IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
print_ht in rhashtable_test calls rht_dereference() with neither
RCU protection or the mutex. This triggers an RCU warning.
So take the mutex to silence the warning.
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull drm fixes from Dave Airlie:
"Just run of the mill fixes,
core:
- regression fix in device unplug
qxl:
- regression fix for might sleep in cursor handling
nouveau:
- regression fix in multi-screen cursor handling
amdgpu:
- switch off DC by default on Kaveri and older
- some minor fixes
i915:
- some GEM regression fixes
- doublescan mode fixes
sun4i:
- revert fix for a regression
sii8620 bridge:
- misc fixes"
* tag 'drm-fixes-2018-06-22' of git://anongit.freedesktop.org/drm/drm: (28 commits)
drm/bridge/sii8620: fix display of packed pixel modes in MHL2
drm/amdgpu: Make amdgpu_vram_mgr_bo_invisible_size always accurate
drm/amdgpu: Refactor amdgpu_vram_mgr_bo_invisible_size helper
drm/amdgpu: Update pin_size values before unpinning BO
drm/amdgpu:All UVD instances share one idle_work handle
drm/amdgpu: Don't default to DC support for Kaveri and older
drm/amdgpu: Use kvmalloc_array for allocating VRAM manager nodes array
drm/amd/pp: Fix uninitialized variable
drm/i915: Enable provoking vertex fix on Gen9 systems.
drm/i915: Fix context ban and hang accounting for client
drm/i915: Turn off g4x DP port in .post_disable()
drm/i915: Disallow interlaced modes on g4x DP outputs
drm/i915: Fix PIPESTAT irq ack on i965/g4x
drm/i915: Allow DBLSCAN user modes with eDP/LVDS/DSI
drm/i915/execlists: Avoid putting the error pointer
drm/i915: Apply batch location restrictions before pinning
drm/nouveau/kms/nv50-: cursors always use core channel vram ctxdma
Revert "drm/sun4i: Handle DRM_BUS_FLAG_PIXDATA_*EDGE"
drm/atmel-hlcdc: check stride values in the first plane
drm/bridge/sii8620: fix HDMI cable connection to dongle
...
One of my tests compiles the kernel with gcc 4.5.3, and I hit the
following build error:
include/linux/semaphore.h: In function 'sema_init':
include/linux/semaphore.h:35:17: error: unknown field 'val' specified in initializer
include/linux/semaphore.h:35:17: warning: missing braces around initializer
include/linux/semaphore.h:35:17: warning: (near initialization for '(anonymous).raw_lock.<anonymous>.val')
I bisected it down to:
625e88be1f ("locking/qspinlock: Merge 'struct __qspinlock' into 'struct qspinlock'")
... which makes qspinlock have an anonymous union, which makes initializing it special
for older compilers. By adding strategic brackets, it makes the build
happy again.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Fixes: 625e88be1f ("locking/qspinlock: Merge 'struct __qspinlock' into 'struct qspinlock'")
Link: http://lkml.kernel.org/r/20180621203526.172ab5c4@vmware.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The dst_cid and src_cid are 64 bits, therefore 64 bit accessors should be
used, and in fact in virtio_transport_common.c only 64 bit accessors are
used. Using 32 bit accessors for 64 bit values breaks big endian systems.
This patch fixes a wrong use of le32_to_cpu in virtio_transport_send_pkt.
Fixes: b911682318 ("VSOCK: add loopback to virtio_transport")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function cpdma_desc_pool_create is local to the source and does not
need to be in global scope, so make it static.
Cleans up sparse warning:
warning: symbol 'cpdma_desc_pool_create' was not declared. Should it
be static?
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ross Lagerwall says:
====================
xen-netfront: Fix issues with commit f599c64fdf
Fix a couple of issues with commit f599c64fdf ("xen-netfront: Fix race
between device setup and open").
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Update the features after calling register_netdev() otherwise the
device features are not set up correctly and it not possible to change
the MTU of the device. After this change, the features reported by
ethtool match the device's features before the commit which introduced
the issue and it is possible to change the device's MTU.
Fixes: f599c64fdf ("xen-netfront: Fix race between device setup and open")
Reported-by: Liam Shepherd <liam@dancer.es>
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If flower filter is created without the skip_sw flag, fl_mask_put()
can race with fl_classify() and we can destroy the mask rhashtable
while a lookup operation is accessing it.
BUG: unable to handle kernel paging request at 00000000000911d1
PGD 0 P4D 0
SMP PTI
CPU: 3 PID: 5582 Comm: vhost-5541 Not tainted 4.18.0-rc1.vanilla+ #1950
Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016
RIP: 0010:rht_bucket_nested+0x20/0x60
Code: 31 c8 c1 c1 18 29 c8 c3 66 90 8b 4f 04 ba 01 00 00 00 8b 07 48 8b bf 80 00 00 0
RSP: 0018:ffffafc5cfbb7a48 EFLAGS: 00010206
RAX: 0000000000001978 RBX: ffff9f12dff88a00 RCX: 00000000ffff9f12
RDX: 00000000000911d1 RSI: 0000000000000148 RDI: 0000000000000001
RBP: ffff9f12dff88a00 R08: 000000005f1cc119 R09: 00000000a715fae2
R10: ffffafc5cfbb7aa8 R11: ffff9f1cb4be804e R12: ffff9f1265e13000
R13: 0000000000000000 R14: ffffafc5cfbb7b48 R15: ffff9f12dff88b68
FS: 0000000000000000(0000) GS:ffff9f1d3f0c0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000911d1 CR3: 0000001575a94006 CR4: 00000000001626e0
Call Trace:
fl_lookup+0x134/0x140 [cls_flower]
fl_classify+0xf3/0x180 [cls_flower]
tcf_classify+0x78/0x150
__netif_receive_skb_core+0x69e/0xa50
netif_receive_skb_internal+0x42/0xf0
tun_get_user+0xdd5/0xfd0 [tun]
tun_sendmsg+0x52/0x70 [tun]
handle_tx+0x2b3/0x5f0 [vhost_net]
vhost_worker+0xab/0x100 [vhost]
kthread+0xf8/0x130
ret_from_fork+0x35/0x40
Modules linked in: act_mirred act_gact cls_flower vhost_net vhost tap sch_ingress
CR2: 00000000000911d1
Fix the above waiting for a RCU grace period before destroying the
rhashtable: we need to use tcf_queue_work(), as rhashtable_destroy()
must run in process context, as pointed out by Cong Wang.
v1 -> v2: use tcf_queue_work to run rhashtable_destroy().
Fixes: 05cd271fd6 ("cls_flower: Support multiple masks per priority")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull NFS client bugfixes from Trond Myklebust:
"Hightlights include:
- fix an rcu deadlock in nfs_delegation_find_inode()
- fix NFSv4 deadlocks due to not freeing the session slot in
layoutget
- don't send layoutreturn if the layout is already invalid
- prevent duplicate XID allocation
- flexfiles: Don't tie up all the rpciod threads in resends"
* tag 'nfs-for-4.18-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
pNFS/flexfiles: Process writeback resends from nfsiod context as well
pNFS/flexfiles: Don't tie up all the rpciod threads in resends
sunrpc: Prevent duplicate XID allocation
pNFS: Don't send layoutreturn if the layout is already invalid
pNFS: Always free the session slot on error in nfs4_layoutget_handle_exception
NFS: Fix an rcu deadlock in nfs_delegation_find_inode()
Pull pin control fixes from Linus Walleij:
"Some fallout in the pin control subsystem in the first week after the
merge window, some minor fixes so I'd like to get it to you ASAP.
- fix a serious kernel panic on the Mediatek driver with the external
interrupt controller.
- fix an uninitialized compiler warning in the owl (actions) driver.
- allocation failure in the pinctrl-single driver.
- pointer overwrite problem in the i.MX driver.
- fix a small compiler warning"
* tag 'pinctrl-v4.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
pinctrl: mt7622: fix a kernel panic when pio don't work as EINT controller
pinctrl: actions: Fix uninitialized error in owl_pin_config_set()
pinctrl: single: Add allocation failure checking of saved_vals
pinctrl: devicetree: Fix pctldev pointer overwrite
pinctrl: mediatek: remove redundant return value check of platform_get_resource()
Pull hwmon fixes from Guenter Roeck:
- fix a loop limit in nct6775 driver
- disable fan support for Dell XPS13 9333
* tag 'hwmon-for-linus-v4.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
hwmon: (nct6775) Fix loop limit
hwmon: (dell-smm) Disable fan support for Dell XPS13 9333
Pull ACPI fixes from Rafael Wysocki:
"These fix a suspend/resume regression in the ACPI driver for Intel
SoCs (LPSS), add a new system wakeup quirk to the ACPI EC driver and
fix an inline stub of a function in the ACPI processor driver that
diverged from the original.
Specifics:
- Fix a suspend/resume regression in the ACPI driver for Intel SoCs
(LPSS) to make it work on systems where some power management
quirks should only be applied for runtime PM and suspend-to-idle
and not for suspend-to-RAM (Rafael Wysocki).
- Add a system wakeup quirk for Thinkpad X1 Carbon 6th to the ACPI EC
driver to avoid drainig battery too fast while suspended to idle on
those systems (Mika Westerberg).
- Fix an inline stub of acpi_processor_ppc_has_changed() to match the
original function definition (Brian Norris)"
* tag 'acpi-4.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI / processor: Finish making acpi_processor_ppc_has_changed() void
ACPI / EC: Use ec_no_wakeup on Thinkpad X1 Carbon 6th
ACPI / LPSS: Avoid PM quirks on suspend and resume from S3
Pull power management updates from Rafael Wysocki:
"These are mostly fixes, including some fixes for changes made during
the recent merge window and some "stable" material, plus some minor
extensions of the turbostat utility.
Specifics:
- Fix the PM core to avoid introducing a runtime PM usage counter
imbalance when adding device links during driver probe (Rafael
Wysocki).
- Fix the operating performance points (OPP) framework to ensure that
the regulator voltage is always updated as appropriate when
updating clock rates (Waldemar Rymarkiewicz).
- Fix the intel_pstate driver to use correct max/min limits for cores
with differing maximum frequences (Srinivas Pandruvada).
- Fix a typo in the intel_pstate driver documentation (Rafael
Wysocki).
- Fix two issues with the recently added Kryo cpufreq driver (Ilia
Lin).
- Fix two recent regressions and some other minor issues in the
turbostat utility and extend it to provide some more diagnostic
information (Len Brown, Nathan Ciobanu)"
* tag 'pm-4.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
Documentation: intel_pstate: Fix typo
tools/power turbostat: version 18.06.20
tools/power turbostat: add the missing command line switches
tools/power turbostat: add single character tokens to help
tools/power turbostat: alphabetize the help output
tools/power turbostat: fix segfault on 'no node' machines
tools/power turbostat: add optional APIC X2APIC columns
tools/power turbostat: decode cpuid.1.HT
tools/power turbostat: fix show/hide issues resulting from mis-merge
PM / OPP: Update voltage in case freq == old_freq
cpufreq: intel_pstate: Fix scaling max/min limits with Turbo 3.0
cpufreq: kryo: Add module remove and exit
cpufreq: kryo: Fix possible error code dereference
PM / core: Fix supplier device runtime PM usage counter imbalance
Non gcc-5 builds with CONFIG_STACK_VALIDATION=y and
SKIP_STACK_VALIDATION=1 fail.
Example output:
/bin/sh: init/.tmp_main.o: Permission denied
commit 96f60dfa58 ("trace: Use -mcount-record for dynamic ftrace"),
added a mismatched endif. This causes cmd_objtool to get mistakenly
set.
Relocate endif to balance the newly added -record-mcount check.
Link: http://lkml.kernel.org/r/20180608214746.136554-1-gthelen@google.com
Fixes: 96f60dfa58 ("trace: Use -mcount-record for dynamic ftrace")
Acked-by: Andi Kleen <ak@linux.intel.com>
Tested-by: David Rientjes <rientjes@google.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
The syzkaller detected a out-of-bounds issue with the events filter code,
specifically here:
prog[N].pred = NULL; /* #13 */
prog[N].target = 1; /* TRUE */
prog[N+1].pred = NULL;
prog[N+1].target = 0; /* FALSE */
-> prog[N-1].target = N;
prog[N-1].when_to_branch = false;
As that's the first reference to a "N-1" index, it appears that the code got
here with N = 0, which means the filter parser found no filter to parse
(which shouldn't ever happen, but apparently it did).
Add a new error to the parsing code that will check to make sure that N is
not zero before going into this part of the code. If N = 0, then -EINVAL is
returned, and a error message is added to the filter.
Cc: stable@vger.kernel.org
Fixes: 80765597bc ("tracing: Rewrite filter logic to be simpler and faster")
Reported-by: air icy <icytxw@gmail.com>
bugzilla url: https://bugzilla.kernel.org/show_bug.cgi?id=200019
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
nvme requires an sg table allocation for each request. If the request
is large, then the allocation can become quite large. For instance,
with our default software settings of 1280KB IO size, we'll need
10248 bytes of sg table. That turns into a 2nd order allocation,
which we can't always guarantee. If we fail the allocation, blk-mq
will retry it later. But there's no guarantee that we'll EVER be
able to allocate that much contigious memory.
Limit the IO size such that we never need more than a single page
of memory. That's a lot faster and more reliable. Then back that
allocation with a mempool, so that we know we'll always be able
to succeed the allocation at some point.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
There is very little point in trying to support the 32bit KVM/arm API
on arm64, and this was never an anticipated use case.
Let's make it clear by not selecting KVM_COMPAT.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
The current behaviour of the compat ioctls is a bit odd.
We provide a compat_ioctl method when KVM_COMPAT is set, and NULL
otherwise. But NULL means that the normal, non-compat ioctl should
be used directly for compat tasks, and there is no way to actually
prevent a compat task from issueing KVM ioctls.
This patch changes this behaviour, by always registering a compat_ioctl
method, even if KVM_COMPAT is not selected. In that case, the callback
will always return -EINVAL.
Fixes: de8e5d7440 ("KVM: Disable compat ioctl for s390")
Reported-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
There is race between nvme_remove and nvme_reset_work that can
lead to io hang.
nvme_remove nvme_reset_work
-> nvme_remove_dead_ctrl
-> nvme_dev_disable
-> quiesce request_queue
-> queue remove_work
-> cancel_work_sync reset_work
-> nvme_remove_namespaces
-> splice ctrl->namespaces
nvme_remove_dead_ctrl_work
-> nvme_kill_queues
-> nvme_ns_remove do nothing
-> blk_cleanup_queue
-> blk_freeze_queue
Finally, the request_queue is quiesced state when wait freeze,
we will get io hang here. To fix it, move the nvme_kill_queues
from nvme_remove_dead_ctrl_work to nvme_remove_dead_ctrl.
Suggested-by: Keith Busch <keith.busch@linux.intel.com>
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Mark Rutland noticed that GCC optimization passes have the potential to elide
necessary invocations of the array_index_mask_nospec() instruction sequence,
so mark the asm() volatile.
Mark explains:
"The volatile will inhibit *some* cases where the compiler could lift the
array_index_nospec() call out of a branch, e.g. where there are multiple
invocations of array_index_nospec() with the same arguments:
if (idx < foo) {
idx1 = array_idx_nospec(idx, foo)
do_something(idx1);
}
< some other code >
if (idx < foo) {
idx2 = array_idx_nospec(idx, foo);
do_something_else(idx2);
}
... since the compiler can determine that the two invocations yield the same
result, and reuse the first result (likely the same register as idx was in
originally) for the second branch, effectively re-writing the above as:
if (idx < foo) {
idx = array_idx_nospec(idx, foo);
do_something(idx);
}
< some other code >
if (idx < foo) {
do_something_else(idx);
}
... if we don't take the first branch, then speculatively take the second, we
lose the nospec protection.
There's more info on volatile asm in the GCC docs:
https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html#Volatile
"
Reported-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: babdde2698 ("x86: Implement array_index_mask_nospec")
Link: https://lkml.kernel.org/lkml/152838798950.14521.4893346294059739135.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
These are a stable-candidate suspend/resume fix of the ACPI driver for
Intel SoCs (LPSS) and an inline stub fix for the ACPI processor driver.
* acpi-soc:
ACPI / LPSS: Avoid PM quirks on suspend and resume from S3
* acpi-processor:
ACPI / processor: Finish making acpi_processor_ppc_has_changed() void
These are turbostat utility updates for 4.18-rc2 including two fixes
for recent regressions and some minor extensions.
* pm-tools:
tools/power turbostat: version 18.06.20
tools/power turbostat: add the missing command line switches
tools/power turbostat: add single character tokens to help
tools/power turbostat: alphabetize the help output
tools/power turbostat: fix segfault on 'no node' machines
tools/power turbostat: add optional APIC X2APIC columns
tools/power turbostat: decode cpuid.1.HT
tools/power turbostat: fix show/hide issues resulting from mis-merge
Xen PV domain kernel is not by design affected by meltdown as it's
enforcing split CR3 itself. Let's not report such systems as "Vulnerable"
in sysfs (we're also already forcing PTI to off in X86_HYPER_XEN_PV cases);
the security of the system ultimately depends on presence of mitigation in
the Hypervisor, which can't be easily detected from DomU; let's report
that.
Reported-and-tested-by: Mike Latimer <mlatimer@suse.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Juergen Gross <jgross@suse.com>
Cc: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1806180959080.6203@cbobk.fhfr.pm
[ Merge the user-visible string into a single line. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
These are a PM core fix and an OPP framework fix for 4.18-rc2,
both "stable" material.
* pm-core:
PM / core: Fix supplier device runtime PM usage counter imbalance
* pm-opp:
PM / OPP: Update voltage in case freq == old_freq
Reverts the following commit:
b0108f9e93 ("kexec: purgatory: add clean-up for purgatory directory")
... which incorrectly stated that the kexec-purgatory.c and purgatory.ro files
were not removed after 'make mrproper'.
In fact, they are. You can confirm it after reverting it.
$ make mrproper
$ touch arch/x86/purgatory/kexec-purgatory.c
$ touch arch/x86/purgatory/purgatory.ro
$ make mrproper
CLEAN arch/x86/purgatory
$ ls arch/x86/purgatory/
entry64.S Makefile purgatory.c setup-x86_64.S stack.S string.c
This is obvious from the build system point of view.
arch/x86/Makefile adds 'arch/x86' to core-y.
Hence 'make clean' descends like this:
arch/x86/Kbuild
-> arch/x86/purgatory/Makefile
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/1529401422-28838-2-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a panic in armv8a server(QDF2400) under memory pressure tests
(start 20 guests and run memhog in the host).
---------------------------------begin--------------------------------
[35380.800950] BUG: Bad page state in process qemu-kvm pfn:dd0b6
[35380.805825] page:ffff7fe003742d80 count:-4871 mapcount:-2126053375
mapping: (null) index:0x0
[35380.815024] flags: 0x1fffc00000000000()
[35380.818845] raw: 1fffc00000000000 0000000000000000 0000000000000000
ffffecf981470000
[35380.826569] raw: dead000000000100 dead000000000200 ffff8017c001c000
0000000000000000
[35380.805825] page:ffff7fe003742d80 count:-4871 mapcount:-2126053375
mapping: (null) index:0x0
[35380.815024] flags: 0x1fffc00000000000()
[35380.818845] raw: 1fffc00000000000 0000000000000000 0000000000000000
ffffecf981470000
[35380.826569] raw: dead000000000100 dead000000000200 ffff8017c001c000
0000000000000000
[35380.834294] page dumped because: nonzero _refcount
[...]
--------------------------------end--------------------------------------
The root cause might be what was fixed at [1]. But from the KVM points of
view, it would be better if the issue was caught earlier.
If the size is not PAGE_SIZE aligned, unmap_stage2_range might unmap the
wrong(more or less) page range. Hence it caused the "BUG: Bad page
state"
Let's WARN in that case, so that the issue is obvious.
[1] https://lkml.org/lkml/2018/5/3/1042
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: jia.he@hxt-semitech.com
[maz: tidied up commit message]
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Commit e6b673b ("KVM: arm64: Optimise FPSIMD handling to reduce
guest/host thrashing") uses fpsimd_save() to save the FPSIMD state
for a vcpu when scheduling the vcpu out. However, currently
current's value of TIF_SVE is restored before calling fpsimd_save()
which means that fpsimd_save() may erroneously attempt to save SVE
state from the vcpu. This enables current's vector state to be
polluted with guest data. current->thread.sve_state may be
unallocated or not large enough, so this can also trigger a NULL
dereference or buffer overrun.
Instead of this, TIF_SVE should be configured properly for the
guest when calling fpsimd_save() with the vcpu context loaded.
This patch ensures this by delaying restoration of current's
TIF_SVE until after the call to fpsimd_save().
Fixes: e6b673b741 ("KVM: arm64: Optimise FPSIMD handling to reduce guest/host thrashing")
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Commit e6b673b ("KVM: arm64: Optimise FPSIMD handling to reduce
guest/host thrashing") attempts to restore the configuration of
userspace SVE trapping via a call to fpsimd_bind_task_to_cpu(), but
the logic for determining when to do this is not correct.
The patch makes the errnoenous assumption that the only task that
may try to enter userspace with the currently loaded FPSIMD/SVE
register content is current. This may not be the case however: if
some other user task T is scheduled on the CPU during the execution
of the KVM run loop, and the vcpu does not try to use the registers
in the meantime, then T's state may be left there intact. If T
happens to be the next task to enter userspace on this CPU then the
hooks for reloading the register state and configuring traps will
be skipped.
(Also, current never has SVE state at this point anyway and should
always have the trap enabled, as a side-effect of the ioctl()
syscall needed to reach the KVM run loop in the first place.)
This patch instead restores the state of the EL0 trap from the
state observed at the most recent vcpu_load(), ensuring that the
trap is set correctly for the loaded context (if any).
Fixes: e6b673b741 ("KVM: arm64: Optimise FPSIMD handling to reduce guest/host thrashing")
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Commit e6b673b ("KVM: arm64: Optimise FPSIMD handling to reduce
guest/host thrashing") introduces a specific helper
kvm_arch_vcpu_put_fp() for saving the vcpu FPSIMD state during
vcpu_put().
This function uses local_bh_disable()/_enable() to protect the
FPSIMD context manipulation from interruption by softirqs.
This approach is not correct, because vcpu_put() can be invoked
either from the KVM host vcpu thread (when exiting the vcpu run
loop), or via a preempt notifier. In the former case, only
preemption is disabled. In the latter case, the function is called
from inside __schedule(), which means that IRQs are disabled.
Use of local_bh_disable()/_enable() with IRQs disabled is considerd
an error, resulting in lockdep splats while running VMs if lockdep
is enabled.
This patch disables IRQs instead of attempting to disable softirqs,
avoiding the problem of calling local_bh_enable() with IRQs
disabled in the __schedule() path. This creates an additional
interrupt blackout during vcpu run loop exit, but this is the rare
case and the blackout latency is still less than that of
__schedule().
Fixes: e6b673b741 ("KVM: arm64: Optimise FPSIMD handling to reduce guest/host thrashing")
Reported-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Currently we have a couple of helpers to manipulate bits in particular
sysregs:
* config_sctlr_el1(u32 clear, u32 set)
* change_cpacr(u64 val, u64 mask)
The parameters of these differ in naming convention, order, and size,
which is unfortunate. They also differ slightly in behaviour, as
change_cpacr() skips the sysreg write if the bits are unchanged, which
is a useful optimization when sysreg writes are expensive.
Before we gain yet another sysreg manipulation function, let's
unify these with a common helper, providing a consistent order for
clear/set operands, and the write skipping behaviour from
change_cpacr(). Code will be migrated to the new helper in subsequent
patches.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
When booting a 64 KB pages kernel on a ACPI GICv3 system that
implements support for v2 emulation, the following warning is
produced
GICV size 0x2000 not a multiple of page size 0x10000
and support for v2 emulation is disabled, preventing GICv2 VMs
from being able to run on such hosts.
The reason is that vgic_v3_probe() performs a sanity check on the
size of the window (it should be a multiple of the page size),
while the ACPI MADT parsing code hardcodes the size of the window
to 8 KB. This makes sense, considering that ACPI does not bother
to describe the size in the first place, under the assumption that
platforms implementing ACPI will follow the architecture and not
put anything else in the same 64 KB window.
So let's just drop the sanity check altogether, and assume that
the window is at least 64 KB in size.
Fixes: 9097773245 ("KVM: arm/arm64: vgic-new: vgic_init: implement kvm_vgic_hyp_init")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
