Skip to contentSkip to conversation

drm/amdkfd: Fix lock dependency warning with srcu

PATCH In review Philip Yang 2 participants 2 messages Jan 3, 2024

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/amdkfd: Fix lock dependency warning with srcu

======================================================
WARNING: possible circular locking dependency detected 6.5.0-kfd-yangp #2289 Not tainted
------------------------------------------------------
kworker/0:2/996 is trying to acquire lock:

        (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0

but task is already holding lock:

        ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at:
	process_one_work+0x211/0x560

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}:

        __flush_work+0x88/0x4f0
        svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu]
        svm_range_set_attr+0xd6/0x14c0 [amdgpu]
        kfd_ioctl+0x1d1/0x630 [amdgpu]
        __x64_sys_ioctl+0x88/0xc0

-> #2 (&info->lock#2){+.+.}-{3:3}:

        __mutex_lock+0x99/0xc70
        amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu]
        restore_process_helper+0x22/0x80 [amdgpu]
        restore_process_worker+0x2d/0xa0 [amdgpu]
        process_one_work+0x29b/0x560
        worker_thread+0x3d/0x3d0

-> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}:

        __flush_work+0x88/0x4f0
        __cancel_work_timer+0x12c/0x1c0
        kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu]
        __mmu_notifier_release+0xad/0x240
        exit_mmap+0x6a/0x3a0
        mmput+0x6a/0x120
        do_exit+0x322/0xb90
        do_group_exit+0x37/0xa0
        __x64_sys_exit_group+0x18/0x20
        do_syscall_64+0x38/0x80

-> #0 (srcu){.+.+}-{0:0}:

        __lock_acquire+0x1521/0x2510
        lock_sync+0x5f/0x90
        __synchronize_srcu+0x4f/0x1a0
        __mmu_notifier_release+0x128/0x240
        exit_mmap+0x6a/0x3a0
        mmput+0x6a/0x120
        svm_range_deferred_list_work+0x19f/0x350 [amdgpu]
        process_one_work+0x29b/0x560
        worker_thread+0x3d/0x3d0

other info that might help us debug this:

Chain exists of:
  srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work)

Possible unsafe locking scenario:
        CPU0                    CPU1
        ----                    ----
        lock((work_completion)(&svms->deferred_list_work));
                        lock(&info->lock#2);
			lock((work_completion)(&svms->deferred_list_work));
        sync(srcu);
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +4 -2
index 2ac0c7788dfc..6c0e6d654a26 100644
@@ -2340,8 +2340,10 @@ static void svm_range_deferred_list_work(struct work_struct *work)
 		mutex_unlock(&svms->lock);
 		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
Signature · 1 line
2.35.1
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 59 lines · Philip Yang

======================================================
WARNING: possible circular locking dependency detected 6.5.0-kfd-yangp #2289 Not tainted
------------------------------------------------------
kworker/0:2/996 is trying to acquire lock:

         (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0

but task is already holding lock:

         ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at:
	process_one_work+0x211/0x560

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}:

         __flush_work+0x88/0x4f0
         svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu]
         svm_range_set_attr+0xd6/0x14c0 [amdgpu]
         kfd_ioctl+0x1d1/0x630 [amdgpu]
         __x64_sys_ioctl+0x88/0xc0

-> #2 (&info->lock#2){+.+.}-{3:3}:

         __mutex_lock+0x99/0xc70
         amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu]
         restore_process_helper+0x22/0x80 [amdgpu]
         restore_process_worker+0x2d/0xa0 [amdgpu]
         process_one_work+0x29b/0x560
         worker_thread+0x3d/0x3d0

-> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}:

         __flush_work+0x88/0x4f0
         __cancel_work_timer+0x12c/0x1c0
         kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu]
         __mmu_notifier_release+0xad/0x240
         exit_mmap+0x6a/0x3a0
         mmput+0x6a/0x120
         do_exit+0x322/0xb90
         do_group_exit+0x37/0xa0
         __x64_sys_exit_group+0x18/0x20
         do_syscall_64+0x38/0x80

-> #0 (srcu){.+.+}-{0:0}:

         __lock_acquire+0x1521/0x2510
         lock_sync+0x5f/0x90
         __synchronize_srcu+0x4f/0x1a0
         __mmu_notifier_release+0x128/0x240
         exit_mmap+0x6a/0x3a0
         mmput+0x6a/0x120
         svm_range_deferred_list_work+0x19f/0x350 [amdgpu]
         process_one_work+0x29b/0x560
         worker_thread+0x3d/0x3d0

other info that might help us debug this:

Chain exists of:
   srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work)

Possible unsafe locking scenario:
Quoted 8 lines
         CPU0                    CPU1
         ----                    ----
         lock((work_completion)(&svms->deferred_list_work));
                         lock(&info->lock#2);
			lock((work_completion)(&svms->deferred_list_work));
         sync(srcu);
Quoted 21 lines
---
  drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 ++++--
  1 file changed, 4 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +4 -2
index 2ac0c7788dfc..6c0e6d654a26 100644
@@ -2340,8 +2340,10 @@ static void svm_range_deferred_list_work(struct work_struct *work)
  		mutex_unlock(&svms->lock);
  		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
  		spin_lock(&svms->deferred_list_lock);
  	}