| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Return type of wait_for_completion_timeout() is unsigned long not int.
An appropriately named unsigned long is added and the assignment fixed.
Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
If a device is used as the root filesystem, it can't be built
off of devices which are within the root filesystem (just like
command line arguments to root=). For this reason, Linux has a
pseudo-filesystem for root= and MD initialization (based on the
function name_to_dev_t) which handles different ways of specifying
devices including PARTUUID and major:minor.
Switch to using name_to_dev_t() in dm_get_device(). Rather than
having DM assume that all things which are not major:minor are paths in
an already-mounted filesystem, change dm_get_device() to first attempt
to look up the device in the filesystem, and if not found it will fall
back to using name_to_dev_t().
In terms of backwards compatibility, there are some cases where
behavior will be different:
- If you have a file in the current working directory named 1:2 and
you initialze DM there, then it will try to use that file rather
than the disk with that major:minor pair as a backing device.
- Similarly for other bdev types which name_to_dev_t() knows how to
interpret, the previous behavior was to repeatedly check for the
existence of the file (e.g., while waiting for rootfs to come up)
but the new behavior is to use the name_to_dev_t() interpretation.
For example, if you have a file named /dev/ubiblock0_0 which is
a symlink to /dev/sda3, but it is not yet present when DM starts
to initialize, then the name_to_dev_t() interpretation will take
precedence.
These incompatibilities would only show up in really strange setups
with bad practices so we shouldn't have to worry about them.
Signed-off-by: Dan Ehrenberg <dehrenberg@chromium.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
In the kernel command-line, previously, root=1:2jakshflaksjdhfa would
be accepted and interpreted just like root=1:2. This patch adds
stricter checking so that additional characters after major:minor are
rejected by root=.
The goal of this change is to help in unifying DM's interpretation of
its block device argument by using existing kernel code (name_to_dev_t).
But DM rejects malformed major:minor pairs, it seems reasonable for
root= to reject them as well.
Signed-off-by: Dan Ehrenberg <dehrenberg@chromium.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
DM will switch its device lookup code to using name_to_dev_t() so it
must be exported. Also, the @name argument should be marked const.
Signed-off-by: Dan Ehrenberg <dehrenberg@chromium.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Request-based DM's blk-mq support defaults to off; but a user can easily
change the default using the dm_mod.use_blk_mq module/boot option.
Also, you can check what mode a given request-based DM device is using
with: cat /sys/block/dm-X/dm/use_blk_mq
This change enabled further cleanup and reduced work (e.g. the
md->io_pool and md->rq_pool isn't created if using blk-mq).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
dm_mq_queue_rq() is in atomic context so care must be taken to not
sleep -- as such GFP_ATOMIC is used for the md->bs bioset allocations
and dm-mpath's call to blk_get_request(). In the future the bioset
allocations will hopefully go away (by removing support for partial
completions of bios in a cloned request).
Also prepare for supporting DM blk-mq ontop of old-style request_fn
device(s) if a new dm-mod 'use_blk_mq' parameter is set. The kthread
will still be used to queue work if blk-mq is used ontop of old-style
request_fn device(s).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Commit e5863d9ad ("dm: allocate requests in target when stacking on
blk-mq devices") served as the first step toward fully utilizing blk-mq
in request-based DM -- it enabled stacking an old-style (request_fn)
request_queue ontop of the underlying blk-mq device(s). That first step
didn't improve performance of DM multipath ontop of fast blk-mq devices
(e.g. NVMe) because the top-level old-style request_queue was severely
limited by the queue_lock.
The second step offered here enables stacking a blk-mq request_queue
ontop of the underlying blk-mq device(s). This unlocks significant
performance gains on fast blk-mq devices, Keith Busch tested on his NVMe
testbed and offered this really positive news:
"Just providing a performance update. All my fio tests are getting
roughly equal performance whether accessed through the raw block
device or the multipath device mapper (~470k IOPS). I could only push
~20% of the raw iops through dm before this conversion, so this latest
tree is looking really solid from a performance standpoint."
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Tested-by: Keith Busch <keith.busch@intel.com>
|
|
Otherwise, for sequential workloads, the dm_request_fn can allow
excessive request merging at the expense of increased service time.
Add a per-device sysfs attribute to allow the user to control how long a
request, that is a reasonable merge candidate, can be queued on the
request queue. The resolution of this request dispatch deadline is in
microseconds (ranging from 1 to 100000 usecs), to set a 20us deadline:
echo 20 > /sys/block/dm-7/dm/rq_based_seq_io_merge_deadline
The dm_request_fn's merge heuristic and associated extra accounting is
disabled by default (rq_based_seq_io_merge_deadline is 0).
This sysfs attribute is not applicable to bio-based DM devices so it
will only ever report 0 for them.
By allowing a request to remain on the queue it will block others
requests on the queue. But introducing a short dequeue delay has proven
very effective at enabling certain sequential IO workloads on really
fast, yet IOPS constrained, devices to build up slightly larger IOs --
yielding 90+% throughput improvements. Having precise control over the
time taken to wait for larger requests to build affords control beyond
that of waiting for certain IO sizes to accumulate (which would require
a deadline anyway). This knob will only ever make sense with sequential
IO workloads and the particular value used is storage configuration
specific.
Given the expected niche use-case for when this knob is useful it has
been deemed acceptable to expose this relatively crude method for
crafting optimal IO on specific storage -- especially given the solution
is simple yet effective. In the context of DM multipath, it is
advisable to tune this sysfs attribute to a value that offers the best
performance for the common case (e.g. if 4 paths are expected active,
tune for that; if paths fail then performance may be slightly reduced).
Alternatives were explored to have request-based DM autotune this value
(e.g. if/when paths fail) but they were quickly deemed too fragile and
complex to warrant further design and development time. If this problem
proves more common as faster storage emerges we'll have to look at
elevating a generic solution into the block core.
Tested-by: Shiva Krishna Merla <shivakrishna.merla@netapp.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Add DM_ATTR_RW() macro and establish .store method in dm_sysfs_ops.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Request-based DM's dm_request_fn() is so fast to pull requests off the
queue that steps need to be taken to promote merging by avoiding request
processing if it makes sense.
If the current request would've merged with previous request let the
current request stay on the queue longer.
Suggested-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Commit 7eaceaccab ("block: remove per-queue plugging") didn't justify
DM's use of a 100ms delay; such an extended delay is a liability when
there is reason to re-kick the queue.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
In request-based DM's dm_request_fn(), if blk_peek_request() returns
NULL just return. Avoids unnecessary blk_delay_queue().
Reported-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
On really fast storage it can be beneficial to delay running the
request_queue to allow the elevator more opportunity to merge requests.
Otherwise, it has been observed that requests are being sent to
q->request_fn much quicker than is ideal on IOPS-bound backends.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
The old dm_request() method used for q->make_request_fn had a branch for
request-based DM support but it isn't needed given that
dm_init_request_based_queue() sets it to the standard blk_queue_bio()
anyway.
Cleanup dm_init_md_queue() to be DM device-type agnostic and have
dm_setup_md_queue() properly finish queue setup based on DM device-type
(bio-based vs request-based).
A followup block patch can be made to remove the export for
blk_queue_bio() now that DM no longer calls it directly.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
DM multipath is the only caller of blk_lld_busy() -- which calls a
queue's lld_busy_fn hook. Request-based DM doesn't support stacking
multipath devices so there is no reason to register the lld_busy_fn hook
on a multipath device's queue using blk_queue_lld_busy().
As such, remove functions dm_lld_busy and dm_table_any_busy_target.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
There is no need for DM to export a wrapper around the already exported
blk_lld_busy().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
__dm_get_module_param() could be useful for future DM module parameters
besides those related to "reserved_ios".
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Writeback takes out a lock on the cache block, so will increase the
latency for any concurrent io.
This patch works by placing 2 sentinel objects on each level of the
multiqueues. Every WRITEBACK_PERIOD the oldest sentinel gets moved to
the newest end of the queue level.
When looking for writeback work:
if less than 25% of the cache is clean:
we select the oldest object with the lowest hit count
otherwise:
we select the oldest object that is not past a writeback sentinel.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Remove to stop wasting memory.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
A sentinel object is placed on each level of the multiqueues. When an
object is hit it is requeued behind the sentinel. When the tick is
incremented we iterate through all objects behind the sentinel and
update the hit_count, then reposition the sentinel at the very back.
This saves memory by avoiding tracking the tick explicitly for every
struct entry object in the multiqueues.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
queue_shift_down() didn't adjust the hit_counts to the new levels, so it
just had the effect of scrambling levels.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Small optimisation, now queue_empty() doesn't need to walk all levels of
the multiqueue.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
|
|
Use a single slab cache to allocate a mempool for each dirty-log.
This _should_ eliminate DM's need for io_schedule_timeout() in
mempool_alloc(); so io_schedule() should be sufficient now.
Also, rename struct flush_entry to dm_dirty_log_flush_entry to allow
KMEM_CACHE() to create a meaningful global name for the slab cache.
Also, eliminate some holes in struct log_c by rearranging members.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Heinz Mauelshagen <heinzm@redhat.com>
|
|
Linux 3.19 commit 69c953c ("lib/lcm.c: lcm(n,0)=lcm(0,n) is 0, not n")
caused blk_stack_limits() to not properly stack queue_limits for stacked
devices (e.g. DM).
Fix this regression by establishing lcm_not_zero() and switching
blk_stack_limits() over to using it.
DM uses blk_set_stacking_limits() to establish the initial top-level
queue_limits that are then built up based on underlying devices' limits
using blk_stack_limits(). In the case of optimal_io_size (io_opt)
blk_set_stacking_limits() establishes a default value of 0. With commit
69c953c, lcm(0, n) is no longer n, which compromises proper stacking of
the underlying devices' io_opt.
Test:
$ modprobe scsi_debug dev_size_mb=10 num_tgts=1 opt_blks=1536
$ cat /sys/block/sde/queue/optimal_io_size
786432
$ dmsetup create node --table "0 100 linear /dev/sde 0"
Before this fix:
$ cat /sys/block/dm-5/queue/optimal_io_size
0
After this fix:
$ cat /sys/block/dm-5/queue/optimal_io_size
786432
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.19+
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
|
|
Don't assign ->rq_timeout twice.
Signed-off-by: Wei Fang <fangwei1@huawei.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
|
|
At the beginning of blk_mq_alloc_tag_set(), we have already checked whether
'set->nr_hw_queues' is zero, so here remove this redundant check.
Signed-off-by: Xiaoguang Wang <wangxg.fnst@cn.fujitsu.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
|
|
|
|
The UART reference clock speed is 7273.8 kHz, not 72738 kHz.
Dots aren't usually used in node names even though ePAPR permits
them. However, this can easily be avoided by expressing the
frequency in Hz, not kHz.
This patch changes the name to refclk7273800hz, reflecting the
actual clock speed.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Acked-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
The IMG PDC watchdog driver heartbeat module parameter has no default so
it is initialised to zero. This results in the following warning during
probe:
imgpdc-wdt 2006000.wdt: Initial timeout out of range! setting max timeout
The module parameter description implies that the default value should
be PDC_WDT_DEF_TIMEOUT, which isn't yet used, so initialise it to that.
Also tweak the heartbeat module parameter description for consistency.
Fixes: 93937669e9b5 ("watchdog: ImgTec PDC Watchdog Timer Driver")
Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Ezequiel Garcia <ezequiel.garcia@imgtec.com>
Cc: Naidu Tellapati <Naidu.Tellapati@imgtec.com>
Cc: Jude Abraham <Jude.Abraham@imgtec.com>
Cc: linux-watchdog@vger.kernel.org
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
|
|
The IMG PDC watchdog probe function calls pdc_wdt_stop() prior to
watchdog_set_drvdata(), causing a NULL pointer dereference when
pdc_wdt_stop() retrieves the struct pdc_wdt_dev pointer using
watchdog_get_drvdata() and reads the register base address through it.
Fix by moving the watchdog_set_drvdata() call earlier, to where various
other pdc_wdt->wdt_dev fields are initialised.
Fixes: 93937669e9b5 ("watchdog: ImgTec PDC Watchdog Timer Driver")
Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Ezequiel Garcia <ezequiel.garcia@imgtec.com>
Cc: Naidu Tellapati <Naidu.Tellapati@imgtec.com>
Cc: Jude Abraham <Jude.Abraham@imgtec.com>
Cc: linux-watchdog@vger.kernel.org
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
|
|
"ret" should be signed for the error handling to work correctly. This
doesn't matter much in real life since mtk_wdt_set_timeout() always
succeeds.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
|
|
This is a very similar bug in the load detect code fixed in
commit 9128b040eb774e04bc23777b005ace2b66ab2a85
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue Mar 3 17:31:21 2015 +0100
drm/i915: Fix modeset state confusion in the load detect code
But this time around it was the initial fb code that forgot to update
the plane->crtc pointer. Otherwise it's the exact same bug, with the
exact same restrains (any set_config call/ioctl that doesn't disable
the pipe papers over the bug for free, so fairly hard to hit in normal
testing). So if you want the full explanation just go read that one
over there - it's rather long ...
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Josh Boyer <jwboyer@fedoraproject.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Reported-and-tested-by: Josh Boyer <jwboyer@fedoraproject.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[Jani: backported to drm-intel-fixes for v4.0-rc]
Reference: http://mid.gmane.org/CA+5PVA7ChbtJrknqws1qvZcbrg1CW2pQAFkSMURWWgyASRyGXg@mail.gmail.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
|
|
Right now, we get a warning when taking over the firmware fb:
[drm:drm_atomic_plane_check] FB set but no CRTC
with the following backtrace:
[<ffffffffa010339d>] drm_atomic_check_only+0x35d/0x510 [drm]
[<ffffffffa0103567>] drm_atomic_commit+0x17/0x60 [drm]
[<ffffffffa00a6ccd>] drm_atomic_helper_plane_set_property+0x8d/0xd0 [drm_kms_helper]
[<ffffffffa00f1fed>] drm_mode_plane_set_obj_prop+0x2d/0x90 [drm]
[<ffffffffa00a8a1b>] restore_fbdev_mode+0x6b/0xf0 [drm_kms_helper]
[<ffffffffa00aa969>] drm_fb_helper_restore_fbdev_mode_unlocked+0x29/0x80 [drm_kms_helper]
[<ffffffffa00aa9e2>] drm_fb_helper_set_par+0x22/0x50 [drm_kms_helper]
[<ffffffffa050a71a>] intel_fbdev_set_par+0x1a/0x60 [i915]
[<ffffffff813ad444>] fbcon_init+0x4f4/0x580
That's because we update the plane state with the fb from the firmware, but we
never associate the plane to that CRTC.
We don't quite have the full DRM take over from HW state just yet, so
fake enough of the plane atomic state to pass the checks.
v2: Fix the state on which we set the CRTC in the case we're sharing the
initial fb with another pipe. (Matt)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[Jani: backported to drm-intel-fixes for v4.0-rc]
Reference: http://mid.gmane.org/CA+5PVA7yXH=U757w8V=Zj2U1URG4nYNav20NpjtQ4svVueyPNw@mail.gmail.com
Reference: http://lkml.kernel.org/r/CA+55aFweWR=nDzc2Y=rCtL_H8JfdprQiCimN5dwc+TgyD4Bjsg@mail.gmail.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
|
|
We have a HP machine which use the codec node 0x17 connecting the
internal speaker, and from the node capability, we saw the EAPD,
if we don't set the EAPD on for this node, the internal speaker
can't output any sound.
Cc: <stable@vger.kernel.org>
BugLink: https://bugs.launchpad.net/bugs/1436745
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
|
|
The sun5i timer is used as the sched-clock on certain systems, and ever
since we started using cpufreq, the cpu clock (that is one of the
timer's clock indirect parent) now changes as well, along with the
actual sched_clock() rate.
This is not accurate and not desirable.
We can safely remove the sun5i sched-clock on those systems, since we
have other reliable sched_clock() sources in the system.
Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ Improved the changelog. ]
Cc: richard@nod.at
Link: http://lkml.kernel.org/r/1427362029-6511-4-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Fix !CONFIG_HAS_IOMEM related build failures in three clocksource drivers.
The build failures have the pattern of:
drivers/clocksource/sh_cmt.c: In function ‘sh_cmt_map_memory’: drivers/clocksource/sh_cmt.c:920:2:
error: implicit declaration of function ‘ioremap_nocache’ [-Werror=implicit-function-declaration] cmt->mapbase = ioremap_nocache(mem->start, resource_size(mem));
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: maxime.ripard@free-electrons.com
Link: http://lkml.kernel.org/r/1427362029-6511-1-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
If we retire requests last, we may use a later seqno and so clear
the requests lists without clearing the active list, leading to
confusion. Hence we should retire requests first for consistency with
the early return. The order used to be important as the lifecycle for
the object on the active list was determined by request->seqno. However,
the requests themselves are now reference counted removing the
constraint from the order of retirement.
Fixes regression from
commit 1b5a433a4dd967b125131da42b89b5cc0d5b1f57
Author: John Harrison <John.C.Harrison@Intel.com>
Date: Mon Nov 24 18:49:42 2014 +0000
drm/i915: Convert 'i915_seqno_passed' calls into 'i915_gem_request_completed
'
and a
WARNING: CPU: 0 PID: 1383 at drivers/gpu/drm/i915/i915_gem_evict.c:279 i915_gem_evict_vm+0x10c/0x140()
WARN_ON(!list_empty(&vm->active_list))
Identified by updating WATCH_LISTS:
[drm:i915_verify_lists] *ERROR* blitter ring: active list not empty, but no requests
WARNING: CPU: 0 PID: 681 at drivers/gpu/drm/i915/i915_gem.c:2751 i915_gem_retire_requests_ring+0x149/0x230()
WARN_ON(i915_verify_lists(ring->dev))
Note that this is only a problem in evict_vm where the following happens
after a retire_request has cleaned out all requests, but not all active
bo:
- intel_ring_idle called from i915_gpu_idle notices that no requests are
outstanding and immediately returns.
- i915_gem_retire_requests_ring called from i915_gem_retire_requests also
immediately returns when there's no request, still leaving the bo on the
active list.
- evict_vm hits the WARN_ON(!list_empty(&vm->active_list)) after evicting
all active objects that there's still stuff left that shouldn't be
there.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
|
|
The total stream number of Sunrise Point's input and output stream
exceeds 15, which will cause some streams do not work because
of the overflow on SDxCTL.STRM field if using the legacy
stream tag allocation method.
This patch uses the new stream tag allocation method by add
the flag AZX_DCAPS_SEPARATE_STREAM_TAG for Skylake platform.
Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
|
|
A malicious signal handler / restorer can DOS the system by fudging the
user regs saved on stack, causing weird things such as sigreturn returning
to user mode PC but cpu state still being kernel mode....
Ensure that in sigreturn path status32 always has U bit; any other bogosity
(gargbage PC etc) will be taken care of by normal user mode exceptions mechanisms.
Reproducer signal handler:
void handle_sig(int signo, siginfo_t *info, void *context)
{
ucontext_t *uc = context;
struct user_regs_struct *regs = &(uc->uc_mcontext.regs);
regs->scratch.status32 = 0;
}
Before the fix, kernel would go off to weeds like below:
--------->8-----------
[ARCLinux]$ ./signal-test
Path: /signal-test
CPU: 0 PID: 61 Comm: signal-test Not tainted 4.0.0-rc5+ #65
task: 8f177880 ti: 5ffe6000 task.ti: 8f15c000
[ECR ]: 0x00220200 => Invalid Write @ 0x00000010 by insn @ 0x00010698
[EFA ]: 0x00000010
[BLINK ]: 0x2007c1ee
[ERET ]: 0x10698
[STAT32]: 0x00000000 : <--------
BTA: 0x00010680 SP: 0x5ffe7e48 FP: 0x00000000
LPS: 0x20003c6c LPE: 0x20003c70 LPC: 0x00000000
...
--------->8-----------
Reported-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
|
|
The regfile provided to SA_SIGINFO signal handler as ucontext was off by
one due to pt_regs gutter cleanups in 2013.
Before handling signal, user pt_regs are copied onto user_regs_struct and copied
back later. Both structs are binary compatible. This was all fine until
commit 2fa919045b72 (ARC: pt_regs update #2) which removed the empty stack slot
at top of pt_regs (corresponding to first pad) and made the corresponding
fixup in struct user_regs_struct (the pad in there was moved out of
@scratch - not removed altogether as it is part of ptrace ABI)
struct user_regs_struct {
+ long pad;
struct {
- long pad;
long bta, lp_start, lp_end,....
} scratch;
...
}
This meant that now user_regs_struct was off by 1 reg w.r.t pt_regs and
signal code needs to user_regs_struct.scratch to reflect it as pt_regs,
which is what this commit does.
This problem was hidden for 2 years, because both save/restore, despite
using wrong location, were using the same location. Only an interim
inspection (reproducer below) exposed the issue.
void handle_segv(int signo, siginfo_t *info, void *context)
{
ucontext_t *uc = context;
struct user_regs_struct *regs = &(uc->uc_mcontext.regs);
printf("regs %x %x\n", <=== prints 7 8 (vs. 8 9)
regs->scratch.r8, regs->scratch.r9);
}
int main()
{
struct sigaction sa;
sa.sa_sigaction = handle_segv;
sa.sa_flags = SA_SIGINFO;
sigemptyset(&sa.sa_mask);
sigaction(SIGSEGV, &sa, NULL);
asm volatile(
"mov r7, 7 \n"
"mov r8, 8 \n"
"mov r9, 9 \n"
"mov r10, 10 \n"
:::"r7","r8","r9","r10");
*((unsigned int*)0x10) = 0;
}
Fixes: 2fa919045b72ec892e "ARC: pt_regs update #2: Remove unused gutter at start of pt_regs"
CC: <stable@vger.kernel.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
|
|
Base PTEs are marked young when the NUMA hinting information is cleared
but the same does not happen for huge pages which this patch addresses.
Note that migrated pages are not marked young as the base page migration
code does not assume that migrated pages have been referenced. This
could be addressed but beyond the scope of this series which is aimed at
Dave Chinners shrink workload that is unlikely to be affected by this
issue.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226
Across the board the 4.0-rc1 numbers are much slower, and the degradation
is far worse when using the large memory footprint configs. Perf points
straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config:
- 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys
- default_send_IPI_mask_sequence_phys
- 99.99% physflat_send_IPI_mask
- 99.37% native_send_call_func_ipi
smp_call_function_many
- native_flush_tlb_others
- 99.85% flush_tlb_page
ptep_clear_flush
try_to_unmap_one
rmap_walk
try_to_unmap
migrate_pages
migrate_misplaced_page
- handle_mm_fault
- 99.73% __do_page_fault
trace_do_page_fault
do_async_page_fault
+ async_page_fault
0.63% native_send_call_func_single_ipi
generic_exec_single
smp_call_function_single
This is showing excessive migration activity even though excessive
migrations are meant to get throttled. Normally, the scan rate is tuned
on a per-task basis depending on the locality of faults. However, if
migrations fail for any reason then the PTE scanner may scan faster if
the faults continue to be remote. This means there is higher system CPU
overhead and fault trapping at exactly the time we know that migrations
cannot happen. This patch tracks when migration failures occur and
slows the PTE scanner.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Protecting a PTE to trap a NUMA hinting fault clears the writable bit
and further faults are needed after trapping a NUMA hinting fault to set
the writable bit again. This patch preserves the writable bit when
trapping NUMA hinting faults. The impact is obvious from the number of
minor faults trapped during the basis balancing benchmark and the system
CPU usage;
autonumabench
4.0.0-rc4 4.0.0-rc4
baseline preserve
Time System-NUMA01 107.13 ( 0.00%) 103.13 ( 3.73%)
Time System-NUMA01_THEADLOCAL 131.87 ( 0.00%) 83.30 ( 36.83%)
Time System-NUMA02 8.95 ( 0.00%) 10.72 (-19.78%)
Time System-NUMA02_SMT 4.57 ( 0.00%) 3.99 ( 12.69%)
Time Elapsed-NUMA01 515.78 ( 0.00%) 517.26 ( -0.29%)
Time Elapsed-NUMA01_THEADLOCAL 384.10 ( 0.00%) 384.31 ( -0.05%)
Time Elapsed-NUMA02 48.86 ( 0.00%) 48.78 ( 0.16%)
Time Elapsed-NUMA02_SMT 47.98 ( 0.00%) 48.12 ( -0.29%)
4.0.0-rc4 4.0.0-rc4
baseline preserve
User 44383.95 43971.89
System 252.61 201.24
Elapsed 998.68 1000.94
Minor Faults 2597249 1981230
Major Faults 365 364
There is a similar drop in system CPU usage using Dave Chinner's xfsrepair
workload
4.0.0-rc4 4.0.0-rc4
baseline preserve
Amean real-xfsrepair 454.14 ( 0.00%) 442.36 ( 2.60%)
Amean syst-xfsrepair 277.20 ( 0.00%) 204.68 ( 26.16%)
The patch looks hacky but the alternatives looked worse. The tidest was
to rewalk the page tables after a hinting fault but it was more complex
than this approach and the performance was worse. It's not generally
safe to just mark the page writable during the fault if it's a write
fault as it may have been read-only for COW so that approach was
discarded.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
These are three follow-on patches based on the xfsrepair workload Dave
Chinner reported was problematic in 4.0-rc1 due to changes in page table
management -- https://lkml.org/lkml/2015/3/1/226.
Much of the problem was reduced by commit 53da3bc2ba9e ("mm: fix up numa
read-only thread grouping logic") and commit ba68bc0115eb ("mm: thp:
Return the correct value for change_huge_pmd"). It was known that the
performance in 3.19 was still better even if is far less safe. This
series aims to restore the performance without compromising on safety.
For the test of this mail, I'm comparing 3.19 against 4.0-rc4 and the
three patches applied on top
autonumabench
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8
Time System-NUMA01 124.00 ( 0.00%) 161.86 (-30.53%) 107.13 ( 13.60%) 103.13 ( 16.83%) 145.01 (-16.94%)
Time System-NUMA01_THEADLOCAL 115.54 ( 0.00%) 107.64 ( 6.84%) 131.87 (-14.13%) 83.30 ( 27.90%) 92.35 ( 20.07%)
Time System-NUMA02 9.35 ( 0.00%) 10.44 (-11.66%) 8.95 ( 4.28%) 10.72 (-14.65%) 8.16 ( 12.73%)
Time System-NUMA02_SMT 3.87 ( 0.00%) 4.63 (-19.64%) 4.57 (-18.09%) 3.99 ( -3.10%) 3.36 ( 13.18%)
Time Elapsed-NUMA01 570.06 ( 0.00%) 567.82 ( 0.39%) 515.78 ( 9.52%) 517.26 ( 9.26%) 543.80 ( 4.61%)
Time Elapsed-NUMA01_THEADLOCAL 393.69 ( 0.00%) 384.83 ( 2.25%) 384.10 ( 2.44%) 384.31 ( 2.38%) 380.73 ( 3.29%)
Time Elapsed-NUMA02 49.09 ( 0.00%) 49.33 ( -0.49%) 48.86 ( 0.47%) 48.78 ( 0.63%) 50.94 ( -3.77%)
Time Elapsed-NUMA02_SMT 47.51 ( 0.00%) 47.15 ( 0.76%) 47.98 ( -0.99%) 48.12 ( -1.28%) 49.56 ( -4.31%)
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8
User 46334.60 46391.94 44383.95 43971.89 44372.12
System 252.84 284.66 252.61 201.24 249.00
Elapsed 1062.14 1050.96 998.68 1000.94 1026.78
Overall the system CPU usage is comparable and the test is naturally a
bit variable. The slowing of the scanner hurts numa01 but on this
machine it is an adverse workload and patches that dramatically help it
often hurt absolutely everything else.
Due to patch 2, the fault activity is interesting
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8
Minor Faults 2097811 2656646 2597249 1981230 1636841
Major Faults 362 450 365 364 365
Note the impact preserving the write bit across protection updates and
fault reduces faults.
NUMA alloc hit 1229008 1217015 1191660 1178322 1199681
NUMA alloc miss 0 0 0 0 0
NUMA interleave hit 0 0 0 0 0
NUMA alloc local 1228514 1216317 1190871 1177448 1199021
NUMA base PTE updates 245706197 240041607 238195516 244704842 115012800
NUMA huge PMD updates 479530 468448 464868 477573 224487
NUMA page range updates 491225557 479886983 476207932 489222218 229950144
NUMA hint faults 659753 656503 641678 656926 294842
NUMA hint local faults 381604 373963 360478 337585 186249
NUMA hint local percent 57 56 56 51 63
NUMA pages migrated 5412140 6374899 6266530 5277468 5755096
AutoNUMA cost 5121% 5083% 4994% 5097% 2388%
Here the impact of slowing the PTE scanner on migratrion failures is
obvious as "NUMA base PTE updates" and "NUMA huge PMD updates" are
massively reduced even though the headline performance is very similar.
As xfsrepair was the reported workload here is the impact of the series
on it.
xfsrepair
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8
Min real-fsmark 1183.29 ( 0.00%) 1165.73 ( 1.48%) 1152.78 ( 2.58%) 1153.64 ( 2.51%) 1177.62 ( 0.48%)
Min syst-fsmark 4107.85 ( 0.00%) 4027.75 ( 1.95%) 3986.74 ( 2.95%) 3979.16 ( 3.13%) 4048.76 ( 1.44%)
Min real-xfsrepair 441.51 ( 0.00%) 463.96 ( -5.08%) 449.50 ( -1.81%) 440.08 ( 0.32%) 439.87 ( 0.37%)
Min syst-xfsrepair 195.76 ( 0.00%) 278.47 (-42.25%) 262.34 (-34.01%) 203.70 ( -4.06%) 143.64 ( 26.62%)
Amean real-fsmark 1188.30 ( 0.00%) 1177.34 ( 0.92%) 1157.97 ( 2.55%) 1158.21 ( 2.53%) 1182.22 ( 0.51%)
Amean syst-fsmark 4111.37 ( 0.00%) 4055.70 ( 1.35%) 3987.19 ( 3.02%) 3998.72 ( 2.74%) 4061.69 ( 1.21%)
Amean real-xfsrepair 450.88 ( 0.00%) 468.32 ( -3.87%) 454.14 ( -0.72%) 442.36 ( 1.89%) 440.59 ( 2.28%)
Amean syst-xfsrepair 199.66 ( 0.00%) 290.60 (-45.55%) 277.20 (-38.84%) 204.68 ( -2.51%) 150.55 ( 24.60%)
Stddev real-fsmark 4.12 ( 0.00%) 10.82 (-162.29%) 4.14 ( -0.28%) 5.98 (-45.05%) 4.60 (-11.53%)
Stddev syst-fsmark 2.63 ( 0.00%) 20.32 (-671.82%) 0.37 ( 85.89%) 16.47 (-525.59%) 15.05 (-471.79%)
Stddev real-xfsrepair 6.87 ( 0.00%) 4.55 ( 33.75%) 3.46 ( 49.58%) 1.78 ( 74.12%) 0.52 ( 92.50%)
Stddev syst-xfsrepair 3.02 ( 0.00%) 10.30 (-241.37%) 13.17 (-336.37%) 0.71 ( 76.63%) 5.00 (-65.61%)
CoeffVar real-fsmark 0.35 ( 0.00%) 0.92 (-164.73%) 0.36 ( -2.91%) 0.52 (-48.82%) 0.39 (-12.10%)
CoeffVar syst-fsmark 0.06 ( 0.00%) 0.50 (-682.41%) 0.01 ( 85.45%) 0.41 (-543.22%) 0.37 (-478.78%)
CoeffVar real-xfsrepair 1.52 ( 0.00%) 0.97 ( 36.21%) 0.76 ( 49.94%) 0.40 ( 73.62%) 0.12 ( 92.33%)
CoeffVar syst-xfsrepair 1.51 ( 0.00%) 3.54 (-134.54%) 4.75 (-214.31%) 0.34 ( 77.20%) 3.32 (-119.63%)
Max real-fsmark 1193.39 ( 0.00%) 1191.77 ( 0.14%) 1162.90 ( 2.55%) 1166.66 ( 2.24%) 1188.50 ( 0.41%)
Max syst-fsmark 4114.18 ( 0.00%) 4075.45 ( 0.94%) 3987.65 ( 3.08%) 4019.45 ( 2.30%) 4082.80 ( 0.76%)
Max real-xfsrepair 457.80 ( 0.00%) 474.60 ( -3.67%) 457.82 ( -0.00%) 444.42 ( 2.92%) 441.03 ( 3.66%)
Max syst-xfsrepair 203.11 ( 0.00%) 303.65 (-49.50%) 294.35 (-44.92%) 205.33 ( -1.09%) 155.28 ( 23.55%)
The really relevant lines as syst-xfsrepair which is the system CPU
usage when running xfsrepair. Note that on my machine the overhead was
45% higher on 4.0-rc4 which may be part of what Dave is seeing. Once we
preserve the write bit across faults, it's only 2.51% higher on average.
With the full series applied, system CPU usage is 24.6% lower on
average.
Again, the impact of preserving the write bit on minor faults is obvious
and the impact of slowing scanning after migration failures is obvious
on the PTE updates. Note also that the number of pages migrated is much
reduced even though the headline performance is comparable.
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8
Minor Faults 153466827 254507978 249163829 153501373 105737890
Major Faults 610 702 690 649 724
NUMA base PTE updates 217735049 210756527 217729596 216937111 144344993
NUMA huge PMD updates 129294 85044 106921 127246 79887
NUMA pages migrated 21938995 29705270 28594162 22687324 16258075
3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4
vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8
Mean sdb-avgqusz 13.47 2.54 2.55 2.47 2.49
Mean sdb-avgrqsz 202.32 140.22 139.50 139.02 138.12
Mean sdb-await 25.92 5.09 5.33 5.02 5.22
Mean sdb-r_await 4.71 0.19 0.83 0.51 0.11
Mean sdb-w_await 104.13 5.21 5.38 5.05 5.32
Mean sdb-svctm 0.59 0.13 0.14 0.13 0.14
Mean sdb-rrqm 0.16 0.00 0.00 0.00 0.00
Mean sdb-wrqm 3.59 1799.43 1826.84 1812.21 1785.67
Max sdb-avgqusz 111.06 12.13 14.05 11.66 15.60
Max sdb-avgrqsz 255.60 190.34 190.01 187.33 191.78
Max sdb-await 168.24 39.28 49.22 44.64 65.62
Max sdb-r_await 660.00 52.00 280.00 76.00 12.00
Max sdb-w_await 7804.00 39.28 49.22 44.64 65.62
Max sdb-svctm 4.00 2.82 2.86 1.98 2.84
Max sdb-rrqm 8.30 0.00 0.00 0.00 0.00
Max sdb-wrqm 34.20 5372.80 5278.60 5386.60 5546.15
FWIW, I also checked SPECjbb in different configurations but it's
similar observations -- minor faults lower, PTE update activity lower
and performance is roughly comparable against 3.19.
This patch (of 3):
Threads that share writable data within pages are grouped together as
related tasks. This decision is based on whether the PTE is marked
dirty which is subject to timing races between the PTE scanner update
and when the application writes the page. If the page is file-backed,
then background flushes and sync also affect placement. This is
unpredictable behaviour which is impossible to reason about so this
patch makes grouping decisions based on the VMA flags.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Fix B-tree corruption when a new record is inserted at position 0 in the
node in hfs_brec_insert(). In this case a hfs_brec_update_parent() is
called to update the parent index node (if exists) and it is passed
hfs_find_data with a search_key containing a newly inserted key instead
of the key to be updated. This results in an inconsistent index node.
The bug reproduces on my machine after an extents overflow record for
the catalog file (CNID=4) is inserted into the extents overflow B-tree.
Because of a low (reserved) value of CNID=4, it has to become the first
record in the first leaf node.
The resulting first leaf node is correct:
----------------------------------------------------
| key0.CNID=4 | key1.CNID=123 | key2.CNID=456, ... |
----------------------------------------------------
But the parent index key0 still contains the previous key CNID=123:
-----------------------
| key0.CNID=123 | ... |
-----------------------
A change in hfs_brec_insert() makes hfs_brec_update_parent() work
correctly by preventing it from getting fd->record=-1 value from
__hfs_brec_find().
Along the way, I removed duplicate code with unification of the if
condition. The resulting code is equivalent to the original code
because node is never 0.
Also hfs_brec_update_parent() will now return an error after getting a
negative fd->record value. However, the return value of
hfs_brec_update_parent() is not checked anywhere in the file and I'm
leaving it unchanged by this patch. brec.c lacks error checking after
some other calls too, but this issue is of less importance than the one
being fixed by this patch.
Signed-off-by: Sergei Antonov <saproj@gmail.com>
Cc: Joe Perches <joe@perches.com>
Reviewed-by: Vyacheslav Dubeyko <slava@dubeyko.com>
Acked-by: Hin-Tak Leung <htl10@users.sourceforge.net>
Cc: Anton Altaparmakov <aia21@cam.ac.uk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
I am familiar with these drivers and I care about them so let me add
myself as their maintainer.
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Acked-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
When affs_bread_ino() fails, correctly unlock the page and release the
page cache with proper error value. All write_end() should
unlock/release the page that was locked by write_beg().
Signed-off-by: Taesoo Kim <tsgatesv@gmail.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Commit 3c605096d315 ("mm/page_alloc: restrict max order of merging on
isolated pageblock") changed the logic of unset_migratetype_isolate to
check the buddy allocator and explicitly call __free_pages to merge.
The page that is being freed in this path never had prep_new_page called
so set_page_refcounted is called explicitly but there is no call to
kernel_map_pages. With the default kernel_map_pages this is mostly
harmless but if kernel_map_pages does any manipulation of the page
tables (unmapping or setting pages to read only) this may trigger a
fault:
alloc_contig_range test_pages_isolated(ceb00, ced00) failed
Unable to handle kernel paging request at virtual address ffffffc0cec00000
pgd = ffffffc045fc4000
[ffffffc0cec00000] *pgd=0000000000000000
Internal error: Oops: 9600004f [#1] PREEMPT SMP
Modules linked in: exfatfs
CPU: 1 PID: 23237 Comm: TimedEventQueue Not tainted 3.10.49-gc72ad36-dirty #1
task: ffffffc03de52100 ti: ffffffc015388000 task.ti: ffffffc015388000
PC is at memset+0xc8/0x1c0
LR is at kernel_map_pages+0x1ec/0x244
Fix this by calling kernel_map_pages to ensure the page is set in the
page table properly
Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock")
Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Gioh Kim <gioh.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Commit 9aabf810a67c ("mm/slub: optimize alloc/free fastpath by removing
preemption on/off") introduced an occasional hang for kernels built with
CONFIG_PREEMPT && !CONFIG_SMP.
The problem is the following loop the patch introduced to
slab_alloc_node and slab_free:
do {
tid = this_cpu_read(s->cpu_slab->tid);
c = raw_cpu_ptr(s->cpu_slab);
} while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
GCC 4.9 has been observed to hoist the load of c and c->tid above the
loop for !SMP kernels (as in this case raw_cpu_ptr(x) is compile-time
constant and does not force a reload). On arm64 the generated assembly
looks like:
ldr x4, [x0,#8]
loop:
ldr x1, [x0,#8]
cmp x1, x4
b.ne loop
If the thread is preempted between the load of c->tid (into x1) and tid
(into x4), and an allocation or free occurs in another thread (bumping
the cpu_slab's tid), the thread will be stuck in the loop until
s->cpu_slab->tid wraps, which may be forever in the absence of
allocations/frees on the same CPU.
This patch changes the loop condition to access c->tid with READ_ONCE.
This ensures that the value is reloaded even when the compiler would
otherwise assume it could cache the value, and also ensures that the
load will not be torn.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Steve Capper <steve.capper@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
Nicholas Mc Guire
Dan Ehrenberg
Mike Snitzer
Joe Thornber
Wei Fang
Xiaoguang Wang
Linus Torvalds
Dave Martin
James Hogan
Dan Carpenter
Daniel Vetter
Damien Lespiau
Hui Wang
Maxime Ripard
Richard Weinberger
Chris Wilson
Libin Yang
Vineet Gupta
Mel Gorman
Sergei Antonov
Jean Delvare
Taesoo Kim
Laura Abbott
Mark Rutland