delayed_work submitted to an offlined cpu, will not get executed,
after the specified delay if the cpu remains offline. If the cpu
never comes online the work will never get executed.
checking for online cpu in __queue_delayed_work, does not sound
like a good idea because to do this reliably we need hotplug lock
and since work may be submitted from atomic contexts, we would
have to use cpus_read_trylock. But if trylock fails we would queue
the work on any cpu and this may not be optimal because our intended
cpu might still be online.
Putting a WARN_ON_ONCE for an already offlined cpu, will indicate users
of queue_delayed_work_on, if they are (wrongly) trying to queue
delayed_work on offlined cpu. Also indicate the problem of using
offlined cpu with queue_delayed_work_on, in its description.
Signed-off-by: Imran Khan <imran.f.khan@oracle.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
kthread_create() creates a kthread without running it yet. kthread_run()
creates a kthread and runs it.
On the other hand, kthread_create_worker() creates a kthread worker and
runs it.
This difference in behaviours is confusing. Also there is no way to
create a kthread worker and affine it using kthread_bind_mask() or
kthread_affine_preferred() before starting it.
Consolidate the behaviours and introduce kthread_run_worker[_on_cpu]()
that behaves just like kthread_run(). kthread_create_worker[_on_cpu]()
will now only create a kthread worker without starting it.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
After commit
746ae46c11 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
amdgpu started seeing the following warning:
[ ] workqueue: WQ_MEM_RECLAIM sdma0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_device_delay_enable_gfx_off [amdgpu]
...
[ ] Workqueue: sdma0 drm_sched_run_job_work [gpu_sched]
...
[ ] Call Trace:
[ ] <TASK>
...
[ ] ? check_flush_dependency+0xf5/0x110
...
[ ] cancel_delayed_work_sync+0x6e/0x80
[ ] amdgpu_gfx_off_ctrl+0xab/0x140 [amdgpu]
[ ] amdgpu_ring_alloc+0x40/0x50 [amdgpu]
[ ] amdgpu_ib_schedule+0xf4/0x810 [amdgpu]
[ ] ? drm_sched_run_job_work+0x22c/0x430 [gpu_sched]
[ ] amdgpu_job_run+0xaa/0x1f0 [amdgpu]
[ ] drm_sched_run_job_work+0x257/0x430 [gpu_sched]
[ ] process_one_work+0x217/0x720
...
[ ] </TASK>
The intent of the verifcation done in check_flush_depedency is to ensure
forward progress during memory reclaim, by flagging cases when either a
memory reclaim process, or a memory reclaim work item is flushed from a
context not marked as memory reclaim safe.
This is correct when flushing, but when called from the
cancel(_delayed)_work_sync() paths it is a false positive because work is
either already running, or will not be running at all. Therefore
cancelling it is safe and we can relax the warning criteria by letting the
helper know of the calling context.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: fca839c00a ("workqueue: warn if memory reclaim tries to flush !WQ_MEM_RECLAIM workqueue")
References: 746ae46c11 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
Cc: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v4.5+
Signed-off-by: Tejun Heo <tj@kernel.org>
For unbound workqueue, pwqs usually map to just a few pools. Most of
the time, pwqs will be linked sequentially to wq->pwqs list by cpu
index. Usually, consecutive CPUs have the same workqueue attribute
(e.g. belong to the same NUMA node). This makes pwqs with the same
pool cluster together in the pwq list.
Only do lock/unlock if the pool has changed in flush_workqueue_prep_pwqs().
This reduces the number of expensive lock operations.
The performance data shows this change boosts FIO by 65x in some cases
when multiple concurrent threads write to xfs mount points with fsync.
FIO Benchmark Details
- FIO version: v3.35
- FIO Options: ioengine=libaio,iodepth=64,norandommap=1,rw=write,
size=128M,bs=4k,fsync=1
- FIO Job Configs: 64 jobs in total writing to 4 mount points (ramdisks
formatted as xfs file system).
- Kernel Codebase: v6.12-rc5
- Test Platform: Xeon 8380 (2 sockets)
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Wangyang Guo <wangyang.guo@intel.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Marc Hartmayer reported:
[ 23.133876] Unable to handle kernel pointer dereference in virtual kernel address space
[ 23.133950] Failing address: 0000000000000000 TEID: 0000000000000483
[ 23.133954] Fault in home space mode while using kernel ASCE.
[ 23.133957] AS:000000001b8f0007 R3:0000000056cf4007 S:0000000056cf3800 P:000000000000003d
[ 23.134207] Oops: 0004 ilc:2 [#1] SMP
(snip)
[ 23.134516] Call Trace:
[ 23.134520] [<0000024e326caf28>] worker_thread+0x48/0x430
[ 23.134525] ([<0000024e326caf18>] worker_thread+0x38/0x430)
[ 23.134528] [<0000024e326d3a3e>] kthread+0x11e/0x130
[ 23.134533] [<0000024e3264b0dc>] __ret_from_fork+0x3c/0x60
[ 23.134536] [<0000024e333fb37a>] ret_from_fork+0xa/0x38
[ 23.134552] Last Breaking-Event-Address:
[ 23.134553] [<0000024e333f4c04>] mutex_unlock+0x24/0x30
[ 23.134562] Kernel panic - not syncing: Fatal exception: panic_on_oops
With debuging and analysis, worker_thread() accesses to the nullified
worker->pool when the newly created worker is destroyed before being
waken-up, in which case worker_thread() can see the result detach_worker()
reseting worker->pool to NULL at the begining.
Move the code "worker->pool = NULL;" out from detach_worker() to fix the
problem.
worker->pool had been designed to be constant for regular workers and
changeable for rescuer. To share attaching/detaching code for regular
and rescuer workers and to avoid worker->pool being accessed inadvertently
when the worker has been detached, worker->pool is reset to NULL when
detached no matter the worker is rescuer or not.
To maintain worker->pool being reset after detached, move the code
"worker->pool = NULL;" in the worker thread context after detached.
It is either be in the regular worker thread context after PF_WQ_WORKER
is cleared or in rescuer worker thread context with wq_pool_attach_mutex
held. So it is safe to do so.
Cc: Marc Hartmayer <mhartmay@linux.ibm.com>
Link: https://lore.kernel.org/lkml/87wmjj971b.fsf@linux.ibm.com/
Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Fixes: f4b7b53c94 ("workqueue: Detach workers directly in idle_cull_fn()")
Cc: stable@vger.kernel.org # v6.11+
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Make tags always produces below annoying warnings:
ctags: Warning: kernel/workqueue.c:470: null expansion of name pattern "\1"
ctags: Warning: kernel/workqueue.c:474: null expansion of name pattern "\1"
ctags: Warning: kernel/workqueue.c:478: null expansion of name pattern "\1"
In commit 25528213fe ("tags: Fix DEFINE_PER_CPU expansions"), codes in
places have been adjusted including cpu_worker_pools definition. I noticed
in commit 4cb1ef6460 ("workqueue: Implement BH workqueues to eventually
replace tasklets"), cpu_worker_pools definition was unfolded back. Not
sure if it was intentionally done or ignored carelessly.
Makes change to mute them specifically.
Signed-off-by: Baoquan He <bhe@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
wq->lockdep_map is set only after __alloc_workqueue()
successfully returns. However, on its error path
__alloc_workqueue() may call destroy_workqueue() which
expects wq->lockdep_map to be already set, which results
in a null-ptr-deref in touch_wq_lockdep_map().
Add a simple NULL-check to touch_wq_lockdep_map().
Oops: general protection fault, probably for non-canonical address
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:__lock_acquire+0x81/0x7800
[..]
Call Trace:
<TASK>
? __die_body+0x66/0xb0
? die_addr+0xb2/0xe0
? exc_general_protection+0x300/0x470
? asm_exc_general_protection+0x22/0x30
? __lock_acquire+0x81/0x7800
? mark_lock+0x94/0x330
? __lock_acquire+0x12fd/0x7800
? __lock_acquire+0x3439/0x7800
lock_acquire+0x14c/0x3e0
? __flush_workqueue+0x167/0x13a0
? __init_swait_queue_head+0xaf/0x150
? __flush_workqueue+0x167/0x13a0
__flush_workqueue+0x17d/0x13a0
? __flush_workqueue+0x167/0x13a0
? lock_release+0x50f/0x830
? drain_workqueue+0x94/0x300
drain_workqueue+0xe3/0x300
destroy_workqueue+0xac/0xc40
? workqueue_sysfs_register+0x159/0x2f0
__alloc_workqueue+0x1506/0x1760
alloc_workqueue+0x61/0x150
...
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Calling va_start / va_end multiple times is undefined and causes
problems with certain compiler / platforms.
Change alloc_ordered_workqueue_lockdep_map to a macro and updated
__alloc_workqueue to take a va_list argument.
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Add an interface for a user-defined workqueue lockdep map, which is
helpful when multiple workqueues are created for the same purpose. This
also helps avoid leaking lockdep maps on each workqueue creation.
v2:
- Add alloc_workqueue_lockdep_map (Tejun)
v3:
- Drop __WQ_USER_OWNED_LOCKDEP (Tejun)
- static inline alloc_ordered_workqueue_lockdep_map (Tejun)
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Will help enable user-defined lockdep maps for workqueues.
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Will help enable user-defined lockdep maps for workqueues.
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
When we want to debug the workqueue stall, we can immediately make
a panic to get the information we want.
In some systems, it may be necessary to quickly reboot the system to
escape from a workqueue lockup situation. In this case, we can control
the number of stall detections to generate panic.
workqueue.panic_on_stall sets the number times of the stall to trigger
panic. 0 disables the panic on stall.
Signed-off-by: Sangmoon Kim <sangmoon.kim@samsung.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
cpu_pwq is used in various percpu functions that expect variable in
__percpu address space. Correct the declaration of cpu_pwq to
struct pool_workqueue __rcu * __percpu *cpu_pwq
to declare the variable as __percpu pointer.
The patch also fixes following sparse errors:
workqueue.c:380:37: warning: duplicate [noderef]
workqueue.c:380:37: error: multiple address spaces given: __rcu & __percpu
workqueue.c:2271:15: error: incompatible types in comparison expression (different address spaces):
workqueue.c:2271:15: struct pool_workqueue [noderef] __rcu *
workqueue.c:2271:15: struct pool_workqueue [noderef] __percpu *
and uncovers a couple of exisiting "incorrect type in assignment"
warnings (from __rcu address space), which this patch does not address.
Found by GCC's named address space checks.
There were no changes in the resulting object files.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
When flushing a work item for cancellation, __flush_work() knows that it
exclusively owns the work item through its PENDING bit. 134874e2ee
("workqueue: Allow cancel_work_sync() and disable_work() from atomic
contexts on BH work items") added a read of @work->data to determine whether
to use busy wait for BH work items that are being canceled. While the read
is safe when @from_cancel, @work->data was read before testing @from_cancel
to simplify code structure:
data = *work_data_bits(work);
if (from_cancel &&
!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) {
While the read data was never used if !@from_cancel, this could trigger
KCSAN data race detection spuriously:
==================================================================
BUG: KCSAN: data-race in __flush_work / __flush_work
write to 0xffff8881223aa3e8 of 8 bytes by task 3998 on cpu 0:
instrument_write include/linux/instrumented.h:41 [inline]
___set_bit include/asm-generic/bitops/instrumented-non-atomic.h:28 [inline]
insert_wq_barrier kernel/workqueue.c:3790 [inline]
start_flush_work kernel/workqueue.c:4142 [inline]
__flush_work+0x30b/0x570 kernel/workqueue.c:4178
flush_work kernel/workqueue.c:4229 [inline]
...
read to 0xffff8881223aa3e8 of 8 bytes by task 50 on cpu 1:
__flush_work+0x42a/0x570 kernel/workqueue.c:4188
flush_work kernel/workqueue.c:4229 [inline]
flush_delayed_work+0x66/0x70 kernel/workqueue.c:4251
...
value changed: 0x0000000000400000 -> 0xffff88810006c00d
Reorganize the code so that @from_cancel is tested before @work->data is
accessed. The only problem is triggering KCSAN detection spuriously. This
shouldn't need READ_ONCE() or other access qualifiers.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: syzbot+b3e4f2f51ed645fd5df2@syzkaller.appspotmail.com
Fixes: 134874e2ee ("workqueue: Allow cancel_work_sync() and disable_work() from atomic contexts on BH work items")
Link: http://lkml.kernel.org/r/000000000000ae429e061eea2157@google.com
Cc: Jens Axboe <axboe@kernel.dk>
- Lai fixed a bug where CPU hotplug and workqueue attribute changes race
leaving some workqueues not fully updated. This involved refactoring and
changing how online CPUs are tracked. The resulting code is cleaner.
- Workqueue watchdog touch operation was causing too much cacheline
contention on very large machines. Nicholas improved scalabililty by
avoiding unnecessary global updates.
- Code cleanups and minor rescuer behavior improvement.
- The last commit 58629d4871 ("workqueue: Always queue work items to the
newest PWQ for order workqueues") is a cherry-picked straggler commit from
for-6.10-fixes, a fix for a bug which may not actually trigger.
Unfortunately, maybe because for-6.10-fixes was branched off at a
different point from for-6.11, I couldn't persuade git request-pull to
generate clean diffstat if pulled into for-6.11.
-----BEGIN PGP SIGNATURE-----
iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCZpSn2g4cdGpAa2VybmVs
Lm9yZwAKCRCxYfJx3gVYGe4UAQCc4Zo2qShh6M97r7K5Epa0XmHKqGcOvafiEZQx
qwXfyAD9HWBrwPfdA+L1hHnMRTtZJapvWnBRK/swdg8Rou5Grgk=
=t60j
-----END PGP SIGNATURE-----
Merge tag 'wq-for-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq
Pull workqueue updates from Tejun Heo:
- Lai fixed a bug where CPU hotplug and workqueue attribute changes
race leaving some workqueues not fully updated. This involved
refactoring and changing how online CPUs are tracked. The resulting
code is cleaner.
- Workqueue watchdog touch operation was causing too much cacheline
contention on very large machines. Nicholas improved scalabililty by
avoiding unnecessary global updates.
- Code cleanups and minor rescuer behavior improvement.
- The last commit 58629d4871 ("workqueue: Always queue work items to
the newest PWQ for order workqueues") is a cherry-picked straggler
commit from for-6.10-fixes, a fix for a bug which may not actually
trigger.
* tag 'wq-for-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (24 commits)
workqueue: Always queue work items to the newest PWQ for order workqueues
workqueue: Rename wq_update_pod() to unbound_wq_update_pwq()
workqueue: Remove the arguments @hotplug_cpu and @online from wq_update_pod()
workqueue: Remove the argument @cpu_going_down from wq_calc_pod_cpumask()
workqueue: Remove the unneeded cpumask empty check in wq_calc_pod_cpumask()
workqueue: Remove cpus_read_lock() from apply_wqattrs_lock()
workqueue: Simplify wq_calc_pod_cpumask() with wq_online_cpumask
workqueue: Add wq_online_cpumask
workqueue: Init rescuer's affinities as the wq's effective cpumask
workqueue: Put PWQ allocation and WQ enlistment in the same lock C.S.
workqueue: Move kthread_flush_worker() out of alloc_and_link_pwqs()
workqueue: Make rescuer initialization as the last step of the creation of a new wq
workqueue: Register sysfs after the whole creation of the new wq
workqueue: Simplify goto statement
workqueue: Update cpumasks after only applying it successfully
workqueue: Improve scalability of workqueue watchdog touch
workqueue: wq_watchdog_touch is always called with valid CPU
workqueue: Remove useless pool->dying_workers
workqueue: Detach workers directly in idle_cull_fn()
workqueue: Don't bind the rescuer in the last working cpu
...
To ensure non-reentrancy, __queue_work() attempts to enqueue a work
item to the pool of the currently executing worker. This is not only
unnecessary for an ordered workqueue, where order inherently suggests
non-reentrancy, but it could also disrupt the sequence if the item is
not enqueued on the newest PWQ.
Just queue it to the newest PWQ and let order management guarantees
non-reentrancy.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Fixes: 4c065dbce1 ("workqueue: Enable unbound cpumask update on ordered workqueues")
Cc: stable@vger.kernel.org # v6.9+
Signed-off-by: Tejun Heo <tj@kernel.org>
(cherry picked from commit 74347be3edfd11277799242766edf844c43dd5d3)
What wq_update_pod() does is just to update the pwq of the specific
cpu. Rename it and update the comments.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The arguments @hotplug_cpu and @online are not used in wq_update_pod()
since the functions called by wq_update_pod() don't need them.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
wq_calc_pod_cpumask() uses wq_online_cpumask, which excludes the cpu
going down, so the argument cpu_going_down is unused and can be removed.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The cpumask empty check in wq_calc_pod_cpumask() has long been useless.
It just works purely as documents which states that the cpumask is not
possible empty after the function returns.
Now the code above is even more explicit that the cpumask is not empty,
so the document-only empty check can be removed.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
1726a17135 ("workqueue: Put PWQ allocation and WQ enlistment in the same
lock C.S.") led to the following possible deadlock:
WARNING: possible recursive locking detected
6.10.0-rc5-00004-g1d4c6111406c #1 Not tainted
--------------------------------------------
swapper/0/1 is trying to acquire lock:
c27760f4 (cpu_hotplug_lock){++++}-{0:0}, at: alloc_workqueue (kernel/workqueue.c:5152 kernel/workqueue.c:5730)
but task is already holding lock:
c27760f4 (cpu_hotplug_lock){++++}-{0:0}, at: padata_alloc (kernel/padata.c:1007)
...
stack backtrace:
...
cpus_read_lock (include/linux/percpu-rwsem.h:53 kernel/cpu.c:488)
alloc_workqueue (kernel/workqueue.c:5152 kernel/workqueue.c:5730)
padata_alloc (kernel/padata.c:1007 (discriminator 1))
pcrypt_init_padata (crypto/pcrypt.c:327 (discriminator 1))
pcrypt_init (crypto/pcrypt.c:353)
do_one_initcall (init/main.c:1267)
do_initcalls (init/main.c:1328 (discriminator 1) init/main.c:1345 (discriminator 1))
kernel_init_freeable (init/main.c:1364)
kernel_init (init/main.c:1469)
ret_from_fork (arch/x86/kernel/process.c:153)
ret_from_fork_asm (arch/x86/entry/entry_32.S:737)
entry_INT80_32 (arch/x86/entry/entry_32.S:944)
This is caused by pcrypt allocating a workqueue while holding
cpus_read_lock(), so workqueue code can't do it again as that can lead to
deadlocks if down_write starts after the first down_read.
The pwq creations and installations have been reworked based on
wq_online_cpumask rather than cpu_online_mask making cpus_read_lock() is
unneeded during wqattrs changes. Fix the deadlock by removing
cpus_read_lock() from apply_wqattrs_lock().
tj: Updated changelog.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Fixes: 1726a17135 ("workqueue: Put PWQ allocation and WQ enlistment in the same lock C.S.")
Link: http://lkml.kernel.org/r/202407081521.83b627c1-lkp@intel.com
Signed-off-by: Tejun Heo <tj@kernel.org>
Avoid relying on cpu_online_mask for wqattrs changes so that
cpus_read_lock() can be removed from apply_wqattrs_lock().
And with wq_online_cpumask, attrs->__pod_cpumask doesn't need to be
reused as a temporary storage to calculate if the pod have any online
CPUs @attrs wants since @cpu_going_down is not in the wq_online_cpumask.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The new wq_online_mask mirrors the cpu_online_mask except during
hotplugging; specifically, it differs between the hotplugging stages
of workqueue_offline_cpu() and workqueue_online_cpu(), during which
the transitioning CPU is not represented in the mask.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Make it consistent with apply_wqattrs_commit().
Link: https://lore.kernel.org/lkml/20240203154334.791910-5-longman@redhat.com/
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The PWQ allocation and WQ enlistment are not within the same lock-held
critical section; therefore, their states can become out of sync when
the user modifies the unbound mask or if CPU hotplug events occur in
the interim since those operations only update the WQs that are already
in the list.
Make the PWQ allocation and WQ enlistment atomic.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
kthread_flush_worker() can't be called with wq_pool_mutex held.
Prepare for moving wq_pool_mutex and cpu hotplug lock out of
alloc_and_link_pwqs().
Cc: Zqiang <qiang.zhang1211@gmail.com>
Link: https://lore.kernel.org/lkml/20230920060704.24981-1-qiang.zhang1211@gmail.com/
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
For early wq allocation, rescuer initialization is the last step of the
creation of a new wq. Make the behavior the same for all allocations.
Prepare for initializing rescuer's affinities with the default pwq's
affinities.
Prepare for moving the whole workqueue initializing procedure into
wq_pool_mutex and cpu hotplug locks.
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
workqueue creation includes adding it to the workqueue list.
Prepare for moving the whole workqueue initializing procedure into
wq_pool_mutex and cpu hotplug locks.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Use a simple if-statement to replace the cumbersome goto-statement in
workqueue_set_unbound_cpumask().
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Make workqueue_unbound_exclude_cpumask() and workqueue_set_unbound_cpumask()
only update wq_isolated_cpumask and wq_requested_unbound_cpumask when
workqueue_apply_unbound_cpumask() returns successfully.
Fixes: fe28f631fa94("workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask")
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
On a ~2000 CPU powerpc system, hard lockups have been observed in the
workqueue code when stop_machine runs (in this case due to CPU hotplug).
This is due to lots of CPUs spinning in multi_cpu_stop, calling
touch_nmi_watchdog() which ends up calling wq_watchdog_touch().
wq_watchdog_touch() writes to the global variable wq_watchdog_touched,
and that can find itself in the same cacheline as other important
workqueue data, which slows down operations to the point of lockups.
In the case of the following abridged trace, worker_pool_idr was in
the hot line, causing the lockups to always appear at idr_find.
watchdog: CPU 1125 self-detected hard LOCKUP @ idr_find
Call Trace:
get_work_pool
__queue_work
call_timer_fn
run_timer_softirq
__do_softirq
do_softirq_own_stack
irq_exit
timer_interrupt
decrementer_common_virt
* interrupt: 900 (timer) at multi_cpu_stop
multi_cpu_stop
cpu_stopper_thread
smpboot_thread_fn
kthread
Fix this by having wq_watchdog_touch() only write to the line if the
last time a touch was recorded exceeds 1/4 of the watchdog threshold.
Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Warn in the case it is called with cpu == -1. This does not appear
to happen anywhere.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
A dying worker is first moved from pool->workers to pool->dying_workers
in set_worker_dying() and removed from pool->dying_workers in
detach_dying_workers(). The whole procedure is in the some lock context
of wq_pool_attach_mutex.
So pool->dying_workers is useless, just remove it and keep the dying
worker in pool->workers after set_worker_dying() and remove it in
detach_dying_workers() with wq_pool_attach_mutex held.
Cc: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The code to kick off the destruction of workers is now in a process
context (idle_cull_fn()), and the detaching of a worker is not required
to be inside the worker thread now, so just do the detaching directly
in idle_cull_fn().
wake_dying_workers() is renamed to detach_dying_workers() and the unneeded
wakeup in wake_dying_workers() is also removed.
Cc: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
So that when the rescuer is woken up next time, it will not interrupt
the last working cpu which might be busy on other crucial works but
have nothing to do with the rescuer's incoming works.
Cc: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The code to kick off the destruction of workers is now in a process
context (idle_cull_fn()), so kthread_stop() can be used in the process
context to replace the work of pool->detach_completion.
The wakeup in wake_dying_workers() is unneeded after this change, but it
is harmless, jut keep it here until next patch renames wake_dying_workers()
rather than renaming it again and again.
Cc: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Current try_to_grab_pending() activates the inactive item and
subsequently treats it as though it were a standard activated item.
This approach prevents duplicating handling logic for both active and
inactive items, yet the premature activation of an inactive item
triggers trace_workqueue_activate_work(), yielding an unintended user
space visible side effect.
And the unnecessary increment of the nr_active, which is not a simple
counter now, followed by a counteracted decrement, is inefficient and
complicates the code.
Just remove the nr_active manipulation code in grabbing inactive items.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Since SLOB was removed, it is not necessary to use call_rcu
when the callback only performs kmem_cache_free. Use
kfree_rcu() directly.
The changes were done using the following Coccinelle semantic patch.
This semantic patch is designed to ignore cases where the callback
function is used in another way.
// <smpl>
@r@
expression e;
local idexpression e2;
identifier cb,f;
position p;
@@
(
call_rcu(...,e2)
|
call_rcu(&e->f,cb@p)
)
@r1@
type T;
identifier x,r.cb;
@@
cb(...) {
(
kmem_cache_free(...);
|
T x = ...;
kmem_cache_free(...,x);
|
T x;
x = ...;
kmem_cache_free(...,x);
)
}
@s depends on r1@
position p != r.p;
identifier r.cb;
@@
cb@p
@script:ocaml@
cb << r.cb;
p << s.p;
@@
Printf.eprintf "Other use of %s at %s:%d\n"
cb (List.hd p).file (List.hd p).line
@depends on r1 && !s@
expression e;
identifier r.cb,f;
position r.p;
@@
- call_rcu(&e->f,cb@p)
+ kfree_rcu(e,f)
@r1a depends on !s@
type T;
identifier x,r.cb;
@@
- cb(...) {
(
- kmem_cache_free(...);
|
- T x = ...;
- kmem_cache_free(...,x);
|
- T x;
- x = ...;
- kmem_cache_free(...,x);
)
- }
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
wq->flags would not change, so it's not necessary to check if WQ_BH
is set in loop for_each_possible_cpu(), move define and set of pools
out of loop to simpliy the code.
Signed-off-by: Wenchao Hao <haowenchao22@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Currently, worker ID formatting is open coded in create_worker(),
init_rescuer() and worker_thread() (for %WORKER_DIE case). The formatted ID
is saved into task->comm and wq_worker_comm() uses it as the base name to
append extra information to when generating the name to be shown to
userspace.
However, TASK_COMM_LEN is only 16 leading to badly truncated names for
rescuers. For example, the rescuer for the inet_frag_wq workqueue becomes:
$ ps -ef | grep '[k]worker/R-inet'
root 483 2 0 Apr26 ? 00:00:00 [kworker/R-inet_]
Even for non-rescue workers, it's easy to run over 15 characters on
moderately large machines.
Fit it by consolidating worker ID formatting into a new helper
format_worker_id() and calling it from wq_worker_comm() to obtain the
untruncated worker ID string.
$ ps -ef | grep '[k]worker/R-inet'
root 60 2 0 12:10 ? 00:00:00 [kworker/R-inet_frag_wq]
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Jan Engelhardt <jengelh@inai.de>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
- Add cpufreq pressure feedback for the scheduler
- Rework misfit load-balancing wrt. affinity restrictions
- Clean up and simplify the code around ::overutilized and
::overload access.
- Simplify sched_balance_newidle()
- Bump SCHEDSTAT_VERSION to 16 due to a cleanup of CPU_MAX_IDLE_TYPES
handling that changed the output.
- Rework & clean up <asm/vtime.h> interactions wrt. arch_vtime_task_switch()
- Reorganize, clean up and unify most of the higher level
scheduler balancing function names around the sched_balance_*()
prefix.
- Simplify the balancing flag code (sched_balance_running)
- Miscellaneous cleanups & fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=obph
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Add cpufreq pressure feedback for the scheduler
- Rework misfit load-balancing wrt affinity restrictions
- Clean up and simplify the code around ::overutilized and
::overload access.
- Simplify sched_balance_newidle()
- Bump SCHEDSTAT_VERSION to 16 due to a cleanup of CPU_MAX_IDLE_TYPES
handling that changed the output.
- Rework & clean up <asm/vtime.h> interactions wrt arch_vtime_task_switch()
- Reorganize, clean up and unify most of the higher level
scheduler balancing function names around the sched_balance_*()
prefix
- Simplify the balancing flag code (sched_balance_running)
- Miscellaneous cleanups & fixes
* tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
sched/pelt: Remove shift of thermal clock
sched/cpufreq: Rename arch_update_thermal_pressure() => arch_update_hw_pressure()
thermal/cpufreq: Remove arch_update_thermal_pressure()
sched/cpufreq: Take cpufreq feedback into account
cpufreq: Add a cpufreq pressure feedback for the scheduler
sched/fair: Fix update of rd->sg_overutilized
sched/vtime: Do not include <asm/vtime.h> header
s390/irq,nmi: Include <asm/vtime.h> header directly
s390/vtime: Remove unused __ARCH_HAS_VTIME_TASK_SWITCH leftover
sched/vtime: Get rid of generic vtime_task_switch() implementation
sched/vtime: Remove confusing arch_vtime_task_switch() declaration
sched/balancing: Simplify the sg_status bitmask and use separate ->overloaded and ->overutilized flags
sched/fair: Rename set_rd_overutilized_status() to set_rd_overutilized()
sched/fair: Rename SG_OVERLOAD to SG_OVERLOADED
sched/fair: Rename {set|get}_rd_overload() to {set|get}_rd_overloaded()
sched/fair: Rename root_domain::overload to ::overloaded
sched/fair: Use helper functions to access root_domain::overload
sched/fair: Check root_domain::overload value before update
sched/fair: Combine EAS check with root_domain::overutilized access
sched/fair: Simplify the continue_balancing logic in sched_balance_newidle()
...
The default nna (node_nr_active) is used when the pool isn't tied to a
specific NUMA node. This can happen in the following cases:
1. On NUMA, if per-node pwq init failure and the fallback pwq is used.
2. On NUMA, if a pool is configured to span multiple nodes.
3. On single node setups.
5797b1c189 ("workqueue: Implement system-wide nr_active enforcement for
unbound workqueues") set the default nna->max to min_active because only #1
was being considered. For #2 and #3, using min_active means that the max
concurrency in normal operation is pushed down to min_active which is
currently 8, which can obviously lead to performance issues.
exact value nna->max is set to doesn't really matter. #2 can only happen if
the workqueue is intentionally configured to ignore NUMA boundaries and
there's no good way to distribute max_active in this case. #3 is the default
behavior on single node machines.
Let's set it the default nna->max to max_active. This fixes the artificially
lowered concurrency problem on single node machines and shouldn't hurt
anything for other cases.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Fixes: 5797b1c189 ("workqueue: Implement system-wide nr_active enforcement for unbound workqueues")
Link: https://lore.kernel.org/dm-devel/20240410084531.2134621-1-shinichiro.kawasaki@wdc.com/
Signed-off-by: Tejun Heo <tj@kernel.org>
With cpu_possible_mask=0-63 and cpu_online_mask=0-7 the following
kernel oops was observed:
smp: Bringing up secondary CPUs ...
smp: Brought up 1 node, 8 CPUs
Unable to handle kernel pointer dereference in virtual kernel address space
Failing address: 0000000000000000 TEID: 0000000000000803
[..]
Call Trace:
arch_vcpu_is_preempted+0x12/0x80
select_idle_sibling+0x42/0x560
select_task_rq_fair+0x29a/0x3b0
try_to_wake_up+0x38e/0x6e0
kick_pool+0xa4/0x198
__queue_work.part.0+0x2bc/0x3a8
call_timer_fn+0x36/0x160
__run_timers+0x1e2/0x328
__run_timer_base+0x5a/0x88
run_timer_softirq+0x40/0x78
__do_softirq+0x118/0x388
irq_exit_rcu+0xc0/0xd8
do_ext_irq+0xae/0x168
ext_int_handler+0xbe/0xf0
psw_idle_exit+0x0/0xc
default_idle_call+0x3c/0x110
do_idle+0xd4/0x158
cpu_startup_entry+0x40/0x48
rest_init+0xc6/0xc8
start_kernel+0x3c4/0x5e0
startup_continue+0x3c/0x50
The crash is caused by calling arch_vcpu_is_preempted() for an offline
CPU. To avoid this, select the cpu with cpumask_any_and_distribute()
to mask __pod_cpumask with cpu_online_mask. In case no cpu is left in
the pool, skip the assignment.
tj: This doesn't fully fix the bug as CPUs can still go down between picking
the target CPU and the wake call. Fixing that likely requires adding
cpu_online() test to either the sched or s390 arch code. However, regardless
of how that is fixed, workqueue shouldn't be picking a CPU which isn't
online as that would result in unpredictable and worse behavior.
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Fixes: 8639ecebc9 ("workqueue: Implement non-strict affinity scope for unbound workqueues")
Cc: stable@vger.kernel.org # v6.6+
Signed-off-by: Tejun Heo <tj@kernel.org>
While reviewing users of subsys_virtual_register() I noticed that
wq_sysfs_init() ignores the @groups argument. This looks like a
historical artifact as the original wq_subsys only had one attribute to
register.
On the way to building up an @groups argument to pass to
subsys_virtual_register() a few more cleanups fell out:
* Use DEVICE_ATTR_RO() and DEVICE_ATTR_RW() for
cpumask_{isolated,requested} and cpumask respectively. Rename the
@show and @store methods accordingly.
* Co-locate the attribute definition with the methods. This required
moving wq_unbound_cpumask_show down next to wq_unbound_cpumask_store
(renamed to cpumask_show() and cpumask_store())
* Use ATTRIBUTE_GROUPS() to skip some boilerplate declarations
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Allow more pools can be shared when attrs->affn_strict.
Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Now that work_grab_pending() can always grab the PENDING bit without
sleeping, the only thing that prevents allowing cancel_work_sync() of a BH
work item from an atomic context is the flushing of the in-flight instance.
When we're flushing a BH work item for cancel_work_sync(), we know that the
work item is not queued and must be executing in a BH context, which means
that it's safe to busy-wait for its completion from a non-hardirq atomic
context.
This patch updates __flush_work() so that it busy-waits when flushing a BH
work item for cancel_work_sync(). might_sleep() is pushed from
start_flush_work() to its callers - when operating on a BH work item,
__cancel_work_sync() now enforces !in_hardirq() instead of might_sleep().
This allows cancel_work_sync() and disable_work() to be called from
non-hardirq atomic contexts on BH work items.
v3: In __flush_work(), test WORK_OFFQ_BH to tell whether a work item being
canceled can be busy waited instead of making start_flush_work() return
the pool. (Lai)
v2: Lai pointed out that __flush_work() was accessing pool->flags outside
the RCU critical section protecting the pool pointer. Fix it by testing
and remembering the result inside the RCU critical section.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Add an off-queue flag, WORK_OFFQ_BH, that indicates whether the last
workqueue the work item was on was a BH one. This will be used to test
whether a work item is BH in cancel_sync path to implement atomic
cancel_sync'ing for BH work items.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
cancel[_delayed]_work_sync() guarantees that it can shut down
self-requeueing work items. To achieve that, it grabs and then holds
WORK_STRUCT_PENDING bit set while flushing the currently executing instance.
As the PENDING bit is set, all queueing attempts including the
self-requeueing ones fail and once the currently executing instance is
flushed, the work item should be idle as long as someone else isn't actively
queueing it.
This means that the cancel_work_sync path may hold the PENDING bit set while
flushing the target work item. This isn't a problem for the queueing path -
it can just fail which is the desired effect. It doesn't affect flush. It
doesn't matter to cancel_work either as it can just report that the work
item has successfully canceled. However, if there's another cancel_work_sync
attempt on the work item, it can't simply fail or report success and that
would breach the guarantee that it should provide. cancel_work_sync has to
wait for and grab that PENDING bit and go through the motions.
WORK_OFFQ_CANCELING and wq_cancel_waitq are what implement this
cancel_work_sync to cancel_work_sync wait mechanism. When a work item is
being canceled, WORK_OFFQ_CANCELING is also set on it and other
cancel_work_sync attempts wait on the bit to be cleared using the wait
queue.
While this works, it's an isolated wart which doesn't jive with the rest of
flush and cancel mechanisms and forces enable_work() and disable_work() to
require a sleepable context, which hampers their usability.
Now that a work item can be disabled, we can use that to block queueing
while cancel_work_sync is in progress. Instead of holding PENDING the bit,
it can temporarily disable the work item, flush and then re-enable it as
that'd achieve the same end result of blocking queueings while canceling and
thus enable canceling of self-requeueing work items.
- WORK_OFFQ_CANCELING and the surrounding mechanims are removed.
- work_grab_pending() is now simpler, no longer has to wait for a blocking
operation and thus can be called from any context.
- With work_grab_pending() simplified, no need to use try_to_grab_pending()
directly. All users are converted to use work_grab_pending().
- __cancel_work_sync() is updated to __cancel_work() with
WORK_CANCEL_DISABLE to cancel and plug racing queueing attempts. It then
flushes and re-enables the work item if necessary.
- These changes allow disable_work() and enable_work() to be called from any
context.
v2: Lai pointed out that mod_delayed_work_on() needs to check the disable
count before queueing the delayed work item. Added
clear_pending_if_disabled() call.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
While (delayed) work items could be flushed and canceled, there was no way
to prevent them from being queued in the future. While this didn't lead to
functional deficiencies, it sometimes required a bit more effort from the
workqueue users to e.g. sequence shutdown steps with more care.
Workqueue is currently in the process of replacing tasklet which does
support disabling and enabling. The feature is used relatively widely to,
for example, temporarily suppress main path while a control plane operation
(reset or config change) is in progress.
To enable easy conversion of tasklet users and as it seems like an inherent
useful feature, this patch implements disabling and enabling of work items.
- A work item carries 16bit disable count in work->data while not queued.
The access to the count is synchronized by the PENDING bit like all other
parts of work->data.
- If the count is non-zero, the work item cannot be queued. Any attempt to
queue the work item fails and returns %false.
- disable_work[_sync](), enable_work(), disable_delayed_work[_sync]() and
enable_delayed_work() are added.
v3: enable_work() was using local_irq_enable() instead of
local_irq_restore() to undo IRQ-disable by work_grab_pending(). This is
awkward now and will become incorrect as enable_work() will later be
used from IRQ context too. (Lai)
v2: Lai noticed that queue_work_node() wasn't checking the disable count.
Fixed. queue_rcu_work() is updated to trigger warning if the inner work
item is disabled.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The cancel[_sync] paths acquire and release WORK_STRUCT_PENDING, and
manipulate WORK_OFFQ_CANCELING. However, they assume that all the OFFQ bit
values except for the pool ID are statically known and don't preserve them,
which is not wrong in the current code as the pool ID and CANCELING are the
only information carried. However, the planned disable/enable support will
add more fields and need them to be preserved.
This patch updates work data handling so that only the bits which need
updating are updated.
- struct work_offq_data is added along with work_offqd_unpack() and
work_offqd_pack_flags() to help manipulating multiple fields contained in
work->data. Note that the helpers look a bit silly right now as there
isn't that much to pack. The next patch will add more.
- mark_work_canceling() which is used only by __cancel_work_sync() is
replaced by open-coded usage of work_offq_data and
set_work_pool_and_keep_pending() in __cancel_work_sync().
- __cancel_work[_sync]() uses offq_data helpers to preserve other OFFQ bits
when clearing WORK_STRUCT_PENDING and WORK_OFFQ_CANCELING at the end.
- This removes all users of get_work_pool_id() which is dropped. Note that
get_work_pool_id() could handle both WORK_STRUCT_PWQ and !WORK_STRUCT_PWQ
cases; however, it was only being called after try_to_grab_pending()
succeeded, in which case WORK_STRUCT_PWQ is never set and thus it's safe
to use work_offqd_unpack() instead.
No behavior changes intended.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmYAlq0eHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGYqwH/0fb4pRbVtULpiIK
Cs7/e/IWzRRWLBq+Jj2KVVTxwjyiKFNOq6K/CHHnljIWo1yN2CIWeOgbHfTI0WfN
xmBdJP7OtK8MCN9PwwoWhZxMLcyv4pFCERrrkGa7AD+cdN4j/ytQ3mH5V8f/21fd
rnpQSdpgGXB2SSMHd520Y+e56+gxrrTmsDXjZWM08Wt0bbqAWJrjNe58BMz5hI1t
yQtcgYRTdUuZBn5TMkT99lK9EFQslV38YCo7RUP5D0DWXS1jSfWlgnCD1Nc1ziF4
ps/xPdUMDJAc5Tslg/hgJOciSuLqgMzIUsVgZrKysuu3NhwDY1LDWGORmH1t8E8W
RC25950=
=F+01
-----END PGP SIGNATURE-----
Merge tag 'v6.9-rc1' into sched/core, to pick up fixes and to refresh the branch
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Here is the "big" set of driver core and kernfs changes for 6.9-rc1.
Nothing all that crazy here, just some good updates that include:
- automatic attribute group hiding from Dan Williams (he fixed up my
horrible attempt at doing this.)
- kobject lock contention fixes from Eric Dumazet
- driver core cleanups from Andy
- kernfs rcu work from Tejun
- fw_devlink changes to resolve some reported issues
- other minor changes, all details in the shortlog
All of these have been in linux-next for a long time with no reported
issues.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCZfwsHg8cZ3JlZ0Brcm9h
aC5jb20ACgkQMUfUDdst+ynT4ACePcNRAsYrINlOPPKPHimJtyP01yEAn0pZYnj2
0/UpqIqf3HVPu7zsLKTa
=vR9S
-----END PGP SIGNATURE-----
Merge tag 'driver-core-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core updates from Greg KH:
"Here is the "big" set of driver core and kernfs changes for 6.9-rc1.
Nothing all that crazy here, just some good updates that include:
- automatic attribute group hiding from Dan Williams (he fixed up my
horrible attempt at doing this.)
- kobject lock contention fixes from Eric Dumazet
- driver core cleanups from Andy
- kernfs rcu work from Tejun
- fw_devlink changes to resolve some reported issues
- other minor changes, all details in the shortlog
All of these have been in linux-next for a long time with no reported
issues"
* tag 'driver-core-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (28 commits)
device: core: Log warning for devices pending deferred probe on timeout
driver: core: Use dev_* instead of pr_* so device metadata is added
driver: core: Log probe failure as error and with device metadata
of: property: fw_devlink: Add support for "post-init-providers" property
driver core: Add FWLINK_FLAG_IGNORE to completely ignore a fwnode link
driver core: Adds flags param to fwnode_link_add()
debugfs: fix wait/cancellation handling during remove
device property: Don't use "proxy" headers
device property: Move enum dev_dma_attr to fwnode.h
driver core: Move fw_devlink stuff to where it belongs
driver core: Drop unneeded 'extern' keyword in fwnode.h
firmware_loader: Suppress warning on FW_OPT_NO_WARN flag
sysfs:Addresses documentation in sysfs_merge_group and sysfs_unmerge_group.
firmware_loader: introduce __free() cleanup hanler
platform-msi: Remove usage of the deprecated ida_simple_xx() API
sysfs: Introduce DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE()
sysfs: Document new "group visible" helpers
sysfs: Fix crash on empty group attributes array
sysfs: Introduce a mechanism to hide static attribute_groups
sysfs: Introduce a mechanism to hide static attribute_groups
...
- Standardize on prefixing scheduler-internal functions defined
in <linux/sched.h> with sched_*() prefix. scheduler_tick() was
the only function using the scheduler_ prefix. Harmonize it.
- The other reason to rename it is the NOHZ scheduler tick
handling functions are already named sched_tick_*().
Make the 'git grep sched_tick' more meaningful.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Link: https://lore.kernel.org/r/20240308111819.1101550-3-mingo@kernel.org
- The hierarchical timer pull model
When timer wheel timers are armed they are placed into the timer wheel
of a CPU which is likely to be busy at the time of expiry. This is done
to avoid wakeups on potentially idle CPUs.
This is wrong in several aspects:
1) The heuristics to select the target CPU are wrong by
definition as the chance to get the prediction right is close
to zero.
2) Due to #1 it is possible that timers are accumulated on a
single target CPU
3) The required computation in the enqueue path is just overhead for
dubious value especially under the consideration that the vast
majority of timer wheel timers are either canceled or rearmed
before they expire.
The timer pull model avoids the above by removing the target
computation on enqueue and queueing timers always on the CPU on which
they get armed.
This is achieved by having separate wheels for CPU pinned timers and
global timers which do not care about where they expire.
As long as a CPU is busy it handles both the pinned and the global
timers which are queued on the CPU local timer wheels.
When a CPU goes idle it evaluates its own timer wheels:
- If the first expiring timer is a pinned timer, then the global
timers can be ignored as the CPU will wake up before they expire.
- If the first expiring timer is a global timer, then the expiry time
is propagated into the timer pull hierarchy and the CPU makes sure
to wake up for the first pinned timer.
The timer pull hierarchy organizes CPUs in groups of eight at the
lowest level and at the next levels groups of eight groups up to the
point where no further aggregation of groups is required, i.e. the
number of levels is log8(NR_CPUS). The magic number of eight has been
established by experimention, but can be adjusted if needed.
In each group one busy CPU acts as the migrator. It's only one CPU to
avoid lock contention on remote timer wheels.
The migrator CPU checks in its own timer wheel handling whether there
are other CPUs in the group which have gone idle and have global timers
to expire. If there are global timers to expire, the migrator locks the
remote CPU timer wheel and handles the expiry.
Depending on the group level in the hierarchy this handling can require
to walk the hierarchy downwards to the CPU level.
Special care is taken when the last CPU goes idle. At this point the
CPU is the systemwide migrator at the top of the hierarchy and it
therefore cannot delegate to the hierarchy. It needs to arm its own
timer device to expire either at the first expiring timer in the
hierarchy or at the first CPU local timer, which ever expires first.
This completely removes the overhead from the enqueue path, which is
e.g. for networking a true hotpath and trades it for a slightly more
complex idle path.
This has been in development for a couple of years and the final series
has been extensively tested by various teams from silicon vendors and
ran through extensive CI.
There have been slight performance improvements observed on network
centric workloads and an Intel team confirmed that this allows them to
power down a die completely on a mult-die socket for the first time in
a mostly idle scenario.
There is only one outstanding ~1.5% regression on a specific overloaded
netperf test which is currently investigated, but the rest is either
positive or neutral performance wise and positive on the power
management side.
- Fixes for the timekeeping interpolation code for cross-timestamps:
cross-timestamps are used for PTP to get snapshots from hardware timers
and interpolated them back to clock MONOTONIC. The changes address a
few corner cases in the interpolation code which got the math and logic
wrong.
- Simplifcation of the clocksource watchdog retry logic to automatically
adjust to handle larger systems correctly instead of having more
incomprehensible command line parameters.
- Treewide consolidation of the VDSO data structures.
- The usual small improvements and cleanups all over the place.
-----BEGIN PGP SIGNATURE-----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=iQlu
-----END PGP SIGNATURE-----
Merge tag 'timers-core-2024-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer updates from Thomas Gleixner:
"A large set of updates and features for timers and timekeeping:
- The hierarchical timer pull model
When timer wheel timers are armed they are placed into the timer
wheel of a CPU which is likely to be busy at the time of expiry.
This is done to avoid wakeups on potentially idle CPUs.
This is wrong in several aspects:
1) The heuristics to select the target CPU are wrong by
definition as the chance to get the prediction right is
close to zero.
2) Due to #1 it is possible that timers are accumulated on
a single target CPU
3) The required computation in the enqueue path is just overhead
for dubious value especially under the consideration that the
vast majority of timer wheel timers are either canceled or
rearmed before they expire.
The timer pull model avoids the above by removing the target
computation on enqueue and queueing timers always on the CPU on
which they get armed.
This is achieved by having separate wheels for CPU pinned timers
and global timers which do not care about where they expire.
As long as a CPU is busy it handles both the pinned and the global
timers which are queued on the CPU local timer wheels.
When a CPU goes idle it evaluates its own timer wheels:
- If the first expiring timer is a pinned timer, then the global
timers can be ignored as the CPU will wake up before they
expire.
- If the first expiring timer is a global timer, then the expiry
time is propagated into the timer pull hierarchy and the CPU
makes sure to wake up for the first pinned timer.
The timer pull hierarchy organizes CPUs in groups of eight at the
lowest level and at the next levels groups of eight groups up to
the point where no further aggregation of groups is required, i.e.
the number of levels is log8(NR_CPUS). The magic number of eight
has been established by experimention, but can be adjusted if
needed.
In each group one busy CPU acts as the migrator. It's only one CPU
to avoid lock contention on remote timer wheels.
The migrator CPU checks in its own timer wheel handling whether
there are other CPUs in the group which have gone idle and have
global timers to expire. If there are global timers to expire, the
migrator locks the remote CPU timer wheel and handles the expiry.
Depending on the group level in the hierarchy this handling can
require to walk the hierarchy downwards to the CPU level.
Special care is taken when the last CPU goes idle. At this point
the CPU is the systemwide migrator at the top of the hierarchy and
it therefore cannot delegate to the hierarchy. It needs to arm its
own timer device to expire either at the first expiring timer in
the hierarchy or at the first CPU local timer, which ever expires
first.
This completely removes the overhead from the enqueue path, which
is e.g. for networking a true hotpath and trades it for a slightly
more complex idle path.
This has been in development for a couple of years and the final
series has been extensively tested by various teams from silicon
vendors and ran through extensive CI.
There have been slight performance improvements observed on network
centric workloads and an Intel team confirmed that this allows them
to power down a die completely on a mult-die socket for the first
time in a mostly idle scenario.
There is only one outstanding ~1.5% regression on a specific
overloaded netperf test which is currently investigated, but the
rest is either positive or neutral performance wise and positive on
the power management side.
- Fixes for the timekeeping interpolation code for cross-timestamps:
cross-timestamps are used for PTP to get snapshots from hardware
timers and interpolated them back to clock MONOTONIC. The changes
address a few corner cases in the interpolation code which got the
math and logic wrong.
- Simplifcation of the clocksource watchdog retry logic to
automatically adjust to handle larger systems correctly instead of
having more incomprehensible command line parameters.
- Treewide consolidation of the VDSO data structures.
- The usual small improvements and cleanups all over the place"
* tag 'timers-core-2024-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
timer/migration: Fix quick check reporting late expiry
tick/sched: Fix build failure for CONFIG_NO_HZ_COMMON=n
vdso/datapage: Quick fix - use asm/page-def.h for ARM64
timers: Assert no next dyntick timer look-up while CPU is offline
tick: Assume timekeeping is correctly handed over upon last offline idle call
tick: Shut down low-res tick from dying CPU
tick: Split nohz and highres features from nohz_mode
tick: Move individual bit features to debuggable mask accesses
tick: Move got_idle_tick away from common flags
tick: Assume the tick can't be stopped in NOHZ_MODE_INACTIVE mode
tick: Move broadcast cancellation up to CPUHP_AP_TICK_DYING
tick: Move tick cancellation up to CPUHP_AP_TICK_DYING
tick: Start centralizing tick related CPU hotplug operations
tick/sched: Don't clear ts::next_tick again in can_stop_idle_tick()
tick/sched: Rename tick_nohz_stop_sched_tick() to tick_nohz_full_stop_tick()
tick: Use IS_ENABLED() whenever possible
tick/sched: Remove useless oneshot ifdeffery
tick/nohz: Remove duplicate between lowres and highres handlers
tick/nohz: Remove duplicate between tick_nohz_switch_to_nohz() and tick_setup_sched_timer()
hrtimer: Select housekeeping CPU during migration
...
Boqun pointed out that workqueues aren't handling BH work items on offlined
CPUs. Unlike tasklet which transfers out the pending tasks from
CPUHP_SOFTIRQ_DEAD, BH workqueue would just leave them pending which is
problematic. Note that this behavior is specific to BH workqueues as the
non-BH per-CPU workers just become unbound when the CPU goes offline.
This patch fixes the issue by draining the pending BH work items from an
offlined CPU from CPUHP_SOFTIRQ_DEAD. Because work items carry more context,
it's not as easy to transfer the pending work items from one pool to
another. Instead, run BH work items which execute the offlined pools on an
online CPU.
Note that this assumes that no further BH work items will be queued on the
offlined CPUs. This assumption is shared with tasklet and should be fine for
conversions. However, this issue also exists for per-CPU workqueues which
will just keep executing work items queued after CPU offline on unbound
workers and workqueue should reject per-CPU and BH work items queued on
offline CPUs. This will be addressed separately later.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: http://lkml.kernel.org/r/Zdvw0HdSXcU3JZ4g@boqun-archlinux
When CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel will report
the work functions which violate the intensive_threshold_us repeatedly.
And now, only when the violate times exceed 4 and is a power of 2,
the kernel warning could be triggered.
However, sometimes, even if a long work execution time occurs only once,
it may cause other work to be delayed for a long time. This may also
cause some problems sometimes.
In order to freely control the threshold of warninging, a boot argument
is added so that the user can control the warning threshold to be printed.
At the same time, keep the exponential backoff to prevent reporting too much.
By default, the warning threshold is 4.
tj: Updated kernel-parameters.txt description.
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The implementation of the NOHZ pull at expiry model will change the timer
bases per CPU. Timers, that have to expire on a specific CPU, require the
TIMER_PINNED flag. If the CPU doesn't matter, the TIMER_PINNED flag must be
dropped. This is required for call sites which use the timer alternately as
pinned and not pinned timer like workqueues do.
Therefore use add_timer_global() in __queue_delayed_work() for non-bound
delayed work to make sure the TIMER_PINNED flag is dropped.
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20240221090548.36600-7-anna-maria@linutronix.de
- set_work_data() takes a separate @flags argument but just ORs it to @data.
This is more confusing than helpful. Just take @data.
- Use the name @flags consistently and add the parameter to
set_work_pool_and_{keep|clear}_pending(). This will be used by the planned
disable/enable support.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
clear_work_data() is only used in one place and immediately followed by
smp_mb(), making it equivalent to set_work_pool_and_clear_pending() w/
WORK_OFFQ_POOL_NONE for @pool_id. Drop it. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The planned disable/enable support will need the same logic. Let's factor it
out. No functional changes.
v2: Update function comment to include @irq_flags.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The bits of work->data are used for a few different purposes. How the bits
are used is determined by enum work_bits. The planned disable/enable support
will add another use, so let's clean it up a bit in preparation.
- Let WORK_STRUCT_*_BIT's values be determined by enum definition order.
- Deliminate different bit sections the same way using SHIFT and BITS
values.
- Rename __WORK_OFFQ_CANCELING to WORK_OFFQ_CANCELING_BIT for consistency.
- Introduce WORK_STRUCT_PWQ_SHIFT and replace WORK_STRUCT_FLAG_MASK and
WORK_STRUCT_WQ_DATA_MASK with WQ_STRUCT_PWQ_MASK for clarity.
- Improve documentation.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The cancel path used bool @is_dwork to distinguish canceling a regular work
and a delayed one. The planned disable/enable support will need passing
around another flag in the code path. As passing them around with bools will
be confusing, let's introduce named flags to pass around in the cancel path.
WORK_CANCEL_DELAYED replaces @is_dwork. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Using the generic term `flags` for irq flags is conventional but can be
confusing as there's quite a bit of code dealing with work flags which
involves some subtleties. Let's use a more explicit name `irq_flags` for
local irq flags. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
They are currently a bit disorganized with flush and cancel functions mixed.
Reoranize them so that flush functions come first, cancel next and
cancel_sync last. This way, we won't have to add prototypes for internal
functions for the planned disable/enable support.
This is pure code reorganization. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
__cancel_work_timer() is used to implement cancel_work_sync() and
cancel_delayed_work_sync(), similarly to how __cancel_work() is used to
implement cancel_work() and cancel_delayed_work(). ie. The _timer part of
the name is a complete misnomer. The difference from __cancel_work() is the
fact that it syncs against work item execution not whether it handles timers
or not.
Let's rename it to less confusing __cancel_work_sync(). No functional
change.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The different flavors of RCU read critical sections have been unified. Let's
update the locking assertion macros accordingly to avoid requiring
unnecessary explicit rcu_read_[un]lock() calls.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Reorder some global declarations and adjust comments and whitespaces for
clarity and consistency. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmXSbvkeHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGi3kH/iM5AcKeQfee07to
TJP3WORLBt5UrUMgAQbJdNAruCj6brHA6YnZ6AjdhdNZ41RO06h69kTpb+y/CYJz
+ogGK5qhWsC8ETM6rJCioo8uI4GU70p84fGiMfLw8o6vUvmtyI5qH3531Y30Edxt
qqMVtQrVe9J5JcHQjJ/mQo8nAuvZdQQGM90zLGqFP+JheP3CzsCokraIITqoebDC
PCVAsnSbXT/uMjwSr03kdnMnnY++fxz/TyHb/QRMPq/4xU8nz0Z2hlOOYrVkOINu
lkIYtCDGTk0QR3hdDiO9yt+k1OsWi+oBkrhjAQmAk9x3riiXq1NKvZZLDArt7PH5
gSyo9sE=
=h5Ei
-----END PGP SIGNATURE-----
Merge 6.8-rc5 into driver-core-next
We need the driver core changes in here as well.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2f34d7337d ("workqueue: Fix queue_work_on() with BH workqueues") added
irq_work usage to workqueue; however, it turns out irq_work is actually
optional and the change breaks build on configuration which doesn't have
CONFIG_IRQ_WORK enabled.
Fix build by making workqueue use irq_work only when CONFIG_SMP and enabling
CONFIG_IRQ_WORK when CONFIG_SMP is set. It's reasonable to argue that it may
be better to just always enable it. However, this still saves a small bit of
memory for tiny UP configs and also the least amount of change, so, for now,
let's keep it conditional.
Verified to do the right thing for x86_64 allnoconfig and defconfig, and
aarch64 allnoconfig, allnoconfig + prink disable (SMP but nothing selects
IRQ_WORK) and a modified aarch64 Kconfig where !SMP and nothing selects
IRQ_WORK.
v2: `depends on SMP` leads to Kconfig warnings when CONFIG_IRQ_WORK is
selected by something else when !CONFIG_SMP. Use `def_bool y if SMP`
instead.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Fixes: 2f34d7337d ("workqueue: Fix queue_work_on() with BH workqueues")
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
When queue_work_on() is used to queue a BH work item on a remote CPU, the
work item is queued on that CPU but kick_pool() raises softirq on the local
CPU. This leads to stalls as the work item won't be executed until something
else on the remote CPU schedules a BH work item or tasklet locally.
Fix it by bouncing raising softirq to the target CPU using per-cpu irq_work.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 4cb1ef6460 ("workqueue: Implement BH workqueues to eventually replace tasklets")
Since 5797b1c189 ("workqueue: Implement system-wide nr_active enforcement
for unbound workqueues"), unbound workqueues have separate min_active which
sets the number of interdependent work items that can be handled. This value
is currently initialized to WQ_DFL_MIN_ACTIVE which is 8. This isn't high
enough for some users, let's add an interface to adjust the setting.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fix the kernel-doc comment of the unplug_oldest_pwq() function to enable
proper processing and formatting of the embedded ASCII diagram.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Commit 85f0ab43f9 ("kernel/workqueue: Bind rescuer to unbound
cpumask for WQ_UNBOUND") modified init_rescuer() to bind rescuer of
an unbound workqueue to the cpumask in wq->unbound_attrs. However
unbound_attrs->cpumask's of all workqueues are initialized to
cpu_possible_mask and will only be changed if it has the WQ_SYSFS flag
to expose a cpumask sysfs file to be written by users. So this patch
doesn't achieve what it is intended to do.
If an unbound workqueue is created after wq_unbound_cpumask is modified
and there is no more unbound cpumask update after that, the unbound
rescuer will be bound to all CPUs unless the workqueue is created
with the WQ_SYSFS flag and a user explicitly modified its cpumask
sysfs file. Fix this problem by binding directly to wq_unbound_cpumask
in init_rescuer().
Fixes: 85f0ab43f9 ("kernel/workqueue: Bind rescuer to unbound cpumask for WQ_UNBOUND")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
When workqueue cpumask changes are committed the associated rescuer (if
one exists) affinity is not touched and this might be a problem down the
line for isolated setups.
Make sure rescuers affinity is updated every time a workqueue cpumask
changes, so that rescuers can't break isolation.
[longman: set_cpus_allowed_ptr() will block until the designated task
is enqueued on an allowed CPU, no wake_up_process() needed. Also use
the unbound_effective_cpumask() helper as suggested by Tejun.]
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Ordered workqueues does not currently follow changes made to the
global unbound cpumask because per-pool workqueue changes may break
the ordering guarantee. IOW, a work function in an ordered workqueue
may run on an isolated CPU.
This patch enables ordered workqueues to follow changes made to the
global unbound cpumask by temporaily plug or suspend the newly allocated
pool_workqueue from executing newly queued work items until the old
pwq has been properly drained. For ordered workqueues, there should
only be one pwq that is unplugged, the rests should be plugged.
This enables ordered workqueues to follow the unbound cpumask changes
like other unbound workqueues at the expense of some delay in execution
of work functions during the transition period.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Add a new pwq into the tail of wq->pwqs so that pwq iteration will
start from the oldest pwq to the newest. This ordering will facilitate
the inclusion of ordered workqueues in a wq_unbound_cpumask update.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Now that the driver core can properly handle constant struct bus_type,
move the wq_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: "Ricardo B. Marliere" <ricardo@marliere.net>
Cc: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20240206-bus_cleanup-workqueue-v1-1-72b10d282d58@marliere.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The for-6.8-fixes commit ae9cc8956944 ("Revert "workqueue: Override implicit
ordered attribute in workqueue_apply_unbound_cpumask()") also fixes build for
Signed-off-by: Tejun Heo <tj@kernel.org>
This reverts commit ca10d851b9.
The commit allowed workqueue_apply_unbound_cpumask() to clear __WQ_ORDERED
on now removed implicitly ordered workqueues. This was incorrect in that
system-wide config change shouldn't break ordering properties of all
workqueues. The reason why apply_workqueue_attrs() path was allowed to do so
was because it was targeting the specific workqueue - either the workqueue
had WQ_SYSFS set or the workqueue user specifically tried to change
max_active, both of which indicate that the workqueue doesn't need to be
ordered.
The implicitly ordered workqueue promotion was removed by the previous
commit 3bc1e711c2 ("workqueue: Don't implicitly make UNBOUND workqueues w/
@max_active==1 ordered"). However, it didn't update this path and broke
build. Let's revert the commit which was incorrect in the first place which
also fixes build.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 3bc1e711c2 ("workqueue: Don't implicitly make UNBOUND workqueues w/ @max_active==1 ordered")
Fixes: ca10d851b9 ("workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()")
Cc: stable@vger.kernel.org # v6.6+
Signed-off-by: Tejun Heo <tj@kernel.org>
5c0338c687 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered")
automoatically promoted UNBOUND workqueues w/ @max_active==1 to ordered
workqueues because UNBOUND workqueues w/ @max_active==1 used to be the way
to create ordered workqueues and the new NUMA support broke it. These
problems can be subtle and the fact that they can only trigger on NUMA
machines made them even more difficult to debug.
However, overloading the UNBOUND allocation interface this way creates other
issues. It's difficult to tell whether a given workqueue actually needs to
be ordered and users that legitimately want a min concurrency level wq
unexpectedly gets an ordered one instead. With planned UNBOUND workqueue
udpates to improve execution locality and more prevalence of chiplet designs
which can benefit from such improvements, this isn't a state we wanna be in
forever.
There aren't that many UNBOUND w/ @max_active==1 users in the tree and the
preceding patches audited all and converted them to
alloc_ordered_workqueue() as appropriate. This patch removes the implicit
promotion of UNBOUND w/ @max_active==1 workqueues to ordered ones.
v2: v1 patch incorrectly dropped !list_empty(&wq->pwqs) condition in
apply_workqueue_attrs_locked() which spuriously triggers WARNING and
fails workqueue creation. Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/oe-lkp/202304251050.45a5df1f-oliver.sang@intel.com
Skip updating workqueues with __WQ_DESTROYING bit set when updating
global unbound cpumask to avoid unnecessary work and other complications.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This reverts commit d412ace111. This leads to
build failures as it depends on a driver-core commit 32f78abe59 ("driver
core: bus: constantify subsys_register() calls"). Let's drop it from wq tree
and route it through driver-core tree.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202402051505.kM9Rr3CJ-lkp@intel.com/
The only generic interface to execute asynchronously in the BH context is
tasklet; however, it's marked deprecated and has some design flaws such as
the execution code accessing the tasklet item after the execution is
complete which can lead to subtle use-after-free in certain usage scenarios
and less-developed flush and cancel mechanisms.
This patch implements BH workqueues which share the same semantics and
features of regular workqueues but execute their work items in the softirq
context. As there is always only one BH execution context per CPU, none of
the concurrency management mechanisms applies and a BH workqueue can be
thought of as a convenience wrapper around softirq.
Except for the inability to sleep while executing and lack of max_active
adjustments, BH workqueues and work items should behave the same as regular
workqueues and work items.
Currently, the execution is hooked to tasklet[_hi]. However, the goal is to
convert all tasklet users over to BH workqueues. Once the conversion is
complete, tasklet can be removed and BH workqueues can directly take over
the tasklet softirqs.
system_bh[_highpri]_wq are added. As queue-wide flushing doesn't exist in
tasklet, all existing tasklet users should be able to use the system BH
workqueues without creating their own workqueues.
v3: - Add missing interrupt.h include.
v2: - Instead of using tasklets, hook directly into its softirq action
functions - tasklet[_hi]_action(). This is slightly cheaper and closer
to the eventual code structure we want to arrive at. Suggested by Lai.
- Lai also pointed out several places which need NULL worker->task
handling or can use clarification. Updated.
Signed-off-by: Tejun Heo <tj@kernel.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/CAHk-=wjDW53w4-YcSmgKC5RruiRLHmJ1sXeYdp_ZgVoBw=5byA@mail.gmail.com
Tested-by: Allen Pais <allen.lkml@gmail.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Factor out init_cpu_worker_pool() from workqueue_init_early(). This is pure
reorganization in preparation of BH workqueue support.
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Allen Pais <allen.lkml@gmail.com>
These changes are in preparation of BH workqueue which will execute work
items from BH context.
- Update lock and RCU depth checks in process_one_work() so that it
remembers and checks against the starting depths and prints out the depth
changes.
- Factor out lockdep annotations in the flush paths into
touch_{wq|work}_lockdep_map(). The work->lockdep_map touching is moved
from __flush_work() to its callee - start_flush_work(). This brings it
closer to the wq counterpart and will allow testing the associated wq's
flags which will be needed to support BH workqueues. This is not expected
to cause any functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Allen Pais <allen.lkml@gmail.com>
Now that the driver core can properly handle constant struct bus_type,
move the wq_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Suggested-and-reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ricardo B. Marliere <ricardo@marliere.net>
Signed-off-by: Tejun Heo <tj@kernel.org>
dd6c3c5441 ("workqueue: Move pwq_dec_nr_in_flight() to the end of work
item handling") relocated pwq_dec_nr_in_flight() after
set_work_pool_and_keep_pending(). However, the latter destroys information
contained in work->data that's needed by pwq_dec_nr_in_flight() including
the flush color. With flush color destroyed, flush_workqueue() can stall
easily when mixed with cancel_work*() usages.
This is easily triggered by running xfstests generic/001 test on xfs:
INFO: task umount:6305 blocked for more than 122 seconds.
...
task:umount state:D stack:13008 pid:6305 tgid:6305 ppid:6301 flags:0x00004000
Call Trace:
<TASK>
__schedule+0x2f6/0xa20
schedule+0x36/0xb0
schedule_timeout+0x20b/0x280
wait_for_completion+0x8a/0x140
__flush_workqueue+0x11a/0x3b0
xfs_inodegc_flush+0x24/0xf0
xfs_unmountfs+0x14/0x180
xfs_fs_put_super+0x3d/0x90
generic_shutdown_super+0x7c/0x160
kill_block_super+0x1b/0x40
xfs_kill_sb+0x12/0x30
deactivate_locked_super+0x35/0x90
deactivate_super+0x42/0x50
cleanup_mnt+0x109/0x170
__cleanup_mnt+0x12/0x20
task_work_run+0x60/0x90
syscall_exit_to_user_mode+0x146/0x150
do_syscall_64+0x5d/0x110
entry_SYSCALL_64_after_hwframe+0x6c/0x74
Fix it by stashing work_data before calling set_work_pool_and_keep_pending()
and using the stashed value for pwq_dec_nr_in_flight().
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Chandan Babu R <chandanbabu@kernel.org>
Link: http://lkml.kernel.org/r/87o7cxeehy.fsf@debian-BULLSEYE-live-builder-AMD64
Fixes: dd6c3c5441 ("workqueue: Move pwq_dec_nr_in_flight() to the end of work item handling")
System workqueues are allocated early during boot from
workqueue_init_early(). While allocating unbound workqueues,
wq_update_node_max_active() is invoked from apply_workqueue_attrs() and
accesses NUMA topology to initialize wq->node_nr_active[].max.
However, topology information may not be set up at this point.
wq_update_node_max_active() is explicitly invoked from
workqueue_init_topology() later when topology information is known to be
available.
This doesn't seem to crash anything but it's doing useless work with dubious
data. Let's skip the premature and duplicate node_max_active updates by
initializing the field to WQ_DFL_MIN_ACTIVE on allocation and making
wq_update_node_max_active() noop until workqueue_init_topology().
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/workqueue.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 9221a4c57ae1..a65081ec6780 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -386,6 +386,8 @@ static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
[WQ_AFFN_SYSTEM] = "system",
};
+static bool wq_topo_initialized = false;
+
/*
* Per-cpu work items which run for longer than the following threshold are
* automatically considered CPU intensive and excluded from concurrency
@@ -1510,6 +1512,9 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
lockdep_assert_held(&wq->mutex);
+ if (!wq_topo_initialized)
+ return;
+
if (!cpumask_test_cpu(off_cpu, effective))
off_cpu = -1;
@@ -4356,6 +4361,7 @@ static void free_node_nr_active(struct wq_node_nr_active **nna_ar)
static void init_node_nr_active(struct wq_node_nr_active *nna)
{
+ nna->max = WQ_DFL_MIN_ACTIVE;
atomic_set(&nna->nr, 0);
raw_spin_lock_init(&nna->lock);
INIT_LIST_HEAD(&nna->pending_pwqs);
@@ -7400,6 +7406,8 @@ void __init workqueue_init_topology(void)
init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache);
init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa);
+ wq_topo_initialized = true;
+
mutex_lock(&wq_pool_mutex);
/*
For wq_update_node_max_active(), @off_cpu of -1 indicates that no CPU is
going down. The function was incorrectly calling cpumask_test_cpu() with -1
CPU leading to oopses like the following on some archs:
Unable to handle kernel paging request at virtual address ffff0002100296e0
..
pc : wq_update_node_max_active+0x50/0x1fc
lr : wq_update_node_max_active+0x1f0/0x1fc
...
Call trace:
wq_update_node_max_active+0x50/0x1fc
apply_wqattrs_commit+0xf0/0x114
apply_workqueue_attrs_locked+0x58/0xa0
alloc_workqueue+0x5ac/0x774
workqueue_init_early+0x460/0x540
start_kernel+0x258/0x684
__primary_switched+0xb8/0xc0
Code: 9100a273 35000d01 53067f00 d0016dc1 (f8607a60)
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Attempted to kill the idle task!
---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---
Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reported-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: http://lkml.kernel.org/r/91eacde0-df99-4d5c-a980-91046f66e612@samsung.com
Fixes: 5797b1c189 ("workqueue: Implement system-wide nr_active enforcement for unbound workqueues")
Imran Khan