user/sven/linux.git/kernel/workqueue.c, branch v6.1.148

workqueue: Improve scalability of workqueue watchdog touch

2024-09-12T09:10:27Z

[ Upstream commit 98f887f820c993e05a12e8aa816c80b8661d4c87 ] 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 Signed-off-by: Nicholas Piggin Reviewed-by: Paul E. McKenney Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

workqueue: wq_watchdog_touch is always called with valid CPU

2024-09-12T09:10:27Z

[ Upstream commit 18e24deb1cc92f2068ce7434a94233741fbd7771 ] Warn in the case it is called with cpu == -1. This does not appear to happen anywhere. Signed-off-by: Nicholas Piggin Reviewed-by: Paul E. McKenney Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

workqueue: Provide one lock class key per work_on_cpu() callsite

2023-11-28T17:06:55Z

[ Upstream commit 265f3ed077036f053981f5eea0b5b43e7c5b39ff ] All callers of work_on_cpu() share the same lock class key for all the functions queued. As a result the workqueue related locking scenario for a function A may be spuriously accounted as an inversion against the locking scenario of function B such as in the following model: long A(void *arg) { mutex_lock(&mutex); mutex_unlock(&mutex); } long B(void *arg) { } void launchA(void) { work_on_cpu(0, A, NULL); } void launchB(void) { mutex_lock(&mutex); work_on_cpu(1, B, NULL); mutex_unlock(&mutex); } launchA and launchB running concurrently have no chance to deadlock. However the above can be reported by lockdep as a possible locking inversion because the works containing A() and B() are treated as belonging to the same locking class. The following shows an existing example of such a spurious lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.6.0-rc1-00065-g934ebd6e5359 #35409 Not tainted ------------------------------------------------------ kworker/0:1/9 is trying to acquire lock: ffffffff9bc72f30 (cpu_hotplug_lock){++++}-{0:0}, at: _cpu_down+0x57/0x2b0 but task is already holding lock: ffff9e3bc0057e60 ((work_completion)(&wfc.work)){+.+.}-{0:0}, at: process_scheduled_works+0x216/0x500 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((work_completion)(&wfc.work)){+.+.}-{0:0}: __flush_work+0x83/0x4e0 work_on_cpu+0x97/0xc0 rcu_nocb_cpu_offload+0x62/0xb0 rcu_nocb_toggle+0xd0/0x1d0 kthread+0xe6/0x120 ret_from_fork+0x2f/0x40 ret_from_fork_asm+0x1b/0x30 -> #1 (rcu_state.barrier_mutex){+.+.}-{3:3}: __mutex_lock+0x81/0xc80 rcu_nocb_cpu_deoffload+0x38/0xb0 rcu_nocb_toggle+0x144/0x1d0 kthread+0xe6/0x120 ret_from_fork+0x2f/0x40 ret_from_fork_asm+0x1b/0x30 -> #0 (cpu_hotplug_lock){++++}-{0:0}: __lock_acquire+0x1538/0x2500 lock_acquire+0xbf/0x2a0 percpu_down_write+0x31/0x200 _cpu_down+0x57/0x2b0 __cpu_down_maps_locked+0x10/0x20 work_for_cpu_fn+0x15/0x20 process_scheduled_works+0x2a7/0x500 worker_thread+0x173/0x330 kthread+0xe6/0x120 ret_from_fork+0x2f/0x40 ret_from_fork_asm+0x1b/0x30 other info that might help us debug this: Chain exists of: cpu_hotplug_lock --> rcu_state.barrier_mutex --> (work_completion)(&wfc.work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&wfc.work)); lock(rcu_state.barrier_mutex); lock((work_completion)(&wfc.work)); lock(cpu_hotplug_lock); *** DEADLOCK *** 2 locks held by kworker/0:1/9: #0: ffff900481068b38 ((wq_completion)events){+.+.}-{0:0}, at: process_scheduled_works+0x212/0x500 #1: ffff9e3bc0057e60 ((work_completion)(&wfc.work)){+.+.}-{0:0}, at: process_scheduled_works+0x216/0x500 stack backtrace: CPU: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.6.0-rc1-00065-g934ebd6e5359 #35409 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 Workqueue: events work_for_cpu_fn Call Trace: rcu-torture: rcu_torture_read_exit: Start of episode dump_stack_lvl+0x4a/0x80 check_noncircular+0x132/0x150 __lock_acquire+0x1538/0x2500 lock_acquire+0xbf/0x2a0 ? _cpu_down+0x57/0x2b0 percpu_down_write+0x31/0x200 ? _cpu_down+0x57/0x2b0 _cpu_down+0x57/0x2b0 __cpu_down_maps_locked+0x10/0x20 work_for_cpu_fn+0x15/0x20 process_scheduled_works+0x2a7/0x500 worker_thread+0x173/0x330 ? __pfx_worker_thread+0x10/0x10 kthread+0xe6/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x40 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 Signed-off-by: Frederic Weisbecker Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()

2023-10-19T21:08:54Z

[ Upstream commit ca10d851b9ad0338c19e8e3089e24d565ebfffd7 ] Commit 5c0338c68706 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered") enabled implicit ordered attribute to be added to WQ_UNBOUND workqueues with max_active of 1. This prevented the changing of attributes to these workqueues leading to fix commit 0a94efb5acbb ("workqueue: implicit ordered attribute should be overridable"). However, workqueue_apply_unbound_cpumask() was not updated at that time. So sysfs changes to wq_unbound_cpumask has no effect on WQ_UNBOUND workqueues with implicit ordered attribute. Since not all WQ_UNBOUND workqueues are visible on sysfs, we are not able to make all the necessary cpumask changes even if we iterates all the workqueue cpumasks in sysfs and changing them one by one. Fix this problem by applying the corresponding change made to apply_workqueue_attrs_locked() in the fix commit to workqueue_apply_unbound_cpumask(). Fixes: 5c0338c68706 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

workqueue: clean up WORK_* constant types, clarify masking

2023-07-23T11:49:19Z

commit afa4bb778e48d79e4a642ed41e3b4e0de7489a6c upstream. Dave Airlie reports that gcc-13.1.1 has started complaining about some of the workqueue code in 32-bit arm builds: kernel/workqueue.c: In function ‘get_work_pwq’: kernel/workqueue.c:713:24: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 713 | return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); | ^ [ ... a couple of other cases ... ] and while it's not immediately clear exactly why gcc started complaining about it now, I suspect it's some C23-induced enum type handlign fixup in gcc-13 is the cause. Whatever the reason for starting to complain, the code and data types are indeed disgusting enough that the complaint is warranted. The wq code ends up creating various "helper constants" (like that WORK_STRUCT_WQ_DATA_MASK) using an enum type, which is all kinds of confused. The mask needs to be 'unsigned long', not some unspecified enum type. To make matters worse, the actual "mask and cast to a pointer" is repeated a couple of times, and the cast isn't even always done to the right pointer, but - as the error case above - to a 'void *' with then the compiler finishing the job. That's now how we roll in the kernel. So create the masks using the proper types rather than some ambiguous enumeration, and use a nice helper that actually does the type conversion in one well-defined place. Incidentally, this magically makes clang generate better code. That, admittedly, is really just a sign of clang having been seriously confused before, and cleaning up the typing unconfuses the compiler too. Reported-by: Dave Airlie Link: https://lore.kernel.org/lkml/CAPM=9twNnV4zMCvrPkw3H-ajZOH-01JVh_kDrxdPYQErz8ZTdA@mail.gmail.com/ Cc: Arnd Bergmann Cc: Tejun Heo Cc: Nick Desaulniers Cc: Nathan Chancellor Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

workqueue: Fix hung time report of worker pools

2023-05-11T14:03:32Z

[ Upstream commit 335a42ebb0ca8ee9997a1731aaaae6dcd704c113 ] The workqueue watchdog prints a warning when there is no progress in a worker pool. Where the progress means that the pool started processing a pending work item. Note that it is perfectly fine to process work items much longer. The progress should be guaranteed by waking up or creating idle workers. show_one_worker_pool() prints state of non-idle worker pool. It shows a delay since the last pool->watchdog_ts. The timestamp is updated when a first pending work is queued in __queue_work(). Also it is updated when a work is dequeued for processing in worker_thread() and rescuer_thread(). The delay is misleading when there is no pending work item. In this case it shows how long the last work item is being proceed. Show zero instead. There is no stall if there is no pending work. Fixes: 82607adcf9cdf40fb7b ("workqueue: implement lockup detector") Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

workqueue: Protects wq_unbound_cpumask with wq_pool_attach_mutex

2023-03-10T08:32:53Z

[ Upstream commit 99c621ef243bda726fb8d982a274ded96570b410 ] When unbind_workers() reads wq_unbound_cpumask to set the affinity of freshly-unbound kworkers, it only holds wq_pool_attach_mutex. This isn't sufficient as wq_unbound_cpumask is only protected by wq_pool_mutex. Make wq_unbound_cpumask protected with wq_pool_attach_mutex and also remove the need of temporary saved_cpumask. Fixes: 10a5a651e3af ("workqueue: Restrict kworker in the offline CPU pool running on housekeeping CPUs") Reported-by: Valentin Schneider Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin

Merge tag 'kcfi-v6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

2022-10-04T00:11:07Z

Pull kcfi updates from Kees Cook: "This replaces the prior support for Clang's standard Control Flow Integrity (CFI) instrumentation, which has required a lot of special conditions (e.g. LTO) and work-arounds. The new implementation ("Kernel CFI") is specific to C, directly designed for the Linux kernel, and takes advantage of architectural features like x86's IBT. This series retains arm64 support and adds x86 support. GCC support is expected in the future[1], and additional "generic" architectural support is expected soon[2]. Summary: - treewide: Remove old CFI support details - arm64: Replace Clang CFI support with Clang KCFI support - x86: Introduce Clang KCFI support" Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107048 [1] Link: https://github.com/samitolvanen/llvm-project/commits/kcfi_generic [2] * tag 'kcfi-v6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (22 commits) x86: Add support for CONFIG_CFI_CLANG x86/purgatory: Disable CFI x86: Add types to indirectly called assembly functions x86/tools/relocs: Ignore __kcfi_typeid_ relocations kallsyms: Drop CONFIG_CFI_CLANG workarounds objtool: Disable CFI warnings objtool: Preserve special st_shndx indexes in elf_update_symbol treewide: Drop __cficanonical treewide: Drop WARN_ON_FUNCTION_MISMATCH treewide: Drop function_nocfi init: Drop __nocfi from __init arm64: Drop unneeded __nocfi attributes arm64: Add CFI error handling arm64: Add types to indirect called assembly functions psci: Fix the function type for psci_initcall_t lkdtm: Emit an indirect call for CFI tests cfi: Add type helper macros cfi: Switch to -fsanitize=kcfi cfi: Drop __CFI_ADDRESSABLE cfi: Remove CONFIG_CFI_CLANG_SHADOW ...

treewide: Drop WARN_ON_FUNCTION_MISMATCH

2022-09-26T17:13:14Z

CONFIG_CFI_CLANG no longer breaks cross-module function address equality, which makes WARN_ON_FUNCTION_MISMATCH unnecessary. Remove the definition and switch back to WARN_ON_ONCE. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Tested-by: Kees Cook Tested-by: Nathan Chancellor Acked-by: Peter Zijlstra (Intel) Tested-by: Peter Zijlstra (Intel) Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220908215504.3686827-15-samitolvanen@google.com

workqueue: don't skip lockdep work dependency in cancel_work_sync()

2022-08-16T16:27:35Z

Like Hillf Danton mentioned syzbot should have been able to catch cancel_work_sync() in work context by checking lockdep_map in __flush_work() for both flush and cancel. in [1], being unable to report an obvious deadlock scenario shown below is broken. From locking dependency perspective, sync version of cancel request should behave as if flush request, for it waits for completion of work if that work has already started execution. ---------- #include #include static DEFINE_MUTEX(mutex); static void work_fn(struct work_struct *work) { schedule_timeout_uninterruptible(HZ / 5); mutex_lock(&mutex); mutex_unlock(&mutex); } static DECLARE_WORK(work, work_fn); static int __init test_init(void) { schedule_work(&work); schedule_timeout_uninterruptible(HZ / 10); mutex_lock(&mutex); cancel_work_sync(&work); mutex_unlock(&mutex); return -EINVAL; } module_init(test_init); MODULE_LICENSE("GPL"); ---------- The check this patch restores was added by commit 0976dfc1d0cd80a4 ("workqueue: Catch more locking problems with flush_work()"). Then, lockdep's crossrelease feature was added by commit b09be676e0ff25bd ("locking/lockdep: Implement the 'crossrelease' feature"). As a result, this check was once removed by commit fd1a5b04dfb899f8 ("workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes"). But lockdep's crossrelease feature was removed by commit e966eaeeb623f099 ("locking/lockdep: Remove the cross-release locking checks"). At this point, this check should have been restored. Then, commit d6e89786bed977f3 ("workqueue: skip lockdep wq dependency in cancel_work_sync()") introduced a boolean flag in order to distinguish flush_work() and cancel_work_sync(), for checking "struct workqueue_struct" dependency when called from cancel_work_sync() was causing false positives. Then, commit 87915adc3f0acdf0 ("workqueue: re-add lockdep dependencies for flushing") tried to restore "struct work_struct" dependency check, but by error checked this boolean flag. Like an example shown above indicates, "struct work_struct" dependency needs to be checked for both flush_work() and cancel_work_sync(). Link: https://lkml.kernel.org/r/20220504044800.4966-1-hdanton@sina.com [1] Reported-by: Hillf Danton Suggested-by: Lai Jiangshan Fixes: 87915adc3f0acdf0 ("workqueue: re-add lockdep dependencies for flushing") Cc: Johannes Berg Signed-off-by: Tetsuo Handa Signed-off-by: Tejun Heo