hook_entries; i++) { - err = nfnl_hook_dump_one(nlskb, ctx, ops[i], + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], family, cb->nlh->nlmsg_seq); if (err) break; From 4592ee7f525c4683ec9e290381601fdee50ae110 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Aug 2021 15:02:15 +0200 Subject: [PATCH 1288/1469] netfilter: conntrack: remove offload_pickup sysctl again These two sysctls were added because the hardcoded defaults (2 minutes, tcp, 30 seconds, udp) turned out to be too low for some setups. They appeared in 5.14-rc1 so it should be fine to remove it again. Marcelo convinced me that there should be no difference between a flow that was offloaded vs. a flow that was not wrt. timeout handling. Thus the default is changed to those for TCP established and UDP stream, 5 days and 120 seconds, respectively. Marcelo also suggested to account for the timeout value used for the offloading, this avoids increase beyond the value in the conntrack-sysctl and will also instantly expire the conntrack entry with altered sysctls. Example: nf_conntrack_udp_timeout_stream=60 nf_flowtable_udp_timeout=60 This will remove offloaded udp flows after one minute, rather than two. An earlier version of this patch also cleared the ASSURED bit to allow nf_conntrack to evict the entry via early_drop (i.e., table full). However, it looks like we can safely assume that connection timed out via HW is still in established state, so this isn't needed. Quoting Oz: [..] the hardware sends all packets with a set FIN flags to sw. [..] Connections that are aged in hardware are expected to be in the established state. In case it turns out that back-to-sw-path transition can occur for 'dodgy' connections too (e.g., one side disappeared while software-path would have been in RETRANS timeout), we can adjust this later. Cc: Oz Shlomo Cc: Paul Blakey Suggested-by: Marcelo Ricardo Leitner Signed-off-by: Florian Westphal Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Oz Shlomo Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.rst | 10 ---------- include/net/netns/conntrack.h | 2 -- net/netfilter/nf_conntrack_proto_tcp.c | 1 - net/netfilter/nf_conntrack_proto_udp.c | 1 - net/netfilter/nf_conntrack_standalone.c | 16 ---------------- net/netfilter/nf_flow_table_core.c | 11 ++++++++--- 6 files changed, 8 insertions(+), 33 deletions(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index d31ed6c1cb0d..024d784157c8 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -191,19 +191,9 @@ nf_flowtable_tcp_timeout - INTEGER (seconds) TCP connections may be offloaded from nf conntrack to nf flow table. Once aged, the connection is returned to nf conntrack with tcp pickup timeout. -nf_flowtable_tcp_pickup - INTEGER (seconds) - default 120 - - TCP connection timeout after being aged from nf flow table offload. - nf_flowtable_udp_timeout - INTEGER (seconds) default 30 Control offload timeout for udp connections. UDP connections may be offloaded from nf conntrack to nf flow table. Once aged, the connection is returned to nf conntrack with udp pickup timeout. - -nf_flowtable_udp_pickup - INTEGER (seconds) - default 30 - - UDP connection timeout after being aged from nf flow table offload. diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 37e5300c7e5a..fefd38db95b3 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -30,7 +30,6 @@ struct nf_tcp_net { u8 tcp_ignore_invalid_rst; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; - unsigned int offload_pickup; #endif }; @@ -44,7 +43,6 @@ struct nf_udp_net { unsigned int timeouts[UDP_CT_MAX]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; - unsigned int offload_pickup; #endif }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3259416f2ea4..af5115e127cf 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1478,7 +1478,6 @@ void nf_conntrack_tcp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; - tn->offload_pickup = 120 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 698fee49e732..f8e3c0d2602f 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -271,7 +271,6 @@ void nf_conntrack_udp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) un->offload_timeout = 30 * HZ; - un->offload_pickup = 30 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 214d9f9e499b..e84b499b7bfa 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -575,7 +575,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, @@ -585,7 +584,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, @@ -776,12 +774,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_tcp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", @@ -832,12 +824,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_udp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", @@ -1018,7 +1004,6 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; #endif } @@ -1111,7 +1096,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 551976e4284c..8788b519255e 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -183,7 +183,7 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) const struct nf_conntrack_l4proto *l4proto; struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); - unsigned int timeout; + s32 timeout; l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) @@ -192,15 +192,20 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[UDP_CT_REPLIED]; + timeout -= tn->offload_timeout; } else { return; } + if (timeout < 0) + timeout = 0; + if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; } From 269fc69533de73a9065c0b7971bcd109880290b3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 6 Aug 2021 12:33:57 +0200 Subject: [PATCH 1289/1469] netfilter: nfnetlink_hook: translate inet ingress to netdev The NFPROTO_INET pseudofamily is not exposed through this new netlink interface. The netlink dump either shows NFPROTO_IPV4 or NFPROTO_IPV6 for NFPROTO_INET prerouting/input/forward/output/postrouting hooks. The NFNLA_CHAIN_FAMILY attribute provides the family chain, which specifies if this hook applies to inet traffic only (either IPv4 or IPv6). Translate the inet/ingress hook to netdev/ingress to fully hide the NFPROTO_INET implementation details. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_hook.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 32eea785ae25..f554e2ea32ee 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -119,6 +119,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, unsigned int portid = NETLINK_CB(nlskb).portid; struct nlmsghdr *nlh; int ret = -EMSGSIZE; + u32 hooknum; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; char *module_name; @@ -156,7 +157,12 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, goto nla_put_failure; #endif - ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ops->pf == NFPROTO_INET && ops->hooknum == NF_INET_INGRESS) + hooknum = NF_NETDEV_INGRESS; + else + hooknum = ops->hooknum; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(hooknum)); if (ret) goto nla_put_failure; From ad89c9aa24603a6a26464316fab94d285792c942 Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Mon, 2 Aug 2021 16:25:25 +0800 Subject: [PATCH 1290/1469] drm/amd/pm: update smu v13.0.1 firmware header Update smu v13.0.1 firmware header for yellow carp. Signed-off-by: Xiaomeng Hou Reviewed-by: Aaron Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h index 5627de734246..c5e26d619bf0 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h @@ -111,7 +111,9 @@ typedef struct { uint32_t InWhisperMode : 1; uint32_t spare0 : 1; uint32_t ZstateStatus : 4; - uint32_t spare1 :12; + uint32_t spare1 : 4; + uint32_t DstateFun : 4; + uint32_t DstateDev : 4; // MP1_EXT_SCRATCH2 uint32_t P2JobHandler :24; uint32_t RsmuPmiP2FinishedCnt : 8; From 39932ef75897bfcb8ba1120e7b09d615d74762fd Mon Sep 17 00:00:00 2001 From: John Clements Date: Wed, 4 Aug 2021 17:11:40 +0800 Subject: [PATCH 1291/1469] drm/amdgpu: set RAS EEPROM address from VBIOS update to latest atombios fw table [Backport to 5.14 - Alex] Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1670 Signed-off-by: John Clements Reviewed-by: Hawking Zhang . Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- .../gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c | 40 +++++++++++++++++++ .../gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h | 1 + .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 4 ++ drivers/gpu/drm/amd/include/atomfirmware.h | 2 +- 4 files changed, 46 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 3b5d13189073..8f53837d4d3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -468,6 +468,46 @@ bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *ade return (fw_cap & ATOM_FIRMWARE_CAP_DYNAMIC_BOOT_CFG_ENABLE) ? true : false; } +/* + * Helper function to query RAS EEPROM address + * + * @adev: amdgpu_device pointer + * + * Return true if vbios supports ras rom address reporting + */ +bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address) +{ + struct amdgpu_mode_info *mode_info = &adev->mode_info; + int index; + u16 data_offset, size; + union firmware_info *firmware_info; + u8 frev, crev; + + if (i2c_address == NULL) + return false; + + *i2c_address = 0; + + index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, + firmwareinfo); + + if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context, + index, &size, &frev, &crev, &data_offset)) { + /* support firmware_info 3.4 + */ + if ((frev == 3 && crev >=4) || (frev > 3)) { + firmware_info = (union firmware_info *) + (mode_info->atom_context->bios + data_offset); + *i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr; + } + } + + if (*i2c_address != 0) + return true; + + return false; +} + + union smu_info { struct atom_smu_info_v3_1 v31; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h index 1bbbb195015d..751248b253de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h @@ -36,6 +36,7 @@ int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev); int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev); bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev); bool amdgpu_atomfirmware_sram_ecc_supported(struct amdgpu_device *adev); +bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address); bool amdgpu_atomfirmware_mem_training_supported(struct amdgpu_device *adev); bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *adev); int amdgpu_atomfirmware_get_fw_reserved_fb_size(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index f40c871da0c6..38222de921d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -26,6 +26,7 @@ #include "amdgpu_ras.h" #include #include "atom.h" +#include "amdgpu_atomfirmware.h" #define EEPROM_I2C_TARGET_ADDR_VEGA20 0xA0 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS 0xA8 @@ -96,6 +97,9 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, if (!i2c_addr) return false; + if (amdgpu_atomfirmware_ras_rom_addr(adev, (uint8_t*)i2c_addr)) + return true; + switch (adev->asic_type) { case CHIP_VEGA20: *i2c_addr = EEPROM_I2C_TARGET_ADDR_VEGA20; diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 3811e58dd857..44955458fe38 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -590,7 +590,7 @@ struct atom_firmware_info_v3_4 { uint8_t board_i2c_feature_id; // enum of atom_board_i2c_feature_id_def uint8_t board_i2c_feature_gpio_id; // i2c id find in gpio_lut data table gpio_id uint8_t board_i2c_feature_slave_addr; - uint8_t reserved3; + uint8_t ras_rom_i2c_slave_addr; uint16_t bootup_mvddq_mv; uint16_t bootup_mvpp_mv; uint32_t zfbstartaddrin16mb; From 202ead5a3c589b0594a75cb99f080174f6851fed Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 2 Aug 2021 10:03:30 -0400 Subject: [PATCH 1292/1469] drm/amdgpu: don't enable baco on boco platforms in runpm If the platform uses BOCO, don't use BACO in runtime suspend. We could end up executing the BACO path if the platform supports both. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1669 Reviewed-by: Evan Quan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 5ed8381ae0f5..971c5b8e75dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1571,6 +1571,8 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) pci_ignore_hotplug(pdev); pci_set_power_state(pdev, PCI_D3cold); drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF; + } else if (amdgpu_device_supports_boco(drm_dev)) { + /* nothing to do */ } else if (amdgpu_device_supports_baco(drm_dev)) { amdgpu_device_baco_enter(drm_dev); } From 5126da7d99cf6396c929f3b577ba3aed1e74acd7 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 5 Aug 2021 20:37:14 +0200 Subject: [PATCH 1293/1469] drm/amd/pm: Fix a memory leak in an error handling path in 'vangogh_tables_init()' 'watermarks_table' must be freed instead 'clocks_table', because 'clocks_table' is known to be NULL at this point and 'watermarks_table' is never freed if the last kzalloc fails. Fixes: c98ee89736b8 ("drm/amd/pm: add the fine grain tuning function for vangogh") Signed-off-by: Christophe JAILLET Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 18681dc458da..bcaaa086fc2f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -256,7 +256,7 @@ static int vangogh_tables_init(struct smu_context *smu) return 0; err3_out: - kfree(smu_table->clocks_table); + kfree(smu_table->watermarks_table); err2_out: kfree(smu_table->gpu_metrics_table); err1_out: From 877ba3f729fd3d8ef0e29bc2a55e57cfa54b2e43 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 4 Aug 2021 14:23:55 -0400 Subject: [PATCH 1294/1469] ext4: fix potential htree corruption when growing large_dir directories MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b5776e7524af ("ext4: fix potential htree index checksum corruption) removed a required restart when multiple levels of index nodes need to be split. Fix this to avoid directory htree corruptions when using the large_dir feature. Cc: stable@kernel.org # v5.11 Cc: Благодаренко Артём Fixes: b5776e7524af ("ext4: fix potential htree index checksum corruption) Reported-by: Denis Signed-off-by: Theodore Ts'o --- fs/ext4/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5fd56f616cf0..f3bbcd4efb56 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2517,7 +2517,7 @@ again: goto journal_error; err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); - if (err) + if (restart || err) goto journal_error; } else { struct dx_root *dxroot; From 46dd2965bdd1c5a4f6499c73ff32e636fa8f9769 Mon Sep 17 00:00:00 2001 From: Solomon Chiu Date: Wed, 28 Jul 2021 00:20:30 +0800 Subject: [PATCH 1295/1469] drm/amdgpu: Add preferred mode in modeset when freesync video mode's enabled. [Why] With kernel module parameter "freesync_video" is enabled, if the mode is changed to preferred mode(the mode with highest rate), then Freesync fails because the preferred mode is treated as one of freesync video mode, and then be configurated as freesync video mode(fixed refresh rate). [How] Skip freesync fixed rate configurating when modeset to preferred mode. Signed-off-by: Solomon Chiu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c0ae73b0691c..afa96c8f721b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9605,7 +9605,12 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, } else if (amdgpu_freesync_vid_mode && aconnector && is_freesync_video_mode(&new_crtc_state->mode, aconnector)) { - set_freesync_fixed_config(dm_new_crtc_state); + struct drm_display_mode *high_mode; + + high_mode = get_highest_refresh_rate_mode(aconnector, false); + if (!drm_mode_equal(&new_crtc_state->mode, high_mode)) { + set_freesync_fixed_config(dm_new_crtc_state); + } } ret = dm_atomic_get_state(state, &dm_state); From fb7b9b0231ba8f77587c23f5257a4fdb6df1219e Mon Sep 17 00:00:00 2001 From: Vincent Fu Date: Wed, 4 Aug 2021 19:49:23 +0000 Subject: [PATCH 1296/1469] kyber: make trace_block_rq call consistent with documentation The kyber ioscheduler calls trace_block_rq_insert() *after* the request is added to the queue but the documentation for trace_block_rq_insert() says that the call should be made *before* the request is added to the queue. Move the tracepoint for the kyber ioscheduler so that it is consistent with the documentation. Signed-off-by: Vincent Fu Link: https://lore.kernel.org/r/20210804194913.10497-1-vincent.fu@samsung.com Reviewed by: Adam Manzanares Signed-off-by: Jens Axboe --- block/kyber-iosched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 81e3279ecd57..15a8be57203d 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -596,13 +596,13 @@ static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx, struct list_head *head = &kcq->rq_list[sched_domain]; spin_lock(&kcq->lock); + trace_block_rq_insert(rq); if (at_head) list_move(&rq->queuelist, head); else list_move_tail(&rq->queuelist, head); sbitmap_set_bit(&khd->kcq_map[sched_domain], rq->mq_ctx->index_hw[hctx->type]); - trace_block_rq_insert(rq); spin_unlock(&kcq->lock); } } From 62376365048878f770d8b7d11b89b8b3e18018f1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 3 Aug 2021 15:14:27 +0000 Subject: [PATCH 1297/1469] powerpc/32s: Fix napping restore in data storage interrupt (DSI) When a DSI (Data Storage Interrupt) is taken while in NAP mode, r11 doesn't survive the call to power_save_ppc32_restore(). So use r1 instead of r11 as they both contain the virtual stack pointer at that point. Fixes: 4c0104a83fc3 ("powerpc/32: Dismantle EXC_XFER_STD/LITE/TEMPLATE") Cc: stable@vger.kernel.org # v5.13+ Reported-by: Finn Thain Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/731694e0885271f6ee9ffc179eb4bcee78313682.1628003562.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_book3s_32.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 764edd860ed4..68e5c0a7e99d 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -300,7 +300,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1 prepare_transfer_to_handler - lwz r5, _DSISR(r11) + lwz r5, _DSISR(r1) andis. r0, r5, DSISR_DABRMATCH@h bne- 1f bl do_page_fault From b5cfc9cd7b0426e94ffd9e9ed79d1b00ace7780a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 7 Jul 2021 05:55:07 +0000 Subject: [PATCH 1298/1469] powerpc/32: Fix critical and debug interrupts on BOOKE 32 bits BOOKE have special interrupts for debug and other critical events. When handling those interrupts, dedicated registers are saved in the stack frame in addition to the standard registers, leading to a shift of the pt_regs struct. Since commit db297c3b07af ("powerpc/32: Don't save thread.regs on interrupt entry"), the pt_regs struct is expected to be at the same place all the time. Instead of handling a special struct in addition to pt_regs, just add those special registers to struct pt_regs. Fixes: db297c3b07af ("powerpc/32: Don't save thread.regs on interrupt entry") Cc: stable@vger.kernel.org Reported-by: Radu Rendec Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/028d5483b4851b01ea4334d0751e7f260419092b.1625637264.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/ptrace.h | 16 ++++++++++++++++ arch/powerpc/kernel/asm-offsets.c | 31 ++++++++++++++----------------- arch/powerpc/kernel/head_booke.h | 27 +++------------------------ 3 files changed, 33 insertions(+), 41 deletions(-) diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 3e5d470a6155..14422e851494 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -70,6 +70,22 @@ struct pt_regs unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */ }; #endif +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + struct { /* Must be a multiple of 16 bytes */ + unsigned long mas0; + unsigned long mas1; + unsigned long mas2; + unsigned long mas3; + unsigned long mas6; + unsigned long mas7; + unsigned long srr0; + unsigned long srr1; + unsigned long csrr0; + unsigned long csrr1; + unsigned long dsrr0; + unsigned long dsrr1; + }; +#endif }; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a47eefa09bcb..5bee245d832b 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -309,24 +309,21 @@ int main(void) STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr); #endif -#if defined(CONFIG_PPC32) -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) - DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE); - DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + STACK_PT_REGS_OFFSET(MAS0, mas0); /* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */ - DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); - DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1)); - DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2)); - DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3)); - DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6)); - DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7)); - DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0)); - DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1)); - DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0)); - DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1)); - DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0)); - DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1)); -#endif + STACK_PT_REGS_OFFSET(MMUCR, mas0); + STACK_PT_REGS_OFFSET(MAS1, mas1); + STACK_PT_REGS_OFFSET(MAS2, mas2); + STACK_PT_REGS_OFFSET(MAS3, mas3); + STACK_PT_REGS_OFFSET(MAS6, mas6); + STACK_PT_REGS_OFFSET(MAS7, mas7); + STACK_PT_REGS_OFFSET(_SRR0, srr0); + STACK_PT_REGS_OFFSET(_SRR1, srr1); + STACK_PT_REGS_OFFSET(_CSRR0, csrr0); + STACK_PT_REGS_OFFSET(_CSRR1, csrr1); + STACK_PT_REGS_OFFSET(_DSRR0, dsrr0); + STACK_PT_REGS_OFFSET(_DSRR1, dsrr1); #endif /* About the CPU features table */ diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 87b806e8eded..e5503420b6c6 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -168,20 +168,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) /* only on e500mc */ #define DBG_STACK_BASE dbgirq_ctx -#define EXC_LVL_FRAME_OVERHEAD (THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE) - #ifdef CONFIG_SMP #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ mfspr r8,SPRN_PIR; \ slwi r8,r8,2; \ addis r8,r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #else #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ lis r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #endif /* @@ -208,7 +206,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) mtmsr r11; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\ - addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\ + addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE; /* allocate stack frame */\ beq 1f; \ /* COMING FROM USER MODE */ \ stw r9,_CCR(r11); /* save CR */\ @@ -516,24 +514,5 @@ label: bl kernel_fp_unavailable_exception; \ b interrupt_return -#else /* __ASSEMBLY__ */ -struct exception_regs { - unsigned long mas0; - unsigned long mas1; - unsigned long mas2; - unsigned long mas3; - unsigned long mas6; - unsigned long mas7; - unsigned long srr0; - unsigned long srr1; - unsigned long csrr0; - unsigned long csrr1; - unsigned long dsrr0; - unsigned long dsrr1; -}; - -/* ensure this structure is always sized to a multiple of the stack alignment */ -#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16) - #endif /* __ASSEMBLY__ */ #endif /* __HEAD_BOOKE_H__ */ From 8241461536f21bbe51308a6916d1c9fb2e6b75a7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 4 Aug 2021 18:24:10 +0000 Subject: [PATCH 1299/1469] powerpc/smp: Fix OOPS in topology_init() Running an SMP kernel on an UP platform not prepared for it, I encountered the following OOPS: BUG: Kernel NULL pointer dereference on read at 0x00000034 Faulting instruction address: 0xc0a04110 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=4K SMP NR_CPUS=2 CMPCPRO Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-pmac-00001-g230fedfaad21 #5234 NIP: c0a04110 LR: c0a040d8 CTR: c0a04084 REGS: e100dda0 TRAP: 0300 Not tainted (5.13.0-pmac-00001-g230fedfaad21) MSR: 00009032 CR: 84000284 XER: 00000000 DAR: 00000034 DSISR: 20000000 GPR00: c0006bd4 e100de60 c1033320 00000000 00000000 c0942274 00000000 00000000 GPR08: 00000000 00000000 00000001 00000063 00000007 00000000 c0006f30 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000005 GPR24: c0c67d74 c0c67f1c c0c60000 c0c67d70 c0c0c558 1efdf000 c0c00020 00000000 NIP [c0a04110] topology_init+0x8c/0x138 LR [c0a040d8] topology_init+0x54/0x138 Call Trace: [e100de60] [80808080] 0x80808080 (unreliable) [e100de90] [c0006bd4] do_one_initcall+0x48/0x1bc [e100def0] [c0a0150c] kernel_init_freeable+0x1c8/0x278 [e100df20] [c0006f44] kernel_init+0x14/0x10c [e100df30] [c00190fc] ret_from_kernel_thread+0x14/0x1c Instruction dump: 7c692e70 7d290194 7c035040 7c7f1b78 5529103a 546706fe 5468103a 39400001 7c641b78 40800054 80c690b4 7fb9402e <81060034> 7fbeea14 2c080000 7fa3eb78 ---[ end trace b246ffbc6bbbb6fb ]--- Fix it by checking smp_ops before using it, as already done in several other places in the arch/powerpc/kernel/smp.c Fixes: 39f87561454d ("powerpc/smp: Move ppc_md.cpu_die() to smp_ops.cpu_offline_self()") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/75287841cbb8740edd44880fe60be66d489160d9.1628097995.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5ff0e55d0db1..defecb3b1b15 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1167,7 +1167,7 @@ static int __init topology_init(void) * CPU. For instance, the boot cpu might never be valid * for hotplugging. */ - if (smp_ops->cpu_offline_self) + if (smp_ops && smp_ops->cpu_offline_self) c->hotpluggable = 1; #endif From c18956e6e0b95f78dad2773ecc8c61a9e41f6405 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Thu, 5 Aug 2021 17:23:08 +0200 Subject: [PATCH 1300/1469] powerpc/pseries: Fix update of LPAR security flavor after LPM After LPM, when migrating from a system with security mitigation enabled to a system with mitigation disabled, the security flavor exposed in /proc is not correctly set back to 0. Do not assume the value of the security flavor is set to 0 when entering init_cpu_char_feature_flags(), so when called after a LPM, the value is set correctly even if the mitigation are not turned off. Fixes: 6ce56e1ac380 ("powerpc/pseries: export LPAR security flavor in lparcfg") Cc: stable@vger.kernel.org # v5.13+ Signed-off-by: Laurent Dufour Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210805152308.33988-1-ldufour@linux.ibm.com --- arch/powerpc/platforms/pseries/setup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6b0886668465..0dfaa6ab44cc 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -539,9 +539,10 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) * H_CPU_BEHAV_FAVOUR_SECURITY_H could be set only if * H_CPU_BEHAV_FAVOUR_SECURITY is. */ - if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) + if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) { security_ftr_clear(SEC_FTR_FAVOUR_SECURITY); - else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) + pseries_security_flavor = 0; + } else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) pseries_security_flavor = 1; else pseries_security_flavor = 2; From 78d14bda861dd2729f15bb438fe355b48514bfe0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Robin=20G=C3=B6gge?= Date: Thu, 29 Jul 2021 00:58:25 +0200 Subject: [PATCH 1301/1469] libbpf: Fix probe for BPF_PROG_TYPE_CGROUP_SOCKOPT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the probe for BPF_PROG_TYPE_CGROUP_SOCKOPT, so the probe reports accurate results when used by e.g. bpftool. Fixes: 4cdbfb59c44a ("libbpf: support sockopt hooks") Signed-off-by: Robin Gögge Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Reviewed-by: Quentin Monnet Link: https://lore.kernel.org/bpf/20210728225825.2357586-1-r.goegge@gmail.com --- tools/lib/bpf/libbpf_probes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ecaae2927ab8..cd8c703dde71 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -75,6 +75,9 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + break; case BPF_PROG_TYPE_SK_LOOKUP: xattr.expected_attach_type = BPF_SK_LOOKUP; break; @@ -104,7 +107,6 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: From c34c338a40e4f3b6f80889cd17fd9281784d1c32 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Wed, 28 Jul 2021 16:09:21 -0700 Subject: [PATCH 1302/1469] libbpf: Do not close un-owned FD 0 on errors Before this patch, btf_new() was liable to close an arbitrary FD 0 if BTF parsing failed. This was because: * btf->fd was initialized to 0 through the calloc() * btf__free() (in the `done` label) closed any FDs >= 0 * btf->fd is left at 0 if parsing fails This issue was discovered on a system using libbpf v0.3 (without BTF_KIND_FLOAT support) but with a kernel that had BTF_KIND_FLOAT types in BTF. Thus, parsing fails. While this patch technically doesn't fix any issues b/c upstream libbpf has BTF_KIND_FLOAT support, it'll help prevent issues in the future if more BTF types are added. It also allow the fix to be backported to older libbpf's. Fixes: 3289959b97ca ("libbpf: Support BTF loading and raw data output in both endianness") Signed-off-by: Daniel Xu Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/5969bb991adedb03c6ae93e051fd2a00d293cf25.1627513670.git.dxu@dxuuu.xyz --- tools/lib/bpf/btf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index b46760b93bb4..7ff3d5ce44f9 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -804,6 +804,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) btf->nr_types = 0; btf->start_id = 1; btf->start_str_off = 0; + btf->fd = -1; if (base_btf) { btf->base_btf = base_btf; @@ -832,8 +833,6 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (err) goto done; - btf->fd = -1; - done: if (err) { btf__free(btf); From 7c4a22339e7ce7b6ed473a8e682da622c3a774ee Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Aug 2021 18:50:37 -0700 Subject: [PATCH 1303/1469] libbpf, doc: Eliminate warnings in libbpf_naming_convention Use "code-block: none" instead of "c" for non-C-language code blocks. Removes these warnings: lnx-514-rc4/Documentation/bpf/libbpf/libbpf_naming_convention.rst:111: WARNING: Could not lex literal_block as "c". Highlighting skipped. lnx-514-rc4/Documentation/bpf/libbpf/libbpf_naming_convention.rst:124: WARNING: Could not lex literal_block as "c". Highlighting skipped. Fixes: f42cfb469f9b ("bpf: Add documentation for libbpf including API autogen") Signed-off-by: Randy Dunlap Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210802015037.787-1-rdunlap@infradead.org --- Documentation/bpf/libbpf/libbpf_naming_convention.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/bpf/libbpf/libbpf_naming_convention.rst b/Documentation/bpf/libbpf/libbpf_naming_convention.rst index 3de1d51e41da..6bf9c5ac7576 100644 --- a/Documentation/bpf/libbpf/libbpf_naming_convention.rst +++ b/Documentation/bpf/libbpf/libbpf_naming_convention.rst @@ -108,7 +108,7 @@ This bump in ABI version is at most once per kernel development cycle. For example, if current state of ``libbpf.map`` is: -.. code-block:: c +.. code-block:: none LIBBPF_0.0.1 { global: @@ -121,7 +121,7 @@ For example, if current state of ``libbpf.map`` is: , and a new symbol ``bpf_func_c`` is being introduced, then ``libbpf.map`` should be changed like this: -.. code-block:: c +.. code-block:: none LIBBPF_0.0.1 { global: From c4eb1f403243fc7bbb7de644db8587c03de36da6 Mon Sep 17 00:00:00 2001 From: Tatsuhiko Yasumatsu Date: Sat, 7 Aug 2021 00:04:18 +0900 Subject: [PATCH 1304/1469] bpf: Fix integer overflow involving bucket_size In __htab_map_lookup_and_delete_batch(), hash buckets are iterated over to count the number of elements in each bucket (bucket_size). If bucket_size is large enough, the multiplication to calculate kvmalloc() size could overflow, resulting in out-of-bounds write as reported by KASAN: [...] [ 104.986052] BUG: KASAN: vmalloc-out-of-bounds in __htab_map_lookup_and_delete_batch+0x5ce/0xb60 [ 104.986489] Write of size 4194224 at addr ffffc9010503be70 by task crash/112 [ 104.986889] [ 104.987193] CPU: 0 PID: 112 Comm: crash Not tainted 5.14.0-rc4 #13 [ 104.987552] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 104.988104] Call Trace: [ 104.988410] dump_stack_lvl+0x34/0x44 [ 104.988706] print_address_description.constprop.0+0x21/0x140 [ 104.988991] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60 [ 104.989327] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60 [ 104.989622] kasan_report.cold+0x7f/0x11b [ 104.989881] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60 [ 104.990239] kasan_check_range+0x17c/0x1e0 [ 104.990467] memcpy+0x39/0x60 [ 104.990670] __htab_map_lookup_and_delete_batch+0x5ce/0xb60 [ 104.990982] ? __wake_up_common+0x4d/0x230 [ 104.991256] ? htab_of_map_free+0x130/0x130 [ 104.991541] bpf_map_do_batch+0x1fb/0x220 [...] In hashtable, if the elements' keys have the same jhash() value, the elements will be put into the same bucket. By putting a lot of elements into a single bucket, the value of bucket_size can be increased to trigger the integer overflow. Triggering the overflow is possible for both callers with CAP_SYS_ADMIN and callers without CAP_SYS_ADMIN. It will be trivial for a caller with CAP_SYS_ADMIN to intentionally reach this overflow by enabling BPF_F_ZERO_SEED. As this flag will set the random seed passed to jhash() to 0, it will be easy for the caller to prepare keys which will be hashed into the same value, and thus put all the elements into the same bucket. If the caller does not have CAP_SYS_ADMIN, BPF_F_ZERO_SEED cannot be used. However, it will be still technically possible to trigger the overflow, by guessing the random seed value passed to jhash() (32bit) and repeating the attempt to trigger the overflow. In this case, the probability to trigger the overflow will be low and will take a very long time. Fix the integer overflow by calling kvmalloc_array() instead of kvmalloc() to allocate memory. Fixes: 057996380a42 ("bpf: Add batch ops to all htab bpf map") Signed-off-by: Tatsuhiko Yasumatsu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210806150419.109658-1-th.yasumatsu@gmail.com --- kernel/bpf/hashtab.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 72c58cc516a3..9c011f3a2687 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1565,8 +1565,8 @@ alloc: /* We cannot do copy_from_user or copy_to_user inside * the rcu_read_lock. Allocate enough space here. */ - keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); - values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + keys = kvmalloc_array(key_size, bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc_array(value_size, bucket_size, GFP_USER | __GFP_NOWARN); if (!keys || !values) { ret = -ENOMEM; goto after_loop; From 6d7f91d914bc90a15ebc426440c26081337ceaa1 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 21 Jul 2021 09:59:35 +0200 Subject: [PATCH 1305/1469] riscv: Get rid of CONFIG_PHYS_RAM_BASE in kernel physical address conversion The usage of CONFIG_PHYS_RAM_BASE for all kernel types was a mistake: this value is implementation-specific and this breaks the genericity of the RISC-V kernel. Fix this by introducing a new variable phys_ram_base that holds this value at runtime and use it in the kernel physical address conversion macro. Since this value is used only for XIP kernels, evaluate it only if CONFIG_XIP_KERNEL is set which in addition optimizes this macro for standard kernels at compile-time. Signed-off-by: Alexandre Ghiti Tested-by: Emil Renner Berthing Reviewed-by: Jisheng Zhang Fixes: 44c922572952 ("RISC-V: enable XIP") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/page.h | 7 ++++--- arch/riscv/mm/init.c | 17 ++++++++++++----- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index cca8764aed83..b0ca5058e7ae 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -103,6 +103,7 @@ struct kernel_mapping { }; extern struct kernel_mapping kernel_map; +extern phys_addr_t phys_ram_base; #ifdef CONFIG_64BIT #define is_kernel_mapping(x) \ @@ -113,9 +114,9 @@ extern struct kernel_mapping kernel_map; #define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) #define kernel_mapping_pa_to_va(y) ({ \ unsigned long _y = y; \ - (_y >= CONFIG_PHYS_RAM_BASE) ? \ - (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET) : \ - (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset); \ + (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \ + (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset) : \ + (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET); \ }) #define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index a14bf3910eec..88134cc288d9 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -36,6 +36,9 @@ EXPORT_SYMBOL(kernel_map); #define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map)) #endif +phys_addr_t phys_ram_base __ro_after_init; +EXPORT_SYMBOL(phys_ram_base); + #ifdef CONFIG_XIP_KERNEL extern char _xiprom[], _exiprom[]; #endif @@ -160,7 +163,7 @@ static void __init setup_bootmem(void) phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); phys_addr_t __maybe_unused max_mapped_addr; - phys_addr_t dram_end; + phys_addr_t phys_ram_end; #ifdef CONFIG_XIP_KERNEL vmlinux_start = __pa_symbol(&_sdata); @@ -181,9 +184,12 @@ static void __init setup_bootmem(void) #endif memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - dram_end = memblock_end_of_DRAM(); + phys_ram_end = memblock_end_of_DRAM(); #ifndef CONFIG_64BIT +#ifndef CONFIG_XIP_KERNEL + phys_ram_base = memblock_start_of_DRAM(); +#endif /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE @@ -194,12 +200,12 @@ static void __init setup_bootmem(void) * be done in create_kernel_page_table. */ max_mapped_addr = __pa(~(ulong)0); - if (max_mapped_addr == (dram_end - 1)) + if (max_mapped_addr == (phys_ram_end - 1)) memblock_set_current_limit(max_mapped_addr - 4096); #endif - min_low_pfn = PFN_UP(memblock_start_of_DRAM()); - max_low_pfn = max_pfn = PFN_DOWN(dram_end); + min_low_pfn = PFN_UP(phys_ram_base); + max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); @@ -558,6 +564,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); + phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); From 867432bec1c6e7df21a361d7f12022a8c5f54022 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 21 Jul 2021 09:59:36 +0200 Subject: [PATCH 1306/1469] Revert "riscv: Remove CONFIG_PHYS_RAM_BASE_FIXED" This reverts commit 9b79878ced8f7ab85c57623f8b1f6882e484a316. The removal of this config exposes CONFIG_PHYS_RAM_BASE for all kernel types: this value being implementation-specific, this breaks the genericity of the RISC-V kernel so revert it. Signed-off-by: Alexandre Ghiti Tested-by: Emil Renner Berthing Reviewed-by: Jisheng Zhang Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 31f9e92f1402..4f7b70ae7c31 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -495,8 +495,13 @@ config STACKPROTECTOR_PER_TASK depends on !GCC_PLUGIN_RANDSTRUCT depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS +config PHYS_RAM_BASE_FIXED + bool "Explicitly specified physical RAM address" + default n + config PHYS_RAM_BASE hex "Platform Physical RAM address" + depends on PHYS_RAM_BASE_FIXED default "0x80000000" help This is the physical address of RAM in the system. It has to be @@ -509,6 +514,7 @@ config XIP_KERNEL # This prevents XIP from being enabled by all{yes,mod}config, which # fail to build since XIP doesn't support large kernels. depends on !COMPILE_TEST + select PHYS_RAM_BASE_FIXED help Execute-In-Place allows the kernel to run from non-volatile storage directly addressable by the CPU, such as NOR flash. This saves RAM From 739d0959fbed23838a96c48fbce01dd2f6fb2c5f Mon Sep 17 00:00:00 2001 From: Luke D Jones Date: Sat, 7 Aug 2021 14:58:05 +1200 Subject: [PATCH 1307/1469] ALSA: hda: Add quirk for ASUS Flow x13 The ASUS GV301QH sound appears to work well with the quirk for ALC294_FIXUP_ASUS_DUAL_SPK. Signed-off-by: Luke D Jones Cc: Link: https://lore.kernel.org/r/20210807025805.27321-1-luke@ljones.dev Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 21c521596c9d..4043a2362f27 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8465,6 +8465,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), From 2115d3d482656ea702f7cf308c0ded3500282903 Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 6 Aug 2021 17:15:55 +0800 Subject: [PATCH 1308/1469] Revert "r8169: avoid link-up interrupt issue on RTL8106e if user enables ASPM" This reverts commit 1ee8856de82faec9bc8bd0f2308a7f27e30ba207. This is used to re-enable ASPM on RTL8106e, if it is possible. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c7af5bc3b8af..731631511dcf 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3508,6 +3508,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000); rtl_pcie_state_l2l3_disable(tp); + rtl_hw_aspm_clkreq_enable(tp, true); } DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond) From 9c40186488145b57f800de120f0872168772adfe Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 6 Aug 2021 17:15:56 +0800 Subject: [PATCH 1309/1469] r8169: change the L0/L1 entrance latencies for RTL8106e The original L0 and L1 entrance latencies of RTL8106e are 4us. And they cause the delay of link-up interrupt when enabling ASPM. Change the L0 entrance latency to 7us and L1 entrance latency to 32us. Then, they could avoid the issue. Tested-by: Koba Ko Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 731631511dcf..4d8e337f5085 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3502,6 +3502,9 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); + /* The default value is 0x13. Change it to 0x2f */ + rtl_csi_access_enable(tp, 0x2f); + rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000); /* disable EEE */ From 47fac45600aafc5939d9620055c3c46f7135d316 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 Aug 2021 11:47:23 +0200 Subject: [PATCH 1310/1469] net: dsa: qca: ar9331: make proper initial port defaults Make sure that all external port are actually isolated from each other, so no packets are leaked. Fixes: ec6698c272de ("net: dsa: add support for Atheros AR9331 built-in switch") Signed-off-by: Oleksij Rempel Signed-off-by: David S. Miller --- drivers/net/dsa/qca/ar9331.c | 73 +++++++++++++++++++++++++++++++++++- 1 file changed, 72 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 6686192e1883..563d8a279030 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -101,6 +101,23 @@ AR9331_SW_PORT_STATUS_RX_FLOW_EN | AR9331_SW_PORT_STATUS_TX_FLOW_EN | \ AR9331_SW_PORT_STATUS_SPEED_M) +#define AR9331_SW_REG_PORT_CTRL(_port) (0x104 + (_port) * 0x100) +#define AR9331_SW_PORT_CTRL_HEAD_EN BIT(11) +#define AR9331_SW_PORT_CTRL_PORT_STATE GENMASK(2, 0) +#define AR9331_SW_PORT_CTRL_PORT_STATE_DISABLED 0 +#define AR9331_SW_PORT_CTRL_PORT_STATE_BLOCKING 1 +#define AR9331_SW_PORT_CTRL_PORT_STATE_LISTENING 2 +#define AR9331_SW_PORT_CTRL_PORT_STATE_LEARNING 3 +#define AR9331_SW_PORT_CTRL_PORT_STATE_FORWARD 4 + +#define AR9331_SW_REG_PORT_VLAN(_port) (0x108 + (_port) * 0x100) +#define AR9331_SW_PORT_VLAN_8021Q_MODE GENMASK(31, 30) +#define AR9331_SW_8021Q_MODE_SECURE 3 +#define AR9331_SW_8021Q_MODE_CHECK 2 +#define AR9331_SW_8021Q_MODE_FALLBACK 1 +#define AR9331_SW_8021Q_MODE_NONE 0 +#define AR9331_SW_PORT_VLAN_PORT_VID_MEMBER GENMASK(25, 16) + /* MIB registers */ #define AR9331_MIB_COUNTER(x) (0x20000 + ((x) * 0x100)) @@ -371,11 +388,59 @@ static int ar9331_sw_mbus_init(struct ar9331_sw_priv *priv) return 0; } +static int ar9331_sw_setup_port(struct dsa_switch *ds, int port) +{ + struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct regmap *regmap = priv->regmap; + u32 port_mask, port_ctrl, val; + int ret; + + /* Generate default port settings */ + port_ctrl = FIELD_PREP(AR9331_SW_PORT_CTRL_PORT_STATE, + AR9331_SW_PORT_CTRL_PORT_STATE_FORWARD); + + if (dsa_is_cpu_port(ds, port)) { + /* CPU port should be allowed to communicate with all user + * ports. + */ + port_mask = dsa_user_ports(ds); + /* Enable Atheros header on CPU port. This will allow us + * communicate with each port separately + */ + port_ctrl |= AR9331_SW_PORT_CTRL_HEAD_EN; + } else if (dsa_is_user_port(ds, port)) { + /* User ports should communicate only with the CPU port. + */ + port_mask = BIT(dsa_upstream_port(ds, port)); + } else { + /* Other ports do not need to communicate at all */ + port_mask = 0; + } + + val = FIELD_PREP(AR9331_SW_PORT_VLAN_8021Q_MODE, + AR9331_SW_8021Q_MODE_NONE) | + FIELD_PREP(AR9331_SW_PORT_VLAN_PORT_VID_MEMBER, port_mask); + + ret = regmap_write(regmap, AR9331_SW_REG_PORT_VLAN(port), val); + if (ret) + goto error; + + ret = regmap_write(regmap, AR9331_SW_REG_PORT_CTRL(port), port_ctrl); + if (ret) + goto error; + + return 0; +error: + dev_err(priv->dev, "%s: error: %i\n", __func__, ret); + + return ret; +} + static int ar9331_sw_setup(struct dsa_switch *ds) { struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; struct regmap *regmap = priv->regmap; - int ret; + int ret, i; ret = ar9331_sw_reset(priv); if (ret) @@ -402,6 +467,12 @@ static int ar9331_sw_setup(struct dsa_switch *ds) if (ret) goto error; + for (i = 0; i < ds->num_ports; i++) { + ret = ar9331_sw_setup_port(ds, i); + if (ret) + goto error; + } + ds->configure_vlan_while_not_filtering = false; return 0; From 34737e1320db6d51f0d140d5c684b9eb32f0da76 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Fri, 6 Aug 2021 12:35:09 +0200 Subject: [PATCH 1311/1469] net: wwan: mhi_wwan_ctrl: Fix possible deadlock Lockdep detected possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mhiwwan->rx_lock); local_irq_disable(); lock(&mhi_cntrl->pm_lock); lock(&mhiwwan->rx_lock); lock(&mhi_cntrl->pm_lock); *** DEADLOCK *** To prevent this we need to disable the soft-interrupts when taking the rx_lock. Cc: stable@vger.kernel.org Fixes: fa588eba632d ("net: Add Qcom WWAN control driver") Reported-by: Thomas Perrot Signed-off-by: Loic Poulain Reviewed-by: Sergey Ryazanov Signed-off-by: David S. Miller --- drivers/net/wwan/mhi_wwan_ctrl.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index 1e18420ce404..d0a98f34c54d 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -41,14 +41,14 @@ struct mhi_wwan_dev { /* Increment RX budget and schedule RX refill if necessary */ static void mhi_wwan_rx_budget_inc(struct mhi_wwan_dev *mhiwwan) { - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); mhiwwan->rx_budget++; if (test_bit(MHI_WWAN_RX_REFILL, &mhiwwan->flags)) schedule_work(&mhiwwan->rx_refill); - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); } /* Decrement RX budget if non-zero and return true on success */ @@ -56,7 +56,7 @@ static bool mhi_wwan_rx_budget_dec(struct mhi_wwan_dev *mhiwwan) { bool ret = false; - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); if (mhiwwan->rx_budget) { mhiwwan->rx_budget--; @@ -64,7 +64,7 @@ static bool mhi_wwan_rx_budget_dec(struct mhi_wwan_dev *mhiwwan) ret = true; } - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); return ret; } @@ -130,9 +130,9 @@ static void mhi_wwan_ctrl_stop(struct wwan_port *port) { struct mhi_wwan_dev *mhiwwan = wwan_port_get_drvdata(port); - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); clear_bit(MHI_WWAN_RX_REFILL, &mhiwwan->flags); - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); cancel_work_sync(&mhiwwan->rx_refill); From 2383cb9497d113360137a2be308b390faa80632d Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 7 Aug 2021 02:06:18 +0200 Subject: [PATCH 1312/1469] net: phy: micrel: Fix link detection on ksz87xx switch" Commit a5e63c7d38d5 "net: phy: micrel: Fix detection of ksz87xx switch" broke link detection on the external ports of the KSZ8795. The previously unused phy_driver structure for these devices specifies config_aneg and read_status functions that appear to be designed for a fixed link and do not work with the embedded PHYs in the KSZ8795. Delete the use of these functions in favour of the generic PHY implementations which were used previously. Fixes: a5e63c7d38d5 ("net: phy: micrel: Fix detection of ksz87xx switch") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 53bdd673ae56..5c928f827173 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1760,8 +1760,6 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KSZ87XX Switch", /* PHY_BASIC_FEATURES */ .config_init = kszphy_config_init, - .config_aneg = ksz8873mll_config_aneg, - .read_status = ksz8873mll_read_status, .match_phy_device = ksz8795_match_phy_device, .suspend = genphy_suspend, .resume = genphy_resume, From d329e41a08f37c478159d5c3379a17b9c07befa3 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Fri, 6 Aug 2021 18:15:46 -0700 Subject: [PATCH 1313/1469] ptp: Fix possible memory leak caused by invalid cast Fixes possible leak of PTP virtual clocks. The number of PTP virtual clocks to be unregistered is passed as 'u32', but the function that unregister the devices handles that as 'u8'. Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion") Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- drivers/ptp/ptp_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index b3d96b747292..41b92dc2f011 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -154,7 +154,7 @@ static int unregister_vclock(struct device *dev, void *data) struct ptp_clock *ptp = dev_get_drvdata(dev); struct ptp_clock_info *info = ptp->info; struct ptp_vclock *vclock; - u8 *num = data; + u32 *num = data; vclock = info_to_vclock(info); dev_info(dev->parent, "delete virtual clock ptp%d\n", From 1027b96ec9d34f9abab69bc1a4dc5b1ad8ab1349 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 6 Aug 2021 16:21:24 +0800 Subject: [PATCH 1314/1469] once: Fix panic when module unload DO_ONCE DEFINE_STATIC_KEY_TRUE(___once_key); __do_once_done once_disable_jump(once_key); INIT_WORK(&w->work, once_deferred); struct once_work *w; w->key = key; schedule_work(&w->work); module unload //*the key is destroy* process_one_work once_deferred BUG_ON(!static_key_enabled(work->key)); static_key_count((struct static_key *)x) //*access key, crash* When module uses DO_ONCE mechanism, it could crash due to the above concurrency problem, we could reproduce it with link[1]. Fix it by add/put module refcount in the once work process. [1] https://lore.kernel.org/netdev/eaa6c371-465e-57eb-6be9-f4b16b9d7cbf@huawei.com/ Cc: Hannes Frederic Sowa Cc: Daniel Borkmann Cc: David S. Miller Cc: Eric Dumazet Reported-by: Minmin chen Signed-off-by: Kefeng Wang Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/once.h | 4 ++-- lib/once.c | 11 ++++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/linux/once.h b/include/linux/once.h index 9225ee6d96c7..ae6f4eb41cbe 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -7,7 +7,7 @@ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags); + unsigned long *flags, struct module *mod); /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only @@ -46,7 +46,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, if (unlikely(___ret)) { \ func(__VA_ARGS__); \ __do_once_done(&___done, &___once_key, \ - &___flags); \ + &___flags, THIS_MODULE); \ } \ } \ ___ret; \ diff --git a/lib/once.c b/lib/once.c index 8b7d6235217e..59149bf3bfb4 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include #include #include +#include struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,10 +18,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } -static void once_disable_jump(struct static_key_true *key) +static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; @@ -29,6 +32,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } @@ -53,11 +58,11 @@ bool __do_once_start(bool *done, unsigned long *flags) EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags) + unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); - once_disable_jump(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); From fbfee25796e2688004d58ad4d0673279366b97dd Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 7 Aug 2021 15:03:13 -0400 Subject: [PATCH 1315/1469] bnxt_en: Update firmware interface to 1.10.2.52 The key change is the firmware call to retrieve the PTP TX timestamp. The header offset for the PTP sequence number field is now added. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 76 ++++++++++++++----- 1 file changed, 55 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 3fc6781c5b98..94d07a9f7034 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -368,6 +368,7 @@ struct cmd_nums { #define HWRM_FUNC_PTP_TS_QUERY 0x19fUL #define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL #define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL + #define HWRM_FUNC_KEY_CTX_ALLOC 0x1a2UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -531,8 +532,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 47 -#define HWRM_VERSION_STR "1.10.2.47" +#define HWRM_VERSION_RSVD 52 +#define HWRM_VERSION_STR "1.10.2.52" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -585,6 +586,7 @@ struct hwrm_ver_get_output { #define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED 0x1000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED 0x2000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED 0x4000UL + #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE 0x8000UL u8 roce_fw_maj_8b; u8 roce_fw_min_8b; u8 roce_fw_bld_8b; @@ -886,7 +888,8 @@ struct hwrm_async_event_cmpl_reset_notify { #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL (0x2UL << 8) #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL (0x3UL << 8) #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET (0x4UL << 8) - #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET + #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION (0x5UL << 8) + #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK 0xffff0000UL #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT 16 }; @@ -1236,13 +1239,14 @@ struct hwrm_async_event_cmpl_error_report_base { u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD }; /* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */ @@ -1446,6 +1450,8 @@ struct hwrm_func_vf_cfg_input { #define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS 0x200UL #define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS 0x400UL #define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS 0x800UL + #define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_KEY_CTXS 0x1000UL + #define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_KEY_CTXS 0x2000UL __le16 mtu; __le16 guest_vlan; __le16 async_event_cr; @@ -1469,7 +1475,8 @@ struct hwrm_func_vf_cfg_input { __le16 num_vnics; __le16 num_stat_ctxs; __le16 num_hw_ring_grps; - u8 unused_0[4]; + __le16 num_tx_key_ctxs; + __le16 num_rx_key_ctxs; }; /* hwrm_func_vf_cfg_output (size:128b/16B) */ @@ -1493,7 +1500,7 @@ struct hwrm_func_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_qcaps_output (size:704b/88B) */ +/* hwrm_func_qcaps_output (size:768b/96B) */ struct hwrm_func_qcaps_output { __le16 error_code; __le16 req_type; @@ -1587,7 +1594,8 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA 0x4UL #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA 0x8UL #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE 0x10UL - u8 unused_1; + __le16 max_key_ctxs_alloc; + u8 unused_1[7]; u8 valid; }; @@ -1602,7 +1610,7 @@ struct hwrm_func_qcfg_input { u8 unused_0[6]; }; -/* hwrm_func_qcfg_output (size:832b/104B) */ +/* hwrm_func_qcfg_output (size:896b/112B) */ struct hwrm_func_qcfg_output { __le16 error_code; __le16 req_type; @@ -1749,11 +1757,13 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __le16 host_mtu; - u8 unused_3; + __le16 alloc_tx_key_ctxs; + __le16 alloc_rx_key_ctxs; + u8 unused_3[5]; u8 valid; }; -/* hwrm_func_cfg_input (size:832b/104B) */ +/* hwrm_func_cfg_input (size:896b/112B) */ struct hwrm_func_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -1820,6 +1830,8 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW 0x8000000UL #define FUNC_CFG_REQ_ENABLES_TPID 0x10000000UL #define FUNC_CFG_REQ_ENABLES_HOST_MTU 0x20000000UL + #define FUNC_CFG_REQ_ENABLES_TX_KEY_CTXS 0x40000000UL + #define FUNC_CFG_REQ_ENABLES_RX_KEY_CTXS 0x80000000UL __le16 admin_mtu; __le16 mru; __le16 num_rsscos_ctxs; @@ -1929,6 +1941,9 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __be16 tpid; __le16 host_mtu; + __le16 num_tx_key_ctxs; + __le16 num_rx_key_ctxs; + u8 unused_0[4]; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -2099,6 +2114,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT 0x40UL #define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT 0x80UL #define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT 0x100UL + #define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT 0x200UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -2268,7 +2284,7 @@ struct hwrm_func_resource_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_resource_qcaps_output (size:448b/56B) */ +/* hwrm_func_resource_qcaps_output (size:512b/64B) */ struct hwrm_func_resource_qcaps_output { __le16 error_code; __le16 req_type; @@ -2300,11 +2316,15 @@ struct hwrm_func_resource_qcaps_output { __le16 max_tx_scheduler_inputs; __le16 flags; #define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED 0x1UL + __le16 min_tx_key_ctxs; + __le16 max_tx_key_ctxs; + __le16 min_rx_key_ctxs; + __le16 max_rx_key_ctxs; u8 unused_0[5]; u8 valid; }; -/* hwrm_func_vf_resource_cfg_input (size:448b/56B) */ +/* hwrm_func_vf_resource_cfg_input (size:512b/64B) */ struct hwrm_func_vf_resource_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -2331,6 +2351,10 @@ struct hwrm_func_vf_resource_cfg_input { __le16 max_hw_ring_grps; __le16 flags; #define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED 0x1UL + __le16 min_tx_key_ctxs; + __le16 max_tx_key_ctxs; + __le16 min_rx_key_ctxs; + __le16 max_rx_key_ctxs; u8 unused_0[2]; }; @@ -2348,7 +2372,9 @@ struct hwrm_func_vf_resource_cfg_output { __le16 reserved_vnics; __le16 reserved_stat_ctx; __le16 reserved_hw_ring_grps; - u8 unused_0[7]; + __le16 reserved_tx_key_ctxs; + __le16 reserved_rx_key_ctxs; + u8 unused_0[3]; u8 valid; }; @@ -4220,7 +4246,7 @@ struct hwrm_port_lpbk_clr_stats_output { u8 valid; }; -/* hwrm_port_ts_query_input (size:256b/32B) */ +/* hwrm_port_ts_query_input (size:320b/40B) */ struct hwrm_port_ts_query_input { __le16 req_type; __le16 cmpl_ring; @@ -4238,8 +4264,11 @@ struct hwrm_port_ts_query_input { __le16 enables; #define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT 0x1UL #define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID 0x2UL + #define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET 0x4UL __le16 ts_req_timeout; __le32 ptp_seq_id; + __le16 ptp_hdr_offset; + u8 unused_1[6]; }; /* hwrm_port_ts_query_output (size:192b/24B) */ @@ -8172,6 +8201,7 @@ struct hwrm_fw_reset_input { u8 host_idx; u8 flags; #define FW_RESET_REQ_FLAGS_RESET_GRACEFUL 0x1UL + #define FW_RESET_REQ_FLAGS_FW_ACTIVATION 0x2UL u8 unused_0[4]; }; @@ -8952,7 +8982,7 @@ struct hwrm_nvm_get_dir_info_output { u8 valid; }; -/* hwrm_nvm_write_input (size:384b/48B) */ +/* hwrm_nvm_write_input (size:448b/56B) */ struct hwrm_nvm_write_input { __le16 req_type; __le16 cmpl_ring; @@ -8968,7 +8998,11 @@ struct hwrm_nvm_write_input { __le16 option; __le16 flags; #define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG 0x1UL + #define NVM_WRITE_REQ_FLAGS_BATCH_MODE 0x2UL + #define NVM_WRITE_REQ_FLAGS_BATCH_LAST 0x4UL __le32 dir_item_length; + __le32 offset; + __le32 len; __le32 unused_0; }; From 9e26680733d5c6538ba2e7a111fb49c9ac2dc16a Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 7 Aug 2021 15:03:14 -0400 Subject: [PATCH 1316/1469] bnxt_en: Update firmware call to retrieve TX PTP timestamp New firmware interface requires the PTP sequence ID header offset to be passed to the firmware to properly find the matching timestamp for all protocols. Fixes: 83bb623c968e ("bnxt_en: Transmit and retrieve packet timestamps") Reviewed-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++++- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 4 +++- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h | 6 ++++-- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 89606587b156..2fe743503949 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -426,7 +426,10 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb) && atomic_dec_if_positive(&ptp->tx_avail) >= 0) { - if (!bnxt_ptp_parse(skb, &ptp->tx_seqid)) { + if (!bnxt_ptp_parse(skb, &ptp->tx_seqid, + &ptp->tx_hdr_off)) { + if (vlan_tag_flags) + ptp->tx_hdr_off += VLAN_HLEN; lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; } else { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index ec381c2423b8..81f40ab748f1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -20,7 +20,7 @@ #include "bnxt.h" #include "bnxt_ptp.h" -int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id) +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off) { unsigned int ptp_class; struct ptp_header *hdr; @@ -34,6 +34,7 @@ int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id) if (!hdr) return -EINVAL; + *hdr_off = (u8 *)hdr - skb->data; *seq_id = ntohs(hdr->sequence_id); return 0; default: @@ -91,6 +92,7 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts) PORT_TS_QUERY_REQ_FLAGS_PATH_TX) { req.enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES); req.ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid); + req.ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off); req.ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT); } mutex_lock(&bp->hwrm_cmd_lock); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 254ba7bc0f99..57a8b9243a31 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -19,7 +19,8 @@ #define BNXT_PTP_QTS_TIMEOUT 1000 #define BNXT_PTP_QTS_TX_ENABLES (PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID | \ - PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT) + PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT | \ + PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET) struct bnxt_ptp_cfg { struct ptp_clock_info ptp_info; @@ -37,6 +38,7 @@ struct bnxt_ptp_cfg { #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) u16 tx_seqid; + u16 tx_hdr_off; struct bnxt *bp; atomic_t tx_avail; #define BNXT_MAX_TX_TS 1 @@ -74,7 +76,7 @@ do { \ ((dst) = READ_ONCE(src)) #endif -int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id); +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off); int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); From 92529df76db5ab184b82674cf7a4eef4b665b40e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 7 Aug 2021 15:03:15 -0400 Subject: [PATCH 1317/1469] bnxt_en: Use register window 6 instead of 5 to read the PHC Some older Broadcom debug tools use window 5 and may conflict, so switch to use window 6 instead. Fixes: 118612d519d8 ("bnxt_en: Add PTP clock APIs, ioctls, and ethtool methods") Reviewed-by: Andy Gospodarek Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 57a8b9243a31..524f1c272054 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -10,8 +10,8 @@ #ifndef BNXT_PTP_H #define BNXT_PTP_H -#define BNXT_PTP_GRC_WIN 5 -#define BNXT_PTP_GRC_WIN_BASE 0x5000 +#define BNXT_PTP_GRC_WIN 6 +#define BNXT_PTP_GRC_WIN_BASE 0x6000 #define BNXT_MAX_PHC_DRIFT 31000000 #define BNXT_LO_TIMER_MASK 0x0000ffffffffUL From 2459dcb96bcba94c08d6861f8a050185ff301672 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 7 Aug 2021 15:27:03 +0200 Subject: [PATCH 1318/1469] ppp: Fix generating ifname when empty IFLA_IFNAME is specified MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit IFLA_IFNAME is nul-term string which means that IFLA_IFNAME buffer can be larger than length of string which contains. Function __rtnl_newlink() generates new own ifname if either IFLA_IFNAME was not specified at all or userspace passed empty nul-term string. It is expected that if userspace does not specify ifname for new ppp netdev then kernel generates one in format "ppp" where id matches to the ppp unit id which can be later obtained by PPPIOCGUNIT ioctl. And it works in this way if IFLA_IFNAME is not specified at all. But it does not work when IFLA_IFNAME is specified with empty string. So fix this logic also for empty IFLA_IFNAME in ppp_nl_newlink() function and correctly generates ifname based on ppp unit identifier if userspace did not provided preferred ifname. Without this patch when IFLA_IFNAME was specified with empty string then kernel created a new ppp interface in format "ppp" but id did not match ppp unit id returned by PPPIOCGUNIT ioctl. In this case id was some number generated by __rtnl_newlink() function. Signed-off-by: Pali Rohár Fixes: bb8082f69138 ("ppp: build ifname using unit identifier for rtnl based devices") Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 930e49ef15f6..b2b35ec37702 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1306,7 +1306,7 @@ static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, * the PPP unit identifer as suffix (i.e. ppp). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ - if (!tb[IFLA_IFNAME]) + if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(src_net, dev, &conf); From 3125f26c514826077f2a4490b75e9b1c7a644c42 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 7 Aug 2021 18:00:50 +0200 Subject: [PATCH 1319/1469] ppp: Fix generating ppp unit id when ifname is not specified MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When registering new ppp interface via PPPIOCNEWUNIT ioctl then kernel has to choose interface name as this ioctl API does not support specifying it. Kernel in this case register new interface with name "ppp" where is the ppp unit id, which can be obtained via PPPIOCGUNIT ioctl. This applies also in the case when registering new ppp interface via rtnl without supplying IFLA_IFNAME. PPPIOCNEWUNIT ioctl allows to specify own ppp unit id which will kernel assign to ppp interface, in case this ppp id is not already used by other ppp interface. In case user does not specify ppp unit id then kernel choose the first free ppp unit id. This applies also for case when creating ppp interface via rtnl method as it does not provide a way for specifying own ppp unit id. If some network interface (does not have to be ppp) has name "ppp" with this first free ppp id then PPPIOCNEWUNIT ioctl or rtnl call fails. And registering new ppp interface is not possible anymore, until interface which holds conflicting name is renamed. Or when using rtnl method with custom interface name in IFLA_IFNAME. As list of allocated / used ppp unit ids is not possible to retrieve from kernel to userspace, userspace has no idea what happens nor which interface is doing this conflict. So change the algorithm how ppp unit id is generated. And choose the first number which is not neither used as ppp unit id nor in some network interface with pattern "ppp". This issue can be simply reproduced by following pppd call when there is no ppp interface registered and also no interface with name pattern "ppp": pppd ifname ppp1 +ipv6 noip noauth nolock local nodetach pty "pppd +ipv6 noip noauth nolock local nodetach notty" Or by creating the one ppp interface (which gets assigned ppp unit id 0), renaming it to "ppp1" and then trying to create a new ppp interface (which will always fails as next free ppp unit id is 1, but network interface with name "ppp1" exists). This patch fixes above described issue by generating new and new ppp unit id until some non-conflicting id with network interfaces is generated. Signed-off-by: Pali Rohár Cc: stable@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index b2b35ec37702..7a099c37527f 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -284,7 +284,7 @@ static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); -static int unit_get(struct idr *p, void *ptr); +static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); @@ -1155,9 +1155,20 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { - ret = unit_get(&pn->units_idr, ppp); + ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; + if (!ifname_is_set) { + while (1) { + snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); + if (!__dev_get_by_name(ppp->ppp_net, ppp->dev->name)) + break; + unit_put(&pn->units_idr, ret); + ret = unit_get(&pn->units_idr, ppp, ret + 1); + if (ret < 0) + goto err; + } + } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST @@ -3552,9 +3563,9 @@ static int unit_set(struct idr *p, void *ptr, int n) } /* get new free unit number and associate pointer with it */ -static int unit_get(struct idr *p, void *ptr) +static int unit_get(struct idr *p, void *ptr, int min) { - return idr_alloc(p, ptr, 0, 0, GFP_KERNEL); + return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ From 36a21d51725af2ce0700c6ebcb6b9594aac658a6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 Aug 2021 13:49:31 -0700 Subject: [PATCH 1320/1469] Linux 5.14-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9ca176ff1e40..eae1314a5b86 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Opossums on Parade # *DOCUMENTATION* From ef98eb0409c31c39ab55ff46b2721c3b4f84c122 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sat, 7 Aug 2021 17:13:41 -0700 Subject: [PATCH 1321/1469] io_uring: clear TIF_NOTIFY_SIGNAL when running task work When using SQPOLL, the submission queue polling thread calls task_work_run() to run queued work. However, when work is added with TWA_SIGNAL - as done by io_uring itself - the TIF_NOTIFY_SIGNAL remains set afterwards and is never cleared. Consequently, when the submission queue polling thread checks whether signal_pending(), it may always find a pending signal, if task_work_add() was ever called before. The impact of this bug might be different on different kernel versions. It appears that on 5.14 it would only cause unnecessary calculation and prevent the polling thread from sleeping. On 5.13, where the bug was found, it stops the polling thread from finding newly submitted work. Instead of task_work_run(), use tracehook_notify_signal() that clears TIF_NOTIFY_SIGNAL. Test for TIF_NOTIFY_SIGNAL in addition to current->task_works to avoid a race in which task_works is cleared but the TIF_NOTIFY_SIGNAL is set. Fixes: 685fe7feedb96 ("io-wq: eliminate the need for a manager thread") Cc: Jens Axboe Cc: Pavel Begunkov Signed-off-by: Nadav Amit Link: https://lore.kernel.org/r/20210808001342.964634-2-namit@vmware.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index bf548af0426c..1093df3977b8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,6 +78,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -2222,9 +2223,9 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { - if (current->task_works) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); - task_work_run(); + tracehook_notify_signal(); return true; } From 20c0b380f971e7d48f5d978bc27d827f7eabb21a Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sat, 7 Aug 2021 17:13:42 -0700 Subject: [PATCH 1322/1469] io_uring: Use WRITE_ONCE() when writing to sq_flags The compiler should be forbidden from any strange optimization for async writes to user visible data-structures. Without proper protection, the compiler can cause write-tearing or invent writes that would confuse the userspace. However, there are writes to sq_flags which are not protected by WRITE_ONCE(). Use WRITE_ONCE() for these writes. This is purely a theoretical issue. Presumably, any compiler is very unlikely to do such optimizations. Fixes: 75b28affdd6a ("io_uring: allocate the two rings together") Cc: Jens Axboe Cc: Pavel Begunkov Signed-off-by: Nadav Amit Link: https://lore.kernel.org/r/20210808001342.964634-3-namit@vmware.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 1093df3977b8..ca064486cb41 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1500,7 +1500,8 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { clear_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } if (posted) @@ -1579,7 +1580,9 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, } if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; @@ -6804,14 +6807,16 @@ static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } From dc0dc8a73e8e4dc33fba93dfe23356cc5a500c57 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 8 Aug 2021 09:01:16 +0200 Subject: [PATCH 1323/1469] ALSA: pcm: Fix mmap breakage without explicit buffer setup The recent fix c4824ae7db41 ("ALSA: pcm: Fix mmap capability check") restricts the mmap capability only to the drivers that properly set up the buffers, but it caused a regression for a few drivers that manage the buffer on its own way. For those with UNKNOWN buffer type (i.e. the uninitialized / unused substream->dma_buffer), just assume that the driver handles the mmap properly and blindly trust the hardware info bit. Fixes: c4824ae7db41 ("ALSA: pcm: Fix mmap capability check") Reported-and-tested-by: Jeff Woods Cc: Link: https://lore.kernel.org/r/s5him0gpghv.wl-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 09c0e2a6489c..71323d807dbf 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -251,7 +251,10 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) switch (substream->dma_buffer.dev.type) { case SNDRV_DMA_TYPE_UNKNOWN: - return false; + /* we can't know the device, so just assume that the driver does + * everything right + */ + return true; case SNDRV_DMA_TYPE_CONTINUOUS: case SNDRV_DMA_TYPE_VMALLOC: return true; From 43e8f76006592cb1573a959aa287c45421066f9c Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Mon, 9 Aug 2021 10:36:58 +0800 Subject: [PATCH 1324/1469] powerpc/kprobes: Fix kprobe Oops happens in booke When using kprobe on powerpc booke series processor, Oops happens as show bellow: / # echo "p:myprobe do_nanosleep" > /sys/kernel/debug/tracing/kprobe_events / # echo 1 > /sys/kernel/debug/tracing/events/kprobes/myprobe/enable / # sleep 1 [ 50.076730] Oops: Exception in kernel mode, sig: 5 [#1] [ 50.077017] BE PAGE_SIZE=4K SMP NR_CPUS=24 QEMU e500 [ 50.077221] Modules linked in: [ 50.077462] CPU: 0 PID: 77 Comm: sleep Not tainted 5.14.0-rc4-00022-g251a1524293d #21 [ 50.077887] NIP: c0b9c4e0 LR: c00ebecc CTR: 00000000 [ 50.078067] REGS: c3883de0 TRAP: 0700 Not tainted (5.14.0-rc4-00022-g251a1524293d) [ 50.078349] MSR: 00029000 CR: 24000228 XER: 20000000 [ 50.078675] [ 50.078675] GPR00: c00ebdf0 c3883e90 c313e300 c3883ea0 00000001 00000000 c3883ecc 00000001 [ 50.078675] GPR08: c100598c c00ea250 00000004 00000000 24000222 102490c2 bff4180c 101e60d4 [ 50.078675] GPR16: 00000000 102454ac 00000040 10240000 10241100 102410f8 10240000 00500000 [ 50.078675] GPR24: 00000002 00000000 c3883ea0 00000001 00000000 0000c350 3b9b8d50 00000000 [ 50.080151] NIP [c0b9c4e0] do_nanosleep+0x0/0x190 [ 50.080352] LR [c00ebecc] hrtimer_nanosleep+0x14c/0x1e0 [ 50.080638] Call Trace: [ 50.080801] [c3883e90] [c00ebdf0] hrtimer_nanosleep+0x70/0x1e0 (unreliable) [ 50.081110] [c3883f00] [c00ec004] sys_nanosleep_time32+0xa4/0x110 [ 50.081336] [c3883f40] [c001509c] ret_from_syscall+0x0/0x28 [ 50.081541] --- interrupt: c00 at 0x100a4d08 [ 50.081749] NIP: 100a4d08 LR: 101b5234 CTR: 00000003 [ 50.081931] REGS: c3883f50 TRAP: 0c00 Not tainted (5.14.0-rc4-00022-g251a1524293d) [ 50.082183] MSR: 0002f902 CR: 24000222 XER: 00000000 [ 50.082457] [ 50.082457] GPR00: 000000a2 bf980040 1024b4d0 bf980084 bf980084 64000000 00555345 fefefeff [ 50.082457] GPR08: 7f7f7f7f 101e0000 00000069 00000003 28000422 102490c2 bff4180c 101e60d4 [ 50.082457] GPR16: 00000000 102454ac 00000040 10240000 10241100 102410f8 10240000 00500000 [ 50.082457] GPR24: 00000002 bf9803f4 10240000 00000000 00000000 100039e0 00000000 102444e8 [ 50.083789] NIP [100a4d08] 0x100a4d08 [ 50.083917] LR [101b5234] 0x101b5234 [ 50.084042] --- interrupt: c00 [ 50.084238] Instruction dump: [ 50.084483] 4bfffc40 60000000 60000000 60000000 9421fff0 39400402 914200c0 38210010 [ 50.084841] 4bfffc20 00000000 00000000 00000000 <7fe00008> 7c0802a6 7c892378 93c10048 [ 50.085487] ---[ end trace f6fffe98e2fa8f3e ]--- [ 50.085678] Trace/breakpoint trap There is no real mode for booke arch and the MMU translation is always on. The corresponding MSR_IS/MSR_DS bit in booke is used to switch the address space, but not for real mode judgment. Fixes: 21f8b2fa3ca5 ("powerpc/kprobes: Ignore traps that happened in real mode") Signed-off-by: Pu Lehui Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210809023658.218915-1-pulehui@huawei.com --- arch/powerpc/kernel/kprobes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index cbc28d1a2e1b..7a7cd6bda53e 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -292,7 +292,8 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; - if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + if (!IS_ENABLED(CONFIG_BOOKE) && + (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))) return 0; /* From 699aa57b35672c3b2f230e2b7e5d0ab8c2bde80a Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 6 Aug 2021 12:40:56 +0800 Subject: [PATCH 1325/1469] drm/i915/gvt: Fix cached atomics setting for Windows VM We've seen recent regression with host and windows VM running simultaneously that cause gpu hang or even crash. Finally bisect to commit 58586680ffad ("drm/i915: Disable atomics in L3 for gen9"), which seems cached atomics behavior difference caused regression issue. This tries to add new scratch register handler and add those in mmio save/restore list for context switch. No gpu hang produced with this one. Cc: stable@vger.kernel.org # 5.12+ Cc: "Xu, Terrence" Cc: "Bloomfield, Jon" Cc: "Ekstrand, Jason" Reviewed-by: Colin Xu Fixes: 58586680ffad ("drm/i915: Disable atomics in L3 for gen9") Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20210806044056.648016-1-zhenyuw@linux.intel.com --- drivers/gpu/drm/i915/gvt/handlers.c | 1 + drivers/gpu/drm/i915/gvt/mmio_context.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 2358c92733b0..55611c7dbcec 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -3149,6 +3149,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0xb100), D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0xb10c), D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_D(_MMIO(0xb110), D_BDW); + MMIO_D(GEN9_SCRATCH_LNCF1, D_BDW_PLUS); MMIO_F(_MMIO(0x24d0), 48, F_CMD_ACCESS | F_CMD_WRITE_PATCH, 0, 0, D_BDW_PLUS, NULL, force_nonpriv_write); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index c9589e26af93..ac24adc320d3 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -105,6 +105,8 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */ {RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */ {RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */ + {RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */ + {RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */ {RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */ {RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */ {RCS0, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */ From 86aab09a4870bb8346c9579864588c3d7f555299 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 8 Aug 2021 16:04:40 -0700 Subject: [PATCH 1326/1469] dccp: add do-while-0 stubs for dccp_pr_debug macros GCC complains about empty macros in an 'if' statement, so convert them to 'do {} while (0)' macros. Fixes these build warnings: net/dccp/output.c: In function 'dccp_xmit_packet': ../net/dccp/output.c:283:71: warning: suggest braces around empty body in an 'if' statement [-Wempty-body] 283 | dccp_pr_debug("transmit_skb() returned err=%d\n", err); net/dccp/ackvec.c: In function 'dccp_ackvec_update_old': ../net/dccp/ackvec.c:163:80: warning: suggest braces around empty body in an 'else' statement [-Wempty-body] 163 | (unsigned long long)seqno, state); Fixes: dc841e30eaea ("dccp: Extend CCID packet dequeueing interface") Fixes: 380240864451 ("dccp ccid-2: Update code for the Ack Vector input/registration routine") Signed-off-by: Randy Dunlap Cc: dccp@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Gerrit Renker Signed-off-by: David S. Miller --- net/dccp/dccp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9cc9d1ee6cdb..c5c1d2b8045e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -41,9 +41,9 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; From 0fa32ca438b42fadfb293d72690e117ab3d67489 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 6 Aug 2021 09:39:07 +0800 Subject: [PATCH 1327/1469] page_pool: mask the page->signature before the checking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As mentioned in commit c07aea3ef4d4 ("mm: add a signature in struct page"): "The page->signature field is aliased to page->lru.next and page->compound_head." And as the comment in page_is_pfmemalloc(): "lru.next has bit 1 set if the page is allocated from the pfmemalloc reserves. Callers may simply overwrite it if they do not need to preserve that information." The page->signature is OR’ed with PP_SIGNATURE when a page is allocated in page pool, see __page_pool_alloc_pages_slow(), and page->signature is checked directly with PP_SIGNATURE in page_pool_return_skb_page(), which might cause resoure leaking problem for a page from page pool if bit 1 of lru.next is set for a pfmemalloc page. What happens here is that the original pp->signature is OR'ed with PP_SIGNATURE after the allocation in order to preserve any existing bits(such as the bit 1, used to indicate a pfmemalloc page), so when those bits are present, those page is not considered to be from page pool and the DMA mapping of those pages will be left stale. As bit 0 is for page->compound_head, So mask both bit 0/1 before the checking in page_pool_return_skb_page(). And we will return those pfmemalloc pages back to the page allocator after cleaning up the DMA mapping. Fixes: 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling") Reviewed-by: Ilias Apalodimas Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- net/core/page_pool.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45b139c..8ab7b402244c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -634,7 +634,15 @@ bool page_pool_return_skb_page(struct page *page) struct page_pool *pp; page = compound_head(page); - if (unlikely(page->pp_magic != PP_SIGNATURE)) + + /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation + * in order to preserve any existing bits, such as bit 0 for the + * head page of compound page and bit 1 for pfmemalloc page, so + * mask those bits for freeing side when doing below checking, + * and page_is_pfmemalloc() is checked in __page_pool_put_page() + * to avoid recycling the pfmemalloc page. + */ + if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) return false; pp = page->pp; From acc68b8d2a1196c4db806947606f162dbeed2274 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 5 Aug 2021 17:55:11 +0300 Subject: [PATCH 1328/1469] net: ethernet: ti: cpsw: fix min eth packet size for non-switch use-cases The CPSW switchdev driver inherited fix from commit 9421c9015047 ("net: ethernet: ti: cpsw: fix min eth packet size") which changes min TX packet size to 64bytes (VLAN_ETH_ZLEN, excluding ETH_FCS). It was done to fix HW packed drop issue when packets are sent from Host to the port with PVID and un-tagging enabled. Unfortunately this breaks some other non-switch specific use-cases, like: - [1] CPSW port as DSA CPU port with DSA-tag applied at the end of the packet - [2] Some industrial protocols, which expects min TX packet size 60Bytes (excluding FCS). Fix it by configuring min TX packet size depending on driver mode - 60Bytes (ETH_ZLEN) for multi mac (dual-mac) mode - 64Bytes (VLAN_ETH_ZLEN) for switch mode and update it during driver mode change and annotate with READ_ONCE()/WRITE_ONCE() as it can be read by napi while writing. [1] https://lore.kernel.org/netdev/20210531124051.GA15218@cephalopod/ [2] https://e2e.ti.com/support/arm/sitara_arm/f/791/t/701669 Cc: stable@vger.kernel.org Fixes: ed3525eda4c4 ("net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac") Reported-by: Ben Hutchings Signed-off-by: Grygorii Strashko Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw_new.c | 7 +++++-- drivers/net/ethernet/ti/cpsw_priv.h | 4 +++- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 57d279fdcc9f..d1d02001cef6 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -920,7 +920,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, struct cpdma_chan *txch; int ret, q_idx; - if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) { + if (skb_put_padto(skb, READ_ONCE(priv->tx_packet_min))) { cpsw_err(priv, tx_err, "packet pad failed\n"); ndev->stats.tx_dropped++; return NET_XMIT_DROP; @@ -1100,7 +1100,7 @@ static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n, for (i = 0; i < n; i++) { xdpf = frames[i]; - if (xdpf->len < CPSW_MIN_PACKET_SIZE) + if (xdpf->len < READ_ONCE(priv->tx_packet_min)) break; if (cpsw_xdp_tx_frame(priv, xdpf, NULL, priv->emac_port)) @@ -1389,6 +1389,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) priv->dev = dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = i + 1; + priv->tx_packet_min = CPSW_MIN_PACKET_SIZE; if (is_valid_ether_addr(slave_data->mac_addr)) { ether_addr_copy(priv->mac_addr, slave_data->mac_addr); @@ -1686,6 +1687,7 @@ static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, priv = netdev_priv(sl_ndev); slave->port_vlan = vlan; + WRITE_ONCE(priv->tx_packet_min, CPSW_MIN_PACKET_SIZE_VLAN); if (netif_running(sl_ndev)) cpsw_port_add_switch_def_ale_entries(priv, slave); @@ -1714,6 +1716,7 @@ static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, priv = netdev_priv(slave->ndev); slave->port_vlan = slave->data->dual_emac_res_vlan; + WRITE_ONCE(priv->tx_packet_min, CPSW_MIN_PACKET_SIZE); cpsw_port_add_dual_emac_def_ale_entries(priv, slave); } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index a323bea54faa..2951fb7b9dae 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -89,7 +89,8 @@ do { \ #define CPSW_POLL_WEIGHT 64 #define CPSW_RX_VLAN_ENCAP_HDR_SIZE 4 -#define CPSW_MIN_PACKET_SIZE (VLAN_ETH_ZLEN) +#define CPSW_MIN_PACKET_SIZE_VLAN (VLAN_ETH_ZLEN) +#define CPSW_MIN_PACKET_SIZE (ETH_ZLEN) #define CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN +\ ETH_FCS_LEN +\ CPSW_RX_VLAN_ENCAP_HDR_SIZE) @@ -380,6 +381,7 @@ struct cpsw_priv { u32 emac_port; struct cpsw_common *cpsw; int offload_fwd_mark; + u32 tx_packet_min; }; #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw) From 8f3d65c166797746455553f4eaf74a5f89f996d4 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Mon, 9 Aug 2021 11:05:56 +0200 Subject: [PATCH 1329/1469] net/smc: fix wait on already cleared link There can be a race between the waiters for a tx work request buffer and the link down processing that finally clears the link. Although all waiters are woken up before the link is cleared there might be waiters which did not yet get back control and are still waiting. This results in an access to a cleared wait queue head. Fix this by introducing atomic reference counting around the wait calls, and wait with the link clear processing until all waiters have finished. Move the work request layer related calls into smc_wr.c and set the link state to INACTIVE before calling smcr_link_clear() in smc_llc_srv_add_link(). Fixes: 15e1b99aadfb ("net/smc: no WR buffer wait for terminating link group") Signed-off-by: Karsten Graul Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- net/smc/smc_core.h | 2 ++ net/smc/smc_llc.c | 10 ++++------ net/smc/smc_tx.c | 18 +++++++++++++++++- net/smc/smc_wr.c | 10 ++++++++++ 4 files changed, 33 insertions(+), 7 deletions(-) diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 6d6fd1397c87..64d86298e4df 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -97,6 +97,7 @@ struct smc_link { unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ + atomic_t wr_tx_refcnt; /* tx refs to link */ struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ @@ -109,6 +110,7 @@ struct smc_link { struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ + atomic_t wr_reg_refcnt; /* reg refs to link */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 273eaf1bfe49..2e7560eba981 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -888,6 +888,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (!rc) goto out; out_clear_lnk: + lnk_new->state = SMC_LNK_INACTIVE; smcr_link_clear(lnk_new, false); out_reject: smc_llc_cli_add_link_reject(qentry); @@ -1184,6 +1185,7 @@ int smc_llc_srv_add_link(struct smc_link *link) goto out_err; return 0; out_err: + link_new->state = SMC_LNK_INACTIVE; smcr_link_clear(link_new, false); return rc; } @@ -1286,10 +1288,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) del_llc->reason = 0; smc_llc_send_message(lnk, &qentry->msg); /* response */ - if (smc_link_downing(&lnk_del->state)) { - if (smc_switch_conns(lgr, lnk_del, false)) - smc_wr_tx_wait_no_pending_sends(lnk_del); - } + if (smc_link_downing(&lnk_del->state)) + smc_switch_conns(lgr, lnk_del, false); smcr_link_clear(lnk_del, true); active_links = smc_llc_active_link_count(lgr); @@ -1805,8 +1805,6 @@ void smc_llc_link_clear(struct smc_link *link, bool log) link->smcibdev->ibdev->name, link->ibport); complete(&link->llc_testlink_resp); cancel_delayed_work_sync(&link->llc_testlink_wrk); - smc_wr_wakeup_reg_wait(link); - smc_wr_wakeup_tx_wait(link); } /* register a new rtoken at the remote peer (for all links) */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 289025cd545a..c79361dfcdfb 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; @@ -550,6 +550,22 @@ out_unlock: return rc; } +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + struct smc_link *link = conn->lnk; + int rc = -ENOLINK; + + if (!link) + return rc; + + atomic_inc(&link->wr_tx_refcnt); + if (smc_link_usable(link)) + rc = _smcr_tx_sndbuf_nonempty(conn); + if (atomic_dec_and_test(&link->wr_tx_refcnt)) + wake_up_all(&link->wr_tx_wait); + return rc; +} + static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index cbc73a7e4d59..a419e9af36b9 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -322,9 +322,12 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) if (rc) return rc; + atomic_inc(&link->wr_reg_refcnt); rc = wait_event_interruptible_timeout(link->wr_reg_wait, (link->wr_reg_state != POSTED), SMC_WR_REG_MR_WAIT_TIME); + if (atomic_dec_and_test(&link->wr_reg_refcnt)) + wake_up_all(&link->wr_reg_wait); if (!rc) { /* timeout - terminate link */ smcr_link_down_cond_sched(link); @@ -566,10 +569,15 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev; + smc_wr_wakeup_reg_wait(lnk); + smc_wr_wakeup_tx_wait(lnk); + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); + wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt))); + wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt))); if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, @@ -728,7 +736,9 @@ int smc_wr_create_link(struct smc_link *lnk) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); init_waitqueue_head(&lnk->wr_tx_wait); + atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); + atomic_set(&lnk->wr_reg_refcnt, 0); return rc; dma_unmap: From 64513d269e8971aabb7e787955a1b320e3031306 Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Mon, 9 Aug 2021 11:05:57 +0200 Subject: [PATCH 1330/1469] net/smc: Correct smc link connection counter in case of smc client SMC clients may be assigned to a different link after the initial connection between two peers was established. In such a case, the connection counter was not correctly set. Update the connection counter correctly when a smc client connection is assigned to a different smc link. Fixes: 07d51580ff65 ("net/smc: Add connection counters for links") Signed-off-by: Guvenc Gulce Tested-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 2 +- net/smc/smc_core.c | 4 ++-- net/smc/smc_core.h | 2 ++ 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 898389611ae8..c038efc23ce3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -795,7 +795,7 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_NOSRVLINK; goto connect_abort; } - smc->conn.lnk = link; + smc_switch_link_and_count(&smc->conn, link); } /* create send buffer and rmb */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index cd0d7c908b2a..c160ff50c053 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -917,8 +917,8 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, return rc; } -static void smc_switch_link_and_count(struct smc_connection *conn, - struct smc_link *to_lnk) +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); conn->lnk = to_lnk; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 64d86298e4df..c043ecdca5c4 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -446,6 +446,8 @@ void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); From d09c548dbf3b31cb07bba562e0f452edfa01efe3 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 9 Aug 2021 15:04:55 +0800 Subject: [PATCH 1331/1469] net: sched: act_mirred: Reset ct info when mirror/redirect skb When mirror/redirect a skb to a different port, the ct info should be reset for reclassification. Or the pkts will match unexpected rules. For example, with following topology and commands: ----------- | veth0 -+------- | veth1 -+------- | ------------ tc qdisc add dev veth0 clsact # The same with "action mirred egress mirror dev veth1" or "action mirred ingress redirect dev veth1" tc filter add dev veth0 egress chain 1 protocol ip flower ct_state +trk action mirred ingress mirror dev veth1 tc filter add dev veth0 egress chain 0 protocol ip flower ct_state -inv action ct commit action goto chain 1 tc qdisc add dev veth1 clsact tc filter add dev veth1 ingress chain 0 protocol ip flower ct_state +trk action drop ping & tc -s filter show dev veth1 ingress With command 'tc -s filter show', we can find the pkts were dropped on veth1. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: Roi Dayan Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/sched/act_mirred.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 7153c67f641e..2ef4cd2c848b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -273,6 +273,9 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + /* All mirred/redirected skbs should clear previous ct info */ + nf_reset_ct(skb2); + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); expects_nh = want_ingress || !m_mac_header_xmit; From 769f52676756b8c5feb302d2d95af59577fc69ec Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 4 Aug 2021 21:35:01 -0700 Subject: [PATCH 1332/1469] configfs: restore the kernel v5.13 text attribute write behavior Instead of appending new text attribute data at the offset specified by the write() system call, only pass the newly written data to the .store() callback. Reported-by: Bodo Stroesser Tested-by: Bodo Stroesser Signed-off-by: Bart Van Assche Signed-off-by: Christoph Hellwig --- fs/configfs/file.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 5a0be9985bae..0ad32150611e 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -177,28 +177,22 @@ out: return retval; } -/* Fill [buffer, buffer + pos) with data coming from @from. */ -static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos, +/* Fill @buffer with data coming from @from. */ +static int fill_write_buffer(struct configfs_buffer *buffer, struct iov_iter *from) { - loff_t to_copy; int copied; - u8 *to; if (!buffer->page) buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); if (!buffer->page) return -ENOMEM; - to_copy = SIMPLE_ATTR_SIZE - 1 - pos; - if (to_copy <= 0) - return 0; - to = buffer->page + pos; - copied = copy_from_iter(to, to_copy, from); + copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, * so e.g. sscanf() can scan the string easily */ - to[copied] = 0; + buffer->page[copied] = 0; return copied ? : -EFAULT; } @@ -227,10 +221,10 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct configfs_buffer *buffer = file->private_data; - ssize_t len; + int len; mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, iocb->ki_pos, from); + len = fill_write_buffer(buffer, from); if (len > 0) len = flush_write_buffer(file, buffer, len); if (len > 0) From 50ac7479846053ca8054be833c1594e64de496bb Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Wed, 28 Jul 2021 12:39:10 -0700 Subject: [PATCH 1333/1469] ice: Prevent probing virtual functions The userspace utility "driverctl" can be used to change/override the system's default driver choices. This is useful in some situations (buggy driver, old driver missing a device ID, trying a workaround, etc.) where the user needs to load a different driver. However, this is also prone to user error, where a driver is mapped to a device it's not designed to drive. For example, if the ice driver is mapped to driver iavf devices, the ice driver crashes. Add a check to return an error if the ice driver is being used to probe a virtual function. Fixes: 837f08fdecbe ("ice: Add basic driver framework for Intel(R) E800 Series") Signed-off-by: Anirudh Venkataramanan Tested-by: Gurucharan G Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ef8d1815af56..a9506041eb42 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4194,6 +4194,11 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) struct ice_hw *hw; int i, err; + if (pdev->is_virtfn) { + dev_err(dev, "can't probe a virtual function\n"); + return -EINVAL; + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ From c503e63200c679e362afca7aca9d3dc63a0f45ed Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Wed, 4 Aug 2021 12:12:42 -0700 Subject: [PATCH 1334/1469] ice: Stop processing VF messages during teardown When VFs are setup and torn down in quick succession, it is possible that a VF is torn down by the PF while the VF's virtchnl requests are still in the PF's mailbox ring. Processing the VF's virtchnl request when the VF itself doesn't exist results in undefined behavior. Fix this by adding a check to stop processing virtchnl requests when VF teardown is in progress. Fixes: ddf30f7ff840 ("ice: Add handler to configure SR-IOV") Signed-off-by: Anirudh Venkataramanan Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index a450343fbb92..eadcb9958346 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -234,6 +234,7 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, + ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 2826570dab51..e93430ab37f1 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -615,6 +615,8 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i; + set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); + if (!pf->vf) return; @@ -680,6 +682,7 @@ void ice_free_vfs(struct ice_pf *pf) i); clear_bit(ICE_VF_DIS, pf->state); + clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -4415,6 +4418,10 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) struct device *dev; int err = 0; + /* if de-init is underway, don't process messages from VF */ + if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) + return; + dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL; From 3ba7f53f8bf1fb862e36c7f74434ac3aceb60158 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 6 Aug 2021 09:51:27 -0700 Subject: [PATCH 1335/1469] ice: don't remove netdev->dev_addr from uc sync list In some circumstances, such as with bridging, it's possible that the stack will add the device's own MAC address to its unicast address list. If, later, the stack deletes this address, the driver will receive a request to remove this address. The driver stores its current MAC address as part of the VSI MAC filter list instead of separately. So, this causes a problem when the device's MAC address is deleted unexpectedly, which results in traffic failure in some cases. The following configuration steps will reproduce the previously mentioned problem: > ip link set eth0 up > ip link add dev br0 type bridge > ip link set br0 up > ip addr flush dev eth0 > ip link set eth0 master br0 > echo 1 > /sys/class/net/br0/bridge/vlan_filtering > modprobe -r veth > modprobe -r bridge > ip addr add 192.168.1.100/24 dev eth0 The following ping command fails due to the netdev->dev_addr being deleted when removing the bridge module. > ping Fix this by making sure to not delete the netdev->dev_addr during MAC address sync. After fixing this issue it was noticed that the netdev_warn() in .set_mac was overly verbose, so make it at netdev_dbg(). Also, there is a possibility of a race condition between .set_mac and .set_rx_mode. Fix this by calling netif_addr_lock_bh() and netif_addr_unlock_bh() on the device's netdev when the netdev->dev_addr is going to be updated in .set_mac. Fixes: e94d44786693 ("ice: Implement filter sync, NDO operations and bump version") Signed-off-by: Brett Creeley Tested-by: Liang Li Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a9506041eb42..fe2ded775f25 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -191,6 +191,14 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + /* Under some circumstances, we might receive a request to delete our + * own device address from our uc list. Because we store the device + * address in the VSI's MAC filter list, we need to ignore such + * requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + if (ice_fltr_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr, ICE_FWD_TO_VSI)) return -EINVAL; @@ -5124,7 +5132,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return -EADDRNOTAVAIL; if (ether_addr_equal(netdev->dev_addr, mac)) { - netdev_warn(netdev, "already using mac %pM\n", mac); + netdev_dbg(netdev, "already using mac %pM\n", mac); return 0; } @@ -5135,6 +5143,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return -EBUSY; } + netif_addr_lock_bh(netdev); /* Clean up old MAC filter. Not an error if old filter doesn't exist */ status = ice_fltr_remove_mac(vsi, netdev->dev_addr, ICE_FWD_TO_VSI); if (status && status != ICE_ERR_DOES_NOT_EXIST) { @@ -5144,30 +5153,28 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (status == ICE_ERR_ALREADY_EXISTS) { + if (status == ICE_ERR_ALREADY_EXISTS) /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ - memcpy(netdev->dev_addr, mac, netdev->addr_len); netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - return 0; - } - - /* error if the new filter addition failed */ - if (status) + else if (status) + /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; err_update_filters: if (err) { netdev_err(netdev, "can't set MAC %pM. filter update failed\n", mac); + netif_addr_unlock_bh(netdev); return err; } /* change the netdev's MAC address */ memcpy(netdev->dev_addr, mac, netdev->addr_len); + netif_addr_unlock_bh(netdev); netdev_dbg(vsi->netdev, "updated MAC address to %pM\n", netdev->dev_addr); From a7550f8b1c9712894f9e98d6caf5f49451ebd058 Mon Sep 17 00:00:00 2001 From: Md Fahad Iqbal Polash Date: Fri, 4 Jun 2021 09:53:33 -0700 Subject: [PATCH 1336/1469] iavf: Set RSS LUT and key in reset handle path iavf driver should set RSS LUT and key unconditionally in reset path. Currently, the driver does not do that. This patch fixes this issue. Fixes: 2c86ac3c7079 ("i40evf: create a generic config RSS function") Signed-off-by: Md Fahad Iqbal Polash Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 44bafedd09f2..244ec74ceca7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1506,11 +1506,6 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_map_rings_to_vectors(adapter); - - if (RSS_AQ(adapter)) - adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; - else - err = iavf_init_rss(adapter); err: return err; } @@ -2200,6 +2195,14 @@ continue_reset: goto reset_err; } + if (RSS_AQ(adapter)) { + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; + } else { + err = iavf_init_rss(adapter); + if (err) + goto reset_err; + } + adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; From 71330842ff93ae67a066c1fa68d75672527312fa Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 9 Aug 2021 21:45:32 +0200 Subject: [PATCH 1337/1469] bpf: Add _kernel suffix to internal lockdown_bpf_read Rename LOCKDOWN_BPF_READ into LOCKDOWN_BPF_READ_KERNEL so we have naming more consistent with a LOCKDOWN_BPF_WRITE_USER option that we are adding. Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko --- include/linux/security.h | 2 +- kernel/bpf/helpers.c | 4 ++-- kernel/trace/bpf_trace.c | 8 ++++---- security/security.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/linux/security.h b/include/linux/security.h index 24eda04221e9..724d7a4a0c91 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -123,7 +123,7 @@ enum lockdown_reason { LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, - LOCKDOWN_BPF_READ, + LOCKDOWN_BPF_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62cf00383910..0b04553e8c44 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1070,12 +1070,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b4916ef388ad..1836591197a5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -999,19 +999,19 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS diff --git a/security/security.c b/security/security.c index 09533cbb7221..6b83ab4e9d66 100644 --- a/security/security.c +++ b/security/security.c @@ -61,7 +61,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", - [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", + [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", From f153c2246783ba210493054d99c66353f56423c9 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 30 Jul 2021 08:28:54 +0200 Subject: [PATCH 1338/1469] ucounts: add missing data type changes commit f9c82a4ea89c3 ("Increase size of ucounts to atomic_long_t") changed the data type of ucounts/ucounts_max to long, but missed to adjust a few other places. This is noticeable on big endian platforms from user space because the /proc/sys/user/max_*_names files all contain 0. v4 - Made the min and max constants long so the sysctl values are actually settable on little endian machines. -- EWB Fixes: f9c82a4ea89c ("Increase size of ucounts to atomic_long_t") Signed-off-by: Sven Schnelle Tested-by: Nathan Chancellor Tested-by: Linux Kernel Functional Testing Acked-by: Alexey Gladkov v1: https://lkml.kernel.org/r/20210721115800.910778-1-svens@linux.ibm.com v2: https://lkml.kernel.org/r/20210721125233.1041429-1-svens@linux.ibm.com v3: https://lkml.kernel.org/r/20210730062854.3601635-1-svens@linux.ibm.com Link: https://lkml.kernel.org/r/8735rijqlv.fsf_-_@disp2133 Signed-off-by: Eric W. Biederman --- fs/notify/fanotify/fanotify_user.c | 17 +++++++++++------ fs/notify/inotify/inotify_user.c | 17 +++++++++++------ kernel/ucount.c | 19 +++++++++++-------- 3 files changed, 33 insertions(+), 20 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 64864fb40b40..28b67cb9458d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -54,22 +54,27 @@ static int fanotify_max_queued_events __read_mostly; #include +static long ft_zero = 0; +static long ft_int_max = INT_MAX; + struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &ft_zero, + .extra2 = &ft_int_max, }, { .procname = "max_user_marks", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &ft_zero, + .extra2 = &ft_int_max, }, { .procname = "max_queued_events", diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 98f61b31745a..62051247f6d2 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -55,22 +55,27 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly; #include +static long it_zero = 0; +static long it_int_max = INT_MAX; + struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &it_zero, + .extra2 = &it_int_max, }, { .procname = "max_user_watches", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &it_zero, + .extra2 = &it_int_max, }, { .procname = "max_queued_events", diff --git a/kernel/ucount.c b/kernel/ucount.c index 77be3bbe3cc4..bb51849e6375 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -58,14 +58,17 @@ static struct ctl_table_root set_root = { .permissions = set_permissions, }; -#define UCOUNT_ENTRY(name) \ - { \ - .procname = name, \ - .maxlen = sizeof(int), \ - .mode = 0644, \ - .proc_handler = proc_dointvec_minmax, \ - .extra1 = SYSCTL_ZERO, \ - .extra2 = SYSCTL_INT_MAX, \ +static long ue_zero = 0; +static long ue_int_max = INT_MAX; + +#define UCOUNT_ENTRY(name) \ + { \ + .procname = name, \ + .maxlen = sizeof(long), \ + .mode = 0644, \ + .proc_handler = proc_doulongvec_minmax, \ + .extra1 = &ue_zero, \ + .extra2 = &ue_int_max, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), From 669d94219d91a2ba950bb12ece69cf0ada53ad4f Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 9 Aug 2021 13:04:10 -0700 Subject: [PATCH 1339/1469] MAINTAINERS: update Vineet's email address I'll be leaving Synopsys shortly, but will continue to handle maintenance for the transition period. Signed-off-by: Vineet Gupta --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index c9467d2839f5..bbaecde94aa0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17815,7 +17815,7 @@ F: include/linux/sync_file.h F: include/uapi/linux/sync_file.h SYNOPSYS ARC ARCHITECTURE -M: Vineet Gupta +M: Vineet Gupta L: linux-snps-arc@lists.infradead.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc.git From beb7f2de5728b0bd2140a652fa51f6ad85d159f7 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Sun, 8 Aug 2021 09:52:42 +0300 Subject: [PATCH 1340/1469] psample: Add a fwd declaration for skbuff Without this there is a warning if source files include psample.h before skbuff.h or doesn't include it at all. Fixes: 6ae0a6286171 ("net: Introduce psample, a new genetlink channel for packet sampling") Signed-off-by: Roi Dayan Link: https://lore.kernel.org/r/20210808065242.1522535-1-roid@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/psample.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/net/psample.h b/include/net/psample.h index e328c5127757..0509d2d6be67 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -31,6 +31,8 @@ struct psample_group *psample_group_get(struct net *net, u32 group_num); void psample_group_take(struct psample_group *group); void psample_group_put(struct psample_group *group); +struct sk_buff; + #if IS_ENABLED(CONFIG_PSAMPLE) void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, From d6e712aa7e6a3d5a9633f4bcbe2237f3edc292bd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 8 Aug 2021 12:08:34 -0700 Subject: [PATCH 1341/1469] net: openvswitch: fix kernel-doc warnings in flow.c Repair kernel-doc notation in a few places to make it conform to the expected format. Fixes the following kernel-doc warnings: flow.c:296: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Parse vlan tag from vlan header. flow.c:296: warning: missing initial short description on line: * Parse vlan tag from vlan header. flow.c:537: warning: No description found for return value of 'key_extract_l3l4' flow.c:769: warning: No description found for return value of 'key_extract' Signed-off-by: Randy Dunlap Cc: Pravin B Shelar Cc: dev@openvswitch.org Link: https://lore.kernel.org/r/20210808190834.23362-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski --- net/openvswitch/flow.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e586424d8b04..9713035b89e3 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -293,14 +293,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb) } /** - * Parse vlan tag from vlan header. + * parse_vlan_tag - Parse vlan tag from vlan header. * @skb: skb containing frame to parse * @key_vh: pointer to parsed vlan tag * @untag_vlan: should the vlan header be removed from the frame * - * Returns ERROR on memory error. - * Returns 0 if it encounters a non-vlan or incomplete packet. - * Returns 1 after successfully parsing vlan tag. + * Return: ERROR on memory error. + * %0 if it encounters a non-vlan or incomplete packet. + * %1 after successfully parsing vlan tag. */ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh, bool untag_vlan) @@ -532,6 +532,7 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) * L3 header * @key: output flow key * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { @@ -748,8 +749,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * The caller must ensure that skb->len >= ETH_HLEN. * - * Returns 0 if successful, otherwise a negative errno value. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -764,6 +763,8 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * - skb->protocol: the type of the data starting at skb->network_header. * Equals to key->eth.type. + * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { From 143a8526ab5fd4f8a0c4fe2a9cb28c181dc5a95f Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Aug 2021 17:52:06 +0200 Subject: [PATCH 1342/1469] bareudp: Fix invalid read beyond skb's linear data Data beyond the UDP header might not be part of the skb's linear data. Use skb_copy_bits() instead of direct access to skb->data+X, so that we read the correct bytes even on a fragmented skb. Fixes: 4b5f67232d95 ("net: Special handling for IP & MPLS.") Signed-off-by: Guillaume Nault Link: https://lore.kernel.org/r/7741c46545c6ef02e70c80a9b32814b22d9616b3.1628264975.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/bareudp.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index a7ee0af1af90..54e321a695ce 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -71,12 +71,18 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) family = AF_INET6; if (bareudp->ethertype == htons(ETH_P_IP)) { - struct iphdr *iphdr; + __u8 ipversion; - iphdr = (struct iphdr *)(skb->data + BAREUDP_BASE_HLEN); - if (iphdr->version == 4) { - proto = bareudp->ethertype; - } else if (bareudp->multi_proto_mode && (iphdr->version == 6)) { + if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, + sizeof(ipversion))) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + ipversion >>= 4; + + if (ipversion == 4) { + proto = htons(ETH_P_IP); + } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { bareudp->dev->stats.rx_dropped++; From 4956b9eaad456a88b0d56947bef036e086250beb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Aug 2021 07:49:41 -0600 Subject: [PATCH 1343/1469] io_uring: rsrc ref lock needs to be IRQ safe Nadav reports running into the below splat on re-enabling softirqs: WARNING: CPU: 2 PID: 1777 at kernel/softirq.c:364 __local_bh_enable_ip+0xaa/0xe0 Modules linked in: CPU: 2 PID: 1777 Comm: umem Not tainted 5.13.1+ #161 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/22/2020 RIP: 0010:__local_bh_enable_ip+0xaa/0xe0 Code: a9 00 ff ff 00 74 38 65 ff 0d a2 21 8c 7a e8 ed 1a 20 00 fb 66 0f 1f 44 00 00 5b 41 5c 5d c3 65 8b 05 e6 2d 8c 7a 85 c0 75 9a <0f> 0b eb 96 e8 2d 1f 20 00 eb a5 4c 89 e7 e8 73 4f 0c 00 eb ae 65 RSP: 0018:ffff88812e58fcc8 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: dffffc0000000000 RDX: 0000000000000007 RSI: 0000000000000201 RDI: ffffffff8898c5ac RBP: ffff88812e58fcd8 R08: ffffffff8575dbbf R09: ffffed1028ef14f9 R10: ffff88814778a7c3 R11: ffffed1028ef14f8 R12: ffffffff85c9e9ae R13: ffff88814778a000 R14: ffff88814778a7b0 R15: ffff8881086db890 FS: 00007fbcfee17700(0000) GS:ffff8881e0300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c0402a5008 CR3: 000000011c1ac003 CR4: 00000000003706e0 Call Trace: _raw_spin_unlock_bh+0x31/0x40 io_rsrc_node_ref_zero+0x13e/0x190 io_dismantle_req+0x215/0x220 io_req_complete_post+0x1b8/0x720 __io_complete_rw.isra.0+0x16b/0x1f0 io_complete_rw+0x10/0x20 where it's clear we end up calling the percpu count release directly from the completion path, as it's in atomic mode and we drop the last ref. For file/block IO, this can be from IRQ context already, and the softirq locking for rsrc isn't enough. Just make the lock fully IRQ safe, and ensure we correctly safe state from the release path as we don't know the full context there. Reported-by: Nadav Amit Tested-by: Nadav Amit Link: https://lore.kernel.org/io-uring/C187C836-E78B-4A31-B24C-D16919ACA093@gmail.com/ Signed-off-by: Jens Axboe --- fs/io_uring.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ca064486cb41..6a8257233061 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7138,16 +7138,6 @@ static void **io_alloc_page_table(size_t size) return table; } -static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx) -{ - spin_lock_bh(&ctx->rsrc_ref_lock); -} - -static inline void io_rsrc_ref_unlock(struct io_ring_ctx *ctx) -{ - spin_unlock_bh(&ctx->rsrc_ref_lock); -} - static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) { percpu_ref_exit(&ref_node->refs); @@ -7164,9 +7154,9 @@ static void io_rsrc_node_switch(struct io_ring_ctx *ctx, struct io_rsrc_node *rsrc_node = ctx->rsrc_node; rsrc_node->rsrc_data = data_to_kill; - io_rsrc_ref_lock(ctx); + spin_lock_irq(&ctx->rsrc_ref_lock); list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); - io_rsrc_ref_unlock(ctx); + spin_unlock_irq(&ctx->rsrc_ref_lock); atomic_inc(&data_to_kill->refs); percpu_ref_kill(&rsrc_node->refs); @@ -7674,9 +7664,10 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) { struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; bool first_add = false; - io_rsrc_ref_lock(ctx); + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); node->done = true; while (!list_empty(&ctx->rsrc_ref_list)) { @@ -7688,7 +7679,7 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) list_del(&node->node); first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); } - io_rsrc_ref_unlock(ctx); + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); if (first_add) mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ); From 49e7f0c789add1330b111af0b7caeb0e87df063e Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sun, 8 Aug 2021 21:54:33 +0800 Subject: [PATCH 1344/1469] io-wq: fix bug of creating io-wokers unconditionally The former patch to add check between nr_workers and max_workers has a bug, which will cause unconditionally creating io-workers. That's because the result of the check doesn't affect the call of create_io_worker(), fix it by bringing in a boolean value for it. Fixes: 21698274da5b ("io-wq: fix lack of acct->nr_workers < acct->max_workers judgement") Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210808135434.68667-2-haoxu@linux.alibaba.com [axboe: drop hunk that isn't strictly needed] Signed-off-by: Jens Axboe --- fs/io-wq.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 12fc19353bb0..ac8604a35169 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -282,16 +282,24 @@ static void create_worker_cb(struct callback_head *cb) struct io_wq *wq; struct io_wqe *wqe; struct io_wqe_acct *acct; + bool do_create = false; cwd = container_of(cb, struct create_worker_data, work); wqe = cwd->wqe; wq = wqe->wq; acct = &wqe->acct[cwd->index]; raw_spin_lock_irq(&wqe->lock); - if (acct->nr_workers < acct->max_workers) + if (acct->nr_workers < acct->max_workers) { acct->nr_workers++; + do_create = true; + } raw_spin_unlock_irq(&wqe->lock); - create_io_worker(wq, cwd->wqe, cwd->index); + if (do_create) { + create_io_worker(wq, cwd->wqe, cwd->index); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } kfree(cwd); } From 47cae0c71f7a126903f930191e6e9f103674aca1 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sun, 8 Aug 2021 21:54:34 +0800 Subject: [PATCH 1345/1469] io-wq: fix IO_WORKER_F_FIXED issue in create_io_worker() There may be cases like: A B spin_lock(wqe->lock) nr_workers is 0 nr_workers++ spin_unlock(wqe->lock) spin_lock(wqe->lock) nr_wokers is 1 nr_workers++ spin_unlock(wqe->lock) create_io_worker() acct->worker is 1 create_io_worker() acct->worker is 1 There should be one worker marked IO_WORKER_F_FIXED, but no one is. Fix this by introduce a new agrument for create_io_worker() to indicate if it is the first worker. Fixes: 3d4e4face9c1 ("io-wq: fix no lock protection of acct->nr_worker") Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210808135434.68667-3-haoxu@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index ac8604a35169..7d2ed8c7dd31 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -129,7 +129,7 @@ struct io_cb_cancel_data { bool cancel_all; }; -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first); static void io_wqe_dec_running(struct io_worker *worker); static bool io_worker_get(struct io_worker *worker) @@ -248,18 +248,20 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) rcu_read_unlock(); if (!ret) { - bool do_create = false; + bool do_create = false, first = false; raw_spin_lock_irq(&wqe->lock); if (acct->nr_workers < acct->max_workers) { atomic_inc(&acct->nr_running); atomic_inc(&wqe->wq->worker_refs); + if (!acct->nr_workers) + first = true; acct->nr_workers++; do_create = true; } raw_spin_unlock_irq(&wqe->lock); if (do_create) - create_io_worker(wqe->wq, wqe, acct->index); + create_io_worker(wqe->wq, wqe, acct->index, first); } } @@ -282,7 +284,7 @@ static void create_worker_cb(struct callback_head *cb) struct io_wq *wq; struct io_wqe *wqe; struct io_wqe_acct *acct; - bool do_create = false; + bool do_create = false, first = false; cwd = container_of(cb, struct create_worker_data, work); wqe = cwd->wqe; @@ -290,12 +292,14 @@ static void create_worker_cb(struct callback_head *cb) acct = &wqe->acct[cwd->index]; raw_spin_lock_irq(&wqe->lock); if (acct->nr_workers < acct->max_workers) { + if (!acct->nr_workers) + first = true; acct->nr_workers++; do_create = true; } raw_spin_unlock_irq(&wqe->lock); if (do_create) { - create_io_worker(wq, cwd->wqe, cwd->index); + create_io_worker(wq, wqe, cwd->index, first); } else { atomic_dec(&acct->nr_running); io_worker_ref_put(wq); @@ -637,7 +641,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk) raw_spin_unlock_irq(&worker->wqe->lock); } -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first) { struct io_wqe_acct *acct = &wqe->acct[index]; struct io_worker *worker; @@ -678,7 +682,7 @@ fail: worker->flags |= IO_WORKER_F_FREE; if (index == IO_WQ_ACCT_BOUND) worker->flags |= IO_WORKER_F_BOUND; - if ((acct->nr_workers == 1) && (worker->flags & IO_WORKER_F_BOUND)) + if (first && (worker->flags & IO_WORKER_F_BOUND)) worker->flags |= IO_WORKER_F_FIXED; raw_spin_unlock_irq(&wqe->lock); wake_up_new_task(tsk); From c018db4a57f3e31a9cb24d528e9f094eda89a499 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Aug 2021 08:15:50 -0600 Subject: [PATCH 1346/1469] io_uring: drop ctx->uring_lock before flushing work item Ammar reports that he's seeing a lockdep splat on running test/rsrc_tags from the regression suite: ====================================================== WARNING: possible circular locking dependency detected 5.14.0-rc3-bluetea-test-00249-gc7d102232649 #5 Tainted: G OE ------------------------------------------------------ kworker/2:4/2684 is trying to acquire lock: ffff88814bb1c0a8 (&ctx->uring_lock){+.+.}-{3:3}, at: io_rsrc_put_work+0x13d/0x1a0 but task is already holding lock: ffffc90001c6be70 ((work_completion)(&(&ctx->rsrc_put_work)->work)){+.+.}-{0:0}, at: process_one_work+0x1bc/0x530 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 ((work_completion)(&(&ctx->rsrc_put_work)->work)){+.+.}-{0:0}: __flush_work+0x31b/0x490 io_rsrc_ref_quiesce.part.0.constprop.0+0x35/0xb0 __do_sys_io_uring_register+0x45b/0x1060 do_syscall_64+0x35/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae -> #0 (&ctx->uring_lock){+.+.}-{3:3}: __lock_acquire+0x119a/0x1e10 lock_acquire+0xc8/0x2f0 __mutex_lock+0x86/0x740 io_rsrc_put_work+0x13d/0x1a0 process_one_work+0x236/0x530 worker_thread+0x52/0x3b0 kthread+0x135/0x160 ret_from_fork+0x1f/0x30 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&(&ctx->rsrc_put_work)->work)); lock(&ctx->uring_lock); lock((work_completion)(&(&ctx->rsrc_put_work)->work)); lock(&ctx->uring_lock); *** DEADLOCK *** 2 locks held by kworker/2:4/2684: #0: ffff88810004d938 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work+0x1bc/0x530 #1: ffffc90001c6be70 ((work_completion)(&(&ctx->rsrc_put_work)->work)){+.+.}-{0:0}, at: process_one_work+0x1bc/0x530 stack backtrace: CPU: 2 PID: 2684 Comm: kworker/2:4 Tainted: G OE 5.14.0-rc3-bluetea-test-00249-gc7d102232649 #5 Hardware name: Acer Aspire ES1-421/OLVIA_BE, BIOS V1.05 07/02/2015 Workqueue: events io_rsrc_put_work Call Trace: dump_stack_lvl+0x6a/0x9a check_noncircular+0xfe/0x110 __lock_acquire+0x119a/0x1e10 lock_acquire+0xc8/0x2f0 ? io_rsrc_put_work+0x13d/0x1a0 __mutex_lock+0x86/0x740 ? io_rsrc_put_work+0x13d/0x1a0 ? io_rsrc_put_work+0x13d/0x1a0 ? io_rsrc_put_work+0x13d/0x1a0 ? process_one_work+0x1ce/0x530 io_rsrc_put_work+0x13d/0x1a0 process_one_work+0x236/0x530 worker_thread+0x52/0x3b0 ? process_one_work+0x530/0x530 kthread+0x135/0x160 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x1f/0x30 which is due to holding the ctx->uring_lock when flushing existing pending work, while the pending work flushing may need to grab the uring lock if we're using IOPOLL. Fix this by dropping the uring_lock a bit earlier as part of the flush. Cc: stable@vger.kernel.org Link: https://github.com/axboe/liburing/issues/404 Tested-by: Ammar Faizi Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6a8257233061..0c3e90f974e9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7195,17 +7195,19 @@ static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ct /* kill initial ref, already quiesced if zero */ if (atomic_dec_and_test(&data->refs)) break; + mutex_unlock(&ctx->uring_lock); flush_delayed_work(&ctx->rsrc_put_work); ret = wait_for_completion_interruptible(&data->done); - if (!ret) + if (!ret) { + mutex_lock(&ctx->uring_lock); break; + } atomic_inc(&data->refs); /* wait for all works potentially completing data->done */ flush_delayed_work(&ctx->rsrc_put_work); reinit_completion(&data->done); - mutex_unlock(&ctx->uring_lock); ret = io_run_task_work_sig(); mutex_lock(&ctx->uring_lock); } while (ret >= 0); From 43597aac1f87230cb565ab354d331682f13d3c7a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 10 Aug 2021 02:44:23 +0100 Subject: [PATCH 1347/1469] io_uring: fix ctx-exit io_rsrc_put_work() deadlock __io_rsrc_put_work() might need ->uring_lock, so nobody should wait for rsrc nodes holding the mutex. However, that's exactly what io_ring_ctx_free() does with io_wait_rsrc_data(). Split it into rsrc wait + dealloc, and move the first one out of the lock. Cc: stable@vger.kernel.org Fixes: b60c8dce33895 ("io_uring: preparation for rsrc tagging") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0130c5c2693468173ec1afab714e0885d2c9c363.1628559783.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 0c3e90f974e9..04c6d059ea94 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8652,13 +8652,10 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static bool io_wait_rsrc_data(struct io_rsrc_data *data) +static void io_wait_rsrc_data(struct io_rsrc_data *data) { - if (!data) - return false; - if (!atomic_dec_and_test(&data->refs)) + if (data && !atomic_dec_and_test(&data->refs)) wait_for_completion(&data->done); - return true; } static void io_ring_ctx_free(struct io_ring_ctx *ctx) @@ -8670,10 +8667,14 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) ctx->mm_account = NULL; } + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + mutex_lock(&ctx->uring_lock); - if (io_wait_rsrc_data(ctx->buf_data)) + if (ctx->buf_data) __io_sqe_buffers_unregister(ctx); - if (io_wait_rsrc_data(ctx->file_data)) + if (ctx->file_data) __io_sqe_files_unregister(ctx); if (ctx->rings) __io_cqring_overflow_flush(ctx, true); From 11431e26c9c43fa26f6b33ee1a90989f57b86024 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 3 Aug 2021 15:06:08 +0800 Subject: [PATCH 1348/1469] blk-iocost: fix lockdep warning on blkcg->lock blkcg->lock depends on q->queue_lock which may depend on another driver lock required in irq context, one example is dm-thin: Chain exists of: &pool->lock#3 --> &q->queue_lock --> &blkcg->lock Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&blkcg->lock); local_irq_disable(); lock(&pool->lock#3); lock(&q->queue_lock); lock(&pool->lock#3); Fix the issue by using spin_lock_irq(&blkcg->lock) in ioc_weight_write(). Cc: Tejun Heo Reported-by: Bruno Goncalves Link: https://lore.kernel.org/linux-block/CA+QYu4rzz6079ighEanS3Qq_Dmnczcf45ZoJoHKVLVATTo1e4Q@mail.gmail.com/T/#u Signed-off-by: Ming Lei Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210803070608.1766400-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-iocost.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 5fac3757e6e0..0e56557cacf2 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3061,19 +3061,19 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; - spin_lock(&blkcg->lock); + spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { - spin_lock_irq(&iocg->ioc->lock); + spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); - spin_unlock_irq(&iocg->ioc->lock); + spin_unlock(&iocg->ioc->lock); } } - spin_unlock(&blkcg->lock); + spin_unlock_irq(&blkcg->lock); return nbytes; } From 9977d880f7a3c233db9165a75a3a14defc2a4aee Mon Sep 17 00:00:00 2001 From: "Ewan D. Milne" Date: Mon, 9 Aug 2021 11:09:47 -0400 Subject: [PATCH 1349/1469] scsi: lpfc: Move initialization of phba->poll_list earlier to avoid crash The phba->poll_list is traversed in case of an error in lpfc_sli4_hba_setup(), so it must be initialized earlier in case the error path is taken. [ 490.030738] lpfc 0000:65:00.0: 0:1413 Failed to init iocb list. [ 490.036661] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 490.044485] PGD 0 P4D 0 [ 490.047027] Oops: 0000 [#1] SMP PTI [ 490.050518] CPU: 0 PID: 7 Comm: kworker/0:1 Kdump: loaded Tainted: G I --------- - - 4.18. [ 490.060511] Hardware name: Dell Inc. PowerEdge R440/0WKGTH, BIOS 1.4.8 05/22/2018 [ 490.067994] Workqueue: events work_for_cpu_fn [ 490.072371] RIP: 0010:lpfc_sli4_cleanup_poll_list+0x20/0xb0 [lpfc] [ 490.078546] Code: cf e9 04 f7 fe ff 0f 1f 40 00 0f 1f 44 00 00 41 57 49 89 ff 41 56 41 55 41 54 4d 8d a79 [ 490.097291] RSP: 0018:ffffbd1a463dbcc8 EFLAGS: 00010246 [ 490.102518] RAX: 0000000000008200 RBX: ffff945cdb8c0000 RCX: 0000000000000000 [ 490.109649] RDX: 0000000000018200 RSI: ffff9468d0e16818 RDI: 0000000000000000 [ 490.116783] RBP: ffff945cdb8c1740 R08: 00000000000015c5 R09: 0000000000000042 [ 490.123915] R10: 0000000000000000 R11: ffffbd1a463dbab0 R12: ffff945cdb8c25c0 [ 490.131049] R13: 00000000fffffff4 R14: 0000000000001800 R15: ffff945cdb8c0000 [ 490.138182] FS: 0000000000000000(0000) GS:ffff9468d0e00000(0000) knlGS:0000000000000000 [ 490.146267] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 490.152013] CR2: 0000000000000000 CR3: 000000042ca10002 CR4: 00000000007706f0 [ 490.159146] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 490.166277] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 490.173409] PKRU: 55555554 [ 490.176123] Call Trace: [ 490.178598] lpfc_sli4_queue_destroy+0x7f/0x3c0 [lpfc] [ 490.183745] lpfc_sli4_hba_setup+0x1bc7/0x23e0 [lpfc] [ 490.188797] ? kernfs_activate+0x63/0x80 [ 490.192721] ? kernfs_add_one+0xe7/0x130 [ 490.196647] ? __kernfs_create_file+0x80/0xb0 [ 490.201020] ? lpfc_pci_probe_one_s4.isra.48+0x46f/0x9e0 [lpfc] [ 490.206944] lpfc_pci_probe_one_s4.isra.48+0x46f/0x9e0 [lpfc] [ 490.212697] lpfc_pci_probe_one+0x179/0xb70 [lpfc] [ 490.217492] local_pci_probe+0x41/0x90 [ 490.221246] work_for_cpu_fn+0x16/0x20 [ 490.224994] process_one_work+0x1a7/0x360 [ 490.229009] ? create_worker+0x1a0/0x1a0 [ 490.232933] worker_thread+0x1cf/0x390 [ 490.236687] ? create_worker+0x1a0/0x1a0 [ 490.240612] kthread+0x116/0x130 [ 490.243846] ? kthread_flush_work_fn+0x10/0x10 [ 490.248293] ret_from_fork+0x35/0x40 [ 490.251869] Modules linked in: lpfc(+) xt_CHECKSUM ipt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4i [ 490.332609] CR2: 0000000000000000 Link: https://lore.kernel.org/r/20210809150947.18104-1-emilne@redhat.com Fixes: 93a4d6f40198 ("scsi: lpfc: Add registration for CPU Offline/Online events") Cc: stable@vger.kernel.org Reviewed-by: James Smart Signed-off-by: Ewan D. Milne Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 5983e05b648f..e29523a1b530 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13193,6 +13193,8 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) if (!phba) return -ENOMEM; + INIT_LIST_HEAD(&phba->poll_list); + /* Perform generic PCI device enabling operation */ error = lpfc_enable_pci_dev(phba); if (error) @@ -13327,7 +13329,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) /* Enable RAS FW log support */ lpfc_sli4_ras_setup(phba); - INIT_LIST_HEAD(&phba->poll_list); timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp); From dbe7633c394be4a500b887fe8f9ad486dcba9d77 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 6 Aug 2021 10:12:50 -0700 Subject: [PATCH 1350/1469] scsi: storvsc: Log TEST_UNIT_READY errors as warnings Commit 08f76547f08d ("scsi: storvsc: Update error logging") added more robust logging of errors, particularly those reported as Hyper-V errors. But this change produces extra logging noise in that TEST_UNIT_READY may report errors during the normal course of detecting device adds and removes. Fix this by logging TEST_UNIT_READY errors as warnings, so that log lines are produced only if the storvsc log level is changed to WARN level on the kernel boot line. Link: https://lore.kernel.org/r/1628269970-87876-1-git-send-email-mikelley@microsoft.com Fixes: 08f76547f08d ("scsi: storvsc: Update error logging") Signed-off-by: Michael Kelley Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 328bb961c281..37506b3fe5a9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1199,14 +1199,24 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, vstor_packet->vm_srb.sense_info_length); if (vstor_packet->vm_srb.scsi_status != 0 || - vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) - storvsc_log(device, STORVSC_LOGGING_ERROR, + vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) { + + /* + * Log TEST_UNIT_READY errors only as warnings. Hyper-V can + * return errors when detecting devices using TEST_UNIT_READY, + * and logging these as errors produces unhelpful noise. + */ + int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ? + STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR; + + storvsc_log(device, loglevel, "tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n", request->cmd->request->tag, stor_pkt->vm_srb.cdb[0], vstor_packet->vm_srb.scsi_status, vstor_packet->vm_srb.srb_status, vstor_packet->status); + } if (vstor_packet->vm_srb.scsi_status == SAM_STAT_CHECK_CONDITION && (vstor_packet->vm_srb.srb_status & SRB_STATUS_AUTOSENSE_VALID)) From 40d32727931cee82cdc5aaca25ce725d1f3ac864 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 4 Aug 2021 14:49:40 +0100 Subject: [PATCH 1351/1469] scsi: mpt3sas: Fix incorrectly assigned error return and check Currently the call to _base_static_config_pages() is assigning the error return to variable 'rc' but checking the error return in error 'r'. Fix this by assigning the error return to variable 'r' instead of 'rc'. Link: https://lore.kernel.org/r/20210804134940.114011-1-colin.king@canonical.com Fixes: 19a622c39a9d ("scsi: mpt3sas: Handle firmware faults during first half of IOC init") Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen Addresses-Coverity: ("Unused value") --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 19b1c0cf5f2a..cf4a3a2c22ad 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7851,7 +7851,7 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc) return r; } - rc = _base_static_config_pages(ioc); + r = _base_static_config_pages(ioc); if (r) return r; From c633e799641cf13960bd83189b4d5b1b2adb0d4e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 2 Aug 2021 16:39:54 +0300 Subject: [PATCH 1352/1469] net/mlx5: Don't skip subfunction cleanup in case of error in module init Clean SF resources if mlx5 eth failed to initialize. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Signed-off-by: Leon Romanovsky Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 12 ++++-------- drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 5 +++++ 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index eb1b316560a8..c84ad87c99bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1784,16 +1784,14 @@ static int __init init(void) if (err) goto err_sf; -#ifdef CONFIG_MLX5_CORE_EN err = mlx5e_init(); - if (err) { - pci_unregister_driver(&mlx5_core_driver); - goto err_debug; - } -#endif + if (err) + goto err_en; return 0; +err_en: + mlx5_sf_driver_unregister(); err_sf: pci_unregister_driver(&mlx5_core_driver); err_debug: @@ -1803,9 +1801,7 @@ err_debug: static void __exit cleanup(void) { -#ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); -#endif mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); mlx5_unregister_debugfs(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 343807ac2036..da365b8f0141 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -206,8 +206,13 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw, int mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver, u32 *stored_ver); +#ifdef CONFIG_MLX5_CORE_EN int mlx5e_init(void); void mlx5e_cleanup(void); +#else +static inline int mlx5e_init(void){ return 0; } +static inline void mlx5e_cleanup(void){} +#endif static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) { From d3875924dae632d5edd908d285fffc5f07c835a3 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Tue, 22 Jun 2021 16:51:58 +0300 Subject: [PATCH 1353/1469] net/mlx5: DR, Add fail on error check on decap While processing encapsulated packet on RX, one of the fields that is checked is the inner packet length. If the length as specified in the header doesn't match the actual inner packet length, the packet is invalid and should be dropped. However, such packet caused the NIC to hang. This patch turns on a 'fail_on_error' HW bit which allows HW to drop such an invalid packet while processing RX packet and trying to decap it. Fixes: ad17dc8cf910 ("net/mlx5: DR, Move STEv0 action apply logic") Signed-off-by: Alex Vesker Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index f1950e4968da..e4dd4eed5aee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -352,6 +352,7 @@ static void dr_ste_v0_set_rx_decap(u8 *hw_ste_p) { MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, DR_STE_TUNL_ACTION_DECAP); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, fail_on_error, 1); } static void dr_ste_v0_set_rx_pop_vlan(u8 *hw_ste_p) @@ -365,6 +366,7 @@ static void dr_ste_v0_set_rx_decap_l3(u8 *hw_ste_p, bool vlan) MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, DR_STE_TUNL_ACTION_L3_DECAP); MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, fail_on_error, 1); } static void dr_ste_v0_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, From c623c95afa56bf4bf64e4f58742dc94616ef83db Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Sun, 1 Aug 2021 15:47:46 +0300 Subject: [PATCH 1354/1469] net/mlx5e: Avoid creating tunnel headers for local route It could be local and remote are on the same machine and the route result will be a local route which will result in creating encap id with src/dst mac address of 0. Fixes: a54e20b4fcae ("net/mlx5e: Add basic TC tunnel set action for SRIOV offloads") Signed-off-by: Roi Dayan Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 8f79f04eccd6..1e2d117082d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -124,6 +124,11 @@ static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, if (IS_ERR(rt)) return PTR_ERR(rt); + if (rt->rt_type != RTN_UNICAST) { + ret = -ENETUNREACH; + goto err_rt_release; + } + if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) { ret = -ENETUNREACH; goto err_rt_release; From 6d8680da2e98410a25fe49e0a53f28c004be6d6d Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 4 Aug 2021 18:33:26 +0300 Subject: [PATCH 1355/1469] net/mlx5: Bridge, fix ageing time Ageing time is not converted from clock_t to jiffies which results incorrect ageing timeout calculation in workqueue update task. Fix it by applying clock_t_to_jiffies() to provided value. Fixes: c636a0f0f3f0 ("net/mlx5: Bridge, dynamic entry ageing") Signed-off-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index a6e1d4f78268..f3f56f32e435 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -579,7 +579,7 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, xa_init(&bridge->vports); bridge->ifindex = ifindex; bridge->refcnt = 1; - bridge->ageing_time = BR_DEFAULT_AGEING_TIME; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); list_add(&bridge->list, &br_offloads->bridges); return bridge; @@ -1006,7 +1006,7 @@ int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswit if (!vport->bridge) return -EINVAL; - vport->bridge->ageing_time = ageing_time; + vport->bridge->ageing_time = clock_t_to_jiffies(ageing_time); return 0; } From 8ba3e4c85825c8801a2c298dcadac650a40d7137 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Mon, 24 May 2021 16:15:22 +0300 Subject: [PATCH 1356/1469] net/mlx5e: Destroy page pool after XDP SQ to fix use-after-free mlx5e_close_xdpsq does the cleanup: it calls mlx5e_free_xdpsq_descs to free the outstanding descriptors, which relies on mlx5e_page_release_dynamic and page_pool_release_page. However, page_pool_destroy is already called by this point, because mlx5e_close_rq runs before mlx5e_close_xdpsq. This commit fixes the use-after-free by swapping mlx5e_close_xdpsq and mlx5e_close_rq. The commit cited below started calling page_pool_destroy directly from the driver. Previously, the page pool was destroyed under a call_rcu from xdp_rxq_info_unreg_mem_model, which would defer the deallocation until after the XDPSQ is cleaned up. Fixes: 1da4bbeffe41 ("net: core: page_pool: add user refcnt and reintroduce page_pool_destroy") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 20 +++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 37c440837945..fd250f7bcd88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1891,30 +1891,30 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_icosq; + err = mlx5e_open_rxq_rq(c, params, &cparam->rq); + if (err) + goto err_close_sqs; + if (c->xdp) { err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->rq_xdpsq, false); if (err) - goto err_close_sqs; + goto err_close_rq; } - err = mlx5e_open_rxq_rq(c, params, &cparam->rq); - if (err) - goto err_close_xdp_sq; - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true); if (err) - goto err_close_rq; + goto err_close_xdp_sq; return 0; -err_close_rq: - mlx5e_close_rq(&c->rq); - err_close_xdp_sq: if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); +err_close_rq: + mlx5e_close_rq(&c->rq); + err_close_sqs: mlx5e_close_sqs(c); @@ -1949,9 +1949,9 @@ err_close_async_icosq_cq: static void mlx5e_close_queues(struct mlx5e_channel *c) { mlx5e_close_xdpsq(&c->xdpsq); - mlx5e_close_rq(&c->rq); if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); + mlx5e_close_rq(&c->rq); mlx5e_close_sqs(c); mlx5e_close_icosq(&c->icosq); mlx5e_close_icosq(&c->async_icosq); From c85a6b8feb16c0cdbbc8d9f581c7861c4a9ac351 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 28 Jul 2021 18:18:59 +0300 Subject: [PATCH 1357/1469] net/mlx5: Block switchdev mode while devlink traps are active Since switchdev mode can't support devlink traps, verify there are no active devlink traps before moving eswitch to switchdev mode. If there are active traps, prevent the switchdev mode configuration. Fixes: eb3862a0525d ("net/mlx5e: Enable traps according to link state") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 011e766e4f67..3bb71a186004 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -48,6 +48,7 @@ #include "lib/fs_chains.h" #include "en_tc.h" #include "en/mapping.h" +#include "devlink.h" #define mlx5_esw_for_each_rep(esw, i, rep) \ xa_for_each(&((esw)->offloads.vport_reps), i, rep) @@ -3001,12 +3002,19 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (cur_mlx5_mode == mlx5_mode) goto unlock; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { + if (mlx5_devlink_trap_get_num_active(esw->dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Can't change mode while devlink traps are active"); + err = -EOPNOTSUPP; + goto unlock; + } err = esw_offloads_start(esw, extack); - else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { err = esw_offloads_stop(esw, extack); - else + } else { err = -EINVAL; + } unlock: mlx5_esw_unlock(esw); From 3c8946e0e2841aa7cbdabf6acaac6559fa8d1a49 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 16 Jun 2021 18:54:05 +0300 Subject: [PATCH 1358/1469] net/mlx5: Fix order of functions in mlx5_irq_detach_nb() Change order of functions in mlx5_irq_detach_nb() so it will be a mirror of mlx5_irq_attach_nb. Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs") Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index b25f764daa08..95e60da33f03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -251,8 +251,11 @@ int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb) int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb) { + int err = 0; + + err = atomic_notifier_chain_unregister(&irq->nh, nb); irq_put(irq); - return atomic_notifier_chain_unregister(&irq->nh, nb); + return err; } struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq) From 5957cc557dc5d52c3448be15c2474f33224b89b6 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 16 Jun 2021 18:59:05 +0300 Subject: [PATCH 1359/1469] net/mlx5: Set all field of mlx5_irq before inserting it to the xarray Currently irq->pool is set after the irq is insert to the xarray. Set irq->pool before the irq is inserted to the xarray. Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs") Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 95e60da33f03..7b923f6b5462 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -214,6 +214,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) err = -ENOMEM; goto err_cpumask; } + irq->pool = pool; kref_init(&irq->kref); irq->index = i; err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL)); @@ -222,7 +223,6 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) irq->index, err); goto err_xa; } - irq->pool = pool; return irq; err_xa: free_cpumask_var(irq->mask); From ba317e832d457bc8fcecf6a6ed289732544b87e9 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 17 Jun 2021 01:51:00 +0300 Subject: [PATCH 1360/1469] net/mlx5: Destroy pool->mutex Destroy pool->mutex when we destroy the pool. Fixes: c36326d38d93 ("net/mlx5: Round-Robin EQs over IRQs") Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 7b923f6b5462..3465b363fc2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -440,6 +440,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, if (!pool) return ERR_PTR(-ENOMEM); pool->dev = dev; + mutex_init(&pool->lock); xa_init_flags(&pool->irqs, XA_FLAGS_ALLOC); pool->xa_num_irqs.min = start; pool->xa_num_irqs.max = start + size - 1; @@ -448,7 +449,6 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, name); pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ; pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ; - mutex_init(&pool->lock); mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d", name, size, start); return pool; @@ -462,6 +462,7 @@ static void irq_pool_free(struct mlx5_irq_pool *pool) xa_for_each(&pool->irqs, index, irq) irq_release(&irq->kref); xa_destroy(&pool->irqs); + mutex_destroy(&pool->lock); kvfree(pool); } From 88bbd7b2369aca4598eb8f38c5f16be98c3bb5d4 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Thu, 6 May 2021 11:40:34 +0800 Subject: [PATCH 1361/1469] net/mlx5e: TC, Fix error handling memory leak Free the offload sample action on error. Fixes: f94d6389f6a8 ("net/mlx5e: TC, Add support to offload sample action") Signed-off-by: Chris Mi Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c index 794012c5c476..d3ad78aa9d45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c @@ -501,6 +501,7 @@ err_sampler: err_offload_rule: mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr); err_default_tbl: + kfree(sample_flow); return ERR_PTR(err); } From 563476ae0c5e48a028cbfa38fa9d2fc0418eb88f Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 11 Apr 2021 15:32:55 +0300 Subject: [PATCH 1362/1469] net/mlx5: Synchronize correct IRQ when destroying CQ The CQ destroy is performed based on the IRQ number that is stored in cq->irqn. That number wasn't set explicitly during CQ creation and as expected some of the API users of mlx5_core_create_cq() forgot to update it. This caused to wrong synchronization call of the wrong IRQ with a number 0 instead of the real one. As a fix, set the IRQ number directly in the mlx5_core_create_cq() and update all users accordingly. Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices") Fixes: ef1659ade359 ("IB/mlx5: Add DEVX support for CQ events") Signed-off-by: Shay Drory Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cq.c | 4 +--- drivers/infiniband/hw/mlx5/devx.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 1 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 13 ++---------- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 +++++++++++++++---- .../ethernet/mellanox/mlx5/core/fpga/conn.c | 4 +--- .../net/ethernet/mellanox/mlx5/core/lib/eq.h | 2 ++ .../mellanox/mlx5/core/steering/dr_send.c | 4 +--- drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +-- include/linux/mlx5/driver.h | 3 +-- 10 files changed, 27 insertions(+), 30 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 7abeb576b3c5..b8e5e371bb19 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -945,7 +945,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, u32 *cqb = NULL; void *cqc; int cqe_size; - unsigned int irqn; int eqn; int err; @@ -984,7 +983,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, INIT_WORK(&cq->notify_work, notify_soft_wc_handler); } - err = mlx5_vector2eqn(dev->mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, vector, &eqn); if (err) goto err_cqb; @@ -1007,7 +1006,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, goto err_cqb; mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn); - cq->mcq.irqn = irqn; if (udata) cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; else diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index eb9b0a2707f8..c869b2a91a28 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -975,7 +975,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( struct mlx5_ib_dev *dev; int user_vector; int dev_eqn; - unsigned int irqn; int err; if (uverbs_copy_from(&user_vector, attrs, @@ -987,7 +986,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( return PTR_ERR(c); dev = to_mdev(c->ibucontext.device); - err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index df3e4938ecdd..360e093874d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -134,6 +134,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->cqn); cq->uar = dev->priv.uar; + cq->irqn = eq->core.irqn; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index fd250f7bcd88..24f919ef9b8e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1535,15 +1535,9 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; - int eqn_not_used; - unsigned int irqn; int err; u32 i; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - if (err) - return err; - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, &cq->wq_ctrl); if (err) @@ -1557,7 +1551,6 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, mcq->vector = param->eq_ix; mcq->comp = mlx5e_completion_event; mcq->event = mlx5e_cq_error_event; - mcq->irqn = irqn; for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); @@ -1605,11 +1598,10 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) void *in; void *cqc; int inlen; - unsigned int irqn_not_used; int eqn; int err; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); + err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn); if (err) return err; @@ -1983,9 +1975,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_channel *c; unsigned int irq; int err; - int eqn; - err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); + err = mlx5_vector2irqn(priv->mdev, ix, &irq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 6e074cc457de..605c8ecc3610 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -855,8 +855,8 @@ clean: return err; } -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn) +static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_eq_comp *eq, *n; @@ -865,8 +865,10 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) { if (i++ == vector) { - *eqn = eq->core.eqn; - *irqn = eq->core.irqn; + if (irqn) + *irqn = eq->core.irqn; + if (eqn) + *eqn = eq->core.eqn; err = 0; break; } @@ -874,8 +876,18 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, return err; } + +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn) +{ + return vector2eqnirqn(dev, vector, eqn, NULL); +} EXPORT_SYMBOL(mlx5_vector2eqn); +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn) +{ + return vector2eqnirqn(dev, vector, NULL, irqn); +} + unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev) { return dev->priv.eq_table->num_comp_eqs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index bd66ab2af5b5..d5da4ab65766 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -417,7 +417,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) struct mlx5_wq_param wqp; struct mlx5_cqe64 *cqe; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; u32 i; @@ -446,7 +445,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) goto err_cqwq; } - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -476,7 +475,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) *conn->cq.mcq.arm_db = 0; conn->cq.mcq.vector = 0; conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; - conn->cq.mcq.irqn = irqn; conn->cq.mcq.uar = fdev->conn_res.uar; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 624cedebb510..d3d628b862f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -104,4 +104,6 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev); struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev); #endif +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn); + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 12cf323a5943..9df0e73d1c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -749,7 +749,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_cqe64 *cqe; struct mlx5dr_cq *cq; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; int vector; @@ -782,7 +781,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, goto err_cqwq; vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); - err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, vector, &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -818,7 +817,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, *cq->mcq.arm_db = cpu_to_be32(2 << 28); cq->mcq.vector = 0; - cq->mcq.irqn = irqn; cq->mcq.uar = uar; return cq; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2a31467f7ac5..379a19144a25 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -526,7 +526,6 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) void __iomem *uar_page = ndev->mvdev.res.uar->map; u32 out[MLX5_ST_SZ_DW(create_cq_out)]; struct mlx5_vdpa_cq *vcq = &mvq->cq; - unsigned int irqn; __be64 *pas; int inlen; void *cqc; @@ -566,7 +565,7 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) /* Use vector 0 by default. Consider adding code to choose least used * vector. */ - err = mlx5_vector2eqn(mdev, 0, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, 0, &eqn); if (err) goto err_vec; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1efe37466969..25a8be58d289 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1044,8 +1044,7 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); From bd37c2888ccaa5ceb9895718f6909b247cc372e0 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 8 Jun 2021 16:38:30 +0300 Subject: [PATCH 1363/1469] net/mlx5: Fix return value from tracer initialization Check return value of mlx5_fw_tracer_start(), set error path and fix return value of mlx5_fw_tracer_init() accordingly. Fixes: c71ad41ccb0c ("net/mlx5: FW tracer, events handling") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 01a1d02dcf15..3f8a98093f8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1019,12 +1019,19 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER); mlx5_eq_notifier_register(dev, &tracer->nb); - mlx5_fw_tracer_start(tracer); - + err = mlx5_fw_tracer_start(tracer); + if (err) { + mlx5_core_warn(dev, "FWTracer: Failed to start tracer %d\n", err); + goto err_notifier_unregister; + } return 0; +err_notifier_unregister: + mlx5_eq_notifier_unregister(dev, &tracer->nb); + mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); + cancel_work_sync(&tracer->read_fw_strings_work); return err; } From 7b637cd52f02c6d7ff0580143a438940978fc719 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Mon, 2 Aug 2021 06:59:41 +0300 Subject: [PATCH 1364/1469] MAINTAINERS: fix Microchip CAN BUS Analyzer Tool entry typo This patch fixes the abbreviated name of the Microchip CAN BUS Analyzer Tool. Fixes: 8a7b46fa7902 ("MAINTAINERS: add Yasushi SHOJI as reviewer for the Microchip CAN BUS Analyzer Tool driver") Link: https://lore.kernel.org/r/cc4831cb1c8759c15fb32c21fd326e831183733d.1627876781.git.baruch@tkos.co.il Signed-off-by: Baruch Siach Signed-off-by: Marc Kleine-Budde --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index c9467d2839f5..25dc566a67c1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11327,7 +11327,7 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-maxiradio* -MCAB MICROCHIP CAN BUS ANALYZER TOOL DRIVER +MCBA MICROCHIP CAN BUS ANALYZER TOOL DRIVER R: Yasushi SHOJI L: linux-can@vger.kernel.org S: Maintained From aae32b784ebdbda6f6055a8021c9fb8a0ab5bcba Mon Sep 17 00:00:00 2001 From: Hussein Alasadi Date: Mon, 9 Aug 2021 17:36:52 +0000 Subject: [PATCH 1365/1469] can: m_can: m_can_set_bittiming(): fix setting M_CAN_DBTP register This patch fixes the setting of the M_CAN_DBTP register contents: - use DBTP_ (the data bitrate macros) instead of NBTP_ which area used for the nominal bitrate - do not overwrite possibly-existing DBTP_TDC flag by ORing reg_btp instead of overwriting Link: https://lore.kernel.org/r/FRYP281MB06140984ABD9994C0AAF7433D1F69@FRYP281MB0614.DEUP281.PROD.OUTLOOK.COM Fixes: 20779943a080 ("can: m_can: use bits.h macros for all regmasks") Cc: Torin Cooper-Bennun Cc: Chandrasekar Ramakrishnan Signed-off-by: Hussein Alasadi [mkl: update patch description, update indention] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index bba2a449ac70..43bca315a66c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1164,10 +1164,10 @@ static int m_can_set_bittiming(struct net_device *dev) FIELD_PREP(TDCR_TDCO_MASK, tdco)); } - reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) | - FIELD_PREP(NBTP_NSJW_MASK, sjw) | - FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) | - FIELD_PREP(NBTP_NTSEG2_MASK, tseg2); + reg_btp |= FIELD_PREP(DBTP_DBRP_MASK, brp) | + FIELD_PREP(DBTP_DSJW_MASK, sjw) | + FIELD_PREP(DBTP_DTSEG1_MASK, tseg1) | + FIELD_PREP(DBTP_DTSEG2_MASK, tseg2); m_can_write(cdev, M_CAN_DBTP, reg_btp); } From 07d25971b220e477eb019fcb520a9f2e3ac966af Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 31 Jul 2021 20:30:11 +0800 Subject: [PATCH 1366/1469] locking/rtmutex: Use the correct rtmutex debugging config option It's CONFIG_DEBUG_RT_MUTEXES not CONFIG_DEBUG_RT_MUTEX. Fixes: f7efc4799f81 ("locking/rtmutex: Inline chainwalk depth check") Signed-off-by: Zhen Lei Signed-off-by: Thomas Gleixner Acked-by: Will Deacon Acked-by: Boqun Feng Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210731123011.4555-1-thunder.leizhen@huawei.com --- kernel/locking/rtmutex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b5d9bb5202c6..ad0db322ed3b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -343,7 +343,7 @@ static __always_inline bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk chwalk) { - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEX)) + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) return waiter != NULL; return chwalk == RT_MUTEX_FULL_CHAINWALK; } From 664cc971fb259007e49cc8a3ac43b0787d89443f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 10 Aug 2021 09:10:15 +0200 Subject: [PATCH 1367/1469] Revert "usb: dwc3: gadget: Use list_replace_init() before traversing lists" This reverts commit d25d85061bd856d6be221626605319154f9b5043 as it is reported to cause problems on many different types of boards. Reported-by: Thinh Nguyen Reported-by: John Stultz Cc: Ray Chi Link: https://lore.kernel.org/r/CANcMJZCEVxVLyFgLwK98hqBEdc0_n4P0x_K6Gih8zNH3ouzbJQ@mail.gmail.com Fixes: d25d85061bd8 ("usb: dwc3: gadget: Use list_replace_init() before traversing lists") Cc: stable Cc: Felipe Balbi Cc: Wesley Cheng Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index b8d4b2d327b2..84fe57ef5a49 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1741,13 +1741,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; struct dwc3 *dwc = dep->dwc; -restart: - list_replace_init(&dep->cancelled_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) { dwc3_gadget_ep_skip_trbs(dep, req); switch (req->status) { case DWC3_REQUEST_STATUS_DISCONNECTED: @@ -1765,9 +1761,6 @@ restart: break; } } - - if (!list_empty(&dep->cancelled_list)) - goto restart; } static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, @@ -2976,12 +2969,8 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; -restart: - list_replace_init(&dep->started_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->started_list, list) { int ret; ret = dwc3_gadget_ep_cleanup_completed_request(dep, event, @@ -2989,9 +2978,6 @@ restart: if (ret) break; } - - if (!list_empty(&dep->started_list)) - goto restart; } static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep) From bf33677a3c394bb8fddd48d3bbc97adf0262e045 Mon Sep 17 00:00:00 2001 From: Christian Hewitt Date: Fri, 6 Aug 2021 09:40:05 +0000 Subject: [PATCH 1368/1469] drm/meson: fix colour distortion from HDR set during vendor u-boot Add support for the OSD1 HDR registers so meson DRM can handle the HDR properties set by Amlogic u-boot on G12A and newer devices which result in blue/green/pink colour distortion to display output. This takes the original patch submissions from Mathias [0] and [1] with corrections for formatting and the missing description and attribution needed for merge. [0] https://lore.kernel.org/linux-amlogic/59dfd7e6-fc91-3d61-04c4-94e078a3188c@baylibre.com/T/ [1] https://lore.kernel.org/linux-amlogic/CAOKfEHBx_fboUqkENEMd-OC-NSrf46nto+vDLgvgttzPe99kXg@mail.gmail.com/T/#u Fixes: 728883948b0d ("drm/meson: Add G12A Support for VIU setup") Suggested-by: Mathias Steiger Signed-off-by: Christian Hewitt Tested-by: Neil Armstrong Tested-by: Philip Milev [narmsrong: adding missing space on second tested-by tag] Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20210806094005.7136-1-christianshewitt@gmail.com --- drivers/gpu/drm/meson/meson_registers.h | 5 +++++ drivers/gpu/drm/meson/meson_viu.c | 7 ++++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h index 446e7961da48..0f3cafab8860 100644 --- a/drivers/gpu/drm/meson/meson_registers.h +++ b/drivers/gpu/drm/meson/meson_registers.h @@ -634,6 +634,11 @@ #define VPP_WRAP_OSD3_MATRIX_PRE_OFFSET2 0x3dbc #define VPP_WRAP_OSD3_MATRIX_EN_CTRL 0x3dbd +/* osd1 HDR */ +#define OSD1_HDR2_CTRL 0x38a0 +#define OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN BIT(13) +#define OSD1_HDR2_CTRL_REG_ONLY_MAT BIT(16) + /* osd2 scaler */ #define OSD2_VSC_PHASE_STEP 0x3d00 #define OSD2_VSC_INI_PHASE 0x3d01 diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index aede0c67a57f..259f3e6bec90 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -425,9 +425,14 @@ void meson_viu_init(struct meson_drm *priv) if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) || meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) meson_viu_load_matrix(priv); - else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) + else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) { meson_viu_set_g12a_osd1_matrix(priv, RGB709_to_YUV709l_coeff, true); + /* fix green/pink color distortion from vendor u-boot */ + writel_bits_relaxed(OSD1_HDR2_CTRL_REG_ONLY_MAT | + OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN, 0, + priv->io_base + _REG(OSD1_HDR2_CTRL)); + } /* Initialize OSD1 fifo control register */ reg = VIU_OSD_DDR_PRIORITY_URGENT | From 51e1bb9eeaf7868db56e58f47848e364ab4c4129 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 9 Aug 2021 12:43:17 +0200 Subject: [PATCH 1369/1469] bpf: Add lockdown check for probe_write_user helper Back then, commit 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers") added the bpf_probe_write_user() helper in order to allow to override user space memory. Its original goal was to have a facility to "debug, divert, and manipulate execution of semi-cooperative processes" under CAP_SYS_ADMIN. Write to kernel was explicitly disallowed since it would otherwise tamper with its integrity. One use case was shown in cf9b1199de27 ("samples/bpf: Add test/example of using bpf_probe_write_user bpf helper") where the program DNATs traffic at the time of connect(2) syscall, meaning, it rewrites the arguments to a syscall while they're still in userspace, and before the syscall has a chance to copy the argument into kernel space. These days we have better mechanisms in BPF for achieving the same (e.g. for load-balancers), but without having to write to userspace memory. Of course the bpf_probe_write_user() helper can also be used to abuse many other things for both good or bad purpose. Outside of BPF, there is a similar mechanism for ptrace(2) such as PTRACE_PEEK{TEXT,DATA} and PTRACE_POKE{TEXT,DATA}, but would likely require some more effort. Commit 96ae52279594 explicitly dedicated the helper for experimentation purpose only. Thus, move the helper's availability behind a newly added LOCKDOWN_BPF_WRITE_USER lockdown knob so that the helper is disabled under the "integrity" mode. More fine-grained control can be implemented also from LSM side with this change. Fixes: 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers") Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko --- include/linux/security.h | 1 + kernel/trace/bpf_trace.c | 5 +++-- security/security.c | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/include/linux/security.h b/include/linux/security.h index 724d7a4a0c91..5b7288521300 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -120,6 +120,7 @@ enum lockdown_reason { LOCKDOWN_MMIOTRACE, LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, + LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1836591197a5..fdd14072fc3b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -990,12 +990,13 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; - case BPF_FUNC_probe_write_user: - return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: diff --git a/security/security.c b/security/security.c index 6b83ab4e9d66..9ffa9e9c5c55 100644 --- a/security/security.c +++ b/security/security.c @@ -58,6 +58,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", + [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", From 87b7b5335e6995a6d64fca98fc67b92b29caac9c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 9 Aug 2021 16:51:51 -0700 Subject: [PATCH 1370/1469] bpf: Add missing bpf_read_[un]lock_trace() for syscall program Commit 79a7f8bdb159d ("bpf: Introduce bpf_sys_bpf() helper and program type.") added support for syscall program, which is a sleepable program. But the program run missed bpf_read_lock_trace()/bpf_read_unlock_trace(), which is needed to ensure proper rcu callback invocations. This patch adds bpf_read_[un]lock_trace() properly. Fixes: 79a7f8bdb159d ("bpf: Introduce bpf_sys_bpf() helper and program type.") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210809235151.1663680-1-yhs@fb.com --- net/bpf/test_run.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 1cc75c811e24..caa16bf30fb5 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -951,7 +952,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, goto out; } } + + rcu_read_lock_trace(); retval = bpf_prog_run_pin_on_cpu(prog, ctx); + rcu_read_unlock_trace(); if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { err = -EFAULT; From 9011c2791e63fc05721b545c41ad025d8073566e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 26 Apr 2021 18:20:21 +0300 Subject: [PATCH 1371/1469] ovl: skip stale entries in merge dir cache iteration On the first getdents call, ovl_iterate() populates the readdir cache with a list of entries, but for upper entries with origin lower inode, p->ino remains zero. Following getdents calls traverse the readdir cache list and call ovl_cache_update_ino() for entries with zero p->ino to lookup the entry in the overlay and return d_ino that is consistent with st_ino. If the upper file was unlinked between the first getdents call and the getdents call that lists the file entry, ovl_cache_update_ino() will not find the entry and fall back to setting d_ino to the upper real st_ino, which is inconsistent with how this object was presented to users. Instead of listing a stale entry with inconsistent d_ino, simply skip the stale entry, which is better for users. xfstest overlay/077 is failing without this patch. Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/fstests/CAOQ4uxgR_cLnC_vdU5=seP3fwqVkuZM_-WfD6maFTMbMYq=a9w@mail.gmail.com/ Signed-off-by: Miklos Szeredi --- fs/overlayfs/readdir.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index e8ad2c2c77dd..150fdf3bc68d 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -481,6 +481,8 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p) } this = lookup_one_len(p->name, dir, p->len); if (IS_ERR_OR_NULL(this) || !this->d_inode) { + /* Mark a stale entry */ + p->is_whiteout = true; if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -776,6 +778,9 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) if (err) goto out; } + } + /* ovl_cache_update_ino() sets is_whiteout on stale entry */ + if (!p->is_whiteout) { if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) break; } From 9b91b6b019fda817eb52f728eb9c79b3579760bc Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 28 Jul 2021 10:38:43 +0200 Subject: [PATCH 1372/1469] ovl: fix deadlock in splice write There's possibility of an ABBA deadlock in case of a splice write to an overlayfs file and a concurrent splice write to a corresponding real file. The call chain for splice to an overlay file: -> do_splice [takes sb_writers on overlay file] -> do_splice_from -> iter_file_splice_write [takes pipe->mutex] -> vfs_iter_write ... -> ovl_write_iter [takes sb_writers on real file] And the call chain for splice to a real file: -> do_splice [takes sb_writers on real file] -> do_splice_from -> iter_file_splice_write [takes pipe->mutex] Syzbot successfully bisected this to commit 82a763e61e2b ("ovl: simplify file splice"). Fix by reverting the write part of the above commit and by adding missing bits from ovl_write_iter() into ovl_splice_write(). Fixes: 82a763e61e2b ("ovl: simplify file splice") Reported-and-tested-by: syzbot+579885d1a9a833336209@syzkaller.appspotmail.com Signed-off-by: Miklos Szeredi --- fs/overlayfs/file.c | 47 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 46 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4d53d3b7e5fe..d081faa55e83 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -392,6 +392,51 @@ out_unlock: return ret; } +/* + * Calling iter_file_splice_write() directly from overlay's f_op may deadlock + * due to lock order inversion between pipe->mutex in iter_file_splice_write() + * and file_start_write(real.file) in ovl_write_iter(). + * + * So do everything ovl_write_iter() does and call iter_file_splice_write() on + * the real file. + */ +static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + struct fd real; + const struct cred *old_cred; + struct inode *inode = file_inode(out); + struct inode *realinode = ovl_inode_real(inode); + ssize_t ret; + + inode_lock(inode); + /* Update mode */ + ovl_copyattr(realinode, inode); + ret = file_remove_privs(out); + if (ret) + goto out_unlock; + + ret = ovl_real_fdget(out, &real); + if (ret) + goto out_unlock; + + old_cred = ovl_override_creds(inode->i_sb); + file_start_write(real.file); + + ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); + + file_end_write(real.file); + /* Update size */ + ovl_copyattr(realinode, inode); + revert_creds(old_cred); + fdput(real); + +out_unlock: + inode_unlock(inode); + + return ret; +} + static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct fd real; @@ -603,7 +648,7 @@ const struct file_operations ovl_file_operations = { .fadvise = ovl_fadvise, .flush = ovl_flush, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, From 580c610429b3994e8db24418927747cf28443cde Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 6 Aug 2021 10:03:12 +0200 Subject: [PATCH 1373/1469] ovl: fix uninitialized pointer read in ovl_lookup_real_one() One error path can result in release_dentry_name_snapshot() being called before "name" was initialized by take_dentry_name_snapshot(). Fix by moving the release_dentry_name_snapshot() to immediately after the only use. Reported-by: Colin Ian King Signed-off-by: Miklos Szeredi --- fs/overlayfs/export.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 41ebf52f1bbc..ebde05c9cf62 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -392,6 +392,7 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected, */ take_dentry_name_snapshot(&name, real); this = lookup_one_len(name.name.name, connected, name.name.len); + release_dentry_name_snapshot(&name); err = PTR_ERR(this); if (IS_ERR(this)) { goto fail; @@ -406,7 +407,6 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected, } out: - release_dentry_name_snapshot(&name); dput(parent); inode_unlock(dir); return this; From 427215d85e8d1476da1a86b8d67aceb485eb3631 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 9 Aug 2021 10:19:47 +0200 Subject: [PATCH 1374/1469] ovl: prevent private clone if bind mount is not allowed Add the following checks from __do_loopback() to clone_private_mount() as well: - verify that the mount is in the current namespace - verify that there are no locked children Reported-by: Alois Wohlschlager Fixes: c771d683a62e ("vfs: introduce clone_private_mount()") Cc: # v3.18 Signed-off-by: Miklos Szeredi --- fs/namespace.c | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index ab4174a3c802..f79d9471cb76 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1938,6 +1938,20 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +static bool has_locked_children(struct mount *mnt, struct dentry *dentry) +{ + struct mount *child; + + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (!is_subdir(child->mnt_mountpoint, dentry)) + continue; + + if (child->mnt.mnt_flags & MNT_LOCKED) + return true; + } + return false; +} + /** * clone_private_mount - create a private clone of a path * @path: path to clone @@ -1953,10 +1967,19 @@ struct vfsmount *clone_private_mount(const struct path *path) struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; + down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) - return ERR_PTR(-EINVAL); + goto invalid; + + if (!check_mnt(old_mnt)) + goto invalid; + + if (has_locked_children(old_mnt, path->dentry)) + goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); @@ -1964,6 +1987,10 @@ struct vfsmount *clone_private_mount(const struct path *path) new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; + +invalid: + up_read(&namespace_sem); + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); @@ -2315,19 +2342,6 @@ static int do_change_type(struct path *path, int ms_flags) return err; } -static bool has_locked_children(struct mount *mnt, struct dentry *dentry) -{ - struct mount *child; - list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { - if (!is_subdir(child->mnt_mountpoint, dentry)) - continue; - - if (child->mnt.mnt_flags & MNT_LOCKED) - return true; - } - return false; -} - static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); From a2baf4e8bb0f306fbed7b5e6197c02896a638ab5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 9 Aug 2021 18:04:13 -0700 Subject: [PATCH 1375/1469] bpf: Fix potentially incorrect results with bpf_get_local_storage() Commit b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") fixed a bug for bpf_get_local_storage() helper so different tasks won't mess up with each other's percpu local storage. The percpu data contains 8 slots so it can hold up to 8 contexts (same or different tasks), for 8 different program runs, at the same time. This in general is sufficient. But our internal testing showed the following warning multiple times: [...] warning: WARNING: CPU: 13 PID: 41661 at include/linux/bpf-cgroup.h:193 __cgroup_bpf_run_filter_sock_ops+0x13e/0x180 RIP: 0010:__cgroup_bpf_run_filter_sock_ops+0x13e/0x180 tcp_call_bpf.constprop.99+0x93/0xc0 tcp_conn_request+0x41e/0xa50 ? tcp_rcv_state_process+0x203/0xe00 tcp_rcv_state_process+0x203/0xe00 ? sk_filter_trim_cap+0xbc/0x210 ? tcp_v6_inbound_md5_hash.constprop.41+0x44/0x160 tcp_v6_do_rcv+0x181/0x3e0 tcp_v6_rcv+0xc65/0xcb0 ip6_protocol_deliver_rcu+0xbd/0x450 ip6_input_finish+0x11/0x20 ip6_input+0xb5/0xc0 ip6_sublist_rcv_finish+0x37/0x50 ip6_sublist_rcv+0x1dc/0x270 ipv6_list_rcv+0x113/0x140 __netif_receive_skb_list_core+0x1a0/0x210 netif_receive_skb_list_internal+0x186/0x2a0 gro_normal_list.part.170+0x19/0x40 napi_complete_done+0x65/0x150 mlx5e_napi_poll+0x1ae/0x680 __napi_poll+0x25/0x120 net_rx_action+0x11e/0x280 __do_softirq+0xbb/0x271 irq_exit_rcu+0x97/0xa0 common_interrupt+0x7f/0xa0 asm_common_interrupt+0x1e/0x40 RIP: 0010:bpf_prog_1835a9241238291a_tw_egress+0x5/0xbac ? __cgroup_bpf_run_filter_skb+0x378/0x4e0 ? do_softirq+0x34/0x70 ? ip6_finish_output2+0x266/0x590 ? ip6_finish_output+0x66/0xa0 ? ip6_output+0x6c/0x130 ? ip6_xmit+0x279/0x550 ? ip6_dst_check+0x61/0xd0 [...] Using drgn [0] to dump the percpu buffer contents showed that on this CPU slot 0 is still available, but slots 1-7 are occupied and those tasks in slots 1-7 mostly don't exist any more. So we might have issues in bpf_cgroup_storage_unset(). Further debugging confirmed that there is a bug in bpf_cgroup_storage_unset(). Currently, it tries to unset "current" slot with searching from the start. So the following sequence is possible: 1. A task is running and claims slot 0 2. Running BPF program is done, and it checked slot 0 has the "task" and ready to reset it to NULL (not yet). 3. An interrupt happens, another BPF program runs and it claims slot 1 with the *same* task. 4. The unset() in interrupt context releases slot 0 since it matches "task". 5. Interrupt is done, the task in process context reset slot 0. At the end, slot 1 is not reset and the same process can continue to occupy slots 2-7 and finally, when the above step 1-5 is repeated again, step 3 BPF program won't be able to claim an empty slot and a warning will be issued. To fix the issue, for unset() function, we should traverse from the last slot to the first. This way, the above issue can be avoided. The same reverse traversal should also be done in bpf_get_local_storage() helper itself. Otherwise, incorrect local storage may be returned to BPF program. [0] https://github.com/osandov/drgn Fixes: b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210810010413.1976277-1-yhs@fb.com --- include/linux/bpf-cgroup.h | 4 ++-- kernel/bpf/helpers.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b47..6c9b10d82c80 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -201,8 +201,8 @@ static inline void bpf_cgroup_storage_unset(void) { int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 0b04553e8c44..7a97b2f4747d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -397,8 +397,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) void *ptr; int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); From c34f674c8875235725c3ef86147a627f165d23b4 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 00:59:12 +0200 Subject: [PATCH 1376/1469] net: dsa: microchip: Fix ksz_read64() ksz_read64() currently does some dubious byte-swapping on the two halves of a 64-bit register, and then only returns the high bits. Replace this with a straightforward expression. Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz_common.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 2e6bfd333f50..6afbb41ad39e 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -205,12 +205,8 @@ static inline int ksz_read64(struct ksz_device *dev, u32 reg, u64 *val) int ret; ret = regmap_bulk_read(dev->regmap[2], reg, value, 2); - if (!ret) { - /* Ick! ToDo: Add 64bit R/W to regmap on 32bit systems */ - value[0] = swab32(value[0]); - value[1] = swab32(value[1]); - *val = swab64((u64)*value); - } + if (!ret) + *val = (u64)value[0] << 32 | value[1]; return ret; } From ef3b02a1d79b691f9a354c4903cf1e6917e315f9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 00:59:28 +0200 Subject: [PATCH 1377/1469] net: dsa: microchip: ksz8795: Fix PVID tag insertion ksz8795 has never actually enabled PVID tag insertion, and it also programmed the PVID incorrectly. To fix this: * Allow tag insertion to be controlled per ingress port. On most chips, set bit 2 in Global Control 19. On KSZ88x3 this control flag doesn't exist. * When adding a PVID: - Set the appropriate register bits to enable tag insertion on egress at every other port if this was the packet's ingress port. - Mask *out* the VID from the default tag, before or-ing in the new PVID. * When removing a PVID: - Clear the same control bits to disable tag insertion. - Don't update the default tag. This wasn't doing anything useful. Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 26 ++++++++++++++++++------- drivers/net/dsa/microchip/ksz8795_reg.h | 4 ++++ 2 files changed, 23 insertions(+), 7 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 560f6843bb65..b788db829d07 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1124,6 +1124,16 @@ static int ksz8_port_vlan_filtering(struct dsa_switch *ds, int port, bool flag, return 0; } +static void ksz8_port_enable_pvid(struct ksz_device *dev, int port, bool state) +{ + if (ksz_is_ksz88x3(dev)) { + ksz_cfg(dev, REG_SW_INSERT_SRC_PVID, + 0x03 << (4 - 2 * port), state); + } else { + ksz_pwrite8(dev, port, REG_PORT_CTRL_12, state ? 0x0f : 0x00); + } +} + static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) @@ -1160,9 +1170,11 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, u16 vid; ksz_pread16(dev, port, REG_PORT_CTRL_VID, &vid); - vid &= 0xfff; + vid &= ~VLAN_VID_MASK; vid |= new_pvid; ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, vid); + + ksz8_port_enable_pvid(dev, port, true); } return 0; @@ -1173,7 +1185,7 @@ static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, { bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct ksz_device *dev = ds->priv; - u16 data, pvid, new_pvid = 0; + u16 data, pvid; u8 fid, member, valid; if (ksz_is_ksz88x3(dev)) @@ -1195,14 +1207,11 @@ static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, valid = 0; } - if (pvid == vlan->vid) - new_pvid = 1; - ksz8_to_vlan(dev, fid, member, valid, &data); ksz8_w_vlan_table(dev, vlan->vid, data); - if (new_pvid != pvid) - ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, pvid); + if (pvid == vlan->vid) + ksz8_port_enable_pvid(dev, port, false); return 0; } @@ -1435,6 +1444,9 @@ static int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false); + if (!ksz_is_ksz88x3(dev)) + ksz_cfg(dev, REG_SW_CTRL_19, SW_INS_TAG_ENABLE, true); + /* set broadcast storm protection 10% rate */ regmap_update_bits(dev->regmap[1], S_REPLACE_VID_CTRL, BROADCAST_STORM_RATE, diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h index a32355624f31..6b40bc25f7ff 100644 --- a/drivers/net/dsa/microchip/ksz8795_reg.h +++ b/drivers/net/dsa/microchip/ksz8795_reg.h @@ -631,6 +631,10 @@ #define REG_PORT_4_OUT_RATE_3 0xEE #define REG_PORT_5_OUT_RATE_3 0xFE +/* 88x3 specific */ + +#define REG_SW_INSERT_SRC_PVID 0xC2 + /* PME */ #define SW_PME_OUTPUT_ENABLE BIT(1) From 8f4f58f88fe0d9bd591f21f53de7dbd42baeb3fa Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 00:59:37 +0200 Subject: [PATCH 1378/1469] net: dsa: microchip: ksz8795: Reject unsupported VLAN configuration The switches supported by ksz8795 only have a per-port flag for Tag Removal. This means it is not possible to support both tagged and untagged VLANs on the same port. Reject attempts to add a VLAN that requires the flag to be changed, unless there are no VLANs currently configured. VID 0 is excluded from this check since it is untagged regardless of the state of the flag. On the CPU port we could support tagged and untagged VLANs at the same time. This will be enabled by a later patch. Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 27 +++++++++++++++++++++++++- drivers/net/dsa/microchip/ksz_common.h | 1 + 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index b788db829d07..29a18058d1ee 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1140,13 +1140,38 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, { bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct ksz_device *dev = ds->priv; + struct ksz_port *p = &dev->ports[port]; u16 data, new_pvid = 0; u8 fid, member, valid; if (ksz_is_ksz88x3(dev)) return -ENOTSUPP; - ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + /* If a VLAN is added with untagged flag different from the + * port's Remove Tag flag, we need to change the latter. + * Ignore VID 0, which is always untagged. + */ + if (untagged != p->remove_tag && vlan->vid != 0) { + unsigned int vid; + + /* Reject attempts to add a VLAN that requires the + * Remove Tag flag to be changed, unless there are no + * other VLANs currently configured. + */ + for (vid = 1; vid < dev->num_vlans; ++vid) { + /* Skip the VID we are going to add or reconfigure */ + if (vid == vlan->vid) + continue; + + ksz8_from_vlan(dev, dev->vlan_cache[vid].table[0], + &fid, &member, &valid); + if (valid && (member & BIT(port))) + return -EINVAL; + } + + ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + p->remove_tag = untagged; + } ksz8_r_vlan_table(dev, vlan->vid, &data); ksz8_from_vlan(dev, data, &fid, &member, &valid); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 6afbb41ad39e..1597c63988b4 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -27,6 +27,7 @@ struct ksz_port_mib { struct ksz_port { u16 member; u16 vid_member; + bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ int stp_state; struct phy_device phydev; From af01754f9e3c553a2ee63b4693c79a3956e230ab Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 00:59:47 +0200 Subject: [PATCH 1379/1469] net: dsa: microchip: ksz8795: Fix VLAN untagged flag change on deletion When a VLAN is deleted from a port, the flags in struct switchdev_obj_port_vlan are always 0. ksz8_port_vlan_del() copies the BRIDGE_VLAN_INFO_UNTAGGED flag to the port's Tag Removal flag, and therefore always clears it. In case there are multiple VLANs configured as untagged on this port - which seems useless, but is allowed - deleting one of them changes the remaining VLANs to be tagged. It's only ever necessary to change this flag when a VLAN is added to the port, so leave it unchanged in ksz8_port_vlan_del(). Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 29a18058d1ee..af3744d8b6cf 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1208,7 +1208,6 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { - bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct ksz_device *dev = ds->priv; u16 data, pvid; u8 fid, member, valid; @@ -1219,8 +1218,6 @@ static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid); pvid = pvid & 0xFFF; - ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); - ksz8_r_vlan_table(dev, vlan->vid, &data); ksz8_from_vlan(dev, data, &fid, &member, &valid); From 9130c2d30c17846287b803a9803106318cbe5266 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 00:59:57 +0200 Subject: [PATCH 1380/1469] net: dsa: microchip: ksz8795: Use software untagging on CPU port On the CPU port, we can support both tagged and untagged VLANs at the same time by doing any necessary untagging in software rather than hardware. To enable that, keep the CPU port's Remove Tag flag cleared and set the dsa_switch::untag_bridge_pvid flag. Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index af3744d8b6cf..8bcef4b2dd6f 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1150,8 +1150,10 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, /* If a VLAN is added with untagged flag different from the * port's Remove Tag flag, we need to change the latter. * Ignore VID 0, which is always untagged. + * Ignore CPU port, which will always be tagged. */ - if (untagged != p->remove_tag && vlan->vid != 0) { + if (untagged != p->remove_tag && vlan->vid != 0 && + port != dev->cpu_port) { unsigned int vid; /* Reject attempts to add a VLAN that requires the @@ -1751,6 +1753,11 @@ static int ksz8_switch_init(struct ksz_device *dev) /* set the real number of ports */ dev->ds->num_ports = dev->port_cnt; + /* We rely on software untagging on the CPU port, so that we + * can support both tagged and untagged VLANs + */ + dev->ds->untag_bridge_pvid = true; + return 0; } From 164844135a3f215d3018ee9d6875336beb942413 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 01:00:06 +0200 Subject: [PATCH 1381/1469] net: dsa: microchip: ksz8795: Fix VLAN filtering Currently ksz8_port_vlan_filtering() sets or clears the VLAN Enable hardware flag. That controls discarding of packets with a VID that has not been enabled for any port on the switch. Since it is a global flag, set the dsa_switch::vlan_filtering_is_global flag so that the DSA core understands this can't be controlled per port. When VLAN filtering is enabled, the switch should also discard packets with a VID that's not enabled on the ingress port. Set or clear each external port's VLAN Ingress Filter flag in ksz8_port_vlan_filtering() to make that happen. Fixes: e66f840c08a2 ("net: dsa: ksz: Add Microchip KSZ8795 DSA driver") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 8bcef4b2dd6f..b1a3763c97de 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1119,8 +1119,14 @@ static int ksz8_port_vlan_filtering(struct dsa_switch *ds, int port, bool flag, if (ksz_is_ksz88x3(dev)) return -ENOTSUPP; + /* Discard packets with VID not enabled on the switch */ ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag); + /* Discard packets with VID not enabled on the ingress port */ + for (port = 0; port < dev->phy_port_cnt; ++port) + ksz_port_cfg(dev, port, REG_PORT_CTRL_2, PORT_INGRESS_FILTER, + flag); + return 0; } @@ -1758,6 +1764,11 @@ static int ksz8_switch_init(struct ksz_device *dev) */ dev->ds->untag_bridge_pvid = true; + /* VLAN filtering is partly controlled by the global VLAN + * Enable flag + */ + dev->ds->vlan_filtering_is_global = true; + return 0; } From 411d466d94a6b16a20c8b552e403b7e8ce2397a2 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 10 Aug 2021 01:00:15 +0200 Subject: [PATCH 1382/1469] net: dsa: microchip: ksz8795: Don't use phy_port_cnt in VLAN table lookup The magic number 4 in VLAN table lookup was the number of entries we can read and write at once. Using phy_port_cnt here doesn't make sense and presumably broke VLAN filtering for 3-port switches. Change it back to 4. Fixes: 4ce2a984abd8 ("net: dsa: microchip: ksz8795: use phy_port_cnt ...") Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index b1a3763c97de..c5142f86a3c7 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -687,8 +687,8 @@ static void ksz8_r_vlan_entries(struct ksz_device *dev, u16 addr) shifts = ksz8->shifts; ksz8_r_table(dev, TABLE_VLAN, addr, &data); - addr *= dev->phy_port_cnt; - for (i = 0; i < dev->phy_port_cnt; i++) { + addr *= 4; + for (i = 0; i < 4; i++) { dev->vlan_cache[addr + i].table[0] = (u16)data; data >>= shifts[VLAN_TABLE]; } @@ -702,7 +702,7 @@ static void ksz8_r_vlan_table(struct ksz_device *dev, u16 vid, u16 *vlan) u64 buf; data = (u16 *)&buf; - addr = vid / dev->phy_port_cnt; + addr = vid / 4; index = vid & 3; ksz8_r_table(dev, TABLE_VLAN, addr, &buf); *vlan = data[index]; @@ -716,7 +716,7 @@ static void ksz8_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan) u64 buf; data = (u16 *)&buf; - addr = vid / dev->phy_port_cnt; + addr = vid / 4; index = vid & 3; ksz8_r_table(dev, TABLE_VLAN, addr, &buf); data[index] = vlan; From 438553958ba19296663c6d6583d208dfb6792830 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:40 +0200 Subject: [PATCH 1383/1469] PCI/MSI: Enable and mask MSI-X early The ordering of MSI-X enable in hardware is dysfunctional: 1) MSI-X is disabled in the control register 2) Various setup functions 3) pci_msi_setup_msi_irqs() is invoked which ends up accessing the MSI-X table entries 4) MSI-X is enabled and masked in the control register with the comment that enabling is required for some hardware to access the MSI-X table Step #4 obviously contradicts #3. The history of this is an issue with the NIU hardware. When #4 was introduced the table access actually happened in msix_program_entries() which was invoked after enabling and masking MSI-X. This was changed in commit d71d6432e105 ("PCI/MSI: Kill redundant call of irq_set_msi_desc() for MSI-X interrupts") which removed the table write from msix_program_entries(). Interestingly enough nobody noticed and either NIU still works or it did not get any testing with a kernel 3.19 or later. Nevertheless this is inconsistent and there is no reason why MSI-X can't be enabled and masked in the control register early on, i.e. move step #4 above to step #1. This preserves the NIU workaround and has no side effects on other hardware. Fixes: d71d6432e105 ("PCI/MSI: Kill redundant call of irq_set_msi_desc() for MSI-X interrupts") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Ashok Raj Reviewed-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.344136412@linutronix.de --- drivers/pci/msi.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 9232255c8515..5d39ed828085 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -772,18 +772,25 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, u16 control; void __iomem *base; - /* Ensure MSI-X is disabled while it is set up */ - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + /* + * Some devices require MSI-X to be enabled before the MSI-X + * registers can be accessed. Mask all the vectors to prevent + * interrupts coming in before they're fully set up. + */ + pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL | + PCI_MSIX_FLAGS_ENABLE); pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ base = msix_map_region(dev, msix_table_size(control)); - if (!base) - return -ENOMEM; + if (!base) { + ret = -ENOMEM; + goto out_disable; + } ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) - return ret; + goto out_disable; ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) @@ -794,14 +801,6 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, if (ret) goto out_free; - /* - * Some devices require MSI-X to be enabled before we can touch the - * MSI-X registers. We need to mask all the vectors to prevent - * interrupts coming in before they're fully set up. - */ - pci_msix_clear_and_set_ctrl(dev, 0, - PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE); - msix_program_entries(dev, entries); ret = populate_msi_sysfs(dev); @@ -836,6 +835,9 @@ out_avail: out_free: free_msi_irqs(dev); +out_disable: + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + return ret; } From 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:41 +0200 Subject: [PATCH 1384/1469] PCI/MSI: Mask all unused MSI-X entries When MSI-X is enabled the ordering of calls is: msix_map_region(); msix_setup_entries(); pci_msi_setup_msi_irqs(); msix_program_entries(); This has a few interesting issues: 1) msix_setup_entries() allocates the MSI descriptors and initializes them except for the msi_desc:masked member which is left zero initialized. 2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets up the MSI interrupts which ends up in pci_write_msi_msg() unless the interrupt chip provides its own irq_write_msi_msg() function. 3) msix_program_entries() does not do what the name suggests. It solely updates the entries array (if not NULL) and initializes the masked member for each MSI descriptor by reading the hardware state and then masks the entry. Obviously this has some issues: 1) The uninitialized masked member of msi_desc prevents the enforcement of masking the entry in pci_write_msi_msg() depending on the cached masked bit. Aside of that half initialized data is a NONO in general 2) msix_program_entries() only ensures that the actually allocated entries are masked. This is wrong as experimentation with crash testing and crash kernel kexec has shown. This limited testing unearthed that when the production kernel had more entries in use and unmasked when it crashed and the crash kernel allocated a smaller amount of entries, then a full scan of all entries found unmasked entries which were in use in the production kernel. This is obviously a device or emulation issue as the device reset should mask all MSI-X table entries, but obviously that's just part of the paper specification. Cure this by: 1) Masking all table entries in hardware 2) Initializing msi_desc::masked in msix_setup_entries() 3) Removing the mask dance in msix_program_entries() 4) Renaming msix_program_entries() to msix_update_entries() to reflect the purpose of that function. As the masking of unused entries has never been done the Fixes tag refers to a commit in: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de --- drivers/pci/msi.c | 47 ++++++++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 19 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 5d39ed828085..57c9ec9b976b 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -691,6 +691,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, { struct irq_affinity_desc *curmsk, *masks = NULL; struct msi_desc *entry; + void __iomem *addr; int ret, i; int vec_count = pci_msix_vec_count(dev); @@ -711,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.is_msix = 1; entry->msi_attrib.is_64 = 1; + if (entries) entry->msi_attrib.entry_nr = entries[i].entry; else @@ -722,6 +724,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; + addr = pci_msix_desc_addr(entry); + if (addr) + entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + list_add_tail(&entry->list, dev_to_msi_list(&dev->dev)); if (masks) curmsk++; @@ -732,28 +738,27 @@ out: return ret; } -static void msix_program_entries(struct pci_dev *dev, - struct msix_entry *entries) +static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries) { struct msi_desc *entry; - int i = 0; - void __iomem *desc_addr; for_each_pci_msi_entry(entry, dev) { - if (entries) - entries[i++].vector = entry->irq; - - desc_addr = pci_msix_desc_addr(entry); - if (desc_addr) - entry->masked = readl(desc_addr + - PCI_MSIX_ENTRY_VECTOR_CTRL); - else - entry->masked = 0; - - msix_mask_irq(entry, 1); + if (entries) { + entries->vector = entry->irq; + entries++; + } } } +static void msix_mask_all(void __iomem *base, int tsize) +{ + u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT; + int i; + + for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE) + writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); +} + /** * msix_capability_init - configure device's MSI-X capability * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -768,9 +773,9 @@ static void msix_program_entries(struct pci_dev *dev, static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - int ret; - u16 control; void __iomem *base; + int ret, tsize; + u16 control; /* * Some devices require MSI-X to be enabled before the MSI-X @@ -782,12 +787,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ - base = msix_map_region(dev, msix_table_size(control)); + tsize = msix_table_size(control); + base = msix_map_region(dev, tsize); if (!base) { ret = -ENOMEM; goto out_disable; } + /* Ensure that all table entries are masked. */ + msix_mask_all(base, tsize); + ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) goto out_disable; @@ -801,7 +810,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, if (ret) goto out_free; - msix_program_entries(dev, entries); + msix_update_entries(dev, entries); ret = populate_msi_sysfs(dev); if (ret) From da181dc974ad667579baece33c2c8d2d1e4558d5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:42 +0200 Subject: [PATCH 1385/1469] PCI/MSI: Enforce that MSI-X table entry is masked for update The specification (PCIe r5.0, sec 6.1.4.5) states: For MSI-X, a function is permitted to cache Address and Data values from unmasked MSI-X Table entries. However, anytime software unmasks a currently masked MSI-X Table entry either by clearing its Mask bit or by clearing the Function Mask bit, the function must update any Address or Data values that it cached from that entry. If software changes the Address or Data value of an entry while the entry is unmasked, the result is undefined. The Linux kernel's MSI-X support never enforced that the entry is masked before the entry is modified hence the Fixes tag refers to a commit in: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Enforce the entry to be masked across the update. There is no point in enforcing this to be handled at all possible call sites as this is just pointless code duplication and the common update function is the obvious place to enforce this. Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support") Reported-by: Kevin Tian Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.462096385@linutronix.de --- drivers/pci/msi.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 57c9ec9b976b..7ee1ac47caa7 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -289,13 +289,28 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) /* Don't touch the hardware now */ } else if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); + bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT); if (!base) goto skip; + /* + * The specification mandates that the entry is masked + * when the message is modified: + * + * "If software changes the Address or Data value of an + * entry while the entry is unmasked, the result is + * undefined." + */ + if (unmasked) + __pci_msix_desc_mask_irq(entry, PCI_MSIX_ENTRY_CTRL_MASKBIT); + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); writel(msg->data, base + PCI_MSIX_ENTRY_DATA); + + if (unmasked) + __pci_msix_desc_mask_irq(entry, 0); } else { int pos = dev->msi_cap; u16 msgctl; From b9255a7cb51754e8d2645b65dd31805e282b4f3e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:43 +0200 Subject: [PATCH 1386/1469] PCI/MSI: Enforce MSI[X] entry updates to be visible Nothing enforces the posted writes to be visible when the function returns. Flush them even if the flush might be redundant when the entry is masked already as the unmask will flush as well. This is either setup or a rare affinity change event so the extra flush is not the end of the world. While this is more a theoretical issue especially the logic in the X86 specific msi_set_affinity() function relies on the assumption that the update has reached the hardware when the function returns. Again, as this never has been enforced the Fixes tag refers to a commit in: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.515188147@linutronix.de --- drivers/pci/msi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 7ee1ac47caa7..434c7041b176 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -311,6 +311,9 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) if (unmasked) __pci_msix_desc_mask_irq(entry, 0); + + /* Ensure that the writes are visible in the device */ + readl(base + PCI_MSIX_ENTRY_DATA); } else { int pos = dev->msi_cap; u16 msgctl; @@ -331,6 +334,8 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data); } + /* Ensure that the writes are visible in the device */ + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); } skip: From 361fd37397f77578735907341579397d5bed0a2d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:44 +0200 Subject: [PATCH 1387/1469] PCI/MSI: Do not set invalid bits in MSI mask msi_mask_irq() takes a mask and a flags argument. The mask argument is used to mask out bits from the cached mask and the flags argument to set bits. Some places invoke it with a flags argument which sets bits which are not used by the device, i.e. when the device supports up to 8 vectors a full unmask in some places sets the mask to 0xFFFFFF00. While devices probably do not care, it's still bad practice. Fixes: 7ba1930db02f ("PCI MSI: Unmask MSI if setup failed") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.568173099@linutronix.de --- drivers/pci/msi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 434c7041b176..e27ac6b5b8d5 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -656,21 +656,21 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, /* Configure MSI capability structure */ ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = msi_verify_entries(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = populate_msi_sysfs(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } @@ -962,7 +962,7 @@ static void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); /* Keep cached state to be restored */ - __pci_msi_desc_mask_irq(desc, mask, ~mask); + __pci_msi_desc_mask_irq(desc, mask, 0); /* Restore dev->irq to its default pin-assertion IRQ */ dev->irq = desc->msi_attrib.default_irq; From 689e6b5351573c38ccf92a0dd8b3e2c2241e4aff Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:45 +0200 Subject: [PATCH 1388/1469] PCI/MSI: Correct misleading comments The comments about preserving the cached state in pci_msi[x]_shutdown() are misleading as the MSI descriptors are freed right after those functions return. So there is nothing to restore. Preparatory change. Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.621609423@linutronix.de --- drivers/pci/msi.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index e27ac6b5b8d5..b3f58074e8d4 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -961,7 +961,6 @@ static void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); - /* Keep cached state to be restored */ __pci_msi_desc_mask_irq(desc, mask, 0); /* Restore dev->irq to its default pin-assertion IRQ */ @@ -1047,10 +1046,8 @@ static void pci_msix_shutdown(struct pci_dev *dev) } /* Return the device with MSI-X masked as initial states */ - for_each_pci_msi_entry(entry, dev) { - /* Keep cached states to be restored */ + for_each_pci_msi_entry(entry, dev) __pci_msix_desc_mask_irq(entry, 1); - } pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); pci_intx_for_msi(dev, 1); From d28d4ad2a1aef27458b3383725bb179beb8d015c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:46 +0200 Subject: [PATCH 1389/1469] PCI/MSI: Use msi_mask_irq() in pci_msi_shutdown() No point in using the raw write function from shutdown. Preparatory change to introduce proper serialization for the msi_desc::masked cache. Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.674391354@linutronix.de --- drivers/pci/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index b3f58074e8d4..f0f7026b7ac0 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -961,7 +961,7 @@ static void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); - __pci_msi_desc_mask_irq(desc, mask, 0); + msi_mask_irq(desc, mask, 0); /* Restore dev->irq to its default pin-assertion IRQ */ dev->irq = desc->msi_attrib.default_irq; From 77e89afc25f30abd56e76a809ee2884d7c1b63ce Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:47 +0200 Subject: [PATCH 1390/1469] PCI/MSI: Protect msi_desc::masked for multi-MSI Multi-MSI uses a single MSI descriptor and there is a single mask register when the device supports per vector masking. To avoid reading back the mask register the value is cached in the MSI descriptor and updates are done by clearing and setting bits in the cache and writing it to the device. But nothing protects msi_desc::masked and the mask register from being modified concurrently on two different CPUs for two different Linux interrupts which belong to the same multi-MSI descriptor. Add a lock to struct device and protect any operation on the mask and the mask register with it. This makes the update of msi_desc::masked unconditional, but there is no place which requires a modification of the hardware register without updating the masked cache. msi_mask_irq() is now an empty wrapper which will be cleaned up in follow up changes. The problem goes way back to the initial support of multi-MSI, but picking the commit which introduced the mask cache is a valid cut off point (2.6.30). Fixes: f2440d9acbe8 ("PCI MSI: Refactor interrupt masking code") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.726833414@linutronix.de --- drivers/base/core.c | 1 + drivers/pci/msi.c | 19 ++++++++++--------- include/linux/device.h | 1 + include/linux/msi.h | 2 +- 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index f6360490a4a3..6c0ef9d55a34 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2837,6 +2837,7 @@ void device_initialize(struct device *dev) device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index f0f7026b7ac0..e5e75331b415 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -143,24 +143,25 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - u32 mask_bits = desc->masked; + raw_spinlock_t *lock = &desc->dev->msi_lock; + unsigned long flags; if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit) - return 0; + return; - mask_bits &= ~mask; - mask_bits |= flag; + raw_spin_lock_irqsave(lock, flags); + desc->masked &= ~mask; + desc->masked |= flag; pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - mask_bits); - - return mask_bits; + desc->masked); + raw_spin_unlock_irqrestore(lock, flags); } static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag); + __pci_msi_desc_mask_irq(desc, mask, flag); } static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..e53aa5065f58 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -506,6 +506,7 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/msi.h b/include/linux/msi.h index 6aff469e511d..e8bdcb83172b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -233,7 +233,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); From 826da771291fc25a428e871f9e7fb465e390f852 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:48 +0200 Subject: [PATCH 1391/1469] genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP X86 IO/APIC and MSI interrupts (when used without interrupts remapping) require that the affinity setup on startup is done before the interrupt is enabled for the first time as the non-remapped operation mode cannot safely migrate enabled interrupts from arbitrary contexts. Provide a new irq chip flag which allows affected hardware to request this. This has to be opt-in because there have been reports in the past that some interrupt chips cannot handle affinity setting before startup. Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de --- include/linux/irq.h | 2 ++ kernel/irq/chip.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/irq.h b/include/linux/irq.h index 8e9a9ae471a6..c8293c817646 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state + * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +582,7 @@ enum { IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), + IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), }; #include diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7f04c7d8296e..a98bcfc4be7b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: + if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) + irq_setup_affinity(desc); ret = __irq_startup(desc); - irq_setup_affinity(desc); + if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) + irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); From 0c0e37dc11671384e53ba6ede53a4d91162a2cc5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:49 +0200 Subject: [PATCH 1392/1469] x86/ioapic: Force affinity setup before startup The IO/APIC cannot handle interrupt affinity changes safely after startup other than from an interrupt handler. The startup sequence in the generic interrupt code violates that assumption. Mark the irq chip with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that the default interrupt setting happens before the interrupt is started up for the first time. Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.832143400@linutronix.de --- arch/x86/kernel/apic/io_apic.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d5c691a3208b..39224e035e47 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct irq_chip ioapic_ir_chip __read_mostly = { @@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static inline void init_IO_APIC_traps(void) From ff363f480e5997051dd1de949121ffda3b753741 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 23:51:50 +0200 Subject: [PATCH 1393/1469] x86/msi: Force affinity setup before startup The X86 MSI mechanism cannot handle interrupt affinity changes safely after startup other than from an interrupt handler, unless interrupt remapping is enabled. The startup sequence in the generic interrupt code violates that assumption. Mark the irq chips with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that the default interrupt setting happens before the interrupt is started up for the first time. While the interrupt remapping MSI chip does not require this, there is no point in treating it differently as this might spare an interrupt to a CPU which is not in the default affinity mask. For the non-remapping case go to the direct write path when the interrupt is not yet started similar to the not yet activated case. Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)") Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.886722080@linutronix.de --- arch/x86/kernel/apic/msi.c | 11 ++++++++--- arch/x86/kernel/hpet.c | 2 +- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 44ebe25e7703..dbacb9ec8843 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * The quirk bit is not set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ if (!irqd_msi_nomask_quirk(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + !irqd_is_started(irqd) || cfg->dest_apicid == old_cfg.dest_apicid) { irq_msi_update_msg(irqd, cfg); return ret; @@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, @@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct msi_domain_info pci_msi_ir_domain_info = { @@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static int dmar_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 08651a4e6aa0..42fc41dd0e1f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = { .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_write_msi_msg = hpet_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP, }; static int hpet_msi_init(struct irq_domain *domain, From 1090340f7ee53e824fd4eef66a4855d548110c5b Mon Sep 17 00:00:00 2001 From: Takeshi Misawa Date: Thu, 5 Aug 2021 16:54:14 +0900 Subject: [PATCH 1394/1469] net: Fix memory leak in ieee802154_raw_deliver If IEEE-802.15.4-RAW is closed before receive skb, skb is leaked. Fix this, by freeing sk_receive_queue in sk->sk_destruct(). syzbot report: BUG: memory leak unreferenced object 0xffff88810f644600 (size 232): comm "softirq", pid 0, jiffies 4294967032 (age 81.270s) hex dump (first 32 bytes): 10 7d 4b 12 81 88 ff ff 10 7d 4b 12 81 88 ff ff .}K......}K..... 00 00 00 00 00 00 00 00 40 7c 4b 12 81 88 ff ff ........@|K..... backtrace: [] skb_clone+0xaa/0x2b0 net/core/skbuff.c:1496 [] ieee802154_raw_deliver net/ieee802154/socket.c:369 [inline] [] ieee802154_rcv+0x100/0x340 net/ieee802154/socket.c:1070 [] __netif_receive_skb_one_core+0x6a/0xa0 net/core/dev.c:5384 [] __netif_receive_skb+0x27/0xa0 net/core/dev.c:5498 [] netif_receive_skb_internal net/core/dev.c:5603 [inline] [] netif_receive_skb+0x59/0x260 net/core/dev.c:5662 [] ieee802154_deliver_skb net/mac802154/rx.c:29 [inline] [] ieee802154_subif_frame net/mac802154/rx.c:102 [inline] [] __ieee802154_rx_handle_packet net/mac802154/rx.c:212 [inline] [] ieee802154_rx+0x612/0x620 net/mac802154/rx.c:284 [] ieee802154_tasklet_handler+0x86/0xa0 net/mac802154/main.c:35 [] tasklet_action_common.constprop.0+0x5b/0x100 kernel/softirq.c:557 [] __do_softirq+0xbf/0x2ab kernel/softirq.c:345 [] do_softirq kernel/softirq.c:248 [inline] [] do_softirq+0x5c/0x80 kernel/softirq.c:235 [] __local_bh_enable_ip+0x51/0x60 kernel/softirq.c:198 [] local_bh_enable include/linux/bottom_half.h:32 [inline] [] rcu_read_unlock_bh include/linux/rcupdate.h:745 [inline] [] __dev_queue_xmit+0x7f4/0xf60 net/core/dev.c:4221 [] raw_sendmsg+0x1f4/0x2b0 net/ieee802154/socket.c:295 [] sock_sendmsg_nosec net/socket.c:654 [inline] [] sock_sendmsg+0x56/0x80 net/socket.c:674 [] __sys_sendto+0x15c/0x200 net/socket.c:1977 [] __do_sys_sendto net/socket.c:1989 [inline] [] __se_sys_sendto net/socket.c:1985 [inline] [] __x64_sys_sendto+0x26/0x30 net/socket.c:1985 Fixes: 9ec767160357 ("net: add IEEE 802.15.4 socket family implementation") Reported-and-tested-by: syzbot+1f68113fa907bf0695a8@syzkaller.appspotmail.com Signed-off-by: Takeshi Misawa Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20210805075414.GA15796@DESKTOP Signed-off-by: Stefan Schmidt --- net/ieee802154/socket.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a45a0401adc5..c25f7617770c 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -984,6 +984,11 @@ static const struct proto_ops ieee802154_dgram_ops = { .sendpage = sock_no_sendpage, }; +static void ieee802154_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + /* Create a socket. Initialise the socket, blank the addresses * set the state. */ @@ -1024,7 +1029,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, sock->ops = ops; sock_init_data(sock, sk); - /* FIXME: sk->sk_destruct */ + sk->sk_destruct = ieee802154_sock_destruct; sk->sk_family = PF_IEEE802154; /* Checksums on by default */ From 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Aug 2021 02:45:47 -0700 Subject: [PATCH 1395/1469] net: igmp: fix data-race in igmp_ifc_timer_expire() Fix the data-race reported by syzbot [1] Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count while another change just occured from another context. in_dev->mr_ifc_count is only 8bit wide, so the race had little consequences. [1] BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0: igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821 igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356 ____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461 __ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199 ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218 do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline] ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423 tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362 __sys_setsockopt+0x18f/0x200 net/socket.c:2159 __do_sys_setsockopt net/socket.c:2170 [inline] __se_sys_setsockopt net/socket.c:2167 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2167 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1: igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808 call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419 expire_timers+0x135/0x250 kernel/time/timer.c:1464 __run_timers+0x358/0x420 kernel/time/timer.c:1732 run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745 __do_softirq+0x12c/0x26e kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636 sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638 console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646 vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174 vprintk_default+0x22/0x30 kernel/printk/printk.c:2185 vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392 printk+0x62/0x87 kernel/printk/printk.c:2216 selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041 security_netlink_send+0x42/0x90 security/security.c:2070 netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmsg+0x1ed/0x270 net/socket.c:2475 __do_sys_sendmsg net/socket.c:2484 [inline] __se_sys_sendmsg net/socket.c:2482 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2482 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x01 -> 0x02 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f23..a51360087b19 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u8 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } @@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); From 019d0454c61707879cf9853c894e0a191f6b9774 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 9 Aug 2021 14:52:29 -0700 Subject: [PATCH 1396/1469] bpf, core: Fix kernel-doc notation Fix kernel-doc warnings in kernel/bpf/core.c (found by scripts/kernel-doc and W=1 builds). That is, correct a function name in a comment and add return descriptions for 2 functions. Fixes these kernel-doc warnings: kernel/bpf/core.c:1372: warning: expecting prototype for __bpf_prog_run(). Prototype was for ___bpf_prog_run() instead kernel/bpf/core.c:1372: warning: No description found for return value of '___bpf_prog_run' kernel/bpf/core.c:1883: warning: No description found for return value of 'bpf_prog_select_runtime' Signed-off-by: Randy Dunlap Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210809215229.7556-1-rdunlap@infradead.org --- kernel/bpf/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b1a5fc04492b..0a28a8095d3e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1362,11 +1362,13 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) } /** - * __bpf_prog_run - run eBPF program on a given context + * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. + * + * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { @@ -1878,6 +1880,9 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via BPF_PROG_RUN() macro. + * + * Return: the &fp argument along with &err set to 0 for success or + * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { From cd391280bf4693ceddca8f19042cff42f98c1a89 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Aug 2021 14:19:53 +0300 Subject: [PATCH 1397/1469] net: dsa: hellcreek: fix broken backpressure in .port_fdb_dump rtnl_fdb_dump() has logic to split a dump of PF_BRIDGE neighbors into multiple netlink skbs if the buffer provided by user space is too small (one buffer will typically handle a few hundred FDB entries). When the current buffer becomes full, nlmsg_put() in dsa_slave_port_fdb_do_dump() returns -EMSGSIZE and DSA saves the index of the last dumped FDB entry, returns to rtnl_fdb_dump() up to that point, and then the dump resumes on the same port with a new skb, and FDB entries up to the saved index are simply skipped. Since dsa_slave_port_fdb_do_dump() is pointed to by the "cb" passed to drivers, then drivers must check for the -EMSGSIZE error code returned by it. Otherwise, when a netlink skb becomes full, DSA will no longer save newly dumped FDB entries to it, but the driver will continue dumping. So FDB entries will be missing from the dump. Fix the broken backpressure by propagating the "cb" return code and allow rtnl_fdb_dump() to restart the FDB dump with a new skb. Fixes: e4b27ebc780f ("net: dsa: Add DSA driver for Hirschmann Hellcreek switches") Signed-off-by: Vladimir Oltean Acked-by: Kurt Kanzenbach Signed-off-by: David S. Miller --- drivers/net/dsa/hirschmann/hellcreek.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 9fdcc4bde480..5c54ae1be62c 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -912,6 +912,7 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, { struct hellcreek *hellcreek = ds->priv; u16 entries; + int ret = 0; size_t i; mutex_lock(&hellcreek->reg_lock); @@ -943,12 +944,14 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, if (!(entry.portmask & BIT(port))) continue; - cb(entry.mac, 0, entry.is_static, data); + ret = cb(entry.mac, 0, entry.is_static, data); + if (ret) + break; } mutex_unlock(&hellcreek->reg_lock); - return 0; + return ret; } static int hellcreek_vlan_filtering(struct dsa_switch *ds, int port, From ada2fee185d8145afb89056558bb59545b9dbdd0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Aug 2021 14:19:54 +0300 Subject: [PATCH 1398/1469] net: dsa: lan9303: fix broken backpressure in .port_fdb_dump rtnl_fdb_dump() has logic to split a dump of PF_BRIDGE neighbors into multiple netlink skbs if the buffer provided by user space is too small (one buffer will typically handle a few hundred FDB entries). When the current buffer becomes full, nlmsg_put() in dsa_slave_port_fdb_do_dump() returns -EMSGSIZE and DSA saves the index of the last dumped FDB entry, returns to rtnl_fdb_dump() up to that point, and then the dump resumes on the same port with a new skb, and FDB entries up to the saved index are simply skipped. Since dsa_slave_port_fdb_do_dump() is pointed to by the "cb" passed to drivers, then drivers must check for the -EMSGSIZE error code returned by it. Otherwise, when a netlink skb becomes full, DSA will no longer save newly dumped FDB entries to it, but the driver will continue dumping. So FDB entries will be missing from the dump. Fix the broken backpressure by propagating the "cb" return code and allow rtnl_fdb_dump() to restart the FDB dump with a new skb. Fixes: ab335349b852 ("net: dsa: lan9303: Add port_fast_age and port_fdb_dump methods") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/lan9303-core.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 344374025426..d7ce281570b5 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -557,12 +557,12 @@ static int lan9303_alr_make_entry_raw(struct lan9303 *chip, u32 dat0, u32 dat1) return 0; } -typedef void alr_loop_cb_t(struct lan9303 *chip, u32 dat0, u32 dat1, - int portmap, void *ctx); +typedef int alr_loop_cb_t(struct lan9303 *chip, u32 dat0, u32 dat1, + int portmap, void *ctx); -static void lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) +static int lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) { - int i; + int ret = 0, i; mutex_lock(&chip->alr_mutex); lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, @@ -582,13 +582,17 @@ static void lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) LAN9303_ALR_DAT1_PORT_BITOFFS; portmap = alrport_2_portmap[alrport]; - cb(chip, dat0, dat1, portmap, ctx); + ret = cb(chip, dat0, dat1, portmap, ctx); + if (ret) + break; lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, LAN9303_ALR_CMD_GET_NEXT); lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, 0); } mutex_unlock(&chip->alr_mutex); + + return ret; } static void alr_reg_to_mac(u32 dat0, u32 dat1, u8 mac[6]) @@ -606,18 +610,20 @@ struct del_port_learned_ctx { }; /* Clear learned (non-static) entry on given port */ -static void alr_loop_cb_del_port_learned(struct lan9303 *chip, u32 dat0, - u32 dat1, int portmap, void *ctx) +static int alr_loop_cb_del_port_learned(struct lan9303 *chip, u32 dat0, + u32 dat1, int portmap, void *ctx) { struct del_port_learned_ctx *del_ctx = ctx; int port = del_ctx->port; if (((BIT(port) & portmap) == 0) || (dat1 & LAN9303_ALR_DAT1_STATIC)) - return; + return 0; /* learned entries has only one port, we can just delete */ dat1 &= ~LAN9303_ALR_DAT1_VALID; /* delete entry */ lan9303_alr_make_entry_raw(chip, dat0, dat1); + + return 0; } struct port_fdb_dump_ctx { @@ -626,19 +632,19 @@ struct port_fdb_dump_ctx { dsa_fdb_dump_cb_t *cb; }; -static void alr_loop_cb_fdb_port_dump(struct lan9303 *chip, u32 dat0, - u32 dat1, int portmap, void *ctx) +static int alr_loop_cb_fdb_port_dump(struct lan9303 *chip, u32 dat0, + u32 dat1, int portmap, void *ctx) { struct port_fdb_dump_ctx *dump_ctx = ctx; u8 mac[ETH_ALEN]; bool is_static; if ((BIT(dump_ctx->port) & portmap) == 0) - return; + return 0; alr_reg_to_mac(dat0, dat1, mac); is_static = !!(dat1 & LAN9303_ALR_DAT1_STATIC); - dump_ctx->cb(mac, 0, is_static, dump_ctx->data); + return dump_ctx->cb(mac, 0, is_static, dump_ctx->data); } /* Set a static ALR entry. Delete entry if port_map is zero */ @@ -1210,9 +1216,7 @@ static int lan9303_port_fdb_dump(struct dsa_switch *ds, int port, }; dev_dbg(chip->dev, "%s(%d)\n", __func__, port); - lan9303_alr_loop(chip, alr_loop_cb_fdb_port_dump, &dump_ctx); - - return 0; + return lan9303_alr_loop(chip, alr_loop_cb_fdb_port_dump, &dump_ctx); } static int lan9303_port_mdb_prepare(struct dsa_switch *ds, int port, From 871a73a1c8f55da0a3db234e9dd816ea4fd546f2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Aug 2021 14:19:55 +0300 Subject: [PATCH 1399/1469] net: dsa: lantiq: fix broken backpressure in .port_fdb_dump rtnl_fdb_dump() has logic to split a dump of PF_BRIDGE neighbors into multiple netlink skbs if the buffer provided by user space is too small (one buffer will typically handle a few hundred FDB entries). When the current buffer becomes full, nlmsg_put() in dsa_slave_port_fdb_do_dump() returns -EMSGSIZE and DSA saves the index of the last dumped FDB entry, returns to rtnl_fdb_dump() up to that point, and then the dump resumes on the same port with a new skb, and FDB entries up to the saved index are simply skipped. Since dsa_slave_port_fdb_do_dump() is pointed to by the "cb" passed to drivers, then drivers must check for the -EMSGSIZE error code returned by it. Otherwise, when a netlink skb becomes full, DSA will no longer save newly dumped FDB entries to it, but the driver will continue dumping. So FDB entries will be missing from the dump. Fix the broken backpressure by propagating the "cb" return code and allow rtnl_fdb_dump() to restart the FDB dump with a new skb. Fixes: 58c59ef9e930 ("net: dsa: lantiq: Add Forwarding Database access") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/lantiq_gswip.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 314ae78bbdd6..e78026ef6d8c 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1404,11 +1404,17 @@ static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, addr[1] = mac_bridge.key[2] & 0xff; addr[0] = (mac_bridge.key[2] >> 8) & 0xff; if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_STATIC) { - if (mac_bridge.val[0] & BIT(port)) - cb(addr, 0, true, data); + if (mac_bridge.val[0] & BIT(port)) { + err = cb(addr, 0, true, data); + if (err) + return err; + } } else { - if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) == port) - cb(addr, 0, false, data); + if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) == port) { + err = cb(addr, 0, false, data); + if (err) + return err; + } } } return 0; From 21b52fed928e96d2f75d2f6aa9eac7a4b0b55d22 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Aug 2021 14:19:56 +0300 Subject: [PATCH 1400/1469] net: dsa: sja1105: fix broken backpressure in .port_fdb_dump rtnl_fdb_dump() has logic to split a dump of PF_BRIDGE neighbors into multiple netlink skbs if the buffer provided by user space is too small (one buffer will typically handle a few hundred FDB entries). When the current buffer becomes full, nlmsg_put() in dsa_slave_port_fdb_do_dump() returns -EMSGSIZE and DSA saves the index of the last dumped FDB entry, returns to rtnl_fdb_dump() up to that point, and then the dump resumes on the same port with a new skb, and FDB entries up to the saved index are simply skipped. Since dsa_slave_port_fdb_do_dump() is pointed to by the "cb" passed to drivers, then drivers must check for the -EMSGSIZE error code returned by it. Otherwise, when a netlink skb becomes full, DSA will no longer save newly dumped FDB entries to it, but the driver will continue dumping. So FDB entries will be missing from the dump. Fix the broken backpressure by propagating the "cb" return code and allow rtnl_fdb_dump() to restart the FDB dump with a new skb. Fixes: 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 8667c9754330..b188a80eeec6 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1635,7 +1635,9 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, /* We need to hide the dsa_8021q VLANs from the user. */ if (priv->vlan_state == SJA1105_VLAN_UNAWARE) l2_lookup.vlanid = 0; - cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); + rc = cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); + if (rc) + return rc; } return 0; } From d07149aba2ef423eae94a9cc2a6365d0cdf6fd51 Mon Sep 17 00:00:00 2001 From: Jeremy Szu Date: Tue, 10 Aug 2021 18:08:45 +0800 Subject: [PATCH 1401/1469] ALSA: hda/realtek: fix mute/micmute LEDs for HP ProBook 650 G8 Notebook PC The HP ProBook 650 G8 Notebook PC is using ALC236 codec which is using 0x02 to control mute LED and 0x01 to control micmute LED. Therefore, add a quirk to make it works. Signed-off-by: Jeremy Szu Cc: Link: https://lore.kernel.org/r/20210810100846.65844-1-jeremy.szu@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4043a2362f27..a065260d0d20 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8431,6 +8431,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), + SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8847, "HP EliteBook x360 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), From d1dee814168538eba166ae4150b37f0d88257884 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Thu, 22 Jul 2021 14:25:48 +0100 Subject: [PATCH 1402/1469] pinctrl: sunxi: Don't underestimate number of functions When we are building all the various pinctrl structures for the Allwinner pinctrl devices, we do some estimation about the maximum number of distinct function (names) that we will need. So far we take the number of pins as an upper bound, even though we can actually have up to four special functions per pin. This wasn't a problem until now, since we indeed have typically far more pins than functions, and most pins share common functions. However the H616 "-r" pin controller has only two pins, but four functions, so we run over the end of the array when we are looking for a matching function name in sunxi_pinctrl_add_function - there is no NULL sentinel left that would terminate the loop: [ 8.200648] Unable to handle kernel paging request at virtual address fffdff7efbefaff5 [ 8.209179] Mem abort info: .... [ 8.368456] Call trace: [ 8.370925] __pi_strcmp+0x90/0xf0 [ 8.374559] sun50i_h616_r_pinctrl_probe+0x1c/0x28 [ 8.379557] platform_probe+0x68/0xd8 Do an actual worst case allocation (4 functions per pin, three common functions and the sentinel) for the initial array allocation. This is now heavily overestimating the number of functions in the common case, but we will reallocate this array later with the actual number of functions, so it's only temporarily. Fixes: 561c1cf17c46 ("pinctrl: sunxi: Add support for the Allwinner H616-R pin controller") Signed-off-by: Andre Przywara Acked-by: Maxime Ripard Link: https://lore.kernel.org/r/20210722132548.22121-1-andre.przywara@arm.com Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index dc8d39ae045b..9c7679c06dca 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -1219,10 +1219,12 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) } /* - * We suppose that we won't have any more functions than pins, - * we'll reallocate that later anyway + * Find an upper bound for the maximum number of functions: in + * the worst case we have gpio_in, gpio_out, irq and up to four + * special functions per pin, plus one entry for the sentinel. + * We'll reallocate that later anyway. */ - pctl->functions = kcalloc(pctl->ngroups, + pctl->functions = kcalloc(4 * pctl->ngroups + 4, sizeof(*pctl->functions), GFP_KERNEL); if (!pctl->functions) From b9cc7d8a4656a6e815852c27ab50365009cb69c1 Mon Sep 17 00:00:00 2001 From: Ben Dai Date: Sun, 25 Apr 2021 23:09:03 +0800 Subject: [PATCH 1403/1469] genirq/timings: Prevent potential array overflow in __irq_timings_store() When the interrupt interval is greater than 2 ^ PREDICTION_BUFFER_SIZE * PREDICTION_FACTOR us and less than 1s, the calculated index will be greater than the length of irqs->ema_time[]. Check the calculated index before using it to prevent array overflow. Fixes: 23aa3b9a6b7d ("genirq/timings: Encapsulate storing function") Signed-off-by: Ben Dai Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210425150903.25456-1-ben.dai9703@gmail.com --- kernel/irq/timings.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index d309d6fbf5bd..4d2a702d7aa9 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -453,6 +453,11 @@ static __always_inline void __irq_timings_store(int irq, struct irqt_stat *irqs, */ index = irq_timings_interval_index(interval); + if (index > PREDICTION_BUFFER_SIZE - 1) { + irqs->count = 0; + return; + } + /* * Store the index as an element of the pattern in another * circular array. From dbbc93576e03fbe24b365fab0e901eb442237a8a Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Tue, 18 May 2021 11:31:17 +0800 Subject: [PATCH 1404/1469] genirq/msi: Ensure deactivation on teardown msi_domain_alloc_irqs() invokes irq_domain_activate_irq(), but msi_domain_free_irqs() does not enforce deactivation before tearing down the interrupts. This happens when PCI/MSI interrupts are set up and never used before being torn down again, e.g. in error handling pathes. The only place which cleans that up is the error handling path in msi_domain_alloc_irqs(). Move the cleanup from msi_domain_alloc_irqs() into msi_domain_free_irqs() to cure that. Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early") Signed-off-by: Bixuan Cui Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210518033117.78104-1-cuibixuan@huawei.com --- kernel/irq/msi.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index c41965e348b5..85df3ca03efe 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -476,11 +476,6 @@ skip_activate: return 0; cleanup: - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } msi_domain_free_irqs(domain, dev); return ret; } @@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { + struct irq_data *irq_data; struct msi_desc *desc; + int i; + + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); + } for_each_msi_entry(desc, dev) { /* From 7cbe08a930a132d84b4cf79953b00b074ec7a2a7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 9 Aug 2021 11:22:20 -0400 Subject: [PATCH 1405/1469] drm/amdgpu: handle VCN instances when harvesting (v2) There may be multiple instances and only one is harvested. v2: fix typo in commit message Fixes: 83a0b8639185 ("drm/amdgpu: add judgement when add ip blocks (v2)") Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1673 Reviewed-by: Guchun Chen Reviewed-by: James Zhu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 43e7b61d1c5c..ada7bc19118a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -299,6 +299,9 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) ip->major, ip->minor, ip->revision); + if (le16_to_cpu(ip->hw_id) == VCN_HWID) + adev->vcn.num_vcn_inst++; + for (k = 0; k < num_base_address; k++) { /* * convert the endianness of base addresses in place, @@ -385,7 +388,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) { struct binary_header *bhdr; struct harvest_table *harvest_info; - int i; + int i, vcn_harvest_count = 0; bhdr = (struct binary_header *)adev->mman.discovery_bin; harvest_info = (struct harvest_table *)(adev->mman.discovery_bin + @@ -397,8 +400,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) switch (le32_to_cpu(harvest_info->list[i].hw_id)) { case VCN_HWID: - adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; - adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + vcn_harvest_count++; break; case DMU_HWID: adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; @@ -407,6 +409,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) break; } } + if (vcn_harvest_count == adev->vcn.num_vcn_inst) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + } } int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) From 3042f80c6cb9340354dc56ecb06473be57adc432 Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Fri, 6 Aug 2021 10:28:04 +0800 Subject: [PATCH 1406/1469] drm/amd/pm: bug fix for the runtime pm BACO In some systems only MACO is supported. This is to fix the problem that runtime pm is enabled but BACO is not supported. MACO will be handled seperately. Signed-off-by: Kenneth Feng Reviewed-by: Jack Gui Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index c751f717a0da..d92dd2c7448e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -353,8 +353,7 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) struct amdgpu_device *adev = smu->adev; uint32_t val; - if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) { + if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO) { val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); smu_baco->platform_support = (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : From c90f6263f58a28c3d97b83679d6fd693b33dfd4e Mon Sep 17 00:00:00 2001 From: Eric Bernstein Date: Mon, 26 Jul 2021 15:53:18 -0400 Subject: [PATCH 1407/1469] drm/amd/display: Remove invalid assert for ODM + MPC case Reviewed-by: Dmytro Laktyushkin Acked-by: Anson Jacob Signed-off-by: Eric Bernstein Cc: stable@vger.kernel.org Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 253654d605c2..28e15ebf2f43 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1788,7 +1788,6 @@ static bool dcn30_split_stream_for_mpc_or_odm( } pri_pipe->next_odm_pipe = sec_pipe; sec_pipe->prev_odm_pipe = pri_pipe; - ASSERT(sec_pipe->top_pipe == NULL); if (!sec_pipe->top_pipe) sec_pipe->stream_res.opp = pool->opps[pipe_idx]; From 0cde63a8fc4d9f9f580c297211fd05f91c0fd66d Mon Sep 17 00:00:00 2001 From: Anson Jacob Date: Fri, 30 Jul 2021 19:46:20 -0400 Subject: [PATCH 1408/1469] drm/amd/display: use GFP_ATOMIC in amdgpu_dm_irq_schedule_work Replace GFP_KERNEL with GFP_ATOMIC as amdgpu_dm_irq_schedule_work can't sleep. BUG: sleeping function called from invalid context at include/linux/sched/mm.h:196 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 253, name: kworker/6:1H CPU: 6 PID: 253 Comm: kworker/6:1H Tainted: G W OE 5.11.0-promotion_2021_06_07-18_36_28_prelim_revert_retrain #8 Hardware name: System manufacturer System Product Name/PRIME X570-PRO, BIOS 3405 02/01/2021 Workqueue: events_highpri dm_irq_work_func [amdgpu] Call Trace: dump_stack+0x5e/0x74 ___might_sleep.cold+0x87/0x98 __might_sleep+0x4b/0x80 kmem_cache_alloc_trace+0x390/0x4f0 amdgpu_dm_irq_handler+0x171/0x230 [amdgpu] amdgpu_irq_dispatch+0xc0/0x1e0 [amdgpu] amdgpu_ih_process+0x81/0x100 [amdgpu] amdgpu_irq_handler+0x26/0xa0 [amdgpu] __handle_irq_event_percpu+0x49/0x190 ? __hrtimer_get_next_event+0x4d/0x80 handle_irq_event_percpu+0x33/0x80 handle_irq_event+0x33/0x60 handle_edge_irq+0x82/0x190 asm_call_irq_on_stack+0x12/0x20 common_interrupt+0xbb/0x140 asm_common_interrupt+0x1e/0x40 RIP: 0010:amdgpu_device_rreg.part.0+0x44/0xf0 [amdgpu] Code: 53 48 89 fb 4c 3b af c8 08 00 00 73 6d 83 e2 02 75 0d f6 87 40 62 01 00 10 0f 85 83 00 00 00 4c 03 ab d0 08 00 00 45 8b 6d 00 <8b> 05 3e b6 52 00 85 c0 7e 62 48 8b 43 08 0f b7 70 3e 65 8b 05 e3 RSP: 0018:ffffae7740fff9e8 EFLAGS: 00000286 RAX: ffffffffc05ee610 RBX: ffff8aaf8f620000 RCX: 0000000000000006 RDX: 0000000000000000 RSI: 0000000000005430 RDI: ffff8aaf8f620000 RBP: ffffae7740fffa08 R08: 0000000000000001 R09: 000000000000000a R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000005430 R13: 0000000071000000 R14: 0000000000000001 R15: 0000000000005430 ? amdgpu_cgs_write_register+0x20/0x20 [amdgpu] amdgpu_device_rreg+0x17/0x20 [amdgpu] amdgpu_cgs_read_register+0x14/0x20 [amdgpu] dm_read_reg_func+0x38/0xb0 [amdgpu] generic_reg_wait+0x80/0x160 [amdgpu] dce_aux_transfer_raw+0x324/0x7c0 [amdgpu] dc_link_aux_transfer_raw+0x43/0x50 [amdgpu] dm_dp_aux_transfer+0x87/0x110 [amdgpu] drm_dp_dpcd_access+0x72/0x110 [drm_kms_helper] drm_dp_dpcd_read+0xb7/0xf0 [drm_kms_helper] drm_dp_get_one_sb_msg+0x349/0x480 [drm_kms_helper] drm_dp_mst_hpd_irq+0xc5/0xe40 [drm_kms_helper] ? drm_dp_mst_hpd_irq+0xc5/0xe40 [drm_kms_helper] dm_handle_hpd_rx_irq+0x184/0x1a0 [amdgpu] ? dm_handle_hpd_rx_irq+0x184/0x1a0 [amdgpu] handle_hpd_rx_irq+0x195/0x240 [amdgpu] ? __switch_to_asm+0x42/0x70 ? __switch_to+0x131/0x450 dm_irq_work_func+0x19/0x20 [amdgpu] process_one_work+0x209/0x400 worker_thread+0x4d/0x3e0 ? cancel_delayed_work+0xa0/0xa0 kthread+0x124/0x160 ? kthread_park+0x90/0x90 ret_from_fork+0x22/0x30 Reviewed-by: Aurabindo Jayamohanan Pillai Acked-by: Anson Jacob Signed-off-by: Anson Jacob Cc: stable@vger.kernel.org Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 40f617bbb86f..4aba0e8c84f8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -584,7 +584,7 @@ static void amdgpu_dm_irq_schedule_work(struct amdgpu_device *adev, handler_data = container_of(handler_list->next, struct amdgpu_dm_irq_handler_data, list); /*allocate a new amdgpu_dm_irq_handler_data*/ - handler_data_add = kzalloc(sizeof(*handler_data), GFP_KERNEL); + handler_data_add = kzalloc(sizeof(*handler_data), GFP_ATOMIC); if (!handler_data_add) { DRM_ERROR("DM_IRQ: failed to allocate irq handler!\n"); return; From 981567bd965329df7e64b13e92a54da816c1e0a4 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 10 Aug 2021 16:33:55 +1000 Subject: [PATCH 1409/1469] cifs: use the correct max-length for dentry_path_raw() RHBZ: 1972502 PATH_MAX is 4096 but PAGE_SIZE can be >4096 on some architectures such as ppc and would thus write beyond the end of the actual object. Cc: Reported-by: Xiaoli Feng Suggested-by: Brian foster Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 79402ca0ddfa..5f8a302ffcb2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -100,7 +100,7 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0; - s = dentry_path_raw(direntry, page, PAGE_SIZE); + s = dentry_path_raw(direntry, page, PATH_MAX); if (IS_ERR(s)) return s; if (!s[1]) // for root we want "", not "/" From 7b9cae027ba3aaac295ae23a62f47876ed97da73 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 10 Aug 2021 10:19:49 -0700 Subject: [PATCH 1410/1469] KVM: VMX: Use current VMCS to query WAITPKG support for MSR emulation Use the secondary_exec_controls_get() accessor in vmx_has_waitpkg() to effectively get the controls for the current VMCS, as opposed to using vmx->secondary_exec_controls, which is the cached value of KVM's desired controls for vmcs01 and truly not reflective of any particular VMCS. While the waitpkg control is not dynamic, i.e. vmcs01 will always hold the same waitpkg configuration as vmx->secondary_exec_controls, the same does not hold true for vmcs02 if the L1 VMM hides the feature from L2. If L1 hides the feature _and_ does not intercept MSR_IA32_UMWAIT_CONTROL, L2 could incorrectly read/write L1's virtual MSR instead of taking a #GP. Fixes: 6e3ba4abcea5 ("KVM: vmx: Emulate MSR IA32_UMWAIT_CONTROL") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210810171952.2758100-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index db88ed4f2121..17a1cb4b059d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -522,7 +522,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow) static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { - return vmx->secondary_exec_control & + return secondary_exec_controls_get(vmx) & SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; } From 45a687879b31caae4032abd1c2402e289d2b8083 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 10 Aug 2021 14:00:10 +0300 Subject: [PATCH 1411/1469] net: bridge: fix flags interpretation for extern learn fdb entries Ignore fdb flags when adding port extern learn entries and always set BR_FDB_LOCAL flag when adding bridge extern learn entries. This is closest to the behaviour we had before and avoids breaking any use cases which were allowed. This patch fixes iproute2 calls which assume NUD_PERMANENT and were allowed before, example: $ bridge fdb add 00:11:22:33:44:55 dev swp1 extern_learn Extern learn entries are allowed to roam, but do not expire, so static or dynamic flags make no sense for them. Also add a comment for future reference. Fixes: eb100e0e24a2 ("net: bridge: allow to add externally learned entries from user-space") Fixes: 0541a6293298 ("net: bridge: validate the NUD_PERMANENT bit when adding an extern_learn FDB entry") Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: Nikolay Aleksandrov Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210810110010.43859-1-razor@blackwall.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/neighbour.h | 7 +++++-- net/bridge/br.c | 3 +-- net/bridge/br_fdb.c | 11 ++++------- net/bridge/br_private.h | 2 +- 4 files changed, 11 insertions(+), 12 deletions(-) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index dc8b72201f6c..00a60695fa53 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -66,8 +66,11 @@ enum { #define NUD_NONE 0x00 /* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - and make no address resolution or NUD. - NUD_PERMANENT also cannot be deleted by garbage collectors. + * and make no address resolution or NUD. + * NUD_PERMANENT also cannot be deleted by garbage collectors. + * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry + * states don't make sense and thus are ignored. Such entries don't age and + * can roam. */ struct nda_cacheinfo { diff --git a/net/bridge/br.c b/net/bridge/br.c index bbab9984f24e..ef743f94254d 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,8 +166,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, - fdb_info->is_local, false); + fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 835cec1e5a03..5dee30966ed3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1044,10 +1044,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, "FDB entry towards bridge must be permanent"); return -EINVAL; } - - err = br_fdb_external_learn_add(br, p, addr, vid, - ndm->ndm_state & NUD_PERMANENT, - true); + err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1275,7 +1272,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, bool is_local, + const unsigned char *addr, u16 vid, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1293,7 +1290,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); - if (is_local) + if (!p) flags |= BIT(BR_FDB_LOCAL); fdb = fdb_create(br, p, addr, vid, flags); @@ -1322,7 +1319,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); - if (is_local) + if (!p) set_bit(BR_FDB_LOCAL, &fdb->flags); if (modified) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index aa64d8d63ca3..2b48b204205e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -711,7 +711,7 @@ int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, bool is_local, + const unsigned char *addr, u16 vid, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, From c35b57ceff906856dd85af2d6709dab18fbca81f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Aug 2021 14:50:24 +0300 Subject: [PATCH 1412/1469] net: switchdev: zero-initialize struct switchdev_notifier_fdb_info emitted by drivers towards the bridge The blamed commit added a new field to struct switchdev_notifier_fdb_info, but did not make sure that all call paths set it to something valid. For example, a switchdev driver may emit a SWITCHDEV_FDB_ADD_TO_BRIDGE notifier, and since the 'is_local' flag is not set, it contains junk from the stack, so the bridge might interpret those notifications as being for local FDB entries when that was not intended. To avoid that now and in the future, zero-initialize all switchdev_notifier_fdb_info structures created by drivers such that all newly added fields to not need to touch drivers again. Fixes: 2c4eca3ef716 ("net: bridge: switchdev: include local flag in FDB notifications") Reported-by: Ido Schimmel Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Reviewed-by: Leon Romanovsky Reviewed-by: Karsten Graul Link: https://lore.kernel.org/r/20210810115024.1629983-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 4 ++-- drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +- drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c | 2 +- drivers/net/ethernet/rocker/rocker_main.c | 2 +- drivers/net/ethernet/rocker/rocker_ofdpa.c | 2 +- drivers/net/ethernet/ti/am65-cpsw-switchdev.c | 2 +- drivers/net/ethernet/ti/cpsw_switchdev.c | 2 +- drivers/s390/net/qeth_l2_main.c | 4 ++-- net/dsa/slave.c | 2 +- 11 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 0b3e8f2db294..9a309169dbae 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -748,7 +748,7 @@ static void prestera_fdb_offload_notify(struct prestera_port *port, struct switchdev_notifier_fdb_info *info) { - struct switchdev_notifier_fdb_info send_info; + struct switchdev_notifier_fdb_info send_info = {}; send_info.addr = info->addr; send_info.vid = info->vid; @@ -1123,7 +1123,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused, static void prestera_fdb_event(struct prestera_switch *sw, struct prestera_event *evt, void *arg) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; struct net_device *dev = NULL; struct prestera_port *port; struct prestera_lag *lag; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index f3f56f32e435..69a3630818d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -69,7 +69,7 @@ static void mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *addr, u16 vid, unsigned long val) { - struct switchdev_notifier_fdb_info send_info; + struct switchdev_notifier_fdb_info send_info = {}; send_info.addr = addr; send_info.vid = vid; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 7e221ef01437..f69cbb3852d5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -9079,7 +9079,7 @@ mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif, static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; struct net_device *dev; dev = br_fdb_find_port(rif->dev, mac, 0); @@ -9127,8 +9127,8 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) { + struct switchdev_notifier_fdb_info info = {}; u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); - struct switchdev_notifier_fdb_info info; struct net_device *br_dev; struct net_device *dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index c5ef9aa64efe..8f90cd323d5f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2508,7 +2508,7 @@ mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, struct net_device *dev, bool offloaded) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 0443f66b5550..9a8e4f201eb1 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -277,7 +277,7 @@ static void sparx5_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, struct net_device *dev, bool offloaded) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index a46633606cae..1f06b92ee5bb 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2715,7 +2715,7 @@ static void rocker_fdb_offload_notify(struct rocker_port *rocker_port, struct switchdev_notifier_fdb_info *recv_info) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = recv_info->addr; info.vid = recv_info->vid; diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 967a634ee9ac..e33a9d283a4e 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1822,7 +1822,7 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work) container_of(work, struct ofdpa_fdb_learn_work, work); bool removing = (lw->flags & OFDPA_OP_FLAG_REMOVE); bool learned = (lw->flags & OFDPA_OP_FLAG_LEARNED); - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = lw->addr; info.vid = lw->vid; diff --git a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c index 9c29b363e9ae..599708a3e81d 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c +++ b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c @@ -358,7 +358,7 @@ static int am65_cpsw_port_obj_del(struct net_device *ndev, const void *ctx, static void am65_cpsw_fdb_offload_notify(struct net_device *ndev, struct switchdev_notifier_fdb_info *rcv) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = rcv->addr; info.vid = rcv->vid; diff --git a/drivers/net/ethernet/ti/cpsw_switchdev.c b/drivers/net/ethernet/ti/cpsw_switchdev.c index f7fb6e17dadd..a7d97d429e06 100644 --- a/drivers/net/ethernet/ti/cpsw_switchdev.c +++ b/drivers/net/ethernet/ti/cpsw_switchdev.c @@ -368,7 +368,7 @@ static int cpsw_port_obj_del(struct net_device *ndev, const void *ctx, static void cpsw_fdb_offload_notify(struct net_device *ndev, struct switchdev_notifier_fdb_info *rcv) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = rcv->addr; info.vid = rcv->vid; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2abf86c104d5..d7cdd9cfe485 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -279,7 +279,7 @@ static void qeth_l2_set_pnso_mode(struct qeth_card *card, static void qeth_l2_dev2br_fdb_flush(struct qeth_card *card) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; QETH_CARD_TEXT(card, 2, "fdbflush"); @@ -679,7 +679,7 @@ static void qeth_l2_dev2br_fdb_notify(struct qeth_card *card, u8 code, struct net_if_token *token, struct mac_addr_lnid *addr_lnid) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; u8 ntfy_mac[ETH_ALEN]; ether_addr_copy(ntfy_mac, addr_lnid->mac); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 532085da8d8f..23be8e01026b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2291,8 +2291,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { + struct switchdev_notifier_fdb_info info = {}; struct dsa_switch *ds = switchdev_work->ds; - struct switchdev_notifier_fdb_info info; struct dsa_port *dp; if (!dsa_is_user_port(ds, switchdev_work->port)) From 519133debcc19f5c834e7e28480b60bdc234fe02 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 9 Aug 2021 21:20:23 +0800 Subject: [PATCH 1413/1469] net: bridge: fix memleak in br_add_if() I got a memleak report: BUG: memory leak unreferenced object 0x607ee521a658 (size 240): comm "syz-executor.0", pid 955, jiffies 4294780569 (age 16.449s) hex dump (first 32 bytes, cpu 1): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d830ea5a>] br_multicast_add_port+0x1c2/0x300 net/bridge/br_multicast.c:1693 [<00000000274d9a71>] new_nbp net/bridge/br_if.c:435 [inline] [<00000000274d9a71>] br_add_if+0x670/0x1740 net/bridge/br_if.c:611 [<0000000012ce888e>] do_set_master net/core/rtnetlink.c:2513 [inline] [<0000000012ce888e>] do_set_master+0x1aa/0x210 net/core/rtnetlink.c:2487 [<0000000099d1cafc>] __rtnl_newlink+0x1095/0x13e0 net/core/rtnetlink.c:3457 [<00000000a01facc0>] rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3488 [<00000000acc9186c>] rtnetlink_rcv_msg+0x369/0xa10 net/core/rtnetlink.c:5550 [<00000000d4aabb9c>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504 [<00000000bc2e12a3>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<00000000bc2e12a3>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340 [<00000000e4dc2d0e>] netlink_sendmsg+0x789/0xc70 net/netlink/af_netlink.c:1929 [<000000000d22c8b3>] sock_sendmsg_nosec net/socket.c:654 [inline] [<000000000d22c8b3>] sock_sendmsg+0x139/0x170 net/socket.c:674 [<00000000e281417a>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350 [<00000000237aa2ab>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404 [<000000004f2dc381>] __sys_sendmsg+0xd3/0x190 net/socket.c:2433 [<0000000005feca6c>] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:47 [<000000007304477d>] entry_SYSCALL_64_after_hwframe+0x44/0xae On error path of br_add_if(), p->mcast_stats allocated in new_nbp() need be freed, or it will be leaked. Fixes: 1080ab95e3c7 ("net: bridge: add support for IGMP/MLD stats and export them via netlink") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20210809132023.978546-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- net/bridge/br_if.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 6e4a32354a13..14cd6ef96111 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -616,6 +616,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { + br_multicast_del_port(p); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -729,6 +730,7 @@ err4: err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: + br_multicast_del_port(p); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: From bba676cc0b6122a74fa2e246f38a6b05c6f95b36 Mon Sep 17 00:00:00 2001 From: Dhananjay Phadke Date: Thu, 5 Aug 2021 14:49:05 -0700 Subject: [PATCH 1414/1469] i2c: iproc: fix race between client unreg and tasklet Similar NULL deref was originally fixed by graceful teardown sequence - https://lore.kernel.org/linux-i2c/1597106560-79693-1-git-send-email-dphadke@linux.microsoft.com After this, a tasklet was added to take care of FIFO full condition for large i2c transaction. https://lore.kernel.org/linux-arm-kernel/20201102035433.6774-1-rayagonda.kokatanur@broadcom.com/ This introduced regression, a new race condition between tasklet enabling interrupts and client unreg teardown sequence. Kill tasklet before unreg_slave() masks bits in IE_OFFSET. Updated teardown sequence - (1) disable_irq() (2) Kill tasklet (3) Mask event enable bits in control reg (4) Erase slave address (avoid further writes to rx fifo) (5) Flush tx and rx FIFOs (6) Clear pending event (interrupt) bits in status reg (7) Set client pointer to NULL (8) enable_irq() -- Unable to handle kernel read from unreadable memory at virtual address 0000000000000320 Mem abort info: ESR = 0x96000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=000000009212a000 [0000000000000320] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 96000004 [#1] SMP CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O Hardware name: Overlake (DT) pstate: 40400085 (nZcv daIf +PAN -UAO -TCO BTYPE=--) pc : bcm_iproc_i2c_slave_isr+0x2b8/0x8e4 lr : bcm_iproc_i2c_slave_isr+0x1c8/0x8e4 sp : ffff800010003e70 x29: ffff800010003e80 x28: ffffda017acdc000 x27: ffffda017b0ae000 x26: ffff800010004000 x25: ffff800010000000 x24: ffffda017af4a168 x23: 0000000000000073 x22: 0000000000000000 x21: 0000000001400000 x20: 0000000001000000 x19: ffff06f09583f880 x18: 00000000fa83b2da x17: 000000000000b67e x16: 0000000002edb2f3 x15: 00000000000002c7 x14: 00000000000002c7 x13: 0000000000000006 x12: 0000000000000033 x11: 0000000000000000 x10: 0000000001000000 x9 : 0000000003289312 x8 : 0000000003289311 x7 : 02d0cd03a303adbc x6 : 02d18e7f0a4dfc6c x5 : 02edb2f33f76ea68 x4 : 00000000fa83b2da x3 : ffffda017af43cd0 x2 : ffff800010003e74 x1 : 0000000001400000 x0 : 0000000000000000 Call trace: bcm_iproc_i2c_slave_isr+0x2b8/0x8e4 bcm_iproc_i2c_isr+0x178/0x290 __handle_irq_event_percpu+0xd0/0x200 handle_irq_event+0x60/0x1a0 handle_fasteoi_irq+0x130/0x220 __handle_domain_irq+0x8c/0xcc gic_handle_irq+0xc0/0x120 el1_irq+0xcc/0x180 finish_task_switch+0x100/0x1d8 __schedule+0x61c/0x7a0 schedule_idle+0x28/0x44 do_idle+0x254/0x28c cpu_startup_entry+0x28/0x2c rest_init+0xc4/0xd0 arch_call_rest_init+0x14/0x1c start_kernel+0x33c/0x3b8 Code: f9423260 910013e2 11000509 b9047a69 (f9419009) ---[ end trace 4781455b2a7bec15 ]--- Fixes: 4d658451c9d6 ("i2c: iproc: handle rx fifo full interrupt") Signed-off-by: Dhananjay Phadke Acked-by: Ray Jui Acked-by: Rayagonda Kokatanur Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-bcm-iproc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index cceaf69279a9..6304d1dd2dd6 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -1224,14 +1224,14 @@ static int bcm_iproc_i2c_unreg_slave(struct i2c_client *slave) disable_irq(iproc_i2c->irq); + tasklet_kill(&iproc_i2c->slave_rx_tasklet); + /* disable all slave interrupts */ tmp = iproc_i2c_rd_reg(iproc_i2c, IE_OFFSET); tmp &= ~(IE_S_ALL_INTERRUPT_MASK << IE_S_ALL_INTERRUPT_SHIFT); iproc_i2c_wr_reg(iproc_i2c, IE_OFFSET, tmp); - tasklet_kill(&iproc_i2c->slave_rx_tasklet); - /* Erase the slave address programmed */ tmp = iproc_i2c_rd_reg(iproc_i2c, S_CFG_SMBUS_ADDR_OFFSET); tmp &= ~BIT(S_CFG_EN_NIC_SMB_ADDR3_SHIFT); From 86ff25ed6cd8240d18df58930bd8848b19fce308 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 29 Jul 2021 16:35:32 +0200 Subject: [PATCH 1415/1469] i2c: dev: zero out array used for i2c reads from userspace If an i2c driver happens to not provide the full amount of data that a user asks for, it is possible that some uninitialized data could be sent to userspace. While all in-kernel drivers look to be safe, just be sure by initializing the buffer to zero before it is passed to the i2c driver so that any future drivers will not have this issue. Also properly copy the amount of data recvieved to the userspace buffer, as pointed out by Dan Carpenter. Reported-by: Eric Dumazet Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-dev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cb64fe649390..77f576e51652 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -141,7 +141,7 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, if (count > 8192) count = 8192; - tmp = kmalloc(count, GFP_KERNEL); + tmp = kzalloc(count, GFP_KERNEL); if (tmp == NULL) return -ENOMEM; @@ -150,7 +150,8 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, ret = i2c_master_recv(client, tmp, count); if (ret >= 0) - ret = copy_to_user(buf, tmp, count) ? -EFAULT : ret; + if (copy_to_user(buf, tmp, ret)) + ret = -EFAULT; kfree(tmp); return ret; } From 3f12cc4bb0a4d7b542af43b6f1b7175f13015629 Mon Sep 17 00:00:00 2001 From: Hu Haowen Date: Wed, 28 Jul 2021 23:53:46 +0800 Subject: [PATCH 1416/1469] Documentation: i2c: add i2c-sysfs into index Append i2c-sysfs to toctree in order to get rid of building warnings. Fixes: 31df7195b100 ("Documentation: i2c: Add doc for I2C sysfs") Signed-off-by: Hu Haowen Signed-off-by: Wolfram Sang --- Documentation/i2c/index.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/i2c/index.rst b/Documentation/i2c/index.rst index 8b76217e370a..6270f1fd7d4e 100644 --- a/Documentation/i2c/index.rst +++ b/Documentation/i2c/index.rst @@ -17,6 +17,7 @@ Introduction busses/index i2c-topology muxes/i2c-mux-gpio + i2c-sysfs Writing device drivers ====================== From 31697ef7f3f45293bba3da87bcc710953e97fc3e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 6 Aug 2021 09:43:11 +0900 Subject: [PATCH 1417/1469] pinctrl: k210: Fix k210_fpioa_probe() In k210_fpioa_probe(), add missing calls to clk_disable_unprepare() in case of error after cenabling the clk and pclk clocks. Also add missing error handling when enabling pclk. Reported-by: kernel test robot Reported-by: Dan Carpenter Fixes: d4c34d09ab03 ("pinctrl: Add RISC-V Canaan Kendryte K210 FPIOA driver") Cc: Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20210806004311.52859-1-damien.lemoal@wdc.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-k210.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c index f831526d06ff..49e32684dbb2 100644 --- a/drivers/pinctrl/pinctrl-k210.c +++ b/drivers/pinctrl/pinctrl-k210.c @@ -950,23 +950,37 @@ static int k210_fpioa_probe(struct platform_device *pdev) return ret; pdata->pclk = devm_clk_get_optional(dev, "pclk"); - if (!IS_ERR(pdata->pclk)) - clk_prepare_enable(pdata->pclk); + if (!IS_ERR(pdata->pclk)) { + ret = clk_prepare_enable(pdata->pclk); + if (ret) + goto disable_clk; + } pdata->sysctl_map = syscon_regmap_lookup_by_phandle_args(np, "canaan,k210-sysctl-power", 1, &pdata->power_offset); - if (IS_ERR(pdata->sysctl_map)) - return PTR_ERR(pdata->sysctl_map); + if (IS_ERR(pdata->sysctl_map)) { + ret = PTR_ERR(pdata->sysctl_map); + goto disable_pclk; + } k210_fpioa_init_ties(pdata); pdata->pctl = pinctrl_register(&k210_pinctrl_desc, dev, (void *)pdata); - if (IS_ERR(pdata->pctl)) - return PTR_ERR(pdata->pctl); + if (IS_ERR(pdata->pctl)) { + ret = PTR_ERR(pdata->pctl); + goto disable_pclk; + } return 0; + +disable_pclk: + clk_disable_unprepare(pdata->pclk); +disable_clk: + clk_disable_unprepare(pdata->clk); + + return ret; } static const struct of_device_id k210_fpioa_dt_ids[] = { From b4d8a58f8dcfcc890f296696cadb76e77be44b5f Mon Sep 17 00:00:00 2001 From: Hsuan-Chi Kuo Date: Thu, 4 Mar 2021 17:37:08 -0600 Subject: [PATCH 1418/1469] seccomp: Fix setting loaded filter count during TSYNC The desired behavior is to set the caller's filter count to thread's. This value is reported via /proc, so this fixes the inaccurate count exposed to userspace; it is not used for reference counting, etc. Signed-off-by: Hsuan-Chi Kuo Link: https://lore.kernel.org/r/20210304233708.420597-1-hsuanchikuo@gmail.com Co-developed-by: Wiktor Garbacz Signed-off-by: Wiktor Garbacz Link: https://lore.kernel.org/lkml/20210810125158.329849-1-wiktorg@google.com Signed-off-by: Kees Cook Cc: stable@vger.kernel.org Fixes: c818c03b661c ("seccomp: Report number of loaded filters in /proc/$pid/status") --- kernel/seccomp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 057e17f3215d..6469eca8078c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -602,7 +602,7 @@ static inline void seccomp_sync_threads(unsigned long flags) smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); atomic_set(&thread->seccomp.filter_count, - atomic_read(&thread->seccomp.filter_count)); + atomic_read(&caller->seccomp.filter_count)); /* * Don't let an unprivileged task work around From b93dfa6bda4d4e88e5386490f2b277a26958f9d3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 11 Aug 2021 11:53:37 -0700 Subject: [PATCH 1419/1469] ACPI: NFIT: Fix support for virtual SPA ranges Fix the NFIT parsing code to treat a 0 index in a SPA Range Structure as a special case and not match Region Mapping Structures that use 0 to indicate that they are not mapped. Without this fix some platform BIOS descriptions of "virtual disk" ranges do not result in the pmem driver attaching to the range. Details: In addition to typical persistent memory ranges, the ACPI NFIT may also convey "virtual" ranges. These ranges are indicated by a UUID in the SPA Range Structure of UUID_VOLATILE_VIRTUAL_DISK, UUID_VOLATILE_VIRTUAL_CD, UUID_PERSISTENT_VIRTUAL_DISK, or UUID_PERSISTENT_VIRTUAL_CD. The critical difference between virtual ranges and UUID_PERSISTENT_MEMORY, is that virtual do not support associations with Region Mapping Structures. For this reason the "index" value of virtual SPA Range Structures is allowed to be 0. If a platform BIOS decides to represent NVDIMMs with disconnected "Region Mapping Structures" (range-index == 0), the kernel may falsely associate them with standalone ranges where the "SPA Range Structure Index" is also zero. When this happens the driver may falsely require labels where "virtual disks" are expected to be label-less. I.e. "label-less" is where the namespace-range == region-range and the pmem driver attaches with no user action to create a namespace. Cc: Jacek Zloch Cc: Lukasz Sobieraj Cc: "Lee, Chun-Yi" Cc: Fixes: c2f32acdf848 ("acpi, nfit: treat virtual ramdisk SPA as pmem region") Reported-by: Krzysztof Rusocki Reported-by: Damian Bassa Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/162870796589.2521182.1240403310175570220.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 23d9a09d7060..a3ef6cce644c 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3021,6 +3021,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping_desc *mapping; + /* range index 0 == unmapped in SPA or invalid-SPA */ + if (memdev->range_index == 0 || spa->range_index == 0) + continue; if (memdev->range_index != spa->range_index) continue; if (count >= ND_MAX_MAPPINGS) { From d9cee9f85b22fab88d2b76d2e92b18e3d0e6aa8c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 30 Jul 2021 09:46:04 -0700 Subject: [PATCH 1420/1469] libnvdimm/region: Fix label activation vs errors There are a few scenarios where init_active_labels() can return without registering deactivate_labels() to run when the region is disabled. In particular label error injection creates scenarios where a DIMM is disabled, but labels on other DIMMs in the region become activated. Arrange for init_active_labels() to always register deactivate_labels(). Reported-by: Krzysztof Kensicki Cc: Fixes: bf9bccc14c05 ("libnvdimm: pmem label sets and namespace instantiation.") Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/162766356450.3223041.1183118139023841447.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 2403b71b601e..745478213ff2 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -2527,7 +2527,7 @@ static void deactivate_labels(void *region) static int init_active_labels(struct nd_region *nd_region) { - int i; + int i, rc = 0; for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; @@ -2546,13 +2546,14 @@ static int init_active_labels(struct nd_region *nd_region) else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else - return 0; + continue; dev_err(&nd_region->dev, "%s: is %s, failing probe\n", dev_name(&nd_mapping->nvdimm->dev), test_bit(NDD_LOCKED, &nvdimm->flags) ? "locked" : "disabled"); - return -ENXIO; + rc = -ENXIO; + goto out; } nd_mapping->ndd = ndd; atomic_inc(&nvdimm->busy); @@ -2586,13 +2587,17 @@ static int init_active_labels(struct nd_region *nd_region) break; } - if (i < nd_region->ndr_mappings) { + if (i < nd_region->ndr_mappings) + rc = -ENOMEM; + +out: + if (rc) { deactivate_labels(nd_region); - return -ENOMEM; + return rc; } return devm_add_action_or_reset(&nd_region->dev, deactivate_labels, - nd_region); + nd_region); } int nd_region_register_namespaces(struct nd_region *nd_region, int *err) From f21453b0ff6e307bfd59e7a126d9848cea25315c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 30 Jul 2021 13:00:20 -0700 Subject: [PATCH 1421/1469] tools/testing/nvdimm: Fix missing 'fallthrough' warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use "fallthrough;" to address: tools/testing/nvdimm/test/nfit.c: In function ‘nd_intel_test_finish_query’: tools/testing/nvdimm/test/nfit.c:436:37: warning: this statement may fall through [-Wimplicit-fallthrough=] 436 | fw->missed_activate = false; | ~~~~~~~~~~~~~~~~~~~~^~~~~~~ tools/testing/nvdimm/test/nfit.c:438:9: note: here 438 | case FW_STATE_UPDATED: | ^~~~ Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/162767522046.3313209.14767278726893995797.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- tools/testing/nvdimm/test/nfit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 54f367cbadae..b1bff5fb0f65 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -434,7 +434,7 @@ static int nd_intel_test_finish_query(struct nfit_test *t, dev_dbg(dev, "%s: transition out verify\n", __func__); fw->state = FW_STATE_UPDATED; fw->missed_activate = false; - /* fall through */ + fallthrough; case FW_STATE_UPDATED: nd_cmd->status = 0; /* bogus test version */ From 848378812e40152abe9b9baf58ce2004f76fb988 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 30 Jul 2021 19:31:08 -0700 Subject: [PATCH 1422/1469] vmlinux.lds.h: Handle clang's module.{c,d}tor sections A recent change in LLVM causes module_{c,d}tor sections to appear when CONFIG_K{A,C}SAN are enabled, which results in orphan section warnings because these are not handled anywhere: ld.lld: warning: arch/x86/pci/built-in.a(legacy.o):(.text.asan.module_ctor) is being placed in '.text.asan.module_ctor' ld.lld: warning: arch/x86/pci/built-in.a(legacy.o):(.text.asan.module_dtor) is being placed in '.text.asan.module_dtor' ld.lld: warning: arch/x86/pci/built-in.a(legacy.o):(.text.tsan.module_ctor) is being placed in '.text.tsan.module_ctor' Fangrui explains: "the function asan.module_ctor has the SHF_GNU_RETAIN flag, so it is in a separate section even with -fno-function-sections (default)". Place them in the TEXT_TEXT section so that these technologies continue to work with the newer compiler versions. All of the KASAN and KCSAN KUnit tests continue to pass after this change. Cc: stable@vger.kernel.org Link: https://github.com/ClangBuiltLinux/linux/issues/1432 Link: https://github.com/llvm/llvm-project/commit/7b789562244ee941b7bf2cefeb3fc08a59a01865 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Reviewed-by: Fangrui Song Acked-by: Marco Elver Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210731023107.1932981-1-nathan@kernel.org --- include/asm-generic/vmlinux.lds.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 17325416e2de..62669b36a772 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -586,6 +586,7 @@ NOINSTR_TEXT \ *(.text..refcount) \ *(.ref.text) \ + *(.text.asan.* .text.tsan.*) \ TEXT_CFI_JT \ MEM_KEEP(init.text*) \ MEM_KEEP(exit.text*) \ From 0f78399551146bfbed357759e2ad5abb8d39e50a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 11 Aug 2021 07:41:45 -1000 Subject: [PATCH 1423/1469] Revert "block/mq-deadline: Add cgroup support" This reverts commit 08a9ad8bf607 ("block/mq-deadline: Add cgroup support") and a follow-up commit c06bc5a3fb42 ("block/mq-deadline: Remove a WARN_ON_ONCE() call"). The added cgroup support has the following issues: * It breaks cgroup interface file format rule by adding custom elements to a nested key-value file. * It registers mq-deadline as a cgroup-aware policy even though all it's doing is collecting per-cgroup stats. Even if we need these stats, this isn't the right way to add them. * It hasn't been reviewed from cgroup side. Cc: Bart Van Assche Cc: Jens Axboe Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/Kconfig.iosched | 6 - block/Makefile | 2 - block/mq-deadline-cgroup.c | 126 -------------------- block/mq-deadline-cgroup.h | 114 ------------------ block/{mq-deadline-main.c => mq-deadline.c} | 73 +++--------- 5 files changed, 14 insertions(+), 307 deletions(-) delete mode 100644 block/mq-deadline-cgroup.c delete mode 100644 block/mq-deadline-cgroup.h rename block/{mq-deadline-main.c => mq-deadline.c} (95%) diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 64053d67a97b..2f2158e05a91 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -9,12 +9,6 @@ config MQ_IOSCHED_DEADLINE help MQ version of the deadline IO scheduler. -config MQ_IOSCHED_DEADLINE_CGROUP - tristate - default y - depends on MQ_IOSCHED_DEADLINE - depends on BLK_CGROUP - config MQ_IOSCHED_KYBER tristate "Kyber I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index bfbe4e13ca1e..1e1afa10f869 100644 --- a/block/Makefile +++ b/block/Makefile @@ -22,8 +22,6 @@ obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o -mq-deadline-y += mq-deadline-main.o -mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o diff --git a/block/mq-deadline-cgroup.c b/block/mq-deadline-cgroup.c deleted file mode 100644 index 3b4bfddec39f..000000000000 --- a/block/mq-deadline-cgroup.c +++ /dev/null @@ -1,126 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include -#include - -#include "mq-deadline-cgroup.h" - -static struct blkcg_policy dd_blkcg_policy; - -static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp) -{ - struct dd_blkcg *pd; - - pd = kzalloc(sizeof(*pd), gfp); - if (!pd) - return NULL; - pd->stats = alloc_percpu_gfp(typeof(*pd->stats), - GFP_KERNEL | __GFP_ZERO); - if (!pd->stats) { - kfree(pd); - return NULL; - } - return &pd->cpd; -} - -static void dd_cpd_free(struct blkcg_policy_data *cpd) -{ - struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd); - - free_percpu(dd_blkcg->stats); - kfree(dd_blkcg); -} - -static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd) -{ - return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy), - struct dd_blkcg, cpd); -} - -/* - * Convert an association between a block cgroup and a request queue into a - * pointer to the mq-deadline information associated with a (blkcg, queue) pair. - */ -struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) -{ - struct blkg_policy_data *pd; - - pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy); - if (!pd) - return NULL; - - return dd_blkcg_from_pd(pd); -} - -static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) -{ - static const char *const prio_class_name[] = { - [IOPRIO_CLASS_NONE] = "NONE", - [IOPRIO_CLASS_RT] = "RT", - [IOPRIO_CLASS_BE] = "BE", - [IOPRIO_CLASS_IDLE] = "IDLE", - }; - struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); - int res = 0; - u8 prio; - - for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) - res += scnprintf(buf + res, size - res, - " [%s] dispatched=%u inserted=%u merged=%u", - prio_class_name[prio], - ddcg_sum(blkcg, dispatched, prio) + - ddcg_sum(blkcg, merged, prio) - - ddcg_sum(blkcg, completed, prio), - ddcg_sum(blkcg, inserted, prio) - - ddcg_sum(blkcg, completed, prio), - ddcg_sum(blkcg, merged, prio)); - - return res; -} - -static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, - struct blkcg *blkcg) -{ - struct dd_blkg *pd; - - pd = kzalloc(sizeof(*pd), gfp); - if (!pd) - return NULL; - return &pd->pd; -} - -static void dd_pd_free(struct blkg_policy_data *pd) -{ - struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd); - - kfree(dd_blkg); -} - -static struct blkcg_policy dd_blkcg_policy = { - .cpd_alloc_fn = dd_cpd_alloc, - .cpd_free_fn = dd_cpd_free, - - .pd_alloc_fn = dd_pd_alloc, - .pd_free_fn = dd_pd_free, - .pd_stat_fn = dd_pd_stat, -}; - -int dd_activate_policy(struct request_queue *q) -{ - return blkcg_activate_policy(q, &dd_blkcg_policy); -} - -void dd_deactivate_policy(struct request_queue *q) -{ - blkcg_deactivate_policy(q, &dd_blkcg_policy); -} - -int __init dd_blkcg_init(void) -{ - return blkcg_policy_register(&dd_blkcg_policy); -} - -void __exit dd_blkcg_exit(void) -{ - blkcg_policy_unregister(&dd_blkcg_policy); -} diff --git a/block/mq-deadline-cgroup.h b/block/mq-deadline-cgroup.h deleted file mode 100644 index 0143fd74f3ce..000000000000 --- a/block/mq-deadline-cgroup.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#if !defined(_MQ_DEADLINE_CGROUP_H_) -#define _MQ_DEADLINE_CGROUP_H_ - -#include - -struct request_queue; - -/** - * struct io_stats_per_prio - I/O statistics per I/O priority class. - * @inserted: Number of inserted requests. - * @merged: Number of merged requests. - * @dispatched: Number of dispatched requests. - * @completed: Number of I/O completions. - */ -struct io_stats_per_prio { - local_t inserted; - local_t merged; - local_t dispatched; - local_t completed; -}; - -/* I/O statistics per I/O cgroup per I/O priority class (IOPRIO_CLASS_*). */ -struct blkcg_io_stats { - struct io_stats_per_prio stats[4]; -}; - -/** - * struct dd_blkcg - Per cgroup data. - * @cpd: blkcg_policy_data structure. - * @stats: I/O statistics. - */ -struct dd_blkcg { - struct blkcg_policy_data cpd; /* must be the first member */ - struct blkcg_io_stats __percpu *stats; -}; - -/* - * Count one event of type 'event_type' and with I/O priority class - * 'prio_class'. - */ -#define ddcg_count(ddcg, event_type, prio_class) do { \ -if (ddcg) { \ - struct blkcg_io_stats *io_stats = get_cpu_ptr((ddcg)->stats); \ - \ - BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ - BUILD_BUG_ON(!__same_type((prio_class), u8)); \ - local_inc(&io_stats->stats[(prio_class)].event_type); \ - put_cpu_ptr(io_stats); \ -} \ -} while (0) - -/* - * Returns the total number of ddcg_count(ddcg, event_type, prio_class) calls - * across all CPUs. No locking or barriers since it is fine if the returned - * sum is slightly outdated. - */ -#define ddcg_sum(ddcg, event_type, prio) ({ \ - unsigned int cpu; \ - u32 sum = 0; \ - \ - BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ - BUILD_BUG_ON(!__same_type((prio), u8)); \ - for_each_present_cpu(cpu) \ - sum += local_read(&per_cpu_ptr((ddcg)->stats, cpu)-> \ - stats[(prio)].event_type); \ - sum; \ -}) - -#ifdef CONFIG_BLK_CGROUP - -/** - * struct dd_blkg - Per (cgroup, request queue) data. - * @pd: blkg_policy_data structure. - */ -struct dd_blkg { - struct blkg_policy_data pd; /* must be the first member */ -}; - -struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio); -int dd_activate_policy(struct request_queue *q); -void dd_deactivate_policy(struct request_queue *q); -int __init dd_blkcg_init(void); -void __exit dd_blkcg_exit(void); - -#else /* CONFIG_BLK_CGROUP */ - -static inline struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) -{ - return NULL; -} - -static inline int dd_activate_policy(struct request_queue *q) -{ - return 0; -} - -static inline void dd_deactivate_policy(struct request_queue *q) -{ -} - -static inline int dd_blkcg_init(void) -{ - return 0; -} - -static inline void dd_blkcg_exit(void) -{ -} - -#endif /* CONFIG_BLK_CGROUP */ - -#endif /* _MQ_DEADLINE_CGROUP_H_ */ diff --git a/block/mq-deadline-main.c b/block/mq-deadline.c similarity index 95% rename from block/mq-deadline-main.c rename to block/mq-deadline.c index 6f612e6dc82b..a09761cbdf12 100644 --- a/block/mq-deadline-main.c +++ b/block/mq-deadline.c @@ -25,7 +25,6 @@ #include "blk-mq-debugfs.h" #include "blk-mq-tag.h" #include "blk-mq-sched.h" -#include "mq-deadline-cgroup.h" /* * See Documentation/block/deadline-iosched.rst @@ -57,6 +56,14 @@ enum dd_prio { enum { DD_PRIO_COUNT = 3 }; +/* I/O statistics per I/O priority. */ +struct io_stats_per_prio { + local_t inserted; + local_t merged; + local_t dispatched; + local_t completed; +}; + /* I/O statistics for all I/O priorities (enum dd_prio). */ struct io_stats { struct io_stats_per_prio stats[DD_PRIO_COUNT]; @@ -79,9 +86,6 @@ struct deadline_data { * run time data */ - /* Request queue that owns this data structure. */ - struct request_queue *queue; - struct dd_per_prio per_prio[DD_PRIO_COUNT]; /* Data direction of latest dispatched request. */ @@ -234,10 +238,8 @@ static void dd_merged_requests(struct request_queue *q, struct request *req, struct deadline_data *dd = q->elevator->elevator_data; const u8 ioprio_class = dd_rq_ioclass(next); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; - struct dd_blkcg *blkcg = next->elv.priv[0]; dd_count(dd, merged, prio); - ddcg_count(blkcg, merged, ioprio_class); /* * if next expires before rq, assign its expire time to rq @@ -375,7 +377,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, { struct request *rq, *next_rq; enum dd_data_dir data_dir; - struct dd_blkcg *blkcg; enum dd_prio prio; u8 ioprio_class; @@ -474,8 +475,6 @@ done: ioprio_class = dd_rq_ioclass(rq); prio = ioprio_class_to_prio[ioprio_class]; dd_count(dd, dispatched, prio); - blkcg = rq->elv.priv[0]; - ddcg_count(blkcg, dispatched, ioprio_class); /* * If the request needs its target zone locked, do it. */ @@ -569,8 +568,6 @@ static void dd_exit_sched(struct elevator_queue *e) struct deadline_data *dd = e->elevator_data; enum dd_prio prio; - dd_deactivate_policy(dd->queue); - for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; @@ -584,7 +581,7 @@ static void dd_exit_sched(struct elevator_queue *e) } /* - * Initialize elevator private data (deadline_data) and associate with blkcg. + * initialize elevator private data (deadline_data). */ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) { @@ -593,12 +590,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) enum dd_prio prio; int ret = -ENOMEM; - /* - * Initialization would be very tricky if the queue is not frozen, - * hence the warning statement below. - */ - WARN_ON_ONCE(!percpu_ref_is_zero(&q->q_usage_counter)); - eq = elevator_alloc(q, e); if (!eq) return ret; @@ -614,8 +605,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) if (!dd->stats) goto free_dd; - dd->queue = q; - for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; @@ -635,17 +624,9 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) spin_lock_init(&dd->lock); spin_lock_init(&dd->zone_lock); - ret = dd_activate_policy(q); - if (ret) - goto free_stats; - - ret = 0; q->elevator = eq; return 0; -free_stats: - free_percpu(dd->stats); - free_dd: kfree(dd); @@ -718,7 +699,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); struct dd_per_prio *per_prio; enum dd_prio prio; - struct dd_blkcg *blkcg; LIST_HEAD(free); lockdep_assert_held(&dd->lock); @@ -729,18 +709,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, */ blk_req_zone_write_unlock(rq); - /* - * If a block cgroup has been associated with the submitter and if an - * I/O priority has been set in the associated block cgroup, use the - * lowest of the cgroup priority and the request priority for the - * request. If no priority has been set in the request, use the cgroup - * priority. - */ prio = ioprio_class_to_prio[ioprio_class]; dd_count(dd, inserted, prio); - blkcg = dd_blkcg_from_bio(rq->bio); - ddcg_count(blkcg, inserted, ioprio_class); - rq->elv.priv[0] = blkcg; if (blk_mq_sched_try_insert_merge(q, rq, &free)) { blk_mq_free_requests(&free); @@ -789,10 +759,12 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, spin_unlock(&dd->lock); } -/* Callback from inside blk_mq_rq_ctx_init(). */ +/* + * Nothing to do here. This is defined only to ensure that .finish_request + * method is called upon request completion. + */ static void dd_prepare_request(struct request *rq) { - rq->elv.priv[0] = NULL; } /* @@ -815,13 +787,11 @@ static void dd_finish_request(struct request *rq) { struct request_queue *q = rq->q; struct deadline_data *dd = q->elevator->elevator_data; - struct dd_blkcg *blkcg = rq->elv.priv[0]; const u8 ioprio_class = dd_rq_ioclass(rq); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; struct dd_per_prio *per_prio = &dd->per_prio[prio]; dd_count(dd, completed, prio); - ddcg_count(blkcg, completed, ioprio_class); if (blk_queue_is_zoned(q)) { unsigned long flags; @@ -1144,26 +1114,11 @@ MODULE_ALIAS("mq-deadline-iosched"); static int __init deadline_init(void) { - int ret; - - ret = elv_register(&mq_deadline); - if (ret) - goto out; - ret = dd_blkcg_init(); - if (ret) - goto unreg; - -out: - return ret; - -unreg: - elv_unregister(&mq_deadline); - goto out; + return elv_register(&mq_deadline); } static void __exit deadline_exit(void) { - dd_blkcg_exit(); elv_unregister(&mq_deadline); } From 6922110d152e56d7569616b45a1f02876cf3eb9f Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 9 Aug 2021 18:06:28 +0200 Subject: [PATCH 1424/1469] net: linkwatch: fix failure to restore device state across suspend/resume After migrating my laptop from 4.19-LTS to 5.4-LTS a while ago I noticed that my Ethernet port to which a bond and a VLAN interface are attached appeared to remain up after resuming from suspend with the cable unplugged (and that problem still persists with 5.10-LTS). It happens that the following happens: - the network driver (e1000e here) prepares to suspend, calls e1000e_down() which calls netif_carrier_off() to signal that the link is going down. - netif_carrier_off() adds a link_watch event to the list of events for this device - the device is completely stopped. - the machine suspends - the cable is unplugged and the machine brought to another location - the machine is resumed - the queued linkwatch events are processed for the device - the device doesn't yet have the __LINK_STATE_PRESENT bit and its events are silently dropped - the device is resumed with its link down - the upper VLAN and bond interfaces are never notified that the link had been turned down and remain up - the only way to provoke a change is to physically connect the machine to a port and possibly unplug it. The state after resume looks like this: $ ip -br li | egrep 'bond|eth' bond0 UP e8:6a:64:64:64:64 eth0 DOWN e8:6a:64:64:64:64 eth0.2@eth0 UP e8:6a:64:64:64:64 Placing an explicit call to netdev_state_change() either in the suspend or the resume code in the NIC driver worked around this but the solution is not satisfying. The issue in fact really is in link_watch that loses events while it ought not to. It happens that the test for the device being present was added by commit 124eee3f6955 ("net: linkwatch: add check for netdevice being present to linkwatch_do_dev") in 4.20 to avoid an access to devices that are not present. Instead of dropping events, this patch proceeds slightly differently by postponing their handling so that they happen after the device is fully resumed. Fixes: 124eee3f6955 ("net: linkwatch: add check for netdevice being present to linkwatch_do_dev") Link: https://lists.openwall.net/netdev/2018/03/15/62 Cc: Heiner Kallweit Cc: Geert Uytterhoeven Cc: Florian Fainelli Signed-off-by: Willy Tarreau Link: https://lore.kernel.org/r/20210809160628.22623-1-w@1wt.eu Signed-off-by: Jakub Kicinski --- net/core/link_watch.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 75431ca9300f..1a455847da54 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -158,7 +158,7 @@ static void linkwatch_do_dev(struct net_device *dev) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); - if (dev->flags & IFF_UP && netif_device_present(dev)) { + if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else @@ -204,7 +204,8 @@ static void __linkwatch_run_queue(int urgent_only) dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); - if (urgent_only && !linkwatch_urgent_event(dev)) { + if (!netif_device_present(dev) || + (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } From 2cad5d2ed1b47eded5a2f2372c2a94bb065a8f97 Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Tue, 10 Aug 2021 16:58:12 +0800 Subject: [PATCH 1425/1469] net: pcs: xpcs: fix error handling on failed to allocate memory Drivers such as sja1105 and stmmac that call xpcs_create() expects an error returned by the pcs-xpcs module, but this was not the case on failed to allocate memory. Fixed this by returning an -ENOMEM instead of a NULL pointer. Fixes: 3ad1d171548e ("net: dsa: sja1105: migrate to xpcs for SGMII") Signed-off-by: Wong Vee Khee Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210810085812.1808466-1-vee.khee.wong@linux.intel.com Signed-off-by: Jakub Kicinski --- drivers/net/pcs/pcs-xpcs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 63fda3fc40aa..4bd61339823c 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1089,7 +1089,7 @@ struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, xpcs = kzalloc(sizeof(*xpcs), GFP_KERNEL); if (!xpcs) - return NULL; + return ERR_PTR(-ENOMEM); xpcs->mdiodev = mdiodev; From 6de035fec045f8ae5ee5f3a02373a18b939e91fb Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 10 Aug 2021 22:40:56 -0400 Subject: [PATCH 1426/1469] tcp_bbr: fix u32 wrap bug in round logic if bbr_init() called after 2B packets Currently if BBR congestion control is initialized after more than 2B packets have been delivered, depending on the phase of the tp->delivered counter the tracking of BBR round trips can get stuck. The bug arises because if tp->delivered is between 2^31 and 2^32 at the time the BBR congestion control module is initialized, then the initialization of bbr->next_rtt_delivered to 0 will cause the logic to believe that the end of the round trip is still billions of packets in the future. More specifically, the following check will fail repeatedly: !before(rs->prior_delivered, bbr->next_rtt_delivered) and thus the connection will take up to 2B packets delivered before that check will pass and the connection will set: bbr->round_start = 1; This could cause many mechanisms in BBR to fail to trigger, for example bbr_check_full_bw_reached() would likely never exit STARTUP. This bug is 5 years old and has not been observed, and as a practical matter this would likely rarely trigger, since it would require transferring at least 2B packets, or likely more than 3 terabytes of data, before switching congestion control algorithms to BBR. This patch is a stable candidate for kernels as far back as v4.9, when tcp_bbr.c was added. Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control") Signed-off-by: Neal Cardwell Reviewed-by: Yuchung Cheng Reviewed-by: Kevin Yang Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20210811024056.235161-1-ncardwell@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_bbr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6ea3dc2e4219..6274462b86b4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1041,7 +1041,7 @@ static void bbr_init(struct sock *sk) bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; - bbr->next_rtt_delivered = 0; + bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; From 0271824d9ebe945a2ecefdb87e1ce0a520be704d Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Tue, 10 Aug 2021 23:17:12 +0300 Subject: [PATCH 1427/1469] MAINTAINERS: switch to my OMP email for Renesas Ethernet drivers I'm still going to continue looking after the Renesas Ethernet drivers and device tree bindings. Now my new employer, Open Mobile Platform (OMP), will pay for all my upstream work. Let's switch to my OMP email for the reviews. Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/9c212711-a0d7-39cd-7840-ff7abf938da1@omp.ru Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 25dc566a67c1..f13c0d3b7d0c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15803,7 +15803,7 @@ F: Documentation/devicetree/bindings/i2c/renesas,iic-emev2.yaml F: drivers/i2c/busses/i2c-emev2.c RENESAS ETHERNET DRIVERS -R: Sergei Shtylyov +R: Sergey Shtylyov L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org F: Documentation/devicetree/bindings/net/renesas,*.yaml From b69dd5b3780a7298bd893816a09da751bc0636f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Aug 2021 12:57:15 -0700 Subject: [PATCH 1428/1469] net: igmp: increase size of mr_ifc_count Some arches support cmpxchg() on 4-byte and 8-byte only. Increase mr_ifc_count width to 32bit to fix this problem. Fixes: 4a2b285e7e10 ("net: igmp: fix data-race in igmp_ifc_timer_expire()") Signed-off-by: Eric Dumazet Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/20210811195715.3684218-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 2 +- net/ipv4/igmp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 53aa0343bf69..aaf4f1b4c277 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,7 +41,7 @@ struct in_device { unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; - unsigned char mr_ifc_count; + u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a51360087b19..00576bae183d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,7 +803,7 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); - u8 mr_ifc_count; + u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: From 48c812e0327744b4965296f65c23fe2405692afc Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 10 Aug 2021 13:37:48 +0100 Subject: [PATCH 1429/1469] net: mscc: Fix non-GPL export of regmap APIs The ocelot driver makes use of regmap, wrapping it with driver specific operations that are thin wrappers around the core regmap APIs. These are exported with EXPORT_SYMBOL, dropping the _GPL from the core regmap exports which is frowned upon. Add _GPL suffixes to at least the APIs that are doing register I/O. Signed-off-by: Mark Brown Acked-by: Alexandre Belloni Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot_io.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c index ea4e83410fe4..7390fa3980ec 100644 --- a/drivers/net/ethernet/mscc/ocelot_io.c +++ b/drivers/net/ethernet/mscc/ocelot_io.c @@ -21,7 +21,7 @@ u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset) ocelot->map[target][reg & REG_MASK] + offset, &val); return val; } -EXPORT_SYMBOL(__ocelot_read_ix); +EXPORT_SYMBOL_GPL(__ocelot_read_ix); void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset) { @@ -32,7 +32,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset) regmap_write(ocelot->targets[target], ocelot->map[target][reg & REG_MASK] + offset, val); } -EXPORT_SYMBOL(__ocelot_write_ix); +EXPORT_SYMBOL_GPL(__ocelot_write_ix); void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, u32 offset) @@ -45,7 +45,7 @@ void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, ocelot->map[target][reg & REG_MASK] + offset, mask, val); } -EXPORT_SYMBOL(__ocelot_rmw_ix); +EXPORT_SYMBOL_GPL(__ocelot_rmw_ix); u32 ocelot_port_readl(struct ocelot_port *port, u32 reg) { @@ -58,7 +58,7 @@ u32 ocelot_port_readl(struct ocelot_port *port, u32 reg) regmap_read(port->target, ocelot->map[target][reg & REG_MASK], &val); return val; } -EXPORT_SYMBOL(ocelot_port_readl); +EXPORT_SYMBOL_GPL(ocelot_port_readl); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg) { @@ -69,7 +69,7 @@ void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg) regmap_write(port->target, ocelot->map[target][reg & REG_MASK], val); } -EXPORT_SYMBOL(ocelot_port_writel); +EXPORT_SYMBOL_GPL(ocelot_port_writel); void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg) { @@ -77,7 +77,7 @@ void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg) ocelot_port_writel(port, (cur & (~mask)) | val, reg); } -EXPORT_SYMBOL(ocelot_port_rmwl); +EXPORT_SYMBOL_GPL(ocelot_port_rmwl); u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, u32 reg, u32 offset) @@ -128,7 +128,7 @@ int ocelot_regfields_init(struct ocelot *ocelot, return 0; } -EXPORT_SYMBOL(ocelot_regfields_init); +EXPORT_SYMBOL_GPL(ocelot_regfields_init); static struct regmap_config ocelot_regmap_config = { .reg_bits = 32, @@ -148,4 +148,4 @@ struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res) return devm_regmap_init_mmio(ocelot->dev, regs, &ocelot_regmap_config); } -EXPORT_SYMBOL(ocelot_regmap_init); +EXPORT_SYMBOL_GPL(ocelot_regmap_init); From 86704993e6a5989e256b4212ca03115cc2694eda Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Wed, 11 Aug 2021 08:22:09 +0700 Subject: [PATCH 1430/1469] Revert "tipc: Return the correct errno code" This reverts commit 0efea3c649f0 because of: - The returning -ENOBUF error is fine on socket buffer allocation. - There is side effect in the calling path tipc_node_xmit()->tipc_link_xmit() when checking error code returning. Fixes: 0efea3c649f0 ("tipc: Return the correct errno code") Acked-by: Jon Maloy Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/link.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index cf586840caeb..1b7a487c8841 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOMEM; + return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOMEM; + return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); From c4b68e513953c3370ce02c3208c1c628c0b86fd3 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 9 Aug 2021 15:15:13 -0500 Subject: [PATCH 1431/1469] pinctrl: amd: Fix an issue with shutdown when system set to s0ix IRQs are getting armed on shutdown causing the system to immediately wake back up. Link: https://lkml.org/lkml/2021/8/2/1114 Reported-by: nix.or.die@googlemail.com Acked-by: Shyam Sundar S K Tested-by: Gabriel Craciunescu CC: Raul E Rangel Fixes: d62bd5ce12d7 ("pinctrl: amd: Implement irq_set_wake") Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20210809201513.12367-1-mario.limonciello@amd.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a76be6cc26ee..5b764740b829 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -444,8 +444,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) unsigned long flags; struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); - u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | - BIT(WAKE_CNTRL_OFF_S4); + u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); From 700fa08da43edb0af3e6a513f0255443e96088e8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 Aug 2021 14:59:45 +0300 Subject: [PATCH 1432/1469] net: dsa: sja1105: unregister the MDIO buses during teardown The call to sja1105_mdiobus_unregister is present in the error path but absent from the main driver unbind path. Fixes: 5a8f09748ee7 ("net: dsa: sja1105: register the MDIO buses for 100base-T1 and 100base-TX") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index b188a80eeec6..49eb0ac41b7d 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3187,6 +3187,7 @@ static void sja1105_teardown(struct dsa_switch *ds) } sja1105_devlink_teardown(ds); + sja1105_mdiobus_unregister(ds); sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); sja1105_ptp_clock_unregister(ds); From abd9d66a055722393d33685214c08386694871d7 Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Wed, 11 Aug 2021 10:48:57 +0530 Subject: [PATCH 1433/1469] drm/i915/display: Fix the 12 BPC bits for PIPE_MISC reg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Till DISPLAY12 the PIPE_MISC bits 5-7 are used to set the Dithering BPC, with valid values of 6, 8, 10 BPC. For ADLP+ these bits are used to set the PORT OUTPUT BPC, with valid values of: 6, 8, 10, 12 BPC, and need to be programmed whether dithering is enabled or not. This patch: -corrects the bits 5-7 for PIPE MISC register for 12 BPC. -renames the bits and mask to have generic names for these bits for dithering bpc and port output bpc. v3: Added a note for MIPI DSI which uses the PIPE_MISC for readout for pipe_bpp. (Uma Shankar) v2: Added 'display' to the subject and fixes tag. (Uma Shankar) Fixes: 756f85cffef2 ("drm/i915/bdw: Broadwell has PIPEMISC") Cc: Paulo Zanoni (v1) Cc: Ville Syrjälä Cc: Daniel Vetter Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: intel-gfx@lists.freedesktop.org Cc: # v3.13+ Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar Signed-off-by: Uma Shankar Link: https://patchwork.freedesktop.org/patch/msgid/20210811051857.109723-1-ankit.k.nautiyal@intel.com (cherry picked from commit 70418a68713c13da3f36c388087d0220b456a430) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_display.c | 34 ++++++++++++++------ drivers/gpu/drm/i915/i915_reg.h | 16 ++++++--- 2 files changed, 35 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 2d5d21740c25..0a8a2395c8ac 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5746,16 +5746,18 @@ static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state) switch (crtc_state->pipe_bpp) { case 18: - val |= PIPEMISC_DITHER_6_BPC; + val |= PIPEMISC_6_BPC; break; case 24: - val |= PIPEMISC_DITHER_8_BPC; + val |= PIPEMISC_8_BPC; break; case 30: - val |= PIPEMISC_DITHER_10_BPC; + val |= PIPEMISC_10_BPC; break; case 36: - val |= PIPEMISC_DITHER_12_BPC; + /* Port output 12BPC defined for ADLP+ */ + if (DISPLAY_VER(dev_priv) > 12) + val |= PIPEMISC_12_BPC_ADLP; break; default: MISSING_CASE(crtc_state->pipe_bpp); @@ -5808,15 +5810,27 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc) tmp = intel_de_read(dev_priv, PIPEMISC(crtc->pipe)); - switch (tmp & PIPEMISC_DITHER_BPC_MASK) { - case PIPEMISC_DITHER_6_BPC: + switch (tmp & PIPEMISC_BPC_MASK) { + case PIPEMISC_6_BPC: return 18; - case PIPEMISC_DITHER_8_BPC: + case PIPEMISC_8_BPC: return 24; - case PIPEMISC_DITHER_10_BPC: + case PIPEMISC_10_BPC: return 30; - case PIPEMISC_DITHER_12_BPC: - return 36; + /* + * PORT OUTPUT 12 BPC defined for ADLP+. + * + * TODO: + * For previous platforms with DSI interface, bits 5:7 + * are used for storing pipe_bpp irrespective of dithering. + * Since the value of 12 BPC is not defined for these bits + * on older platforms, need to find a workaround for 12 BPC + * MIPI DSI HW readout. + */ + case PIPEMISC_12_BPC_ADLP: + if (DISPLAY_VER(dev_priv) > 12) + return 36; + fallthrough; default: MISSING_CASE(tmp); return 0; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 41186c1f771e..476bb3b9ad11 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6163,11 +6163,17 @@ enum { #define PIPEMISC_HDR_MODE_PRECISION (1 << 23) /* icl+ */ #define PIPEMISC_OUTPUT_COLORSPACE_YUV (1 << 11) #define PIPEMISC_PIXEL_ROUNDING_TRUNC REG_BIT(8) /* tgl+ */ -#define PIPEMISC_DITHER_BPC_MASK (7 << 5) -#define PIPEMISC_DITHER_8_BPC (0 << 5) -#define PIPEMISC_DITHER_10_BPC (1 << 5) -#define PIPEMISC_DITHER_6_BPC (2 << 5) -#define PIPEMISC_DITHER_12_BPC (3 << 5) +/* + * For Display < 13, Bits 5-7 of PIPE MISC represent DITHER BPC with + * valid values of: 6, 8, 10 BPC. + * ADLP+, the bits 5-7 represent PORT OUTPUT BPC with valid values of: + * 6, 8, 10, 12 BPC. + */ +#define PIPEMISC_BPC_MASK (7 << 5) +#define PIPEMISC_8_BPC (0 << 5) +#define PIPEMISC_10_BPC (1 << 5) +#define PIPEMISC_6_BPC (2 << 5) +#define PIPEMISC_12_BPC_ADLP (4 << 5) /* adlp+ */ #define PIPEMISC_DITHER_ENABLE (1 << 4) #define PIPEMISC_DITHER_TYPE_MASK (3 << 2) #define PIPEMISC_DITHER_TYPE_SP (0 << 2) From 24d032e2359e3abc926b3d423f49a7c33e0b7836 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Fri, 6 Aug 2021 10:41:30 -0700 Subject: [PATCH 1434/1469] drm/i915: Only access SFC_DONE when media domain is not fused off MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The SFC_DONE register lives within the corresponding VD0/VD2/VD4/VD6 forcewake domain and is not accessible if the vdbox in that domain is fused off and the forcewake is not initialized. This mistake went unnoticed because until recently we were using the wrong register offset for the SFC_DONE register; once the register offset was corrected, we started hitting errors like <4> [544.989065] i915 0000:cc:00.0: Uninitialized forcewake domain(s) 0x80 accessed at 0x1ce000 on parts with fused-off vdbox engines. Fixes: e50dbdbfd9fb ("drm/i915/tgl: Add SFC instdone to error state") Fixes: 9c9c6d0ab08a ("drm/i915: Correct SFC_DONE register offset") Cc: Daniele Ceraolo Spurio Cc: Mika Kuoppala Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210806174130.1058960-1-matthew.d.roper@intel.com Reviewed-by: José Roberto de Souza (cherry picked from commit c5589bb5dccb0c5cb74910da93663f489589f3ce) Signed-off-by: Rodrigo Vivi [Changed Fixes tag to match the cherry-picked 82929a2140eb] --- drivers/gpu/drm/i915/i915_gpu_error.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 35c97c39f125..966664610c8c 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -727,9 +727,18 @@ static void err_print_gt(struct drm_i915_error_state_buf *m, if (GRAPHICS_VER(m->i915) >= 12) { int i; - for (i = 0; i < GEN12_SFC_DONE_MAX; i++) + for (i = 0; i < GEN12_SFC_DONE_MAX; i++) { + /* + * SFC_DONE resides in the VD forcewake domain, so it + * only exists if the corresponding VCS engine is + * present. + */ + if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + continue; + err_printf(m, " SFC_DONE[%d]: 0x%08x\n", i, gt->sfc_done[i]); + } err_printf(m, " GAM_DONE: 0x%08x\n", gt->gam_done); } @@ -1581,6 +1590,14 @@ static void gt_record_regs(struct intel_gt_coredump *gt) if (GRAPHICS_VER(i915) >= 12) { for (i = 0; i < GEN12_SFC_DONE_MAX; i++) { + /* + * SFC_DONE resides in the VD forcewake domain, so it + * only exists if the corresponding VCS engine is + * present. + */ + if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + continue; + gt->sfc_done[i] = intel_uncore_read(uncore, GEN12_SFC_DONE(i)); } From ffd5caa26f6afde0c1e3ed126806607748a83c6e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 10 Aug 2021 16:27:48 +0200 Subject: [PATCH 1435/1469] drm/doc/rfc: drop lmem uapi section We still have quite a bit more work to do with overall reworking of the ttm-based dg1 code, but the uapi stuff is now finalized with the latest pull. So remove that. This also fixes kerneldoc build warnings because we've included the same headers in two places, resulting in sphinx complaining about duplicated symbols. This regression has been created when we moved the uapi definitions to the real include/uapi/ folder in 727ecd99a4c9 ("drm/doc/rfc: drop the i915_gem_lmem.h header") v2: Fix a few references that I missed, the htmldocs build took forever. Acked-by: Jason Ekstrand Acked-by: Maarten Lankhorst Tested-by Stephen Rothwell (v1) References: https://lore.kernel.org/dri-devel/20210603193242.1ce99344@canb.auug.org.au/ Reported-by: Stephen Rothwell Cc: Stephen Rothwell Fixes: 727ecd99a4c9 ("drm/doc/rfc: drop the i915_gem_lmem.h header") Cc: Matthew Auld Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210810142748.1983271-1-daniel.vetter@ffwll.ch (cherry picked from commit dae2d28832968751f7731336b560a4a84a197b76) Signed-off-by: Rodrigo Vivi --- Documentation/gpu/rfc/i915_gem_lmem.rst | 109 ------------------------ 1 file changed, 109 deletions(-) diff --git a/Documentation/gpu/rfc/i915_gem_lmem.rst b/Documentation/gpu/rfc/i915_gem_lmem.rst index 675ba8620d66..b421a3c1806e 100644 --- a/Documentation/gpu/rfc/i915_gem_lmem.rst +++ b/Documentation/gpu/rfc/i915_gem_lmem.rst @@ -18,114 +18,5 @@ real, with all the uAPI bits is: * Route shmem backend over to TTM SYSTEM for discrete * TTM purgeable object support * Move i915 buddy allocator over to TTM - * MMAP ioctl mode(see `I915 MMAP`_) - * SET/GET ioctl caching(see `I915 SET/GET CACHING`_) * Send RFC(with mesa-dev on cc) for final sign off on the uAPI * Add pciid for DG1 and turn on uAPI for real - -New object placement and region query uAPI -========================================== -Starting from DG1 we need to give userspace the ability to allocate buffers from -device local-memory. Currently the driver supports gem_create, which can place -buffers in system memory via shmem, and the usual assortment of other -interfaces, like dumb buffers and userptr. - -To support this new capability, while also providing a uAPI which will work -beyond just DG1, we propose to offer three new bits of uAPI: - -DRM_I915_QUERY_MEMORY_REGIONS ------------------------------ -New query ID which allows userspace to discover the list of supported memory -regions(like system-memory and local-memory) for a given device. We identify -each region with a class and instance pair, which should be unique. The class -here would be DEVICE or SYSTEM, and the instance would be zero, on platforms -like DG1. - -Side note: The class/instance design is borrowed from our existing engine uAPI, -where we describe every physical engine in terms of its class, and the -particular instance, since we can have more than one per class. - -In the future we also want to expose more information which can further -describe the capabilities of a region. - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_memory_class drm_i915_gem_memory_class_instance drm_i915_memory_region_info drm_i915_query_memory_regions - -GEM_CREATE_EXT --------------- -New ioctl which is basically just gem_create but now allows userspace to provide -a chain of possible extensions. Note that if we don't provide any extensions and -set flags=0 then we get the exact same behaviour as gem_create. - -Side note: We also need to support PXP[1] in the near future, which is also -applicable to integrated platforms, and adds its own gem_create_ext extension, -which basically lets userspace mark a buffer as "protected". - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_create_ext - -I915_GEM_CREATE_EXT_MEMORY_REGIONS ----------------------------------- -Implemented as an extension for gem_create_ext, we would now allow userspace to -optionally provide an immutable list of preferred placements at creation time, -in priority order, for a given buffer object. For the placements we expect -them each to use the class/instance encoding, as per the output of the regions -query. Having the list in priority order will be useful in the future when -placing an object, say during eviction. - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_create_ext_memory_regions - -One fair criticism here is that this seems a little over-engineered[2]. If we -just consider DG1 then yes, a simple gem_create.flags or something is totally -all that's needed to tell the kernel to allocate the buffer in local-memory or -whatever. However looking to the future we need uAPI which can also support -upcoming Xe HP multi-tile architecture in a sane way, where there can be -multiple local-memory instances for a given device, and so using both class and -instance in our uAPI to describe regions is desirable, although specifically -for DG1 it's uninteresting, since we only have a single local-memory instance. - -Existing uAPI issues -==================== -Some potential issues we still need to resolve. - -I915 MMAP ---------- -In i915 there are multiple ways to MMAP GEM object, including mapping the same -object using different mapping types(WC vs WB), i.e multiple active mmaps per -object. TTM expects one MMAP at most for the lifetime of the object. If it -turns out that we have to backpedal here, there might be some potential -userspace fallout. - -I915 SET/GET CACHING --------------------- -In i915 we have set/get_caching ioctl. TTM doesn't let us to change this, but -DG1 doesn't support non-snooped pcie transactions, so we can just always -allocate as WB for smem-only buffers. If/when our hw gains support for -non-snooped pcie transactions then we must fix this mode at allocation time as -a new GEM extension. - -This is related to the mmap problem, because in general (meaning, when we're -not running on intel cpus) the cpu mmap must not, ever, be inconsistent with -allocation mode. - -Possible idea is to let the kernel picks the mmap mode for userspace from the -following table: - -smem-only: WB. Userspace does not need to call clflush. - -smem+lmem: We only ever allow a single mode, so simply allocate this as uncached -memory, and always give userspace a WC mapping. GPU still does snooped access -here(assuming we can't turn it off like on DG1), which is a bit inefficient. - -lmem only: always WC - -This means on discrete you only get a single mmap mode, all others must be -rejected. That's probably going to be a new default mode or something like -that. - -Links -===== -[1] https://patchwork.freedesktop.org/series/86798/ - -[2] https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5599#note_553791 From 98694166c27d473c36b434bd3572934c2f2a16ab Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 10 Aug 2021 16:13:16 +0000 Subject: [PATCH 1436/1469] powerpc/interrupt: Fix OOPS by not calling do_IRQ() from timer_interrupt() An interrupt handler shall not be called from another interrupt handler otherwise this leads to problems like the following: Kernel attempted to write user page (afd4fa84) - exploit attempt? (uid: 1000) ------------[ cut here ]------------ Bug: Write fault blocked by KUAP! WARNING: CPU: 0 PID: 1617 at arch/powerpc/mm/fault.c:230 do_page_fault+0x484/0x720 Modules linked in: CPU: 0 PID: 1617 Comm: sshd Tainted: G W 5.13.0-pmac-00010-g8393422eb77 #7 NIP: c001b77c LR: c001b77c CTR: 00000000 REGS: cb9e5bc0 TRAP: 0700 Tainted: G W (5.13.0-pmac-00010-g8393422eb77) MSR: 00021032 CR: 24942424 XER: 00000000 GPR00: c001b77c cb9e5c80 c1582c00 00000021 3ffffbff 085b0000 00000027 c8eb644c GPR08: 00000023 00000000 00000000 00000000 24942424 0063f8c8 00000000 000186a0 GPR16: afd52dd4 afd52dd0 afd52dcc afd52dc8 0065a990 c07640c4 cb9e5e98 cb9e5e90 GPR24: 00000040 afd4fa96 00000040 02000000 c1fda6c0 afd4fa84 00000300 cb9e5cc0 NIP [c001b77c] do_page_fault+0x484/0x720 LR [c001b77c] do_page_fault+0x484/0x720 Call Trace: [cb9e5c80] [c001b77c] do_page_fault+0x484/0x720 (unreliable) [cb9e5cb0] [c000424c] DataAccess_virt+0xd4/0xe4 --- interrupt: 300 at __copy_tofrom_user+0x110/0x20c NIP: c001f9b4 LR: c03250a0 CTR: 00000004 REGS: cb9e5cc0 TRAP: 0300 Tainted: G W (5.13.0-pmac-00010-g8393422eb77) MSR: 00009032 CR: 48028468 XER: 20000000 DAR: afd4fa84 DSISR: 0a000000 GPR00: 20726f6f cb9e5d80 c1582c00 00000004 cb9e5e3a 00000016 afd4fa80 00000000 GPR08: 3835202d 72777872 2d78722d 00000004 28028464 0063f8c8 00000000 000186a0 GPR16: afd52dd4 afd52dd0 afd52dcc afd52dc8 0065a990 c07640c4 cb9e5e98 cb9e5e90 GPR24: 00000040 afd4fa96 00000040 cb9e5e0c 00000daa a0000000 cb9e5e98 afd4fa56 NIP [c001f9b4] __copy_tofrom_user+0x110/0x20c LR [c03250a0] _copy_to_iter+0x144/0x990 --- interrupt: 300 [cb9e5d80] [c03e89c0] n_tty_read+0xa4/0x598 (unreliable) [cb9e5df0] [c03e2a0c] tty_read+0xdc/0x2b4 [cb9e5e80] [c0156bf8] vfs_read+0x274/0x340 [cb9e5f00] [c01571ac] ksys_read+0x70/0x118 [cb9e5f30] [c0016048] ret_from_syscall+0x0/0x28 --- interrupt: c00 at 0xa7855c88 NIP: a7855c88 LR: a7855c5c CTR: 00000000 REGS: cb9e5f40 TRAP: 0c00 Tainted: G W (5.13.0-pmac-00010-g8393422eb77) MSR: 0000d032 CR: 2402446c XER: 00000000 GPR00: 00000003 afd4ec70 a72137d0 0000000b afd4ecac 00004000 0065a990 00000800 GPR08: 00000000 a7947930 00000000 00000004 c15831b0 0063f8c8 00000000 000186a0 GPR16: afd52dd4 afd52dd0 afd52dcc afd52dc8 0065a990 0065a9e0 00000001 0065fac0 GPR24: 00000000 00000089 00664050 00000000 00668e30 a720c8dc a7943ff4 0065f9b0 NIP [a7855c88] 0xa7855c88 LR [a7855c5c] 0xa7855c5c --- interrupt: c00 Instruction dump: 3884aa88 38630178 48076861 807f0080 48042e45 2f830000 419e0148 3c80c079 3c60c076 38841be4 386301c0 4801f705 <0fe00000> 3860000b 4bfffe30 3c80c06b ---[ end trace fd69b91a8046c2e5 ]--- Here the problem is that by re-enterring an exception handler, kuap_save_and_lock() is called a second time with this time KUAP access locked, leading to regs->kuap being overwritten hence KUAP not being unlocked at exception exit as expected. Do not call do_IRQ() from timer_interrupt() directly. Instead, redefine do_IRQ() as a standard function named __do_IRQ(), and call it from both do_IRQ() and time_interrupt() handlers. Fixes: 3a96570ffceb ("powerpc: convert interrupt handlers to use wrappers") Cc: stable@vger.kernel.org # v5.12+ Reported-by: Stan Johnson Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c17d234f4927d39a1d7100864a8e1145323d33a0.1628611927.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/interrupt.h | 3 +++ arch/powerpc/include/asm/irq.h | 2 +- arch/powerpc/kernel/irq.c | 7 ++++++- arch/powerpc/kernel/time.c | 2 +- 4 files changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index d4bdf7d274ac..6b800d3e2681 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -583,6 +583,9 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode); DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException); +/* irq.c */ +DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ); + void __noreturn unrecoverable_exception(struct pt_regs *regs); void replay_system_reset(void); diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 4982f3711fc3..2b3278534bc1 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -52,7 +52,7 @@ extern void *mcheckirq_ctx[NR_CPUS]; extern void *hardirq_ctx[NR_CPUS]; extern void *softirq_ctx[NR_CPUS]; -extern void do_IRQ(struct pt_regs *regs); +void __do_IRQ(struct pt_regs *regs); extern void __init init_IRQ(void); extern void __do_irq(struct pt_regs *regs); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 91e63eac4e8f..551b653228c4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -750,7 +750,7 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } -DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); void *cursp, *irqsp, *sirqsp; @@ -774,6 +774,11 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) set_irq_regs(old_regs); } +DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +{ + __do_IRQ(regs); +} + static void *__init alloc_vm_stack(void) { return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e45ce427bffb..c487ba5a6e11 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -586,7 +586,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) - do_IRQ(regs); + __do_IRQ(regs); #endif old_regs = set_irq_regs(regs); From 01fcac8e4dfc112f420dcaeb70056a74e326cacf Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 10 Aug 2021 16:13:17 +0000 Subject: [PATCH 1437/1469] powerpc/interrupt: Do not call single_step_exception() from other exceptions single_step_exception() is called by emulate_single_step() which is called from (at least) alignment exception() handler and program_check_exception() handler. Redefine it as a regular __single_step_exception() which is called by both single_step_exception() handler and emulate_single_step() function. Fixes: 3a96570ffceb ("powerpc: convert interrupt handlers to use wrappers") Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/aed174f5cbc06f2cf95233c071d8aac948e46043.1628611921.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/traps.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index dfbce527c98e..d56254f05e17 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1104,7 +1104,7 @@ DEFINE_INTERRUPT_HANDLER(RunModeException) _exception(SIGTRAP, regs, TRAP_UNK, 0); } -DEFINE_INTERRUPT_HANDLER(single_step_exception) +static void __single_step_exception(struct pt_regs *regs) { clear_single_step(regs); clear_br_trace(regs); @@ -1121,6 +1121,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); } +DEFINE_INTERRUPT_HANDLER(single_step_exception) +{ + __single_step_exception(regs); +} + /* * After we have successfully emulated an instruction, we have to * check if the instruction was being single-stepped, and if so, @@ -1130,7 +1135,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) static void emulate_single_step(struct pt_regs *regs) { if (single_stepping(regs)) - single_step_exception(regs); + __single_step_exception(regs); } static inline int __parse_fpscr(unsigned long fpscr) From cbc06f051c524dcfe52ef0d1f30647828e226d30 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Sat, 7 Aug 2021 09:20:57 +0200 Subject: [PATCH 1438/1469] powerpc/xive: Do not skip CPU-less nodes when creating the IPIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On PowerVM, CPU-less nodes can be populated with hot-plugged CPUs at runtime. Today, the IPI is not created for such nodes, and hot-plugged CPUs use a bogus IPI, which leads to soft lockups. We can not directly allocate and request the IPI on demand because bringup_up() is called under the IRQ sparse lock. The alternative is to allocate the IPIs for all possible nodes at startup and to request the mapping on demand when the first CPU of a node is brought up. Fixes: 7dcc37b3eff9 ("powerpc/xive: Map one IPI interrupt per node") Cc: stable@vger.kernel.org # v5.13 Reported-by: Geetika Moolchandani Signed-off-by: Cédric Le Goater Tested-by: Srikar Dronamraju Tested-by: Laurent Vivier Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210807072057.184698-1-clg@kaod.org --- arch/powerpc/sysdev/xive/common.c | 35 +++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index dbdbbc2f1dc5..943fd30095af 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -67,6 +67,7 @@ static struct irq_domain *xive_irq_domain; static struct xive_ipi_desc { unsigned int irq; char name[16]; + atomic_t started; } *xive_ipis; /* @@ -1120,7 +1121,7 @@ static const struct irq_domain_ops xive_ipi_irq_domain_ops = { .alloc = xive_ipi_irq_domain_alloc, }; -static int __init xive_request_ipi(void) +static int __init xive_init_ipis(void) { struct fwnode_handle *fwnode; struct irq_domain *ipi_domain; @@ -1144,10 +1145,6 @@ static int __init xive_request_ipi(void) struct xive_ipi_desc *xid = &xive_ipis[node]; struct xive_ipi_alloc_info info = { node }; - /* Skip nodes without CPUs */ - if (cpumask_empty(cpumask_of_node(node))) - continue; - /* * Map one IPI interrupt per node for all cpus of that node. * Since the HW interrupt number doesn't have any meaning, @@ -1159,11 +1156,6 @@ static int __init xive_request_ipi(void) xid->irq = ret; snprintf(xid->name, sizeof(xid->name), "IPI-%d", node); - - ret = request_irq(xid->irq, xive_muxed_ipi_action, - IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL); - - WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); } return ret; @@ -1178,6 +1170,22 @@ out: return ret; } +static int __init xive_request_ipi(unsigned int cpu) +{ + struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)]; + int ret; + + if (atomic_inc_return(&xid->started) > 1) + return 0; + + ret = request_irq(xid->irq, xive_muxed_ipi_action, + IRQF_PERCPU | IRQF_NO_THREAD, + xid->name, NULL); + + WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); + return ret; +} + static int xive_setup_cpu_ipi(unsigned int cpu) { unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu); @@ -1192,6 +1200,9 @@ static int xive_setup_cpu_ipi(unsigned int cpu) if (xc->hw_ipi != XIVE_BAD_IRQ) return 0; + /* Register the IPI */ + xive_request_ipi(cpu); + /* Grab an IPI from the backend, this will populate xc->hw_ipi */ if (xive_ops->get_ipi(cpu, xc)) return -EIO; @@ -1231,6 +1242,8 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc) if (xc->hw_ipi == XIVE_BAD_IRQ) return; + /* TODO: clear IPI mapping */ + /* Mask the IPI */ xive_do_source_set_mask(&xc->ipi_data, true); @@ -1253,7 +1266,7 @@ void __init xive_smp_probe(void) smp_ops->cause_ipi = xive_cause_ipi; /* Register the IPI */ - xive_request_ipi(); + xive_init_ipis(); /* Allocate and setup IPI for the boot CPU */ xive_setup_cpu_ipi(smp_processor_id()); From 030d6dbf0c2e5fdf23ad29557f0c87a882993e26 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 22 Jul 2021 10:17:15 +0800 Subject: [PATCH 1439/1469] riscv: kexec: do not add '-mno-relax' flag if compiler doesn't support it The RISC-V special option '-mno-relax' which to disable linker relaxations is supported by GCC8+. For GCC7 and lower versions do not support this option. Fixes: fba8a8674f68 ("RISC-V: Add kexec support") Signed-off-by: Changbin Du Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index d3081e4d9600..3397ddac1a30 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -11,7 +11,7 @@ endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_KEXEC -AFLAGS_kexec_relocate.o := -mcmodel=medany -mno-relax +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) endif extra-y += head.o From fdf3a7a1e0a67a52f631b055975c6ac7e0e49a65 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 26 Jul 2021 07:42:54 +0200 Subject: [PATCH 1440/1469] riscv: Fix comment regarding kernel mapping overlapping with IS_ERR_VALUE The current comment states that we check if the 64-bit kernel mapping overlaps with the last 4K of the address space that is reserved to error values in create_kernel_page_table, which is not the case since it is done in setup_vm. But anyway, remove the reference to any function and simply note that in 64-bit kernel, the check should be done as soon as the kernel mapping base address is known. Fixes: db6b84a368b4 ("riscv: Make sure the kernel mapping does not overlap with IS_ERR_VALUE") Signed-off-by: Alexandre Ghiti Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 88134cc288d9..7cb4f391d106 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -197,7 +197,7 @@ static void __init setup_bootmem(void) * if end of dram is equal to maximum addressable memory. For 64-bit * kernel, this problem can't happen here as the end of the virtual * address space is occupied by the kernel mapping then this check must - * be done in create_kernel_page_table. + * be done as soon as the kernel mapping base address is determined. */ max_mapped_addr = __pa(~(ulong)0); if (max_mapped_addr == (phys_ram_end - 1)) From 839ad22f755132838f406751439363c07272ad87 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 30 Jul 2021 17:01:46 -0700 Subject: [PATCH 1441/1469] x86/tools: Fix objdump version check again Skip (omit) any version string info that is parenthesized. Warning: objdump version 15) is older than 2.19 Warning: Skipping posttest. where 'objdump -v' says: GNU objdump (GNU Binutils; SUSE Linux Enterprise 15) 2.35.1.20201123-7.18 Fixes: 8bee738bb1979 ("x86: Fix objdump version check in chkobjdump.awk for different formats.") Signed-off-by: Randy Dunlap Signed-off-by: Thomas Gleixner Reviewed-by: Masami Hiramatsu Link: https://lore.kernel.org/r/20210731000146.2720-1-rdunlap@infradead.org --- arch/x86/tools/chkobjdump.awk | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index fd1ab80be0de..a4cf678cf5c8 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -10,6 +10,7 @@ BEGIN { /^GNU objdump/ { verstr = "" + gsub(/\(.*\)/, ""); for (i = 3; i <= NF; i++) if (match($(i), "^[0-9]")) { verstr = $(i); From 88ca2521bd5b4e8b83743c01a2d4cb09325b51e9 Mon Sep 17 00:00:00 2001 From: Maximilian Heyne Date: Thu, 12 Aug 2021 13:09:27 +0000 Subject: [PATCH 1442/1469] xen/events: Fix race in set_evtchn_to_irq There is a TOCTOU issue in set_evtchn_to_irq. Rows in the evtchn_to_irq mapping are lazily allocated in this function. The check whether the row is already present and the row initialization is not synchronized. Two threads can at the same time allocate a new row for evtchn_to_irq and add the irq mapping to the their newly allocated row. One thread will overwrite what the other has set for evtchn_to_irq[row] and therefore the irq mapping is lost. This will trigger a BUG_ON later in bind_evtchn_to_cpu: INFO: pci 0000:1a:15.4: [1d0f:8061] type 00 class 0x010802 INFO: nvme 0000:1a:12.1: enabling device (0000 -> 0002) INFO: nvme nvme77: 1/0/0 default/read/poll queues CRIT: kernel BUG at drivers/xen/events/events_base.c:427! WARN: invalid opcode: 0000 [#1] SMP NOPTI WARN: Workqueue: nvme-reset-wq nvme_reset_work [nvme] WARN: RIP: e030:bind_evtchn_to_cpu+0xc2/0xd0 WARN: Call Trace: WARN: set_affinity_irq+0x121/0x150 WARN: irq_do_set_affinity+0x37/0xe0 WARN: irq_setup_affinity+0xf6/0x170 WARN: irq_startup+0x64/0xe0 WARN: __setup_irq+0x69e/0x740 WARN: ? request_threaded_irq+0xad/0x160 WARN: request_threaded_irq+0xf5/0x160 WARN: ? nvme_timeout+0x2f0/0x2f0 [nvme] WARN: pci_request_irq+0xa9/0xf0 WARN: ? pci_alloc_irq_vectors_affinity+0xbb/0x130 WARN: queue_request_irq+0x4c/0x70 [nvme] WARN: nvme_reset_work+0x82d/0x1550 [nvme] WARN: ? check_preempt_wakeup+0x14f/0x230 WARN: ? check_preempt_curr+0x29/0x80 WARN: ? nvme_irq_check+0x30/0x30 [nvme] WARN: process_one_work+0x18e/0x3c0 WARN: worker_thread+0x30/0x3a0 WARN: ? process_one_work+0x3c0/0x3c0 WARN: kthread+0x113/0x130 WARN: ? kthread_park+0x90/0x90 WARN: ret_from_fork+0x3a/0x50 This patch sets evtchn_to_irq rows via a cmpxchg operation so that they will be set only once. The row is now cleared before writing it to evtchn_to_irq in order to not create a race once the row is visible for other threads. While at it, do not require the page to be zeroed, because it will be overwritten with -1's in clear_evtchn_to_irq_row anyway. Signed-off-by: Maximilian Heyne Fixes: d0b075ffeede ("xen/events: Refactor evtchn_to_irq array to be dynamically allocated") Link: https://lore.kernel.org/r/20210812130930.127134-1-mheyne@amazon.de Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/events/events_base.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 154daddbdcb4..a78704ae3618 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -198,12 +198,12 @@ static void disable_dynirq(struct irq_data *data); static DEFINE_PER_CPU(unsigned int, irq_epoch); -static void clear_evtchn_to_irq_row(unsigned row) +static void clear_evtchn_to_irq_row(int *evtchn_row) { unsigned col; for (col = 0; col < EVTCHN_PER_ROW; col++) - WRITE_ONCE(evtchn_to_irq[row][col], -1); + WRITE_ONCE(evtchn_row[col], -1); } static void clear_evtchn_to_irq_all(void) @@ -213,7 +213,7 @@ static void clear_evtchn_to_irq_all(void) for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) { if (evtchn_to_irq[row] == NULL) continue; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_to_irq[row]); } } @@ -221,6 +221,7 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) { unsigned row; unsigned col; + int *evtchn_row; if (evtchn >= xen_evtchn_max_channels()) return -EINVAL; @@ -233,11 +234,18 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) if (irq == -1) return 0; - evtchn_to_irq[row] = (int *)get_zeroed_page(GFP_KERNEL); - if (evtchn_to_irq[row] == NULL) + evtchn_row = (int *) __get_free_pages(GFP_KERNEL, 0); + if (evtchn_row == NULL) return -ENOMEM; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_row); + + /* + * We've prepared an empty row for the mapping. If a different + * thread was faster inserting it, we can drop ours. + */ + if (cmpxchg(&evtchn_to_irq[row], NULL, evtchn_row) != NULL) + free_page((unsigned long) evtchn_row); } WRITE_ONCE(evtchn_to_irq[row][col], irq); From 41535701da3324b80029cabb501e86c4fafe339d Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Thu, 29 Jul 2021 07:45:29 +0000 Subject: [PATCH 1443/1469] cifs: Handle race conditions during rename When rename is executed on directory which has files for which close is deferred, then rename will fail with EACCES. This patch will try to close all deferred files when EACCES is received and retry rename on a directory. Signed-off-by: Rohith Surabattula Cc: stable@vger.kernel.org # 5.13 Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/inode.c | 19 +++++++++++++++++-- fs/cifs/misc.c | 16 +++++++++++----- 2 files changed, 28 insertions(+), 7 deletions(-) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index b96b253e7635..65f8a70cece3 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1625,7 +1625,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(inode)); if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -2084,6 +2084,7 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; + int retry_count = 0; if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2113,10 +2114,24 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(d_inode(source_dentry))); + if (d_inode(target_dentry) != NULL) + cifs_close_deferred_file(CIFS_I(d_inode(target_dentry))); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); + if (rc == -EACCES) { + while (retry_count < 3) { + cifs_close_all_deferred_files(tcon); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, + to_name); + if (rc != -EACCES) + break; + retry_count++; + } + } + /* * No-replace is the natural behavior for CIFS, so skip unlink hacks. */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 844abeb2b48f..cdb1ec1461de 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -723,13 +723,19 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *cfile = NULL; - struct cifs_deferred_close *dclose; + + if (cifs_inode == NULL) + return; list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { - spin_lock(&cifs_inode->deferred_lock); - if (cifs_is_deferred_close(cfile, &dclose)) - mod_delayed_work(deferredclose_wq, &cfile->deferred, 0); - spin_unlock(&cifs_inode->deferred_lock); + if (delayed_work_pending(&cfile->deferred)) { + /* + * If there is no pending work, mod_delayed_work queues new work. + * So, Increase the ref count to avoid use-after-free. + */ + if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) + cifsFileInfo_get(cfile); + } } } From 9e992755be8f2d458a0bcbefd19e493483c1dba2 Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Mon, 9 Aug 2021 09:32:46 +0000 Subject: [PATCH 1444/1469] cifs: Call close synchronously during unlink/rename/lease break. During unlink/rename/lease break, deferred work for close is scheduled immediately but in an asynchronous manner which might lead to race with actual(unlink/rename) commands. This change will schedule close synchronously which will avoid the race conditions with other commands. Signed-off-by: Rohith Surabattula Reviewed-by: Shyam Prasad N Cc: stable@vger.kernel.org # 5.13 Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 5 +++++ fs/cifs/file.c | 35 +++++++++++++++++------------------ fs/cifs/misc.c | 46 ++++++++++++++++++++++++++++++++++------------ 3 files changed, 56 insertions(+), 30 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c0bfc2f01030..c6a9542ca281 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1611,6 +1611,11 @@ struct dfs_info3_param { int ttl; }; +struct file_list { + struct list_head list; + struct cifsFileInfo *cfile; +}; + /* * common struct for holding inode info when searching for or updating an * inode with new info diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0a72840a88f1..bb98fbdd22a9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4847,6 +4847,22 @@ void cifs_oplock_break(struct work_struct *work) cifs_dbg(VFS, "Push locks rc = %d\n", rc); oplock_break_ack: + /* + * When oplock break is received and there are no active + * file handles but cached, then schedule deferred close immediately. + * So, new open will not use cached handle. + */ + spin_lock(&CIFS_I(inode)->deferred_lock); + is_deferred = cifs_is_deferred_close(cfile, &dclose); + spin_unlock(&CIFS_I(inode)->deferred_lock); + if (is_deferred && + cfile->deferred_close_scheduled && + delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + _cifsFileInfo_put(cfile, false, false); + goto oplock_break_done; + } + } /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do @@ -4858,24 +4874,7 @@ oplock_break_ack: cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - /* - * When oplock break is received and there are no active - * file handles but cached, then schedule deferred close immediately. - * So, new open will not use cached handle. - */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - if (is_deferred && - cfile->deferred_close_scheduled && - delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); - } - spin_unlock(&CIFS_I(inode)->deferred_lock); +oplock_break_done: _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index cdb1ec1461de..9469f1cf0b46 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -723,20 +723,32 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *cfile = NULL; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; if (cifs_inode == NULL) return; + INIT_LIST_HEAD(&file_head); + spin_lock(&cifs_inode->open_file_lock); list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { if (delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } } } + spin_unlock(&cifs_inode->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } } void @@ -744,20 +756,30 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) { struct cifsFileInfo *cfile; struct list_head *tmp; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + INIT_LIST_HEAD(&file_head); spin_lock(&tcon->open_file_lock); list_for_each(tmp, &tcon->openFileList) { cfile = list_entry(tmp, struct cifsFileInfo, tlist); if (delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } } } spin_unlock(&tcon->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } } /* parses DFS refferal V3 structure From d9d5b8961284b0051726e0fcda91d1e297e087f5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 11 Aug 2021 15:48:45 +0300 Subject: [PATCH 1445/1469] wwan: core: Avoid returning NULL from wwan_create_dev() Make wwan_create_dev() to return either valid or error pointer, In some cases it may return NULL. Prevent this by converting it to the respective error pointer. Fixes: 9a44c1cc6388 ("net: Add a WWAN subsystem") Signed-off-by: Andy Shevchenko Acked-by: Sergey Ryazanov Reviewed-by: Loic Poulain Link: https://lore.kernel.org/r/20210811124845.10955-1-andriy.shevchenko@linux.intel.com Signed-off-by: Jakub Kicinski --- drivers/net/wwan/wwan_core.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 674a81d79db3..35ece98134c0 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -164,11 +164,14 @@ static struct wwan_device *wwan_create_dev(struct device *parent) goto done_unlock; id = ida_alloc(&wwan_dev_ids, GFP_KERNEL); - if (id < 0) + if (id < 0) { + wwandev = ERR_PTR(id); goto done_unlock; + } wwandev = kzalloc(sizeof(*wwandev), GFP_KERNEL); if (!wwandev) { + wwandev = ERR_PTR(-ENOMEM); ida_free(&wwan_dev_ids, id); goto done_unlock; } @@ -182,7 +185,8 @@ static struct wwan_device *wwan_create_dev(struct device *parent) err = device_register(&wwandev->dev); if (err) { put_device(&wwandev->dev); - wwandev = NULL; + wwandev = ERR_PTR(err); + goto done_unlock; } done_unlock: @@ -1014,8 +1018,8 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, return -EINVAL; wwandev = wwan_create_dev(parent); - if (!wwandev) - return -ENOMEM; + if (IS_ERR(wwandev)) + return PTR_ERR(wwandev); if (WARN_ON(wwandev->ops)) { wwan_remove_dev(wwandev); From 49b0b6ffe20c5344f4173f3436298782a08da4f2 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Thu, 12 Aug 2021 13:30:56 +0800 Subject: [PATCH 1446/1469] vsock/virtio: avoid potential deadlock when vsock device remove There's a potential deadlock case when remove the vsock device or process the RESET event: vsock_for_each_connected_socket: spin_lock_bh(&vsock_table_lock) ----------- (1) ... virtio_vsock_reset_sock: lock_sock(sk) --------------------- (2) ... spin_unlock_bh(&vsock_table_lock) lock_sock() may do initiative schedule when the 'sk' is owned by other thread at the same time, we would receivce a warning message that "scheduling while atomic". Even worse, if the next task (selected by the scheduler) try to release a 'sk', it need to request vsock_table_lock and the deadlock occur, cause the system into softlockup state. Call trace: queued_spin_lock_slowpath vsock_remove_bound vsock_remove_sock virtio_transport_release __vsock_release vsock_release __sock_release sock_close __fput ____fput So we should not require sk_lock in this case, just like the behavior in vhost_vsock or vmci. Fixes: 0ea9e1d3a9e3 ("VSOCK: Introduce virtio_transport.ko") Cc: Stefan Hajnoczi Signed-off-by: Longpeng(Mike) Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20210812053056.1699-1-longpeng2@huawei.com Signed-off-by: Jakub Kicinski --- net/vmw_vsock/virtio_transport.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e0c2c992ad9c..4f7c99dfd16c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -357,11 +357,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { - lock_sock(sk); + /* vmci_transport.c doesn't take sk_lock here either. At least we're + * under vsock_table_lock so the sock cannot disappear while we're + * executing. + */ + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk_error_report(sk); - release_sock(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) From 064855a69003c24bd6b473b367d364e418c57625 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 2 Aug 2021 14:38:58 -0500 Subject: [PATCH 1447/1469] x86/resctrl: Fix default monitoring groups reporting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Creating a new sub monitoring group in the root /sys/fs/resctrl leads to getting the "Unavailable" value for mbm_total_bytes and mbm_local_bytes on the entire filesystem. Steps to reproduce: 1. mount -t resctrl resctrl /sys/fs/resctrl/ 2. cd /sys/fs/resctrl/ 3. cat mon_data/mon_L3_00/mbm_total_bytes 23189832 4. Create sub monitor group: mkdir mon_groups/test1 5. cat mon_data/mon_L3_00/mbm_total_bytes Unavailable When a new monitoring group is created, a new RMID is assigned to the new group. But the RMID is not active yet. When the events are read on the new RMID, it is expected to report the status as "Unavailable". When the user reads the events on the default monitoring group with multiple subgroups, the events on all subgroups are consolidated together. Currently, if any of the RMID reads report as "Unavailable", then everything will be reported as "Unavailable". Fix the issue by discarding the "Unavailable" reads and reporting all the successful RMID reads. This is not a problem on Intel systems as Intel reports 0 on Inactive RMIDs. Fixes: d89b7379015f ("x86/intel_rdt/cqm: Add mon_data") Reported-by: Paweł Szulik Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov Acked-by: Reinette Chatre Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=213311 Link: https://lkml.kernel.org/r/162793309296.9224.15871659871696482080.stgit@bmoger-ubuntu --- arch/x86/kernel/cpu/resctrl/monitor.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f07c10b87a87..57e4bb695ff9 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -285,15 +285,14 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >>= shift; } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { - rr->val = tval; - return -EINVAL; + return tval; } switch (rr->evtid) { case QOS_L3_OCCUP_EVENT_ID: @@ -305,12 +304,6 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) case QOS_L3_MBM_LOCAL_EVENT_ID: m = &rr->d->mbm_local[rmid]; break; - default: - /* - * Code would never reach here because - * an invalid event id would fail the __rmid_read. - */ - return -EINVAL; } if (rr->first) { @@ -361,23 +354,29 @@ void mon_event_count(void *info) struct rdtgroup *rdtgrp, *entry; struct rmid_read *rr = info; struct list_head *head; + u64 ret_val; rdtgrp = rr->rgrp; - if (__mon_event_count(rdtgrp->mon.rmid, rr)) - return; + ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); /* - * For Ctrl groups read data from child monitor groups. + * For Ctrl groups read data from child monitor groups and + * add them together. Count events which are read successfully. + * Discard the rmid_read's reporting errors. */ head = &rdtgrp->mon.crdtgrp_list; if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr)) - return; + if (__mon_event_count(entry->mon.rmid, rr) == 0) + ret_val = 0; } } + + /* Report error if none of rmid_reads are successful */ + if (ret_val) + rr->val = ret_val; } /* From 1383279c6494c6b62d1d6939f34906a4d2ef721c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 5 Aug 2021 11:38:04 -0700 Subject: [PATCH 1448/1469] KVM: x86: Allow guest to set EFER.NX=1 on non-PAE 32-bit kernels Remove an ancient restriction that disallowed exposing EFER.NX to the guest if EFER.NX=0 on the host, even if NX is fully supported by the CPU. The motivation of the check, added by commit 2cc51560aed0 ("KVM: VMX: Avoid saving and restoring msr_efer on lightweight vmexit"), was to rule out the case of host.EFER.NX=0 and guest.EFER.NX=1 so that KVM could run the guest with the host's EFER.NX and thus avoid context switching EFER if the only divergence was the NX bit. Fast forward to today, and KVM has long since stopped running the guest with the host's EFER.NX. Not only does KVM context switch EFER if host.EFER.NX=1 && guest.EFER.NX=0, KVM also forces host.EFER.NX=0 && guest.EFER.NX=1 when using shadow paging (to emulate SMEP). Furthermore, the entire motivation for the restriction was made obsolete over a decade ago when Intel added dedicated host and guest EFER fields in the VMCS (Nehalem timeframe), which reduced the overhead of context switching EFER from 400+ cycles (2 * WRMSR + 1 * RDMSR) to a mere ~2 cycles. In practice, the removed restriction only affects non-PAE 32-bit kernels, as EFER.NX is set during boot if NX is supported and the kernel will use PAE paging (32-bit or 64-bit), regardless of whether or not the kernel will actually use NX itself (mark PTEs non-executable). Alternatively and/or complementarily, startup_32_smp() in head_32.S could be modified to set EFER.NX=1 regardless of paging mode, thus eliminating the scenario where NX is supported but not enabled. However, that runs the risk of breaking non-KVM non-PAE kernels (though the risk is very, very low as there are no known EFER.NX errata), and also eliminates an easy-to-use mechanism for stressing KVM's handling of guest vs. host EFER across nested virtualization transitions. Suggested-by: Paolo Bonzini Signed-off-by: Sean Christopherson Message-Id: <20210805183804.1221554-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 28 +--------------------------- 1 file changed, 1 insertion(+), 27 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 739be5da3bca..fe03bd978761 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_after_set_cpuid(vcpu); } -static int is_efer_nx(void) -{ - return host_efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { - cpuid_entry_clear(entry, X86_FEATURE_NX); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); kvm_update_cpuid_runtime(vcpu); kvm_vcpu_after_set_cpuid(vcpu); @@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) void kvm_set_cpu_caps(void) { - unsigned int f_nx = is_efer_nx() ? F(NX) : 0; #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); @@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void) F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) ); From ffbe17cadaf564b5da0e4eabdcff1b719e184a76 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Aug 2021 07:00:58 -0400 Subject: [PATCH 1449/1469] KVM: x86: remove dead initialization hv_vcpu is initialized again a dozen lines below, and at this point vcpu->arch.hyperv is not valid. Remove the initializer. Reported-by: kernel test robot Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 0b38f944c6b6..41d2a53c5dea 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1933,7 +1933,7 @@ ret_success: void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { From 85aa8889b82e0eec680a21ea28dbf57c6acfe182 Mon Sep 17 00:00:00 2001 From: Junaid Shahid Date: Fri, 6 Aug 2021 15:22:29 -0700 Subject: [PATCH 1450/1469] kvm: vmx: Sync all matching EPTPs when injecting nested EPT fault When a nested EPT violation/misconfig is injected into the guest, the shadow EPT PTEs associated with that address need to be synced. This is done by kvm_inject_emulated_page_fault() before it calls nested_ept_inject_page_fault(). However, that will only sync the shadow EPT PTE associated with the current L1 EPTP. Since the ASID is based on EP4TA rather than the full EPTP, so syncing the current EPTP is not enough. The SPTEs associated with any other L1 EPTPs in the prev_roots cache with the same EP4TA also need to be synced. Signed-off-by: Junaid Shahid Message-Id: <20210806222229.1645356-1-junaids@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 53 ++++++++++++++++++++++++++++++--------- 1 file changed, 41 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1a52134b0c42..81160ebe6acb 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + +static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, + gpa_t addr) +{ + uint i; + struct kvm_mmu_root_info *cached_root; + + WARN_ON_ONCE(!mmu_is_nested(vcpu)); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + cached_root = &vcpu->arch.mmu->prev_roots[i]; + + if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, + eptp)) + vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + } +} + static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; exit_qualification &= INTR_INFO_UNBLOCK_NMI; - } else if (fault->error_code & PFERR_RSVD_MASK) - vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else - vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } else { + if (fault->error_code & PFERR_RSVD_MASK) + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + else + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + + /* + * Although the caller (kvm_inject_emulated_page_fault) would + * have already synced the faulting address in the shadow EPT + * tables for the current EPTP12, we also need to sync it for + * any other cached EPTP02s based on the same EP4TA, since the + * TLB associates mappings to the EP4TA rather than the full EPTP. + */ + nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, + fault->address); + } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; @@ -5325,14 +5362,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -#define EPTP_PA_MASK GENMASK_ULL(51, 12) - -static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) -{ - return VALID_PAGE(root_hpa) && - ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); -} - /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { From 18712c13709d2de9516c5d3414f707c4f0a9c190 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 11 Aug 2021 21:56:15 -0700 Subject: [PATCH 1451/1469] KVM: nVMX: Use vmx_need_pf_intercept() when deciding if L0 wants a #PF Use vmx_need_pf_intercept() when determining if L0 wants to handle a #PF in L2 or if the VM-Exit should be forwarded to L1. The current logic fails to account for the case where #PF is intercepted to handle guest.MAXPHYADDR < host.MAXPHYADDR and ends up reflecting all #PFs into L1. At best, L1 will complain and inject the #PF back into L2. At worst, L1 will eat the unexpected fault and cause L2 to hang on infinite page faults. Note, while the bug was technically introduced by the commit that added support for the MAXPHYADDR madness, the shame is all on commit a0c134347baf ("KVM: VMX: introduce vmx_need_pf_intercept"). Fixes: 1dbf5d68af6f ("KVM: VMX: Add guest physical address check in EPT violation and misconfig") Cc: stable@vger.kernel.org Cc: Peter Shier Cc: Oliver Upton Cc: Jim Mattson Signed-off-by: Sean Christopherson Message-Id: <20210812045615.3167686-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 81160ebe6acb..b3f77d18eb5a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5855,7 +5855,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) - return vcpu->arch.apf.host_apf_flags || !enable_ept; + return vcpu->arch.apf.host_apf_flags || + vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) From 524a1e4e381fc5e7781008d5bd420fd1357c0113 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 12 Aug 2021 11:14:13 -0700 Subject: [PATCH 1452/1469] KVM: x86/mmu: Don't leak non-leaf SPTEs when zapping all SPTEs Pass "all ones" as the end GFN to signal "zap all" for the TDP MMU and really zap all SPTEs in this case. As is, zap_gfn_range() skips non-leaf SPTEs whose range exceeds the range to be zapped. If shadow_phys_bits is not aligned to the range size of top-level SPTEs, e.g. 512gb with 4-level paging, the "zap all" flows will skip top-level SPTEs whose range extends beyond shadow_phys_bits and leak their SPs when the VM is destroyed. Use the current upper bound (based on host.MAXPHYADDR) to detect that the caller wants to zap all SPTEs, e.g. instead of using the max theoretical gfn, 1 << (52 - 12). The more precise upper bound allows the TDP iterator to terminate its walk earlier when running on hosts with MAXPHYADDR < 52. Add a WARN on kmv->arch.tdp_mmu_pages when the TDP MMU is destroyed to help future debuggers should KVM decide to leak SPTEs again. The bug is most easily reproduced by running (and unloading!) KVM in a VM whose host.MAXPHYADDR < 39, as the SPTE for gfn=0 will be skipped. ============================================================================= BUG kvm_mmu_page_header (Not tainted): Objects remaining in kvm_mmu_page_header on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Slab 0x000000004d8f7af1 objects=22 used=2 fp=0x00000000624d29ac flags=0x4000000000000200(slab|zone=1) CPU: 0 PID: 1582 Comm: rmmod Not tainted 5.14.0-rc2+ #420 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Call Trace: dump_stack_lvl+0x45/0x59 slab_err+0x95/0xc9 __kmem_cache_shutdown.cold+0x3c/0x158 kmem_cache_destroy+0x3d/0xf0 kvm_mmu_module_exit+0xa/0x30 [kvm] kvm_arch_exit+0x5d/0x90 [kvm] kvm_exit+0x78/0x90 [kvm] vmx_exit+0x1a/0x50 [kvm_intel] __x64_sys_delete_module+0x13f/0x220 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Cc: stable@vger.kernel.org Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210812181414.3376143-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 0853370bd811..8783b9eb2b33 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; + WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); - kvm_lockdep_assert_mmu_lock_held(kvm, shared); if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) @@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, list_del_rcu(&root->link); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); - zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared); + zap_gfn_range(kvm, root, 0, -1ull, false, false, shared); call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -724,8 +723,17 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, bool can_yield, bool flush, bool shared) { + gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT); + bool zap_all = (start == 0 && end >= max_gfn_host); struct tdp_iter iter; + /* + * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will + * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF, + * and so KVM will never install a SPTE for such addresses. + */ + end = min(end, max_gfn_host); + kvm_lockdep_assert_mmu_lock_held(kvm, shared); rcu_read_lock(); @@ -744,9 +752,10 @@ retry: /* * If this is a non-last-level SPTE that covers a larger range * than should be zapped, continue, and zap the mappings at a - * lower level. + * lower level, except when zapping all SPTEs. */ - if ((iter.gfn < start || + if (!zap_all && + (iter.gfn < start || iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) && !is_last_spte(iter.old_spte, iter.level)) continue; @@ -794,12 +803,11 @@ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush = false; int i; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn, + flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull, flush, false); if (flush) @@ -838,7 +846,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm, */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); struct kvm_mmu_page *next_root; struct kvm_mmu_page *root; bool flush = false; @@ -854,8 +861,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) rcu_read_unlock(); - flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush, - true); + flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true); /* * Put the reference acquired in From 0103098fb4f13b447b26ed514bcd3140f6791047 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 12 Aug 2021 11:14:14 -0700 Subject: [PATCH 1453/1469] KVM: x86/mmu: Don't step down in the TDP iterator when zapping all SPTEs Set the min_level for the TDP iterator at the root level when zapping all SPTEs to optimize the iterator's try_step_down(). Zapping a non-leaf SPTE will recursively zap all its children, thus there is no need for the iterator to attempt to step down. This avoids rereading the top-level SPTEs after they are zapped by causing try_step_down() to short-circuit. In most cases, optimizing try_step_down() will be in the noise as the cost of zapping SPTEs completely dominates the overall time. The optimization is however helpful if the zap occurs with relatively few SPTEs, e.g. if KVM is zapping in response to multiple memslot updates when userspace is adding and removing read-only memslots for option ROMs. In that case, the task doing the zapping likely isn't a vCPU thread, but it still holds mmu_lock for read and thus can be a noisy neighbor of sorts. Reviewed-by: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210812181414.3376143-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 8783b9eb2b33..d80cb122b5f3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -727,6 +727,12 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, bool zap_all = (start == 0 && end >= max_gfn_host); struct tdp_iter iter; + /* + * No need to try to step down in the iterator when zapping all SPTEs, + * zapping the top-level non-leaf SPTEs will recurse on their children. + */ + int min_level = zap_all ? root->role.level : PG_LEVEL_4K; + /* * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF, @@ -738,7 +744,8 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, start, end) { retry: if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) { From ce25681d59ffc4303321e555a2d71b1946af07da Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 12 Aug 2021 11:18:15 -0700 Subject: [PATCH 1454/1469] KVM: x86/mmu: Protect marking SPs unsync when using TDP MMU with spinlock Add yet another spinlock for the TDP MMU and take it when marking indirect shadow pages unsync. When using the TDP MMU and L1 is running L2(s) with nested TDP, KVM may encounter shadow pages for the TDP entries managed by L1 (controlling L2) when handling a TDP MMU page fault. The unsync logic is not thread safe, e.g. the kvm_mmu_page fields are not atomic, and misbehaves when a shadow page is marked unsync via a TDP MMU page fault, which runs with mmu_lock held for read, not write. Lack of a critical section manifests most visibly as an underflow of unsync_children in clear_unsync_child_bit() due to unsync_children being corrupted when multiple CPUs write it without a critical section and without atomic operations. But underflow is the best case scenario. The worst case scenario is that unsync_children prematurely hits '0' and leads to guest memory corruption due to KVM neglecting to properly sync shadow pages. Use an entirely new spinlock even though piggybacking tdp_mmu_pages_lock would functionally be ok. Usurping the lock could degrade performance when building upper level page tables on different vCPUs, especially since the unsync flow could hold the lock for a comparatively long time depending on the number of indirect shadow pages and the depth of the paging tree. For simplicity, take the lock for all MMUs, even though KVM could fairly easily know that mmu_lock is held for write. If mmu_lock is held for write, there cannot be contention for the inner spinlock, and marking shadow pages unsync across multiple vCPUs will be slow enough that bouncing the kvm_arch cacheline should be in the noise. Note, even though L2 could theoretically be given access to its own EPT entries, a nested MMU must hold mmu_lock for write and thus cannot race against a TDP MMU page fault. I.e. the additional spinlock only _needs_ to be taken by the TDP MMU, as opposed to being taken by any MMU for a VM that is running with the TDP MMU enabled. Holding mmu_lock for read also prevents the indirect shadow page from being freed. But as above, keep it simple and always take the lock. Alternative #1, the TDP MMU could simply pass "false" for can_unsync and effectively disable unsync behavior for nested TDP. Write protecting leaf shadow pages is unlikely to noticeably impact traditional L1 VMMs, as such VMMs typically don't modify TDP entries, but the same may not hold true for non-standard use cases and/or VMMs that are migrating physical pages (from L1's perspective). Alternative #2, the unsync logic could be made thread safe. In theory, simply converting all relevant kvm_mmu_page fields to atomics and using atomic bitops for the bitmap would suffice. However, (a) an in-depth audit would be required, (b) the code churn would be substantial, and (c) legacy shadow paging would incur additional atomic operations in performance sensitive paths for no benefit (to legacy shadow paging). Fixes: a2855afc7ee8 ("KVM: x86/mmu: Allow parallel page faults for the TDP MMU") Cc: stable@vger.kernel.org Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210812181815.3378104-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/locking.rst | 8 ++++---- arch/x86/include/asm/kvm_host.h | 7 +++++++ arch/x86/kvm/mmu/mmu.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 4 deletions(-) diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 35eca377543d..88fa495abbac 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -25,10 +25,10 @@ On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock -- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock is - taken inside kvm->arch.mmu_lock, and cannot be taken without already - holding kvm->arch.mmu_lock (typically with ``read_lock``, otherwise - there's no need to take kvm->arch.tdp_mmu_pages_lock at all). +- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and + kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and + cannot be taken without already holding kvm->arch.mmu_lock (typically with + ``read_lock`` for the TDP MMU, thus the need for additional spinlocks). Everything else is a leaf: no other lock is taken inside the critical sections. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 974cbfb1eefe..af6ce8d4c86a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1038,6 +1038,13 @@ struct kvm_arch { struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c4f4fa23320e..47b765270239 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2535,6 +2535,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *sp; + bool locked = false; /* * Force write-protection if the page is being tracked. Note, the page @@ -2557,9 +2558,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) if (sp->unsync) continue; + /* + * TDP MMU page faults require an additional spinlock as they + * run with mmu_lock held for read, not write, and the unsync + * logic is not thread safe. Take the spinklock regardless of + * the MMU type to avoid extra conditionals/parameters, there's + * no meaningful penalty if mmu_lock is held for write. + */ + if (!locked) { + locked = true; + spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + + /* + * Recheck after taking the spinlock, a different vCPU + * may have since marked the page unsync. A false + * positive on the unprotected check above is not + * possible as clearing sp->unsync _must_ hold mmu_lock + * for write, i.e. unsync cannot transition from 0->1 + * while this CPU holds mmu_lock for read (or write). + */ + if (READ_ONCE(sp->unsync)) + continue; + } + WARN_ON(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(vcpu, sp); } + if (locked) + spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -5537,6 +5563,8 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); + if (!kvm_mmu_init_tdp_mmu(kvm)) /* * No smp_load/store wrappers needed here as we are in From 7a3dc4f35bf8e1a07e5c3f8ecc8ac923f48493fe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Aug 2021 12:36:14 +0200 Subject: [PATCH 1455/1469] driver core: Add missing kernel doc for device::msi_lock Fixes: 77e89afc25f3 ("PCI/MSI: Protect msi_desc::masked for multi-MSI") Reported-by: Stephen Rothwell Signed-off-by: Thomas Gleixner --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/device.h b/include/linux/device.h index e53aa5065f58..65d84b67b024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,6 +407,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. From 454bb6775202d94f0f489c4632efecdb62d3c904 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 31 Jul 2021 14:21:30 +0800 Subject: [PATCH 1456/1469] blk-mq: clear active_queues before clearing BLK_MQ_F_TAG_QUEUE_SHARED We run a test that delete and recover devcies frequently(two devices on the same host), and we found that 'active_queues' is super big after a period of time. If device a and device b share a tag set, and a is deleted, then blk_mq_exit_queue() will clear BLK_MQ_F_TAG_QUEUE_SHARED because there is only one queue that are using the tag set. However, if b is still active, the active_queues of b might never be cleared even if b is deleted. Thus clear active_queues before BLK_MQ_F_TAG_QUEUE_SHARED is cleared. Signed-off-by: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210731062130.1533893-1-yukuai3@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54eb..2fe396385a4a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2994,10 +2994,12 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) int i; queue_for_each_hw_ctx(q, hctx, i) { - if (shared) + if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; - else + } else { + blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; + } } } From 8f40d0370795313b6f1b1782035919cfc76b159f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 13 Aug 2021 08:57:07 -0600 Subject: [PATCH 1457/1469] tools/io_uring/io_uring-cp: sync with liburing example This example is missing a few fixes that are in the liburing version, synchronize with the upstream version. Reported-by: Sebastian Andrzej Siewior Signed-off-by: Jens Axboe --- tools/io_uring/io_uring-cp.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c index 81461813ec62..d9bd6f5f8f46 100644 --- a/tools/io_uring/io_uring-cp.c +++ b/tools/io_uring/io_uring-cp.c @@ -131,8 +131,7 @@ static int copy_file(struct io_uring *ring, off_t insize) writes = reads = offset = 0; while (insize || write_left) { - unsigned long had_reads; - int got_comp; + int had_reads, got_comp; /* * Queue up as many reads as we can @@ -174,8 +173,13 @@ static int copy_file(struct io_uring *ring, off_t insize) if (!got_comp) { ret = io_uring_wait_cqe(ring, &cqe); got_comp = 1; - } else + } else { ret = io_uring_peek_cqe(ring, &cqe); + if (ret == -EAGAIN) { + cqe = NULL; + ret = 0; + } + } if (ret < 0) { fprintf(stderr, "io_uring_peek_cqe: %s\n", strerror(-ret)); @@ -194,7 +198,7 @@ static int copy_file(struct io_uring *ring, off_t insize) fprintf(stderr, "cqe failed: %s\n", strerror(-cqe->res)); return 1; - } else if ((size_t) cqe->res != data->iov.iov_len) { + } else if (cqe->res != data->iov.iov_len) { /* Short read/write, adjust and requeue */ data->iov.iov_base += cqe->res; data->iov.iov_len -= cqe->res; @@ -221,6 +225,25 @@ static int copy_file(struct io_uring *ring, off_t insize) } } + /* wait out pending writes */ + while (writes) { + struct io_data *data; + + ret = io_uring_wait_cqe(ring, &cqe); + if (ret) { + fprintf(stderr, "wait_cqe=%d\n", ret); + return 1; + } + if (cqe->res < 0) { + fprintf(stderr, "write res=%d\n", cqe->res); + return 1; + } + data = io_uring_cqe_get_data(cqe); + free(data); + writes--; + io_uring_cqe_seen(ring, cqe); + } + return 0; } From cddce01160582a5f52ada3da9626c052d852ec42 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Fri, 13 Aug 2021 23:13:30 +0800 Subject: [PATCH 1458/1469] nbd: Aovid double completion of a request There is a race between iterating over requests in nbd_clear_que() and completing requests in recv_work(), which can lead to double completion of a request. To fix it, flush the recv worker before iterating over the requests and don't abort the completed request while iterating. Fixes: 96d97e17828f ("nbd: clear_sock on netlink disconnect") Reported-by: Jiang Yadong Signed-off-by: Xie Yongji Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20210813151330.96-1-xieyongji@bytedance.com Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c38317979f74..19f5d5a8b16a 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -818,6 +818,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); + /* don't abort one completed request */ + if (blk_mq_request_completed(req)) + return true; + mutex_lock(&cmd->lock); cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); @@ -2004,15 +2008,19 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) { mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); - nbd_clear_sock(nbd); - mutex_unlock(&nbd->config_lock); + sock_shutdown(nbd); /* * Make sure recv thread has finished, so it does not drop the last * config ref and try to destroy the workqueue from inside the work - * queue. + * queue. And this also ensure that we can safely call nbd_clear_que() + * to cancel the inflight I/Os. */ if (nbd->recv_workq) flush_workqueue(nbd->recv_workq); + nbd_clear_que(nbd); + nbd->task_setup = NULL; + mutex_unlock(&nbd->config_lock); + if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); From 6c7a00b843370feaf7710cef2350367c7e61cd1a Mon Sep 17 00:00:00 2001 From: Kuan-Ying Lee Date: Fri, 13 Aug 2021 16:54:24 -0700 Subject: [PATCH 1459/1469] kasan, kmemleak: reset tags when scanning block Patch series "kasan, slub: reset tag when printing address", v3. With hardware tag-based kasan enabled, we reset the tag when we access metadata to avoid from false alarm. This patch (of 2): Kmemleak needs to scan kernel memory to check memory leak. With hardware tag-based kasan enabled, when it scans on the invalid slab and dereference, the issue will occur as below. Hardware tag-based KASAN doesn't use compiler instrumentation, we can not use kasan_disable_current() to ignore tag check. Based on the below report, there are 11 0xf7 granules, which amounts to 176 bytes, and the object is allocated from the kmalloc-256 cache. So when kmemleak accesses the last 256-176 bytes, it causes faults, as those are marked with KASAN_KMALLOC_REDZONE == KASAN_TAG_INVALID == 0xfe. Thus, we reset tags before accessing metadata to avoid from false positives. BUG: KASAN: out-of-bounds in scan_block+0x58/0x170 Read at addr f7ff0000c0074eb0 by task kmemleak/138 Pointer tag: [f7], memory tag: [fe] CPU: 7 PID: 138 Comm: kmemleak Not tainted 5.14.0-rc2-00001-g8cae8cd89f05-dirty #134 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x1b0 show_stack+0x1c/0x30 dump_stack_lvl+0x68/0x84 print_address_description+0x7c/0x2b4 kasan_report+0x138/0x38c __do_kernel_fault+0x190/0x1c4 do_tag_check_fault+0x78/0x90 do_mem_abort+0x44/0xb4 el1_abort+0x40/0x60 el1h_64_sync_handler+0xb4/0xd0 el1h_64_sync+0x78/0x7c scan_block+0x58/0x170 scan_gray_list+0xdc/0x1a0 kmemleak_scan+0x2ac/0x560 kmemleak_scan_thread+0xb0/0xe0 kthread+0x154/0x160 ret_from_fork+0x10/0x18 Allocated by task 0: kasan_save_stack+0x2c/0x60 __kasan_kmalloc+0xec/0x104 __kmalloc+0x224/0x3c4 __register_sysctl_paths+0x200/0x290 register_sysctl_table+0x2c/0x40 sysctl_init+0x20/0x34 proc_sys_init+0x3c/0x48 proc_root_init+0x80/0x9c start_kernel+0x648/0x6a4 __primary_switched+0xc0/0xc8 Freed by task 0: kasan_save_stack+0x2c/0x60 kasan_set_track+0x2c/0x40 kasan_set_free_info+0x44/0x54 ____kasan_slab_free.constprop.0+0x150/0x1b0 __kasan_slab_free+0x14/0x20 slab_free_freelist_hook+0xa4/0x1fc kfree+0x1e8/0x30c put_fs_context+0x124/0x220 vfs_kern_mount.part.0+0x60/0xd4 kern_mount+0x24/0x4c bdev_cache_init+0x70/0x9c vfs_caches_init+0xdc/0xf4 start_kernel+0x638/0x6a4 __primary_switched+0xc0/0xc8 The buggy address belongs to the object at ffff0000c0074e00 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 176 bytes inside of 256-byte region [ffff0000c0074e00, ffff0000c0074f00) The buggy address belongs to the page: page:(____ptrval____) refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x100074 head:(____ptrval____) order:2 compound_mapcount:0 compound_pincount:0 flags: 0xbfffc0000010200(slab|head|node=0|zone=2|lastcpupid=0xffff|kasantag=0x0) raw: 0bfffc0000010200 0000000000000000 dead000000000122 f5ff0000c0002300 raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000c0074c00: f0 f0 f0 f0 f0 f0 f0 f0 f0 fe fe fe fe fe fe fe ffff0000c0074d00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe >ffff0000c0074e00: f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 f7 fe fe fe fe fe ^ ffff0000c0074f00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe ffff0000c0075000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint kmemleak: 181 new suspected memory leaks (see /sys/kernel/debug/kmemleak) Link: https://lkml.kernel.org/r/20210804090957.12393-1-Kuan-Ying.Lee@mediatek.com Link: https://lkml.kernel.org/r/20210804090957.12393-2-Kuan-Ying.Lee@mediatek.com Signed-off-by: Kuan-Ying Lee Acked-by: Catalin Marinas Reviewed-by: Andrey Konovalov Cc: Marco Elver Cc: Nicholas Tang Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Chinwen Chang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 228a2fbe0657..73d46d16d575 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -290,7 +290,7 @@ static void hex_dump_object(struct seq_file *seq, warn_or_seq_printf(seq, " hex dump (first %zu bytes):\n", len); kasan_disable_current(); warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE, - HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + HEX_GROUP_SIZE, kasan_reset_tag((void *)ptr), len, HEX_ASCII); kasan_enable_current(); } @@ -1171,7 +1171,7 @@ static bool update_checksum(struct kmemleak_object *object) kasan_disable_current(); kcsan_disable_current(); - object->checksum = crc32(0, (void *)object->pointer, object->size); + object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); kasan_enable_current(); kcsan_enable_current(); @@ -1246,7 +1246,7 @@ static void scan_block(void *_start, void *_end, break; kasan_disable_current(); - pointer = *ptr; + pointer = *(unsigned long *)kasan_reset_tag((void *)ptr); kasan_enable_current(); untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer); From 340caf178ddc2efb0294afaf54c715f7928c258e Mon Sep 17 00:00:00 2001 From: Kuan-Ying Lee Date: Fri, 13 Aug 2021 16:54:27 -0700 Subject: [PATCH 1460/1469] kasan, slub: reset tag when printing address The address still includes the tags when it is printed. With hardware tag-based kasan enabled, we will get a false positive KASAN issue when we access metadata. Reset the tag before we access the metadata. Link: https://lkml.kernel.org/r/20210804090957.12393-3-Kuan-Ying.Lee@mediatek.com Fixes: aa1ef4d7b3f6 ("kasan, mm: reset tags when accessing metadata") Signed-off-by: Kuan-Ying Lee Reviewed-by: Marco Elver Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Chinwen Chang Cc: Nicholas Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index af984e4990e8..1583354fbf48 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -576,8 +576,8 @@ static void print_section(char *level, char *text, u8 *addr, unsigned int length) { metadata_access_enable(); - print_hex_dump(level, kasan_reset_tag(text), DUMP_PREFIX_ADDRESS, - 16, 1, addr, length, 1); + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, + 16, 1, kasan_reset_tag((void *)addr), length, 1); metadata_access_disable(); } From 1ed7ce574c136569f55fb5c32e69e382c77ba500 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 13 Aug 2021 16:54:31 -0700 Subject: [PATCH 1461/1469] slub: fix kmalloc_pagealloc_invalid_free unit test The unit test kmalloc_pagealloc_invalid_free makes sure that for the higher order slub allocation which goes to page allocator, the free is called with the correct address i.e. the virtual address of the head page. Commit f227f0faf63b ("slub: fix unreclaimable slab stat for bulk free") unified the free code paths for page allocator based slub allocations but instead of using the address passed by the caller, it extracted the address from the page. Thus making the unit test kmalloc_pagealloc_invalid_free moot. So, fix this by using the address passed by the caller. Should we fix this? I think yes because dev expect kasan to catch these type of programming bugs. Link: https://lkml.kernel.org/r/20210802180819.1110165-1-shakeelb@google.com Fixes: f227f0faf63b ("slub: fix unreclaimable slab stat for bulk free") Signed-off-by: Shakeel Butt Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Muchun Song Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 1583354fbf48..5c2a13d66e71 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3236,12 +3236,12 @@ struct detached_freelist { struct kmem_cache *s; }; -static inline void free_nonslab_page(struct page *page) +static inline void free_nonslab_page(struct page *page, void *object) { unsigned int order = compound_order(page); VM_BUG_ON_PAGE(!PageCompound(page), page); - kfree_hook(page_address(page)); + kfree_hook(object); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(page, order); } @@ -3282,7 +3282,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); p[size] = NULL; /* mark object processed */ return size; } @@ -4258,7 +4258,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); From a7f1d48585b34730765dcda09ead6edc4ac16a5c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 13 Aug 2021 16:54:34 -0700 Subject: [PATCH 1462/1469] mm: slub: fix slub_debug disabling for list of slabs Vijayanand Jitta reports: Consider the scenario where CONFIG_SLUB_DEBUG_ON is set and we would want to disable slub_debug for few slabs. Using boot parameter with slub_debug=-,slab_name syntax doesn't work as expected i.e; only disabling debugging for the specified list of slabs. Instead it disables debugging for all slabs, which is wrong. This patch fixes it by delaying the moment when the global slub_debug flags variable is updated. In case a "slub_debug=-,slab_name" has been passed, the global flags remain as initialized (depending on CONFIG_SLUB_DEBUG_ON enabled or disabled) and are not simply reset to 0. Link: https://lkml.kernel.org/r/8a3d992a-473a-467b-28a0-4ad2ff60ab82@suse.cz Signed-off-by: Vlastimil Babka Reported-by: Vijayanand Jitta Reviewed-by: Vijayanand Jitta Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 5c2a13d66e71..f77d8cd79ef7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1400,12 +1400,13 @@ check_slabs: static int __init setup_slub_debug(char *str) { slab_flags_t flags; + slab_flags_t global_flags; char *saved_str; char *slab_list; bool global_slub_debug_changed = false; bool slab_list_specified = false; - slub_debug = DEBUG_DEFAULT_FLAGS; + global_flags = DEBUG_DEFAULT_FLAGS; if (*str++ != '=' || !*str) /* * No options specified. Switch on full debugging. @@ -1417,7 +1418,7 @@ static int __init setup_slub_debug(char *str) str = parse_slub_debug_flags(str, &flags, &slab_list, true); if (!slab_list) { - slub_debug = flags; + global_flags = flags; global_slub_debug_changed = true; } else { slab_list_specified = true; @@ -1426,16 +1427,18 @@ static int __init setup_slub_debug(char *str) /* * For backwards compatibility, a single list of flags with list of - * slabs means debugging is only enabled for those slabs, so the global - * slub_debug should be 0. We can extended that to multiple lists as + * slabs means debugging is only changed for those slabs, so the global + * slub_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending + * on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as * long as there is no option specifying flags without a slab list. */ if (slab_list_specified) { if (!global_slub_debug_changed) - slub_debug = 0; + global_flags = slub_debug; slub_debug_string = saved_str; } out: + slub_debug = global_flags; if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); else From eb2faa513c246ed47ae34a205928ab663bc5a18f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 13 Aug 2021 16:54:37 -0700 Subject: [PATCH 1463/1469] mm/madvise: report SIGBUS as -EFAULT for MADV_POPULATE_(READ|WRITE) Doing some extended tests and polishing the man page update for MADV_POPULATE_(READ|WRITE), I realized that we end up converting also SIGBUS (via -EFAULT) to -EINVAL, making it look like yet another madvise() user error. We want to report only problematic mappings and permission problems that the user could have know as -EINVAL. Let's not convert -EFAULT arising due to SIGBUS (or SIGSEGV) to -EINVAL, but instead indicate -EFAULT to user space. While we could also convert it to -ENOMEM, using -EFAULT looks more helpful when user space might want to troubleshoot what's going wrong: MADV_POPULATE_(READ|WRITE) is not part of an final Linux release and we can still adjust the behavior. Link: https://lkml.kernel.org/r/20210726154932.102880-1-david@redhat.com Fixes: 4ca9b3859dac ("mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables") Signed-off-by: David Hildenbrand Cc: Arnd Bergmann Cc: Michal Hocko Cc: Oscar Salvador Cc: Matthew Wilcox (Oracle) Cc: Andrea Arcangeli Cc: Minchan Kim Cc: Jann Horn Cc: Jason Gunthorpe Cc: Dave Hansen Cc: Hugh Dickins Cc: Rik van Riel Cc: Michael S. Tsirkin Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Chris Zankel Cc: Max Filippov Cc: Mike Kravetz Cc: Peter Xu Cc: Rolf Eike Beer Cc: Ram Pai Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup.c | 7 +++++-- mm/madvise.c | 4 +++- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 42b8b1fa6521..b94717977d17 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1558,9 +1558,12 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, gup_flags |= FOLL_WRITE; /* - * See check_vma_flags(): Will return -EFAULT on incompatible mappings - * or with insufficient permissions. + * We want to report -EINVAL instead of -EFAULT for any permission + * problems or incompatible mappings. */ + if (check_vma_flags(vma, gup_flags)) + return -EINVAL; + return __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); } diff --git a/mm/madvise.c b/mm/madvise.c index 6d3d348b17f4..5c065bc8b5f6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -862,10 +862,12 @@ static long madvise_populate(struct vm_area_struct *vma, switch (pages) { case -EINTR: return -EINTR; - case -EFAULT: /* Incompatible mappings / permissions. */ + case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; + case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ + return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); From 7fa0dacbaf1259fd3d1dda6d602fdd084dea9c0e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 13 Aug 2021 16:54:41 -0700 Subject: [PATCH 1464/1469] mm/memcg: fix incorrect flushing of lruvec data in obj_stock When mod_objcg_state() is called with a pgdat that is different from that in the obj_stock, the old lruvec data cached in obj_stock are flushed out. Unfortunately, they were flushed to the new pgdat and so the data go to the wrong node. This will screw up the slab data reported in /sys/devices/system/node/node*/meminfo. Fix that by flushing the data to the cached pgdat instead. Link: https://lkml.kernel.org/r/20210802143834.30578-1-longman@redhat.com Fixes: 68ac5b3c8db2 ("mm/memcg: cache vmstat data in percpu memcg_stock_pcp") Signed-off-by: Waiman Long Acked-by: Michal Hocko Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Muchun Song Cc: Alex Shi Cc: Chris Down Cc: Yafang Shao Cc: Wei Yang Cc: Masayoshi Mizuma Cc: Xing Zhengjun Cc: Matthew Wilcox Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index eb8e87c4833f..702a81dfe72d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3106,13 +3106,15 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, stock->cached_pgdat = pgdat; } else if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ + struct pglist_data *oldpg = stock->cached_pgdat; + if (stock->nr_slab_reclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, stock->nr_slab_reclaimable_b); stock->nr_slab_reclaimable_b = 0; } if (stock->nr_slab_unreclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, stock->nr_slab_unreclaimable_b); stock->nr_slab_unreclaimable_b = 0; } From 854f32648b8a5e424d682953b1a9f3b7c3322701 Mon Sep 17 00:00:00 2001 From: Liang Wang Date: Fri, 13 Aug 2021 16:54:45 -0700 Subject: [PATCH 1465/1469] lib: use PFN_PHYS() in devmem_is_allowed() The physical address may exceed 32 bits on 32-bit systems with more than 32 bits of physcial address. Use PFN_PHYS() in devmem_is_allowed(), or the physical address may overflow and be truncated. We found this bug when mapping a high addresses through devmem tool, when CONFIG_STRICT_DEVMEM is enabled on the ARM with ARM_LPAE and devmem is used to map a high address that is not in the iomem address range, an unexpected error indicating no permission is returned. This bug was initially introduced from v2.6.37, and the function was moved to lib in v5.11. Link: https://lkml.kernel.org/r/20210731025057.78825-1-wangliang101@huawei.com Fixes: 087aaffcdf9c ("ARM: implement CONFIG_STRICT_DEVMEM by disabling access to RAM via /dev/mem") Fixes: 527701eda5f1 ("lib: Add a generic version of devmem_is_allowed()") Signed-off-by: Liang Wang Reviewed-by: Luis Chamberlain Cc: Palmer Dabbelt Cc: Greg Kroah-Hartman Cc: Russell King Cc: Liang Wang Cc: Xiaoming Ni Cc: Kefeng Wang Cc: [2.6.37+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/devmem_is_allowed.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/devmem_is_allowed.c b/lib/devmem_is_allowed.c index c0d67c541849..60be9e24bd57 100644 --- a/lib/devmem_is_allowed.c +++ b/lib/devmem_is_allowed.c @@ -19,7 +19,7 @@ */ int devmem_is_allowed(unsigned long pfn) { - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) + if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; From 7c60610d476766e128cc4284bb6349732cbd6606 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Aug 2021 13:40:53 -1000 Subject: [PATCH 1466/1469] Linux 5.14-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index eae1314a5b86..c19d1638da25 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Opossums on Parade # *DOCUMENTATION* From 90e7a6de62781c27d6a111fccfb19b807f9b6887 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 24 Aug 2021 17:25:29 +0300 Subject: [PATCH 1467/1469] lib/scatterlist: Provide a dedicated function to support table append RDMA is the only in-kernel user that uses __sg_alloc_table_from_pages to append pages dynamically. In the next patch. That mode will be extended and that function will get more parameters. So separate it into a unique function to make such change more clear. Link: https://lore.kernel.org/r/20210824142531.3877007-2-maorg@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/gpu/drm/drm_prime.c | 13 ++++--- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 11 +++--- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 14 +++----- drivers/infiniband/core/umem.c | 4 +-- include/linux/scatterlist.h | 39 ++++++++++++++++++--- lib/scatterlist.c | 36 ++++++++++--------- tools/testing/scatterlist/main.c | 25 +++++++++---- 7 files changed, 90 insertions(+), 52 deletions(-) diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 2a54f86856af..cf3278041f9c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -807,8 +807,8 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, struct page **pages, unsigned int nr_pages) { struct sg_table *sg; - struct scatterlist *sge; size_t max_segment = 0; + int err; sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL); if (!sg) @@ -818,13 +818,12 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, max_segment = dma_max_mapping_size(dev->dev); if (max_segment == 0) max_segment = UINT_MAX; - sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, - max_segment, - NULL, 0, GFP_KERNEL); - if (IS_ERR(sge)) { + err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, + nr_pages << PAGE_SHIFT, + max_segment, GFP_KERNEL); + if (err) { kfree(sg); - sg = ERR_CAST(sge); + sg = ERR_PTR(err); } return sg; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 7487bab11f0b..458f797a9e1e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -133,7 +133,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; unsigned int sg_page_sizes; - struct scatterlist *sg; struct page **pvec; int ret; @@ -153,13 +152,11 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) spin_unlock(&i915->mm.notifier_lock); alloc_table: - sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0, - num_pages << PAGE_SHIFT, max_segment, - NULL, 0, GFP_KERNEL); - if (IS_ERR(sg)) { - ret = PTR_ERR(sg); + ret = sg_alloc_table_from_pages_segment(st, pvec, num_pages, 0, + num_pages << PAGE_SHIFT, + max_segment, GFP_KERNEL); + if (ret) goto err; - } ret = i915_gem_gtt_prepare_pages(obj, st); if (ret) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 0488042fb287..fc372d2e52a1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -363,7 +363,6 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) int ret = 0; static size_t sgl_size; static size_t sgt_size; - struct scatterlist *sg; if (vmw_tt->mapped) return 0; @@ -386,15 +385,12 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) if (unlikely(ret != 0)) return ret; - sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, - vsgt->num_pages, 0, - (unsigned long) vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->drm.dev), - NULL, 0, GFP_KERNEL); - if (IS_ERR(sg)) { - ret = PTR_ERR(sg); + ret = sg_alloc_table_from_pages_segment( + &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, + (unsigned long)vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL); + if (ret) goto out_sg_alloc_fail; - } if (vsgt->num_pages > vmw_tt->sgt.orig_nents) { uint64_t over_alloc = diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 0eb40025075f..b741758e528f 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -226,8 +226,8 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, cur_base += ret * PAGE_SIZE; npages -= ret; - sg = __sg_alloc_table_from_pages(&umem->sg_head, page_list, ret, - 0, ret << PAGE_SHIFT, + sg = sg_alloc_append_table_from_pages(&umem->sg_head, page_list, + ret, 0, ret << PAGE_SHIFT, ib_dma_max_seg_size(device), sg, npages, GFP_KERNEL); umem->sg_nents = umem->sg_head.nents; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index ecf87484814f..5c700f2a0d18 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -285,14 +285,45 @@ void sg_free_table(struct sg_table *); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); -struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, +struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, struct scatterlist *prv, unsigned int left_pages, gfp_t gfp_mask); -int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, gfp_t gfp_mask); +int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, + unsigned int n_pages, unsigned int offset, + unsigned long size, + unsigned int max_segment, gfp_t gfp_mask); + +/** + * sg_alloc_table_from_pages - Allocate and initialize an sg table from + * an array of pages + * @sgt: The sg table header to use + * @pages: Pointer to an array of page pointers + * @n_pages: Number of pages in the pages array + * @offset: Offset from start of the first page to the start of a buffer + * @size: Number of valid bytes in the buffer (after offset) + * @gfp_mask: GFP allocation mask + * + * Description: + * Allocate and initialize an sg table from a list of pages. Contiguous + * ranges of the pages are squashed into a single scatterlist node. A user + * may provide an offset at a start and a size of valid data in a buffer + * specified by the page array. The returned sg table is released by + * sg_free_table. + * + * Returns: + * 0 on success, negative error on failure + */ +static inline int sg_alloc_table_from_pages(struct sg_table *sgt, + struct page **pages, + unsigned int n_pages, + unsigned int offset, + unsigned long size, gfp_t gfp_mask) +{ + return sg_alloc_table_from_pages_segment(sgt, pages, n_pages, offset, + size, UINT_MAX, gfp_mask); +} #ifdef CONFIG_SGL_ALLOC struct scatterlist *sgl_alloc_order(unsigned long long length, diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 27efa6178153..611c63d4a958 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -397,7 +397,7 @@ static struct scatterlist *get_next_sg(struct sg_table *table, } /** - * __sg_alloc_table_from_pages - Allocate and initialize an sg table from + * sg_alloc_append_table_from_pages - Allocate and initialize an sg table from * an array of pages * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers @@ -425,7 +425,7 @@ static struct scatterlist *get_next_sg(struct sg_table *table, * If this function returns non-0 (eg failure), the caller must call * sg_free_table() to cleanup any leftover allocations. */ -struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, +struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, struct scatterlist *prv, unsigned int left_pages, @@ -520,36 +520,40 @@ out: sg_mark_end(s); return s; } -EXPORT_SYMBOL(__sg_alloc_table_from_pages); +EXPORT_SYMBOL(sg_alloc_append_table_from_pages); /** - * sg_alloc_table_from_pages - Allocate and initialize an sg table from - * an array of pages + * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from + * an array of pages and given maximum + * segment. * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) + * @max_segment: Maximum size of a scatterlist element in bytes * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous - * ranges of the pages are squashed into a single scatterlist node. A user - * may provide an offset at a start and a size of valid data in a buffer - * specified by the page array. The returned sg table is released by - * sg_free_table. + * ranges of the pages are squashed into a single scatterlist node up to the + * maximum size specified in @max_segment. A user may provide an offset at a + * start and a size of valid data in a buffer specified by the page array. * - * Returns: + * The returned sg table is released by sg_free_table. + * + * Returns: * 0 on success, negative error on failure */ -int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, gfp_t gfp_mask) +int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, + unsigned int n_pages, unsigned int offset, + unsigned long size, unsigned int max_segment, + gfp_t gfp_mask) { - return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages, - offset, size, UINT_MAX, NULL, 0, gfp_mask)); + return PTR_ERR_OR_ZERO(sg_alloc_append_table_from_pages(sgt, pages, + n_pages, offset, size, max_segment, NULL, 0, gfp_mask)); } -EXPORT_SYMBOL(sg_alloc_table_from_pages); +EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); #ifdef CONFIG_SGL_ALLOC diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index 652254754b4c..c2ff9179c2cc 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -87,28 +87,39 @@ int main(void) int left_pages = test->pfn_app ? test->num_pages : 0; struct page *pages[MAX_PAGES]; struct sg_table st; - struct scatterlist *sg; + struct scatterlist *sg = NULL; + int ret; set_pages(pages, test->pfn, test->num_pages); - sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0, - test->size, test->max_seg, NULL, left_pages, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + if (test->pfn_app) { + sg = sg_alloc_append_table_from_pages( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, NULL, left_pages, GFP_KERNEL); + assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + } else { + ret = sg_alloc_table_from_pages_segment( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, GFP_KERNEL); + assert(ret == test->alloc_ret); + } if (test->alloc_ret) continue; if (test->pfn_app) { set_pages(pages, test->pfn_app, test->num_pages); - sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0, - test->size, test->max_seg, sg, 0, GFP_KERNEL); + sg = sg_alloc_append_table_from_pages( + &st, pages, test->num_pages, 0, test->size, + test->max_seg, sg, 0, GFP_KERNEL); assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); } VALIDATE(st.nents == test->expected_segments, &st, test); if (!test->pfn_app) - VALIDATE(st.orig_nents == test->expected_segments, &st, test); + VALIDATE(st.orig_nents == test->expected_segments, &st, + test); sg_free_table(&st); } From 3e302dbc6774a27edaea39a1d5107f0c12e35cf2 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 24 Aug 2021 17:25:30 +0300 Subject: [PATCH 1468/1469] lib/scatterlist: Fix wrong update of orig_nents orig_nents should represent the number of entries with pages, but __sg_alloc_table_from_pages sets orig_nents as the number of total entries in the table. This is wrong when the API is used for dynamic allocation where not all the table entries are mapped with pages. It wasn't observed until now, since RDMA umem who uses this API in the dynamic form doesn't use orig_nents implicit or explicit by the scatterlist APIs. Fix it by changing the append API to track the SG append table state and have an API to free the append table according to the total number of entries in the table. Now all APIs set orig_nents as number of enries with pages. Fixes: 07da1223ec93 ("lib/scatterlist: Add support in dynamic allocation of SG table from pages") Link: https://lore.kernel.org/r/20210824142531.3877007-3-maorg@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem.c | 34 +++++---- include/linux/scatterlist.h | 19 +++-- include/rdma/ib_umem.h | 1 + lib/scatterlist.c | 127 +++++++++++++++++++------------ lib/sg_pool.c | 3 +- tools/testing/scatterlist/main.c | 43 ++++++----- 6 files changed, 135 insertions(+), 92 deletions(-) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index b741758e528f..42481e7a72e8 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -59,7 +59,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d unpin_user_page_range_dirty_lock(sg_page(sg), DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty); - sg_free_table(&umem->sg_head); + sg_free_append_table(&umem->sgt_append); } /** @@ -155,8 +155,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, unsigned long dma_attr = 0; struct mm_struct *mm; unsigned long npages; - int ret; - struct scatterlist *sg = NULL; + int pinned, ret; unsigned int gup_flags = FOLL_WRITE; /* @@ -216,28 +215,33 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, while (npages) { cond_resched(); - ret = pin_user_pages_fast(cur_base, + pinned = pin_user_pages_fast(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof(struct page *)), gup_flags | FOLL_LONGTERM, page_list); - if (ret < 0) + if (pinned < 0) { + ret = pinned; goto umem_release; + } - cur_base += ret * PAGE_SIZE; - npages -= ret; - sg = sg_alloc_append_table_from_pages(&umem->sg_head, page_list, - ret, 0, ret << PAGE_SHIFT, - ib_dma_max_seg_size(device), sg, npages, - GFP_KERNEL); - umem->sg_nents = umem->sg_head.nents; - if (IS_ERR(sg)) { - unpin_user_pages_dirty_lock(page_list, ret, 0); - ret = PTR_ERR(sg); + cur_base += pinned * PAGE_SIZE; + npages -= pinned; + ret = sg_alloc_append_table_from_pages( + &umem->sgt_append, page_list, pinned, 0, + pinned << PAGE_SHIFT, ib_dma_max_seg_size(device), + npages, GFP_KERNEL); + umem->sg_nents = umem->sgt_append.sgt.nents; + if (ret) { + memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, + sizeof(umem->sgt_append.sgt)); + unpin_user_pages_dirty_lock(page_list, pinned, 0); goto umem_release; } } + memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, + sizeof(umem->sgt_append.sgt)); if (access & IB_ACCESS_RELAXED_ORDERING) dma_attr |= DMA_ATTR_WEAK_ORDERING; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 5c700f2a0d18..266754a55327 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -39,6 +39,12 @@ struct sg_table { unsigned int orig_nents; /* original size of list */ }; +struct sg_append_table { + struct sg_table sgt; /* The scatter list table */ + struct scatterlist *prv; /* last populated sge in the table */ + unsigned int total_nents; /* Total entries in the table */ +}; + /* * Notes on SG table design. * @@ -280,16 +286,17 @@ typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); typedef void (sg_free_fn)(struct scatterlist *, unsigned int); void __sg_free_table(struct sg_table *, unsigned int, unsigned int, - sg_free_fn *); + sg_free_fn *, unsigned int); void sg_free_table(struct sg_table *); +void sg_free_append_table(struct sg_append_table *sgt); int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); -struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, - struct page **pages, unsigned int n_pages, unsigned int offset, - unsigned long size, unsigned int max_segment, - struct scatterlist *prv, unsigned int left_pages, - gfp_t gfp_mask); +int sg_alloc_append_table_from_pages(struct sg_append_table *sgt, + struct page **pages, unsigned int n_pages, + unsigned int offset, unsigned long size, + unsigned int max_segment, + unsigned int left_pages, gfp_t gfp_mask); int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 676c57f5ca80..33cb23b2ee3c 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -26,6 +26,7 @@ struct ib_umem { u32 is_odp : 1; u32 is_dmabuf : 1; struct work_struct work; + struct sg_append_table sgt_append; struct sg_table sg_head; int nmap; unsigned int sg_nents; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 611c63d4a958..f4b1ff78ab2d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -182,6 +182,7 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * @nents_first_chunk: Number of entries int the (preallocated) first * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function + * @num_ents: Number of entries in the table * * Description: * Free an sg table previously allocated and setup with @@ -190,7 +191,8 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, - unsigned int nents_first_chunk, sg_free_fn *free_fn) + unsigned int nents_first_chunk, sg_free_fn *free_fn, + unsigned int num_ents) { struct scatterlist *sgl, *next; unsigned curr_max_ents = nents_first_chunk ?: max_ents; @@ -199,8 +201,8 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, return; sgl = table->sgl; - while (table->orig_nents) { - unsigned int alloc_size = table->orig_nents; + while (num_ents) { + unsigned int alloc_size = num_ents; unsigned int sg_size; /* @@ -218,7 +220,7 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, next = NULL; } - table->orig_nents -= sg_size; + num_ents -= sg_size; if (nents_first_chunk) nents_first_chunk = 0; else @@ -231,6 +233,19 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, } EXPORT_SYMBOL(__sg_free_table); +/** + * sg_free_append_table - Free a previously allocated append sg table. + * @table: The mapped sg append table header + * + **/ +void sg_free_append_table(struct sg_append_table *table) +{ + __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->total_nents); +} +EXPORT_SYMBOL(sg_free_append_table); + + /** * sg_free_table - Free a previously allocated sg table * @table: The mapped sg table header @@ -238,7 +253,8 @@ EXPORT_SYMBOL(__sg_free_table); **/ void sg_free_table(struct sg_table *table) { - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree); + __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree, + table->orig_nents); } EXPORT_SYMBOL(sg_free_table); @@ -359,13 +375,12 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree); - + sg_free_table(table); return ret; } EXPORT_SYMBOL(sg_alloc_table); -static struct scatterlist *get_next_sg(struct sg_table *table, +static struct scatterlist *get_next_sg(struct sg_append_table *table, struct scatterlist *cur, unsigned long needed_sges, gfp_t gfp_mask) @@ -386,54 +401,52 @@ static struct scatterlist *get_next_sg(struct sg_table *table, return ERR_PTR(-ENOMEM); sg_init_table(new_sg, alloc_size); if (cur) { + table->total_nents += alloc_size - 1; __sg_chain(next_sg, new_sg); - table->orig_nents += alloc_size - 1; } else { - table->sgl = new_sg; - table->orig_nents = alloc_size; - table->nents = 0; + table->sgt.sgl = new_sg; + table->total_nents = alloc_size; } return new_sg; } /** - * sg_alloc_append_table_from_pages - Allocate and initialize an sg table from - * an array of pages - * @sgt: The sg table header to use - * @pages: Pointer to an array of page pointers - * @n_pages: Number of pages in the pages array + * sg_alloc_append_table_from_pages - Allocate and initialize an append sg + * table from an array of pages + * @sgt_append: The sg append table to use + * @pages: Pointer to an array of page pointers + * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes - * @prv: Last populated sge in sgt * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * * Description: - * If @prv is NULL, allocate and initialize an sg table from a list of pages, - * else reuse the scatterlist passed in at @prv. - * Contiguous ranges of the pages are squashed into a single scatterlist - * entry up to the maximum size specified in @max_segment. A user may - * provide an offset at a start and a size of valid data in a buffer - * specified by the page array. + * In the first call it allocate and initialize an sg table from a list of + * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of + * the pages are squashed into a single scatterlist entry up to the maximum + * size specified in @max_segment. A user may provide an offset at a start + * and a size of valid data in a buffer specified by the page array. The + * returned sg table is released by sg_free_append_table * * Returns: - * Last SGE in sgt on success, PTR_ERR on otherwise. - * The allocation in @sgt must be released by sg_free_table. + * 0 on success, negative error on failure * * Notes: * If this function returns non-0 (eg failure), the caller must call - * sg_free_table() to cleanup any leftover allocations. + * sg_free_append_table() to cleanup any leftover allocations. + * + * In the fist call, sgt_append must by initialized. */ -struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, +int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, - struct scatterlist *prv, unsigned int left_pages, - gfp_t gfp_mask) + unsigned int left_pages, gfp_t gfp_mask) { unsigned int chunks, cur_page, seg_len, i, prv_len = 0; unsigned int added_nents = 0; - struct scatterlist *s = prv; + struct scatterlist *s = sgt_append->prv; /* * The algorithm below requires max_segment to be aligned to PAGE_SIZE @@ -441,25 +454,26 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, */ max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); if (WARN_ON(max_segment < PAGE_SIZE)) - return ERR_PTR(-EINVAL); + return -EINVAL; - if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv) - return ERR_PTR(-EOPNOTSUPP); + if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv) + return -EOPNOTSUPP; - if (prv) { - unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE + - prv->offset + prv->length) / - PAGE_SIZE; + if (sgt_append->prv) { + unsigned long paddr = + (page_to_pfn(sg_page(sgt_append->prv)) * PAGE_SIZE + + sgt_append->prv->offset + sgt_append->prv->length) / + PAGE_SIZE; if (WARN_ON(offset)) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Merge contiguous pages into the last SG */ - prv_len = prv->length; + prv_len = sgt_append->prv->length; while (n_pages && page_to_pfn(pages[0]) == paddr) { - if (prv->length + PAGE_SIZE > max_segment) + if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; - prv->length += PAGE_SIZE; + sgt_append->prv->length += PAGE_SIZE; paddr++; pages++; n_pages--; @@ -496,15 +510,16 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, } /* Pass how many chunks might be left */ - s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask); + s = get_next_sg(sgt_append, s, chunks - i + left_pages, + gfp_mask); if (IS_ERR(s)) { /* * Adjust entry length to be as before function was * called. */ - if (prv) - prv->length = prv_len; - return s; + if (sgt_append->prv) + sgt_append->prv->length = prv_len; + return PTR_ERR(s); } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], @@ -514,11 +529,13 @@ struct scatterlist *sg_alloc_append_table_from_pages(struct sg_table *sgt, offset = 0; cur_page = j; } - sgt->nents += added_nents; + sgt_append->sgt.nents += added_nents; + sgt_append->sgt.orig_nents = sgt_append->sgt.nents; + sgt_append->prv = s; out: if (!left_pages) sg_mark_end(s); - return s; + return 0; } EXPORT_SYMBOL(sg_alloc_append_table_from_pages); @@ -550,8 +567,18 @@ int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned long size, unsigned int max_segment, gfp_t gfp_mask) { - return PTR_ERR_OR_ZERO(sg_alloc_append_table_from_pages(sgt, pages, - n_pages, offset, size, max_segment, NULL, 0, gfp_mask)); + struct sg_append_table append = {}; + int err; + + err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset, + size, max_segment, 0, gfp_mask); + if (err) { + sg_free_append_table(&append); + return err; + } + memcpy(sgt, &append.sgt, sizeof(*sgt)); + WARN_ON(append.total_nents != sgt->orig_nents); + return 0; } EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); diff --git a/lib/sg_pool.c b/lib/sg_pool.c index db29e5c1f790..a0b1a52cd6f7 100644 --- a/lib/sg_pool.c +++ b/lib/sg_pool.c @@ -90,7 +90,8 @@ void sg_free_table_chained(struct sg_table *table, if (nents_first_chunk == 1) nents_first_chunk = 0; - __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free); + __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free, + table->orig_nents); } EXPORT_SYMBOL_GPL(sg_free_table_chained); diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index c2ff9179c2cc..08465a701cd5 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -85,43 +85,46 @@ int main(void) for (i = 0, test = tests; test->expected_segments; test++, i++) { int left_pages = test->pfn_app ? test->num_pages : 0; + struct sg_append_table append = {}; struct page *pages[MAX_PAGES]; - struct sg_table st; - struct scatterlist *sg = NULL; int ret; set_pages(pages, test->pfn, test->num_pages); - if (test->pfn_app) { - sg = sg_alloc_append_table_from_pages( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, NULL, left_pages, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); - } else { + if (test->pfn_app) + ret = sg_alloc_append_table_from_pages( + &append, pages, test->num_pages, 0, test->size, + test->max_seg, left_pages, GFP_KERNEL); + else ret = sg_alloc_table_from_pages_segment( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, GFP_KERNEL); - assert(ret == test->alloc_ret); - } + &append.sgt, pages, test->num_pages, 0, + test->size, test->max_seg, GFP_KERNEL); + + assert(ret == test->alloc_ret); if (test->alloc_ret) continue; if (test->pfn_app) { set_pages(pages, test->pfn_app, test->num_pages); - sg = sg_alloc_append_table_from_pages( - &st, pages, test->num_pages, 0, test->size, - test->max_seg, sg, 0, GFP_KERNEL); + ret = sg_alloc_append_table_from_pages( + &append, pages, test->num_pages, 0, test->size, + test->max_seg, 0, GFP_KERNEL); - assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret); + assert(ret == test->alloc_ret); } - VALIDATE(st.nents == test->expected_segments, &st, test); + VALIDATE(append.sgt.nents == test->expected_segments, + &append.sgt, test); if (!test->pfn_app) - VALIDATE(st.orig_nents == test->expected_segments, &st, - test); + VALIDATE(append.sgt.orig_nents == + test->expected_segments, + &append.sgt, test); - sg_free_table(&st); + if (test->pfn_app) + sg_free_append_table(&append); + else + sg_free_table(&append.sgt); } assert(i == (sizeof(tests) / sizeof(tests[0])) - 1); From 79fbd3e1241cea83dded06db2b8bcd5893d877d7 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 24 Aug 2021 17:25:31 +0300 Subject: [PATCH 1469/1469] RDMA: Use the sg_table directly and remove the opencoded version from umem This allows using the normal sg_table APIs and makes all the code cleaner. Remove sgt, nents and nmapd from ib_umem. Link: https://lore.kernel.org/r/20210824142531.3877007-4-maorg@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem.c | 32 +++++++++---------------- drivers/infiniband/core/umem_dmabuf.c | 5 ++-- drivers/infiniband/hw/hns/hns_roce_db.c | 4 ++-- drivers/infiniband/hw/irdma/verbs.c | 2 +- drivers/infiniband/hw/mlx4/doorbell.c | 3 ++- drivers/infiniband/hw/mlx4/mr.c | 4 ++-- drivers/infiniband/hw/mlx5/doorbell.c | 3 ++- drivers/infiniband/hw/mlx5/mr.c | 3 ++- drivers/infiniband/hw/qedr/verbs.c | 2 +- drivers/infiniband/sw/rdmavt/mr.c | 2 +- drivers/infiniband/sw/rxe/rxe_mr.c | 2 +- include/rdma/ib_umem.h | 12 ++++------ include/rdma/ib_verbs.h | 28 ++++++++++++++++++++++ 13 files changed, 60 insertions(+), 42 deletions(-) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 42481e7a72e8..86d479772fbc 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -51,11 +51,11 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d struct scatterlist *sg; unsigned int i; - if (umem->nmap > 0) - ib_dma_unmap_sg(dev, umem->sg_head.sgl, umem->sg_nents, - DMA_BIDIRECTIONAL); + if (dirty) + ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt, + DMA_BIDIRECTIONAL, 0); - for_each_sg(umem->sg_head.sgl, sg, umem->sg_nents, i) + for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) unpin_user_page_range_dirty_lock(sg_page(sg), DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty); @@ -111,7 +111,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, /* offset into first SGL */ pgoff = umem->address & ~PAGE_MASK; - for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { /* Walk SGL and reduce max page size if VA/PA bits differ * for any address. */ @@ -121,7 +121,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, * the maximum possible page size as the low bits of the iova * must be zero when starting the next chunk. */ - if (i != (umem->nmap - 1)) + if (i != (umem->sgt_append.sgt.nents - 1)) mask |= va; pgoff = 0; } @@ -231,30 +231,19 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, &umem->sgt_append, page_list, pinned, 0, pinned << PAGE_SHIFT, ib_dma_max_seg_size(device), npages, GFP_KERNEL); - umem->sg_nents = umem->sgt_append.sgt.nents; if (ret) { - memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, - sizeof(umem->sgt_append.sgt)); unpin_user_pages_dirty_lock(page_list, pinned, 0); goto umem_release; } } - memcpy(&umem->sg_head.sgl, &umem->sgt_append.sgt, - sizeof(umem->sgt_append.sgt)); if (access & IB_ACCESS_RELAXED_ORDERING) dma_attr |= DMA_ATTR_WEAK_ORDERING; - umem->nmap = - ib_dma_map_sg_attrs(device, umem->sg_head.sgl, umem->sg_nents, - DMA_BIDIRECTIONAL, dma_attr); - - if (!umem->nmap) { - ret = -ENOMEM; + ret = ib_dma_map_sgtable_attrs(device, &umem->sgt_append.sgt, + DMA_BIDIRECTIONAL, dma_attr); + if (ret) goto umem_release; - } - - ret = 0; goto out; umem_release: @@ -314,7 +303,8 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, return -EINVAL; } - ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->sg_nents, dst, length, + ret = sg_pcopy_to_buffer(umem->sgt_append.sgt.sgl, + umem->sgt_append.sgt.orig_nents, dst, length, offset + ib_umem_offset(umem)); if (ret < 0) diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index c6e875619fac..e824baf4640d 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -55,9 +55,8 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) cur += sg_dma_len(sg); } - umem_dmabuf->umem.sg_head.sgl = umem_dmabuf->first_sg; - umem_dmabuf->umem.sg_head.nents = nmap; - umem_dmabuf->umem.nmap = nmap; + umem_dmabuf->umem.sgt_append.sgt.sgl = umem_dmabuf->first_sg; + umem_dmabuf->umem.sgt_append.sgt.nents = nmap; umem_dmabuf->sgt = sgt; wait_fence: diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c index d40ea3d87260..751470c7a2ce 100644 --- a/drivers/infiniband/hw/hns/hns_roce_db.c +++ b/drivers/infiniband/hw/hns/hns_roce_db.c @@ -42,8 +42,8 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, unsigned long virt, found: offset = virt - page_addr; - db->dma = sg_dma_address(page->umem->sg_head.sgl) + offset; - db->virt_addr = sg_virt(page->umem->sg_head.sgl) + offset; + db->dma = sg_dma_address(page->umem->sgt_append.sgt.sgl) + offset; + db->virt_addr = sg_virt(page->umem->sgt_append.sgt.sgl) + offset; db->u.user_page = page; refcount_inc(&page->refcount); diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 717147ed0519..e2114f2134bb 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2235,7 +2235,7 @@ static void irdma_copy_user_pgaddrs(struct irdma_mr *iwmr, u64 *pbl, pinfo = (level == PBLE_LEVEL_1) ? NULL : palloc->level2.leaf; if (iwmr->type == IRDMA_MEMREG_TYPE_QP) - iwpbl->qp_mr.sq_page = sg_page(region->sg_head.sgl); + iwpbl->qp_mr.sq_page = sg_page(region->sgt_append.sgt.sgl); rdma_umem_for_each_dma_block(region, &biter, iwmr->page_size) { *pbl = rdma_block_iter_dma_address(&biter); diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c index d41f03ccb0e1..9bbd695a9fd5 100644 --- a/drivers/infiniband/hw/mlx4/doorbell.c +++ b/drivers/infiniband/hw/mlx4/doorbell.c @@ -75,7 +75,8 @@ int mlx4_ib_db_map_user(struct ib_udata *udata, unsigned long virt, list_add(&page->list, &context->db_page_list); found: - db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK); + db->dma = sg_dma_address(page->umem->sgt_append.sgt.sgl) + + (virt & ~PAGE_MASK); db->u.user_page = page; ++page->refcnt; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 50becc0e4b62..04a67b481608 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -200,7 +200,7 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt, mtt_shift = mtt->page_shift; mtt_size = 1ULL << mtt_shift; - for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { if (cur_start_addr + len == sg_dma_address(sg)) { /* still the same block */ len += sg_dma_len(sg); @@ -273,7 +273,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, *num_of_mtts = ib_umem_num_dma_blocks(umem, PAGE_SIZE); - for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { /* * Initialization - save the first chunk start as the * current_block_start - block means contiguous pages. diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 9ca2e61807ec..6398e2f48579 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -78,7 +78,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt, list_add(&page->list, &context->db_page_list); found: - db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK); + db->dma = sg_dma_address(page->umem->sgt_append.sgt.sgl) + + (virt & ~PAGE_MASK); db->u.user_page = page; ++page->refcnt; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 3f1c5a4f158b..a520ac8ab68c 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1226,7 +1226,8 @@ int mlx5_ib_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags) orig_sg_length = sg.length; cur_mtt = mtt; - rdma_for_each_block (mr->umem->sg_head.sgl, &biter, mr->umem->nmap, + rdma_for_each_block (mr->umem->sgt_append.sgt.sgl, &biter, + mr->umem->sgt_append.sgt.nents, BIT(mr->page_shift)) { if (cur_mtt == (void *)mtt + sg.length) { dma_sync_single_for_device(ddev, sg.addr, sg.length, diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index fdc47ef7d861..f23d324bd5e1 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1481,7 +1481,7 @@ static int qedr_init_srq_user_params(struct ib_udata *udata, return PTR_ERR(srq->prod_umem); } - sg = srq->prod_umem->sg_head.sgl; + sg = srq->prod_umem->sgt_append.sgt.sgl; srq->hw_srq.phy_prod_pair_addr = sg_dma_address(sg); return 0; diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 34b7af6ab9c2..dfb99a56d952 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -410,7 +410,7 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mr->mr.page_shift = PAGE_SHIFT; m = 0; n = 0; - for_each_sg_page (umem->sg_head.sgl, &sg_iter, umem->nmap, 0) { + for_each_sgtable_page (&umem->sgt_append.sgt, &sg_iter, 0) { void *vaddr; vaddr = page_address(sg_page_iter_page(&sg_iter)); diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index be4bcb420fab..b5fcb14350c7 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -143,7 +143,7 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, if (length > 0) { buf = map[0]->buf; - for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->nmap, 0) { + for_each_sgtable_page (&umem->sgt_append.sgt, &sg_iter, 0) { if (num_buf >= RXE_BUF_PER_MAP) { map++; buf = map[0]->buf; diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 33cb23b2ee3c..5ae9dff74dac 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -26,10 +26,7 @@ struct ib_umem { u32 is_odp : 1; u32 is_dmabuf : 1; struct work_struct work; - struct sg_append_table sgt_append; - struct sg_table sg_head; - int nmap; - unsigned int sg_nents; + struct sg_append_table sgt_append; }; struct ib_umem_dmabuf { @@ -57,7 +54,7 @@ static inline int ib_umem_offset(struct ib_umem *umem) static inline unsigned long ib_umem_dma_offset(struct ib_umem *umem, unsigned long pgsz) { - return (sg_dma_address(umem->sg_head.sgl) + ib_umem_offset(umem)) & + return (sg_dma_address(umem->sgt_append.sgt.sgl) + ib_umem_offset(umem)) & (pgsz - 1); } @@ -78,7 +75,8 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, struct ib_umem *umem, unsigned long pgsz) { - __rdma_block_iter_start(biter, umem->sg_head.sgl, umem->nmap, pgsz); + __rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl, + umem->sgt_append.sgt.nents, pgsz); } /** @@ -129,7 +127,7 @@ static inline unsigned long ib_umem_find_best_pgoff(struct ib_umem *umem, unsigned long pgsz_bitmap, u64 pgoff_bitmask) { - struct scatterlist *sg = umem->sg_head.sgl; + struct scatterlist *sg = umem->sgt_append.sgt.sgl; dma_addr_t dma_addr; dma_addr = sg_dma_address(sg) + (umem->address & ~PAGE_MASK); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 371df1c80aeb..2dba30849731 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4057,6 +4057,34 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, dma_attrs); } +/** + * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses + * @dev: The device for which the DMA addresses are to be created + * @sg: The sg_table object describing the buffer + * @direction: The direction of the DMA + * @attrs: Optional DMA attributes for the map operation + */ +static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, + struct sg_table *sgt, + enum dma_data_direction direction, + unsigned long dma_attrs) +{ + if (ib_uses_virt_dma(dev)) { + ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); + return 0; + } + return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); +} + +static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, + struct sg_table *sgt, + enum dma_data_direction direction, + unsigned long dma_attrs) +{ + if (!ib_uses_virt_dma(dev)) + dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); +} + /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created