From 22247efd822e6d263f3c8bd327f3f769aea9b1d9 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 14 May 2021 17:27:04 -0700 Subject: [PATCH 01/13] mm/hugetlb: fix F_SEAL_FUTURE_WRITE Patch series "mm/hugetlb: Fix issues on file sealing and fork", v2. Hugh reported issue with F_SEAL_FUTURE_WRITE not applied correctly to hugetlbfs, which I can easily verify using the memfd_test program, which seems that the program is hardly run with hugetlbfs pages (as by default shmem). Meanwhile I found another probably even more severe issue on that hugetlb fork won't wr-protect child cow pages, so child can potentially write to parent private pages. Patch 2 addresses that. After this series applied, "memfd_test hugetlbfs" should start to pass. This patch (of 2): F_SEAL_FUTURE_WRITE is missing for hugetlb starting from the first day. There is a test program for that and it fails constantly. $ ./memfd_test hugetlbfs memfd-hugetlb: CREATE memfd-hugetlb: BASIC memfd-hugetlb: SEAL-WRITE memfd-hugetlb: SEAL-FUTURE-WRITE mmap() didn't fail as expected Aborted (core dumped) I think it's probably because no one is really running the hugetlbfs test. Fix it by checking FUTURE_WRITE also in hugetlbfs_file_mmap() as what we do in shmem_mmap(). Generalize a helper for that. Link: https://lkml.kernel.org/r/20210503234356.9097-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20210503234356.9097-2-peterx@redhat.com Fixes: ab3948f58ff84 ("mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd") Signed-off-by: Peter Xu Reported-by: Hugh Dickins Reviewed-by: Mike Kravetz Cc: Joel Fernandes (Google) Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 5 +++++ include/linux/mm.h | 32 ++++++++++++++++++++++++++++++++ mm/shmem.c | 22 ++++------------------ 3 files changed, 41 insertions(+), 18 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2a42335e8fd..9d9e0097c1d3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -131,6 +131,7 @@ static void huge_pagevec_release(struct pagevec *pvec) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -146,6 +147,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can diff --git a/include/linux/mm.h b/include/linux/mm.h index 322ec61d0da7..c274f75efcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3216,5 +3216,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/shmem.c b/mm/shmem.c index a08cedefbfaa..eb131b9fb190 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2258,25 +2258,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; - if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; /* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED; From 84894e1c42e9f25c17f2888e0c0e1505cb727538 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 14 May 2021 17:27:07 -0700 Subject: [PATCH 02/13] mm/hugetlb: fix cow where page writtable in child When rework early cow of pinned hugetlb pages, we moved huge_ptep_get() upper but overlooked a side effect that the huge_ptep_get() will fetch the pte after wr-protection. After moving it upwards, we need explicit wr-protect of child pte or we will keep the write bit set in the child process, which could cause data corrution where the child can write to the original page directly. This issue can also be exposed by "memfd_test hugetlbfs" kselftest. Link: https://lkml.kernel.org/r/20210503234356.9097-3-peterx@redhat.com Fixes: 4eae4efa2c299 ("hugetlb: do early cow when page pinned on src mm") Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Hugh Dickins Cc: Joel Fernandes (Google) Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3db405dea3dc..95918f410c0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4056,6 +4056,7 @@ again: * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_pte_wrprotect(entry); } page_dup_rmap(ptepage, true); From afe0c26d1968fe3bbef6a45df945bfeff774ca75 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 14 May 2021 17:27:10 -0700 Subject: [PATCH 03/13] mm, slub: move slub_debug static key enabling outside slab_mutex Paul E. McKenney reported [1] that commit 1f0723a4c0df ("mm, slub: enable slub_debug static key when creating cache with explicit debug flags") results in the lockdep complaint: ====================================================== WARNING: possible circular locking dependency detected 5.12.0+ #15 Not tainted ------------------------------------------------------ rcu_torture_sta/109 is trying to acquire lock: ffffffff96063cd0 (cpu_hotplug_lock){++++}-{0:0}, at: static_key_enable+0x9/0x20 but task is already holding lock: ffffffff96173c28 (slab_mutex){+.+.}-{3:3}, at: kmem_cache_create_usercopy+0x2d/0x250 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (slab_mutex){+.+.}-{3:3}: lock_acquire+0xb9/0x3a0 __mutex_lock+0x8d/0x920 slub_cpu_dead+0x15/0xf0 cpuhp_invoke_callback+0x17a/0x7c0 cpuhp_invoke_callback_range+0x3b/0x80 _cpu_down+0xdf/0x2a0 cpu_down+0x2c/0x50 device_offline+0x82/0xb0 remove_cpu+0x1a/0x30 torture_offline+0x80/0x140 torture_onoff+0x147/0x260 kthread+0x10a/0x140 ret_from_fork+0x22/0x30 -> #0 (cpu_hotplug_lock){++++}-{0:0}: check_prev_add+0x8f/0xbf0 __lock_acquire+0x13f0/0x1d80 lock_acquire+0xb9/0x3a0 cpus_read_lock+0x21/0xa0 static_key_enable+0x9/0x20 __kmem_cache_create+0x38d/0x430 kmem_cache_create_usercopy+0x146/0x250 kmem_cache_create+0xd/0x10 rcu_torture_stats+0x79/0x280 kthread+0x10a/0x140 ret_from_fork+0x22/0x30 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(slab_mutex); lock(cpu_hotplug_lock); lock(slab_mutex); lock(cpu_hotplug_lock); *** DEADLOCK *** 1 lock held by rcu_torture_sta/109: #0: ffffffff96173c28 (slab_mutex){+.+.}-{3:3}, at: kmem_cache_create_usercopy+0x2d/0x250 stack backtrace: CPU: 3 PID: 109 Comm: rcu_torture_sta Not tainted 5.12.0+ #15 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: dump_stack+0x6d/0x89 check_noncircular+0xfe/0x110 ? lock_is_held_type+0x98/0x110 check_prev_add+0x8f/0xbf0 __lock_acquire+0x13f0/0x1d80 lock_acquire+0xb9/0x3a0 ? static_key_enable+0x9/0x20 ? mark_held_locks+0x49/0x70 cpus_read_lock+0x21/0xa0 ? static_key_enable+0x9/0x20 static_key_enable+0x9/0x20 __kmem_cache_create+0x38d/0x430 kmem_cache_create_usercopy+0x146/0x250 ? rcu_torture_stats_print+0xd0/0xd0 kmem_cache_create+0xd/0x10 rcu_torture_stats+0x79/0x280 ? rcu_torture_stats_print+0xd0/0xd0 kthread+0x10a/0x140 ? kthread_park+0x80/0x80 ret_from_fork+0x22/0x30 This is because there's one order of locking from the hotplug callbacks: lock(cpu_hotplug_lock); // from hotplug machinery itself lock(slab_mutex); // in e.g. slab_mem_going_offline_callback() And commit 1f0723a4c0df made the reverse sequence possible: lock(slab_mutex); // in kmem_cache_create_usercopy() lock(cpu_hotplug_lock); // kmem_cache_open() -> static_key_enable() The simplest fix is to move static_key_enable() to a place before slab_mutex is taken. That means kmem_cache_create_usercopy() in mm/slab_common.c which is not ideal for SLUB-specific code, but the #ifdef CONFIG_SLUB_DEBUG makes it at least self-contained and obvious. [1] https://lore.kernel.org/lkml/20210502171827.GA3670492@paulmck-ThinkPad-P17-Gen-1/ Link: https://lkml.kernel.org/r/20210504120019.26791-1-vbabka@suse.cz Fixes: 1f0723a4c0df ("mm, slub: enable slub_debug static key when creating cache with explicit debug flags") Signed-off-by: Vlastimil Babka Reported-by: Paul E. McKenney Tested-by: Paul E. McKenney Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab_common.c | 10 ++++++++++ mm/slub.c | 9 --------- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index f8833d3e5d47..a4a571428c51 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -318,6 +318,16 @@ kmem_cache_create_usercopy(const char *name, const char *cache_name; int err; +#ifdef CONFIG_SLUB_DEBUG + /* + * If no slub_debug was enabled globally, the static key is not yet + * enabled by setup_slub_debug(). Enable it if the cache is being + * created with any of the debugging flags passed explicitly. + */ + if (flags & SLAB_DEBUG_FLAGS) + static_branch_enable(&slub_debug_enabled); +#endif + mutex_lock(&slab_mutex); err = kmem_cache_sanity_check(name, size); diff --git a/mm/slub.c b/mm/slub.c index feda53ae62ba..438fa8d4c970 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3828,15 +3828,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - /* - * If no slub_debug was enabled globally, the static key is not yet - * enabled by setup_slub_debug(). Enable it if the cache is being - * created with any of the debugging flags passed explicitly. - */ - if (flags & SLAB_DEBUG_FLAGS) - static_branch_enable(&slub_debug_enabled); -#endif s->flags = kmem_cache_flags(s->size, flags, s->name); #ifdef CONFIG_SLAB_FREELIST_HARDENED s->random = get_random_long(); From eb1f065f90cdcdcc704e9e2dc678931317c69a99 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Fri, 14 May 2021 17:27:13 -0700 Subject: [PATCH 04/13] kernel/resource: fix return code check in __request_free_mem_region Splitting an earlier version of a patch that allowed calling __request_region() while holding the resource lock into a series of patches required changing the return code for the newly introduced __request_region_locked(). Unfortunately this change was not carried through to a subsequent commit 56fd94919b8b ("kernel/resource: fix locking in request_free_mem_region") in the series. This resulted in a use-after-free due to freeing the struct resource without properly releasing it. Fix this by correcting the return code check so that the struct is not freed if the request to add it was successful. Link: https://lkml.kernel.org/r/20210512073528.22334-1-apopple@nvidia.com Fixes: 56fd94919b8b ("kernel/resource: fix locking in request_free_mem_region") Signed-off-by: Alistair Popple Reported-by: kernel test robot Reviewed-by: David Hildenbrand Cc: Balbir Singh Cc: Dan Williams Cc: Daniel Vetter Cc: Greg Kroah-Hartman Cc: Jerome Glisse Cc: John Hubbard Cc: Muchun Song Cc: Oliver Sang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/resource.c b/kernel/resource.c index 028a5ab18818..ca9f5198a01f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1805,7 +1805,7 @@ static struct resource *__request_free_mem_region(struct device *dev, REGION_DISJOINT) continue; - if (!__request_region_locked(res, &iomem_resource, addr, size, + if (__request_region_locked(res, &iomem_resource, addr, size, name, 0)) break; From d6e621de1fceb3b098ebf435ef7ea91ec4838a1a Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Fri, 14 May 2021 17:27:16 -0700 Subject: [PATCH 05/13] squashfs: fix divide error in calculate_skip() Sysbot has reported a "divide error" which has been identified as being caused by a corrupted file_size value within the file inode. This value has been corrupted to a much larger value than expected. Calculate_skip() is passed i_size_read(inode) >> msblk->block_log. Due to the file_size value corruption this overflows the int argument/variable in that function, leading to the divide error. This patch changes the function to use u64. This will accommodate any unexpectedly large values due to corruption. The value returned from calculate_skip() is clamped to be never more than SQUASHFS_CACHED_BLKS - 1, or 7. So file_size corruption does not lead to an unexpectedly large return result here. Link: https://lkml.kernel.org/r/20210507152618.9447-1-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher Reported-by: Reported-by: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/squashfs/file.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 7b1128398976..89d492916dea 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -211,11 +211,11 @@ failure: * If the skip factor is limited in this way then the file will use multiple * slots. */ -static inline int calculate_skip(int blocks) +static inline int calculate_skip(u64 blocks) { - int skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) * SQUASHFS_META_INDEXES); - return min(SQUASHFS_CACHED_BLKS - 1, skip + 1); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); } From 7ed9d238c7dbb1fdb63ad96a6184985151b0171c Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Fri, 14 May 2021 17:27:19 -0700 Subject: [PATCH 06/13] userfaultfd: release page in error path to avoid BUG_ON Consider the following sequence of events: 1. Userspace issues a UFFD ioctl, which ends up calling into shmem_mfill_atomic_pte(). We successfully account the blocks, we shmem_alloc_page(), but then the copy_from_user() fails. We return -ENOENT. We don't release the page we allocated. 2. Our caller detects this error code, tries the copy_from_user() after dropping the mmap_lock, and retries, calling back into shmem_mfill_atomic_pte(). 3. Meanwhile, let's say another process filled up the tmpfs being used. 4. So shmem_mfill_atomic_pte() fails to account blocks this time, and immediately returns - without releasing the page. This triggers a BUG_ON in our caller, which asserts that the page should always be consumed, unless -ENOENT is returned. To fix this, detect if we have such a "dangling" page when accounting fails, and if so, release it before returning. Link: https://lkml.kernel.org/r/20210428230858.348400-1-axelrasmussen@google.com Fixes: cb658a453b93 ("userfaultfd: shmem: avoid leaking blocks and used blocks in UFFDIO_COPY") Signed-off-by: Axel Rasmussen Reported-by: Hugh Dickins Acked-by: Hugh Dickins Reviewed-by: Peter Xu Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/mm/shmem.c b/mm/shmem.c index eb131b9fb190..5d46611cba8d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2361,8 +2361,18 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pgoff_t offset, max_off; ret = -ENOMEM; - if (!shmem_inode_acct_block(inode, 1)) + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } goto out; + } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); From 628622904b8d229591134e44efd6608a7541eb89 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 14 May 2021 17:27:22 -0700 Subject: [PATCH 07/13] ksm: revert "use GET_KSM_PAGE_NOLOCK to get ksm page in remove_rmap_item_from_tree()" This reverts commit 3e96b6a2e9ad929a3230a22f4d64a74671a0720b. General Protection Fault in rmap_walk_ksm() under memory pressure: remove_rmap_item_from_tree() needs to take page lock, of course. Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2105092253500.1127@eggly.anvils Signed-off-by: Hugh Dickins Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/ksm.c b/mm/ksm.c index 6bbe314c5260..2f3aaeb34a42 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -776,11 +776,12 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); if (!page) goto out; hlist_del(&rmap_item->hlist); + unlock_page(page); put_page(page); if (!hlist_empty(&stable_node->hlist)) From 9ddb3c14afba8bc5950ed297f02d4ae05ff35cd1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 May 2021 17:27:24 -0700 Subject: [PATCH 08/13] mm: fix struct page layout on 32-bit systems 32-bit architectures which expect 8-byte alignment for 8-byte integers and need 64-bit DMA addresses (arm, mips, ppc) had their struct page inadvertently expanded in 2019. When the dma_addr_t was added, it forced the alignment of the union to 8 bytes, which inserted a 4 byte gap between 'flags' and the union. Fix this by storing the dma_addr_t in one or two adjacent unsigned longs. This restores the alignment to that of an unsigned long. We always store the low bits in the first word to prevent the PageTail bit from being inadvertently set on a big endian platform. If that happened, get_user_pages_fast() racing against a page which was freed and reallocated to the page_pool could dereference a bogus compound_head(), which would be hard to trace back to this cause. Link: https://lkml.kernel.org/r/20210510153211.1504886-1-willy@infradead.org Fixes: c25fff7171be ("mm: add dma_addr_t to struct page") Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Ilias Apalodimas Acked-by: Jesper Dangaard Brouer Acked-by: Vlastimil Babka Tested-by: Matteo Croce Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 ++-- include/net/page_pool.h | 12 +++++++++++- net/core/page_pool.c | 12 +++++++----- 3 files changed, 20 insertions(+), 8 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..5aacc1c10a45 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -97,10 +97,10 @@ struct page { }; struct { /* page_pool used by netstack */ /** - * @dma_addr: might require a 64-bit value even on + * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ - dma_addr_t dma_addr; + unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 6d517a37c18b..b4b6de909c93 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr[0]; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + return ret; +} + +static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + page->dma_addr[0] = addr; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + page->dma_addr[1] = upper_32_bits(addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9ec1aa9640ad..3c4c4c7a0402 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma_addr = page_pool_get_dma_addr(page); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma_addr, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (dma_mapping_error(pool->p.dev, dma)) return false; - page->dma_addr = dma; + page_pool_set_dma_addr(page, dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_get_dma_addr(page); - /* When page is unmapped, it cannot be returned our pool */ + /* When page is unmapped, it cannot be returned to our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); - page->dma_addr = 0; + page_pool_set_dma_addr(page, 0); skip_dma_unmap: /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. From f649dc0e0d7b509c75570ee403723660f5b72ec7 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 14 May 2021 17:27:27 -0700 Subject: [PATCH 09/13] kasan: fix unit tests with CONFIG_UBSAN_LOCAL_BOUNDS enabled These tests deliberately access these arrays out of bounds, which will cause the dynamic local bounds checks inserted by CONFIG_UBSAN_LOCAL_BOUNDS to fail and panic the kernel. To avoid this problem, access the arrays via volatile pointers, which will prevent the compiler from being able to determine the array bounds. These accesses use volatile pointers to char (char *volatile) rather than the more conventional pointers to volatile char (volatile char *) because we want to prevent the compiler from making inferences about the pointer itself (i.e. its array bounds), not the data that it refers to. Link: https://lkml.kernel.org/r/20210507025915.1464056-1-pcc@google.com Link: https://linux-review.googlesource.com/id/I90b1713fbfa1bf68ff895aef099ea77b98a7c3b9 Signed-off-by: Peter Collingbourne Tested-by: Alexander Potapenko Reviewed-by: Andrey Konovalov Cc: Peter Collingbourne Cc: George Popescu Cc: Elena Petrova Cc: Evgenii Stepanov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/lib/test_kasan.c b/lib/test_kasan.c index dc05cfc2d12f..cacbbbdef768 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -654,8 +654,20 @@ static char global_array[10]; static void kasan_global_oob(struct kunit *test) { - volatile int i = 3; - char *p = &global_array[ARRAY_SIZE(global_array) + i]; + /* + * Deliberate out-of-bounds access. To prevent CONFIG_UBSAN_LOCAL_BOUNDS + * from failing here and panicing the kernel, access the array via a + * volatile pointer, which will prevent the compiler from being able to + * determine the array bounds. + * + * This access uses a volatile pointer to char (char *volatile) rather + * than the more conventional pointer to volatile char (volatile char *) + * because we want to prevent the compiler from making inferences about + * the pointer itself (i.e. its array bounds), not the data that it + * refers to. + */ + char *volatile array = global_array; + char *p = &array[ARRAY_SIZE(global_array) + 3]; /* Only generic mode instruments globals. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -703,8 +715,9 @@ static void ksize_uaf(struct kunit *test) static void kasan_stack_oob(struct kunit *test) { char stack_array[10]; - volatile int i = OOB_TAG_OFF; - char *p = &stack_array[ARRAY_SIZE(stack_array) + i]; + /* See comment in kasan_global_oob. */ + char *volatile array = stack_array; + char *p = &array[ARRAY_SIZE(stack_array) + OOB_TAG_OFF]; KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK); @@ -715,7 +728,9 @@ static void kasan_alloca_oob_left(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array - 1; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array - 1; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -728,7 +743,9 @@ static void kasan_alloca_oob_right(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array + i; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array + i; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); From 076171a67789ad0107de44c2964f2e46a7d0d7b8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 May 2021 17:27:30 -0700 Subject: [PATCH 10/13] mm/filemap: fix readahead return types A readahead request will not allocate more memory than can be represented by a size_t, even on systems that have HIGHMEM available. Change the length functions from returning an loff_t to a size_t. Link: https://lkml.kernel.org/r/20210510201201.1558972-1-willy@infradead.org Fixes: 32c0a6bcaa1f57 ("btrfs: add and use readahead_batch_length") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Reported-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/iomap/buffered-io.c | 4 ++-- include/linux/pagemap.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f2cd2034a87b..9023717c5188 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -394,7 +394,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) { struct inode *inode = rac->mapping->host; loff_t pos = readahead_pos(rac); - loff_t length = readahead_length(rac); + size_t length = readahead_length(rac); struct iomap_readpage_ctx ctx = { .rac = rac, }; @@ -402,7 +402,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) trace_iomap_readahead(inode, readahead_count(rac)); while (length > 0) { - loff_t ret = iomap_apply(inode, pos, length, 0, ops, + ssize_t ret = iomap_apply(inode, pos, length, 0, ops, &ctx, iomap_readahead_actor); if (ret <= 0) { WARN_ON_ONCE(ret == 0); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a4bd41128bf3..e89df447fae3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -997,9 +997,9 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(struct readahead_control *rac) { - return (loff_t)rac->_nr_pages * PAGE_SIZE; + return rac->_nr_pages * PAGE_SIZE; } /** @@ -1024,7 +1024,7 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline loff_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } From c3187cf32216313fb316084efac4dab3a8459b1d Mon Sep 17 00:00:00 2001 From: Jouni Roivas Date: Fri, 14 May 2021 17:27:33 -0700 Subject: [PATCH 11/13] hfsplus: prevent corruption in shrinking truncate I believe there are some issues introduced by commit 31651c607151 ("hfsplus: avoid deadlock on file truncation") HFS+ has extent records which always contains 8 extents. In case the first extent record in catalog file gets full, new ones are allocated from extents overflow file. In case shrinking truncate happens to middle of an extent record which locates in extents overflow file, the logic in hfsplus_file_truncate() was changed so that call to hfs_brec_remove() is not guarded any more. Right action would be just freeing the extents that exceed the new size inside extent record by calling hfsplus_free_extents(), and then check if the whole extent record should be removed. However since the guard (blk_cnt > start) is now after the call to hfs_brec_remove(), this has unfortunate effect that the last matching extent record is removed unconditionally. To reproduce this issue, create a file which has at least 10 extents, and then perform shrinking truncate into middle of the last extent record, so that the number of remaining extents is not under or divisible by 8. This causes the last extent record (8 extents) to be removed totally instead of truncating into middle of it. Thus this causes corruption, and lost data. Fix for this is simply checking if the new truncated end is below the start of this extent record, making it safe to remove the full extent record. However call to hfs_brec_remove() can't be moved to it's previous place since we're dropping ->tree_lock and it can cause a race condition and the cached info being invalidated possibly corrupting the node data. Another issue is related to this one. When entering into the block (blk_cnt > start) we are not holding the ->tree_lock. We break out from the loop not holding the lock, but hfs_find_exit() does unlock it. Not sure if it's possible for someone else to take the lock under our feet, but it can cause hard to debug errors and premature unlocking. Even if there's no real risk of it, the locking should still always be kept in balance. Thus taking the lock now just before the check. Link: https://lkml.kernel.org/r/20210429165139.3082828-1-jouni.roivas@tuxera.com Fixes: 31651c607151f ("hfsplus: avoid deadlock on file truncation") Signed-off-by: Jouni Roivas Reviewed-by: Anton Altaparmakov Cc: Anatoly Trosinenko Cc: Viacheslav Dubeyko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfsplus/extents.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a930ddd15681..7054a542689f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -598,13 +598,15 @@ void hfsplus_file_truncate(struct inode *inode) res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; - hfs_brec_remove(&fd); - mutex_unlock(&fd.tree->tree_lock); start = hip->cached_start; + if (blk_cnt <= start) + hfs_brec_remove(&fd); + mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); + mutex_lock(&fd.tree->tree_lock); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; @@ -612,7 +614,6 @@ void hfsplus_file_truncate(struct inode *inode) alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); - mutex_lock(&fd.tree->tree_lock); } hfs_find_exit(&fd); From f4d3f25aced3b493e57fd4109e2bc86f0831b23e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 14 May 2021 17:27:36 -0700 Subject: [PATCH 12/13] docs: admin-guide: update description for kernel.modprobe sysctl When I added CONFIG_MODPROBE_PATH, I neglected to update Documentation/. It's still true that this defaults to /sbin/modprobe, but now via a level of indirection. So document that the kernel might have been built with something other than /sbin/modprobe as the initial value. Link: https://lkml.kernel.org/r/20210420125324.1246826-1-linux@rasmusvillemoes.dk Fixes: 17652f4240f7a ("modules: add CONFIG_MODPROBE_PATH") Signed-off-by: Rasmus Villemoes Cc: Jonathan Corbet Cc: Greg Kroah-Hartman Cc: Jessica Yu Cc: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/sysctl/kernel.rst | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 1d56a6b73a4e..7ca8df5451d4 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -483,10 +483,11 @@ modprobe ======== The full path to the usermode helper for autoloading kernel modules, -by default "/sbin/modprobe". This binary is executed when the kernel -requests a module. For example, if userspace passes an unknown -filesystem type to mount(), then the kernel will automatically request -the corresponding filesystem module by executing this usermode helper. +by default ``CONFIG_MODPROBE_PATH``, which in turn defaults to +"/sbin/modprobe". This binary is executed when the kernel requests a +module. For example, if userspace passes an unknown filesystem type +to mount(), then the kernel will automatically request the +corresponding filesystem module by executing this usermode helper. This usermode helper should insert the needed module into the kernel. This sysctl only affects module autoloading. It has no effect on the From 86d0c164272536c732853e19391de5159f860701 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 May 2021 17:27:39 -0700 Subject: [PATCH 13/13] mm/ioremap: fix iomap_max_page_shift iomap_max_page_shift is expected to contain a page shift, so it can't be a 'bool', has to be an 'unsigned int' And fix the default values: P4D_SHIFT is when huge iomap is allowed. However, on some architectures (eg: powerpc book3s/64), P4D_SHIFT is not a constant so it can't be used to initialise a static variable. So, initialise iomap_max_page_shift with a maximum shift supported by the architecture, it is gated by P4D_SHIFT in vmap_try_huge_p4d() anyway. Link: https://lkml.kernel.org/r/ad2d366015794a9f21320dcbdd0a8eb98979e9df.1620898113.git.christophe.leroy@csgroup.eu Fixes: bbc180a5adb0 ("mm: HUGE_VMAP arch support cleanup") Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ioremap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/ioremap.c b/mm/ioremap.c index d1dcc7e744ac..8ee0136f8cb0 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -16,16 +16,16 @@ #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT; +static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { - iomap_max_page_shift = P4D_SHIFT; + iomap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const bool iomap_max_page_shift = PAGE_SHIFT; +static const unsigned int iomap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ int ioremap_page_range(unsigned long addr,