Skip to contentSkip to conversation

workqueue: Don't record workqueue stack holding raw_spin_lock

PATCH Superseded Shuah Khan 3 participants 5 messages Aug 27, 2021 – Aug 30, 2021 Workqueue

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Shuah Khan

author
#0 lore raw

PATCH 1/1 workqueue: Don't record workqueue stack holding raw_spin_lock

When CONFIG_PROVE_RAW_LOCK_NESTING and CONFIG_KASAN are enabled, kasan_record_aux_stack() runs into "BUG: Invalid wait context" when it tries to allocate memory attempting to acquire spinlock in page allocation code while holding workqueue pool raw_spinlock.

There are several instances of this problem when block layer tries to __queue_work(). Call trace from one of these instances is below:

    kblockd_mod_delayed_work_on()
      mod_delayed_work_on()
        __queue_delayed_work()
          __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held)
            insert_work()
	      kasan_record_aux_stack()
                kasan_save_stack()
		  stack_depot_save()
                    alloc_pages()
                      __alloc_pages()
                        get_page_from_freelist()
                          rm_queue()
                            rm_queue_pcplist()
                              local_lock_irqsave(&pagesets.lock, flags);
                              [ BUG: Invalid wait context triggered ]

Fix it by calling kasan_record_aux_stack() without holding pool lock. There is no need to hold pool lock in this path.

=============================
[ BUG: Invalid wait context ]
5.14.0-rc7+ #8 Not tainted
-----------------------------
snap/532 is trying to lock:
ffff888374f32ba0 (lock#2){..-.}-{3:3}, at: get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
other info that might help us debug this:
context-{5:5}
3 locks held by snap/532:
#0: ffff888139fa4408 (&type->i_mutex_dir_key#10){.+.+}-{4:4}, at: walk_component (fs/namei.c:1663 fs/namei.c:1959)
#1: ffffffffab870c40 (rcu_read_lock){....}-{1:3}, at: __queue_work (./arch/x86/include/asm/preempt.h:80 ./include/linux/rcupdate.h:68 ./include/linux/rcupdate.h:685 kernel/workqueue.c:1421) #2: ffff888374f36cd8 (&pool->lock){-.-.}-{2:2}, at: __queue_work (kernel/workqueue.c:1466)

 stack backtrace:
 CPU: 14 PID: 532 Comm: snap Not tainted 5.14.0-rc7+ #8
 Hardware name: LENOVO 90Q30008US/3728, BIOS O4ZKT1CA 09/16/2020
 Call Trace:
 dump_stack_lvl (lib/dump_stack.c:106 (discriminator 4))
 dump_stack (lib/dump_stack.c:113)
 __lock_acquire.cold (kernel/locking/lockdep.c:4666 kernel/locking/lockdep.c:4727 kernel/locking/lockdep.c:4965)
 ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4873)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 lock_acquire (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5627 kernel/locking/lockdep.c:5590)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_release (kernel/locking/lockdep.c:5593)
 ? __kasan_check_read (mm/kasan/shadow.c:32)
 ? __lock_acquire (kernel/locking/lockdep.c:5019)
 ? __zone_watermark_ok (./include/linux/list.h:282 ./include/linux/mmzone.h:111 mm/page_alloc.c:3908)
 get_page_from_freelist (./include/linux/local_lock_internal.h:43 mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 ? is_bpf_text_address (./arch/x86/include/asm/preempt.h:85 ./include/linux/rcupdate.h:73 ./include/linux/rcupdate.h:719 kernel/bpf/core.c:708)
 ? lock_downgrade (kernel/locking/lockdep.c:5633)
 ? __zone_watermark_ok (mm/page_alloc.c:4054)
 __alloc_pages (mm/page_alloc.c:5391)
 ? __alloc_pages_slowpath.constprop.0 (mm/page_alloc.c:5354)
 ? create_prof_cpu_mask (kernel/stacktrace.c:82)
? _find_first_bit (lib/find_bit.c:83)
 alloc_pages (mm/mempolicy.c:2249)
 stack_depot_save (lib/stackdepot.c:304)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 kasan_save_stack (mm/kasan/common.c:41)
 ? kasan_save_stack (mm/kasan/common.c:39)
 ? kasan_record_aux_stack (mm/kasan/generic.c:348)
 ? insert_work (./include/linux/instrumented.h:71 ./include/asm-generic/bitops/instrumented-non-atomic.h:134 kernel/workqueue.c:616 kernel/workqueue.c:623 kernel/workqueue.c:1335)
 ? __queue_work (kernel/workqueue.c:1501)
 ? __queue_delayed_work (kernel/workqueue.c:1657)
 ? mod_delayed_work_on (kernel/workqueue.c:1720)
 ? kblockd_mod_delayed_work_on (block/blk-core.c:1633)
 ? __blk_mq_delay_run_hw_queue (block/blk-mq.c:1567)
 ? blk_mq_run_hw_queue (block/blk-mq.c:1610)
 ? blk_mq_sched_insert_request (block/blk-mq-sched.c:480)
 ? blk_mq_submit_bio (block/blk-mq.c:2276)
Fixes e89a85d63fb2 ("workqueue: kasan: record workqueue stack")
---
 kernel/workqueue.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)
kernel/workqueue.c +15 -3
index f148eacda55a..e647b29b9fb0 100644
@@ -1328,9 +1328,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 {
 	struct worker_pool *pool = pwq->pool;
 
-	/* record the work call stack in order to print it in KASAN reports */
-	kasan_record_aux_stack(work);
-
 	/* we own @work, set data and link */
 	set_work_pwq(work, pwq, extra_flags);
 	list_add_tail(&work->entry, head);
@@ -1499,6 +1496,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
 out:
 	raw_spin_unlock(&pwq->pool->lock);
+
+	/*
+	 * record the work call stack in order to print it in KASAN reports
+	 * Do this without pool raw_spinlock hold to avoid nesting raw
+	 * spinlock with page allocation spinlock.
+	 */
+	kasan_record_aux_stack(work);
+
 	rcu_read_unlock();
 }
 
@@ -3012,6 +3017,13 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	insert_wq_barrier(pwq, barr, work, worker);
 	raw_spin_unlock_irq(&pool->lock);
 
+	/*
+	 * record the work call stack in order to print it in KASAN reports
+	 * Do this without pool raw_spinlock hold to avoid nesting raw
+	 * spinlock with page allocation spinlock.
+	 */
+	kasan_record_aux_stack(work);
+
 	/*
 	 * Force a lock recursion deadlock when using flush_work() inside a
 	 * single-threaded or rescuer equipped workqueue.
Signature · 1 line
2.30.2
reviewer
#1 lore raw
Quoted 103 lines · Shuah Khan

When CONFIG_PROVE_RAW_LOCK_NESTING and CONFIG_KASAN are enabled, kasan_record_aux_stack() runs into "BUG: Invalid wait context" when it tries to allocate memory attempting to acquire spinlock in page allocation code while holding workqueue pool raw_spinlock.

There are several instances of this problem when block layer tries to __queue_work(). Call trace from one of these instances is below:

    kblockd_mod_delayed_work_on()
      mod_delayed_work_on()
        __queue_delayed_work()
          __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held)
            insert_work()
              kasan_record_aux_stack()
                kasan_save_stack()
                  stack_depot_save()
                    alloc_pages()
                      __alloc_pages()
                        get_page_from_freelist()
                          rm_queue()
                            rm_queue_pcplist()
                              local_lock_irqsave(&pagesets.lock, flags);
                              [ BUG: Invalid wait context triggered ]

Fix it by calling kasan_record_aux_stack() without holding pool lock. There is no need to hold pool lock in this path.

=============================
[ BUG: Invalid wait context ]
5.14.0-rc7+ #8 Not tainted
-----------------------------
snap/532 is trying to lock:
ffff888374f32ba0 (lock#2){..-.}-{3:3}, at: get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
other info that might help us debug this:
context-{5:5}
3 locks held by snap/532:
#0: ffff888139fa4408 (&type->i_mutex_dir_key#10){.+.+}-{4:4}, at: walk_component (fs/namei.c:1663 fs/namei.c:1959)
#1: ffffffffab870c40 (rcu_read_lock){....}-{1:3}, at: __queue_work (./arch/x86/include/asm/preempt.h:80 ./include/linux/rcupdate.h:68 ./include/linux/rcupdate.h:685 kernel/workqueue.c:1421) #2: ffff888374f36cd8 (&pool->lock){-.-.}-{2:2}, at: __queue_work (kernel/workqueue.c:1466)

 stack backtrace:
 CPU: 14 PID: 532 Comm: snap Not tainted 5.14.0-rc7+ #8
 Hardware name: LENOVO 90Q30008US/3728, BIOS O4ZKT1CA 09/16/2020
 Call Trace:
 dump_stack_lvl (lib/dump_stack.c:106 (discriminator 4))
 dump_stack (lib/dump_stack.c:113)
 __lock_acquire.cold (kernel/locking/lockdep.c:4666 kernel/locking/lockdep.c:4727 kernel/locking/lockdep.c:4965)
 ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4873)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 lock_acquire (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5627 kernel/locking/lockdep.c:5590)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_release (kernel/locking/lockdep.c:5593)
 ? __kasan_check_read (mm/kasan/shadow.c:32)
 ? __lock_acquire (kernel/locking/lockdep.c:5019)
 ? __zone_watermark_ok (./include/linux/list.h:282 ./include/linux/mmzone.h:111 mm/page_alloc.c:3908)
 get_page_from_freelist (./include/linux/local_lock_internal.h:43 mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 ? is_bpf_text_address (./arch/x86/include/asm/preempt.h:85 ./include/linux/rcupdate.h:73 ./include/linux/rcupdate.h:719 kernel/bpf/core.c:708)
 ? lock_downgrade (kernel/locking/lockdep.c:5633)
 ? __zone_watermark_ok (mm/page_alloc.c:4054)
 __alloc_pages (mm/page_alloc.c:5391)
 ? __alloc_pages_slowpath.constprop.0 (mm/page_alloc.c:5354)
 ? create_prof_cpu_mask (kernel/stacktrace.c:82)
? _find_first_bit (lib/find_bit.c:83)
 alloc_pages (mm/mempolicy.c:2249)
 stack_depot_save (lib/stackdepot.c:304)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 kasan_save_stack (mm/kasan/common.c:41)
 ? kasan_save_stack (mm/kasan/common.c:39)
 ? kasan_record_aux_stack (mm/kasan/generic.c:348)
 ? insert_work (./include/linux/instrumented.h:71 ./include/asm-generic/bitops/instrumented-non-atomic.h:134 kernel/workqueue.c:616 kernel/workqueue.c:623 kernel/workqueue.c:1335)
 ? __queue_work (kernel/workqueue.c:1501)
 ? __queue_delayed_work (kernel/workqueue.c:1657)
 ? mod_delayed_work_on (kernel/workqueue.c:1720)
 ? kblockd_mod_delayed_work_on (block/blk-core.c:1633)
 ? __blk_mq_delay_run_hw_queue (block/blk-mq.c:1567)
 ? blk_mq_run_hw_queue (block/blk-mq.c:1610)
 ? blk_mq_sched_insert_request (block/blk-mq-sched.c:480)
 ? blk_mq_submit_bio (block/blk-mq.c:2276)
Fixes e89a85d63fb2 ("workqueue: kasan: record workqueue stack")
---
 kernel/workqueue.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)
kernel/workqueue.c +0 -3
index f148eacda55a..e647b29b9fb0 100644
@@ -1328,9 +1328,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 {
        struct worker_pool *pool = pwq->pool;
 
-       /* record the work call stack in order to print it in KASAN reports */
-       kasan_record_aux_stack(work);
-
        /* we own @work, set data and link */
        set_work_pwq(work, pwq, extra_flags);
        list_add_tail(&work->entry, head);
@@ -1499,6 +1496,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 

kernel/workqueue.c static void __queue_work(int cpu, struct workqueue_struct *wq, · line 1506

Quoted 10 lines
kernel/workqueue.c +8 -0
 out:
        raw_spin_unlock(&pwq->pool->lock);
+
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);
+

Hello

After the pool lock is released, the work item can be executed and be freed before kasan_record_aux_stack() is called. Is it Ok?

And I think queue_work() is allowed to be called with other raw_spin held. If it is the case, kasan_record_aux_stack() is still in raw_spin held section.

Thanks
Lai

Quoted 20 lines
kernel/workqueue.c +7 -1
        rcu_read_unlock();
 }
 
@@ -3012,6 +3017,13 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
        insert_wq_barrier(pwq, barr, work, worker);
        raw_spin_unlock_irq(&pool->lock);
 
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);
+
        /*
         * Force a lock recursion deadlock when using flush_work() inside a
         * single-threaded or rescuer equipped workqueue.
--

2.30.2

author
#2 lore raw
Quoted 117 lines · Lai Jiangshan
Quoted 103 lines · Shuah Khan

When CONFIG_PROVE_RAW_LOCK_NESTING and CONFIG_KASAN are enabled, kasan_record_aux_stack() runs into "BUG: Invalid wait context" when it tries to allocate memory attempting to acquire spinlock in page allocation code while holding workqueue pool raw_spinlock.

There are several instances of this problem when block layer tries to __queue_work(). Call trace from one of these instances is below:

     kblockd_mod_delayed_work_on()
       mod_delayed_work_on()
         __queue_delayed_work()
           __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held)
             insert_work()
               kasan_record_aux_stack()
                 kasan_save_stack()
                   stack_depot_save()
                     alloc_pages()
                       __alloc_pages()
                         get_page_from_freelist()
                           rm_queue()
                             rm_queue_pcplist()
                               local_lock_irqsave(&pagesets.lock, flags);
                               [ BUG: Invalid wait context triggered ]

Fix it by calling kasan_record_aux_stack() without holding pool lock. There is no need to hold pool lock in this path.

=============================
[ BUG: Invalid wait context ]
5.14.0-rc7+ #8 Not tainted
-----------------------------
snap/532 is trying to lock:
ffff888374f32ba0 (lock#2){..-.}-{3:3}, at: get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
other info that might help us debug this:
context-{5:5}
3 locks held by snap/532:
#0: ffff888139fa4408 (&type->i_mutex_dir_key#10){.+.+}-{4:4}, at: walk_component (fs/namei.c:1663 fs/namei.c:1959)
#1: ffffffffab870c40 (rcu_read_lock){....}-{1:3}, at: __queue_work (./arch/x86/include/asm/preempt.h:80 ./include/linux/rcupdate.h:68 ./include/linux/rcupdate.h:685 kernel/workqueue.c:1421) #2: ffff888374f36cd8 (&pool->lock){-.-.}-{2:2}, at: __queue_work (kernel/workqueue.c:1466)

  stack backtrace:
  CPU: 14 PID: 532 Comm: snap Not tainted 5.14.0-rc7+ #8
  Hardware name: LENOVO 90Q30008US/3728, BIOS O4ZKT1CA 09/16/2020
  Call Trace:
  dump_stack_lvl (lib/dump_stack.c:106 (discriminator 4))
  dump_stack (lib/dump_stack.c:113)
  __lock_acquire.cold (kernel/locking/lockdep.c:4666 kernel/locking/lockdep.c:4727 kernel/locking/lockdep.c:4965)
  ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4873)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  lock_acquire (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5627 kernel/locking/lockdep.c:5590)
  ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? lock_release (kernel/locking/lockdep.c:5593)
  ? __kasan_check_read (mm/kasan/shadow.c:32)
  ? __lock_acquire (kernel/locking/lockdep.c:5019)
  ? __zone_watermark_ok (./include/linux/list.h:282 ./include/linux/mmzone.h:111 mm/page_alloc.c:3908)
  get_page_from_freelist (./include/linux/local_lock_internal.h:43 mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  ? is_bpf_text_address (./arch/x86/include/asm/preempt.h:85 ./include/linux/rcupdate.h:73 ./include/linux/rcupdate.h:719 kernel/bpf/core.c:708)
  ? lock_downgrade (kernel/locking/lockdep.c:5633)
  ? __zone_watermark_ok (mm/page_alloc.c:4054)
  __alloc_pages (mm/page_alloc.c:5391)
  ? __alloc_pages_slowpath.constprop.0 (mm/page_alloc.c:5354)
  ? create_prof_cpu_mask (kernel/stacktrace.c:82)
? _find_first_bit (lib/find_bit.c:83)
  alloc_pages (mm/mempolicy.c:2249)
  stack_depot_save (lib/stackdepot.c:304)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  kasan_save_stack (mm/kasan/common.c:41)
  ? kasan_save_stack (mm/kasan/common.c:39)
  ? kasan_record_aux_stack (mm/kasan/generic.c:348)
  ? insert_work (./include/linux/instrumented.h:71 ./include/asm-generic/bitops/instrumented-non-atomic.h:134 kernel/workqueue.c:616 kernel/workqueue.c:623 kernel/workqueue.c:1335)
  ? __queue_work (kernel/workqueue.c:1501)
  ? __queue_delayed_work (kernel/workqueue.c:1657)
  ? mod_delayed_work_on (kernel/workqueue.c:1720)
  ? kblockd_mod_delayed_work_on (block/blk-core.c:1633)
  ? __blk_mq_delay_run_hw_queue (block/blk-mq.c:1567)
  ? blk_mq_run_hw_queue (block/blk-mq.c:1610)
  ? blk_mq_sched_insert_request (block/blk-mq-sched.c:480)
  ? blk_mq_submit_bio (block/blk-mq.c:2276)
Fixes e89a85d63fb2 ("workqueue: kasan: record workqueue stack")
---
  kernel/workqueue.c | 18 +++++++++++++++---
  1 file changed, 15 insertions(+), 3 deletions(-)
kernel/workqueue.c +0 -3
index f148eacda55a..e647b29b9fb0 100644
@@ -1328,9 +1328,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
  {
         struct worker_pool *pool = pwq->pool;
 
-       /* record the work call stack in order to print it in KASAN reports */
-       kasan_record_aux_stack(work);
-
         /* we own @work, set data and link */
         set_work_pwq(work, pwq, extra_flags);
         list_add_tail(&work->entry, head);
@@ -1499,6 +1496,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 

kernel/workqueue.c static void __queue_work(int cpu, struct workqueue_struct *wq, · line 1506

Quoted 10 lines
kernel/workqueue.c +8 -0
  out:
         raw_spin_unlock(&pwq->pool->lock);
+
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);
+

Hello

Quoted 3 lines

After the pool lock is released, the work item can be executed and be freed before kasan_record_aux_stack() is called. Is it Ok?

Right. That is a concern. As Dmitry pointed out there is a bug in the code that kasan_record_aux_stack() is in the "out:" path.

Quoted 3 lines

And I think queue_work() is allowed to be called with other raw_spin held. If it is the case, kasan_record_aux_stack() is still in raw_spin held section.

I looked for queue_work() -> queue_work_on() -> __queue_work() and function header doc. I couldn't find any place it says it is okay to call queue_work() with raw spinlock held.

I am thinking that is not the case, since __queue_work() acquires pool lock which is a raw spinlock. The lockdep warning will occur when the pool lock acquire happens. I haven't seen it. We have 1290 callers of queue_work() and we would have seen this before.

thanks,
-- Shuah

#3 lore raw
In reply to Shuah Khan
Quoted 102 lines · Shuah Khan

When CONFIG_PROVE_RAW_LOCK_NESTING and CONFIG_KASAN are enabled, kasan_record_aux_stack() runs into "BUG: Invalid wait context" when it tries to allocate memory attempting to acquire spinlock in page allocation code while holding workqueue pool raw_spinlock.

There are several instances of this problem when block layer tries to __queue_work(). Call trace from one of these instances is below:

    kblockd_mod_delayed_work_on()
      mod_delayed_work_on()
        __queue_delayed_work()
          __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held)
            insert_work()
              kasan_record_aux_stack()
                kasan_save_stack()
                  stack_depot_save()
                    alloc_pages()
                      __alloc_pages()
                        get_page_from_freelist()
                          rm_queue()
                            rm_queue_pcplist()
                              local_lock_irqsave(&pagesets.lock, flags);
                              [ BUG: Invalid wait context triggered ]

Fix it by calling kasan_record_aux_stack() without holding pool lock. There is no need to hold pool lock in this path.

=============================
[ BUG: Invalid wait context ]
5.14.0-rc7+ #8 Not tainted
-----------------------------
snap/532 is trying to lock:
ffff888374f32ba0 (lock#2){..-.}-{3:3}, at: get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
other info that might help us debug this:
context-{5:5}
3 locks held by snap/532:
#0: ffff888139fa4408 (&type->i_mutex_dir_key#10){.+.+}-{4:4}, at: walk_component (fs/namei.c:1663 fs/namei.c:1959)
#1: ffffffffab870c40 (rcu_read_lock){....}-{1:3}, at: __queue_work (./arch/x86/include/asm/preempt.h:80 ./include/linux/rcupdate.h:68 ./include/linux/rcupdate.h:685 kernel/workqueue.c:1421) #2: ffff888374f36cd8 (&pool->lock){-.-.}-{2:2}, at: __queue_work (kernel/workqueue.c:1466)

 stack backtrace:
 CPU: 14 PID: 532 Comm: snap Not tainted 5.14.0-rc7+ #8
 Hardware name: LENOVO 90Q30008US/3728, BIOS O4ZKT1CA 09/16/2020
 Call Trace:
 dump_stack_lvl (lib/dump_stack.c:106 (discriminator 4))
 dump_stack (lib/dump_stack.c:113)
 __lock_acquire.cold (kernel/locking/lockdep.c:4666 kernel/locking/lockdep.c:4727 kernel/locking/lockdep.c:4965)
 ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4873)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 lock_acquire (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5627 kernel/locking/lockdep.c:5590)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_release (kernel/locking/lockdep.c:5593)
 ? __kasan_check_read (mm/kasan/shadow.c:32)
 ? __lock_acquire (kernel/locking/lockdep.c:5019)
 ? __zone_watermark_ok (./include/linux/list.h:282 ./include/linux/mmzone.h:111 mm/page_alloc.c:3908)
 get_page_from_freelist (./include/linux/local_lock_internal.h:43 mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 ? is_bpf_text_address (./arch/x86/include/asm/preempt.h:85 ./include/linux/rcupdate.h:73 ./include/linux/rcupdate.h:719 kernel/bpf/core.c:708)
 ? lock_downgrade (kernel/locking/lockdep.c:5633)
 ? __zone_watermark_ok (mm/page_alloc.c:4054)
 __alloc_pages (mm/page_alloc.c:5391)
 ? __alloc_pages_slowpath.constprop.0 (mm/page_alloc.c:5354)
 ? create_prof_cpu_mask (kernel/stacktrace.c:82)
? _find_first_bit (lib/find_bit.c:83)
 alloc_pages (mm/mempolicy.c:2249)
 stack_depot_save (lib/stackdepot.c:304)
 ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
 kasan_save_stack (mm/kasan/common.c:41)
 ? kasan_save_stack (mm/kasan/common.c:39)
 ? kasan_record_aux_stack (mm/kasan/generic.c:348)
 ? insert_work (./include/linux/instrumented.h:71 ./include/asm-generic/bitops/instrumented-non-atomic.h:134 kernel/workqueue.c:616 kernel/workqueue.c:623 kernel/workqueue.c:1335)
 ? __queue_work (kernel/workqueue.c:1501)
 ? __queue_delayed_work (kernel/workqueue.c:1657)
 ? mod_delayed_work_on (kernel/workqueue.c:1720)
 ? kblockd_mod_delayed_work_on (block/blk-core.c:1633)
 ? __blk_mq_delay_run_hw_queue (block/blk-mq.c:1567)
 ? blk_mq_run_hw_queue (block/blk-mq.c:1610)
 ? blk_mq_sched_insert_request (block/blk-mq-sched.c:480)
 ? blk_mq_submit_bio (block/blk-mq.c:2276)
Fixes e89a85d63fb2 ("workqueue: kasan: record workqueue stack")
---
 kernel/workqueue.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)
kernel/workqueue.c +0 -3
index f148eacda55a..e647b29b9fb0 100644
@@ -1328,9 +1328,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 {
        struct worker_pool *pool = pwq->pool;
 
-       /* record the work call stack in order to print it in KASAN reports */
-       kasan_record_aux_stack(work);
-
        /* we own @work, set data and link */
        set_work_pwq(work, pwq, extra_flags);
        list_add_tail(&work->entry, head);

kernel/workqueue.c static void __queue_work(int cpu, struct workqueue_struct *wq, · line 1505

Quoted 10 lines
kernel/workqueue.c +7 -0
@@ -1499,6 +1496,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
 out:
        raw_spin_unlock(&pwq->pool->lock);
+
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);

Hi Shuah,

I agree that the current code is problematic and we don't need to hold the lock around kasan_record_aux_stack().

However, I think we need to call kasan_record_aux_stack() before the actual queueing, otherwise the work can be dequeued and cause a bug before we call kasan_record_aux_stack() in this task (it's like setting permissions on an fd after publishing it in fd table).

Also, this happens after "out:" label and it seems we go to it even if we don't queue the work in some cases. Ideally we only call kasan_record_aux_stack() only if we queue it, because the capacity for aux stacks are only 2 stacks (the oldest gets evicted). However, I think the first point is more important. So if move kasan_record_aux_stack() to happen before insert_work() and won't be able to predict if we actually queue it later or not, then I think it's fine to episodically call kasan_record_aux_stack() even if we don't queue later. At least I don't see a better solution.

Quoted 20 lines
kernel/workqueue.c +7 -1
        rcu_read_unlock();
 }
 
@@ -3012,6 +3017,13 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
        insert_wq_barrier(pwq, barr, work, worker);
        raw_spin_unlock_irq(&pool->lock);
 
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);
+
        /*
         * Force a lock recursion deadlock when using flush_work() inside a
         * single-threaded or rescuer equipped workqueue.
--

2.30.2

author
#4 lore raw
Quoted 116 lines · Dmitry Vyukov
Quoted 102 lines · Shuah Khan

When CONFIG_PROVE_RAW_LOCK_NESTING and CONFIG_KASAN are enabled, kasan_record_aux_stack() runs into "BUG: Invalid wait context" when it tries to allocate memory attempting to acquire spinlock in page allocation code while holding workqueue pool raw_spinlock.

There are several instances of this problem when block layer tries to __queue_work(). Call trace from one of these instances is below:

     kblockd_mod_delayed_work_on()
       mod_delayed_work_on()
         __queue_delayed_work()
           __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held)
             insert_work()
               kasan_record_aux_stack()
                 kasan_save_stack()
                   stack_depot_save()
                     alloc_pages()
                       __alloc_pages()
                         get_page_from_freelist()
                           rm_queue()
                             rm_queue_pcplist()
                               local_lock_irqsave(&pagesets.lock, flags);
                               [ BUG: Invalid wait context triggered ]

Fix it by calling kasan_record_aux_stack() without holding pool lock. There is no need to hold pool lock in this path.

=============================
[ BUG: Invalid wait context ]
5.14.0-rc7+ #8 Not tainted
-----------------------------
snap/532 is trying to lock:
ffff888374f32ba0 (lock#2){..-.}-{3:3}, at: get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
other info that might help us debug this:
context-{5:5}
3 locks held by snap/532:
#0: ffff888139fa4408 (&type->i_mutex_dir_key#10){.+.+}-{4:4}, at: walk_component (fs/namei.c:1663 fs/namei.c:1959)
#1: ffffffffab870c40 (rcu_read_lock){....}-{1:3}, at: __queue_work (./arch/x86/include/asm/preempt.h:80 ./include/linux/rcupdate.h:68 ./include/linux/rcupdate.h:685 kernel/workqueue.c:1421) #2: ffff888374f36cd8 (&pool->lock){-.-.}-{2:2}, at: __queue_work (kernel/workqueue.c:1466)

  stack backtrace:
  CPU: 14 PID: 532 Comm: snap Not tainted 5.14.0-rc7+ #8
  Hardware name: LENOVO 90Q30008US/3728, BIOS O4ZKT1CA 09/16/2020
  Call Trace:
  dump_stack_lvl (lib/dump_stack.c:106 (discriminator 4))
  dump_stack (lib/dump_stack.c:113)
  __lock_acquire.cold (kernel/locking/lockdep.c:4666 kernel/locking/lockdep.c:4727 kernel/locking/lockdep.c:4965)
  ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4873)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  lock_acquire (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5627 kernel/locking/lockdep.c:5590)
  ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? lock_release (kernel/locking/lockdep.c:5593)
  ? __kasan_check_read (mm/kasan/shadow.c:32)
  ? __lock_acquire (kernel/locking/lockdep.c:5019)
  ? __zone_watermark_ok (./include/linux/list.h:282 ./include/linux/mmzone.h:111 mm/page_alloc.c:3908)
  get_page_from_freelist (./include/linux/local_lock_internal.h:43 mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? get_page_from_freelist (mm/page_alloc.c:3665 mm/page_alloc.c:3703 mm/page_alloc.c:4165)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  ? is_bpf_text_address (./arch/x86/include/asm/preempt.h:85 ./include/linux/rcupdate.h:73 ./include/linux/rcupdate.h:719 kernel/bpf/core.c:708)
  ? lock_downgrade (kernel/locking/lockdep.c:5633)
  ? __zone_watermark_ok (mm/page_alloc.c:4054)
  __alloc_pages (mm/page_alloc.c:5391)
  ? __alloc_pages_slowpath.constprop.0 (mm/page_alloc.c:5354)
  ? create_prof_cpu_mask (kernel/stacktrace.c:82)
? _find_first_bit (lib/find_bit.c:83)
  alloc_pages (mm/mempolicy.c:2249)
  stack_depot_save (lib/stackdepot.c:304)
  ? lock_is_held_type (kernel/locking/lockdep.c:5368 kernel/locking/lockdep.c:5668)
  kasan_save_stack (mm/kasan/common.c:41)
  ? kasan_save_stack (mm/kasan/common.c:39)
  ? kasan_record_aux_stack (mm/kasan/generic.c:348)
  ? insert_work (./include/linux/instrumented.h:71 ./include/asm-generic/bitops/instrumented-non-atomic.h:134 kernel/workqueue.c:616 kernel/workqueue.c:623 kernel/workqueue.c:1335)
  ? __queue_work (kernel/workqueue.c:1501)
  ? __queue_delayed_work (kernel/workqueue.c:1657)
  ? mod_delayed_work_on (kernel/workqueue.c:1720)
  ? kblockd_mod_delayed_work_on (block/blk-core.c:1633)
  ? __blk_mq_delay_run_hw_queue (block/blk-mq.c:1567)
  ? blk_mq_run_hw_queue (block/blk-mq.c:1610)
  ? blk_mq_sched_insert_request (block/blk-mq-sched.c:480)
  ? blk_mq_submit_bio (block/blk-mq.c:2276)
Fixes e89a85d63fb2 ("workqueue: kasan: record workqueue stack")
---
  kernel/workqueue.c | 18 +++++++++++++++---
  1 file changed, 15 insertions(+), 3 deletions(-)
kernel/workqueue.c +0 -3
index f148eacda55a..e647b29b9fb0 100644
@@ -1328,9 +1328,6 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
  {
         struct worker_pool *pool = pwq->pool;
 
-       /* record the work call stack in order to print it in KASAN reports */
-       kasan_record_aux_stack(work);
-
         /* we own @work, set data and link */
         set_work_pwq(work, pwq, extra_flags);
         list_add_tail(&work->entry, head);

kernel/workqueue.c static void __queue_work(int cpu, struct workqueue_struct *wq, · line 1505

Quoted 10 lines
kernel/workqueue.c +7 -0
@@ -1499,6 +1496,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
  out:
         raw_spin_unlock(&pwq->pool->lock);
+
+       /*
+        * record the work call stack in order to print it in KASAN reports
+        * Do this without pool raw_spinlock hold to avoid nesting raw
+        * spinlock with page allocation spinlock.
+        */
+       kasan_record_aux_stack(work);

Hi Shuah,

Quoted 3 lines

I agree that the current code is problematic and we don't need to hold the lock around kasan_record_aux_stack().

Good.

Quoted 5 lines

However, I think we need to call kasan_record_aux_stack() before the actual queueing, otherwise the work can be dequeued and cause a bug before we call kasan_record_aux_stack() in this task (it's like setting permissions on an fd after publishing it in fd table).

You are right. This patch does change the order of recording by moving from insert_work(). I couldn't find a unrecord step in the current code? Where does that happen? Is it necessary to deallocate and do other cleanup when work gets dequeued?

Quoted 11 lines

Also, this happens after "out:" label and it seems we go to it even if we don't queue the work in some cases. Ideally we only call kasan_record_aux_stack() only if we queue it, because the capacity for aux stacks are only 2 stacks (the oldest gets evicted). However, I think the first point is more important. So if move kasan_record_aux_stack() to happen before insert_work() and won't be able to predict if we actually queue it later or not, then I think it's fine to episodically call kasan_record_aux_stack() even if we don't queue later. At least I don't see a better solution.

Yeah. I missed that. I was careful with the start_flush_work() out leg.

thanks,
-- Shuah