From: Philip Yang <Philip.Yang@xxxxxxx>
[ Upstream commit 6225bb3a88d22594aacea2485dc28ca12d596721 ]
kfd_process_notifier_release flush svm_range_restore_work
which calls svm_range_list_lock_and_flush_work to flush deferred_list
work, but if deferred_list work mmput release the last user, it will
call exit_mmap -> notifier_release, it is deadlock with below backtrace.
Move flush svm_range_restore_work to kfd_process_wq_release to avoid
deadlock. Then svm_range_restore_work take task->mm ref to avoid mm is
gone while validating and mapping ranges to GPU.
Workqueue: events svm_range_deferred_list_work [amdgpu]
Call Trace:
wait_for_completion+0x94/0x100
__flush_work+0x12a/0x1e0
__cancel_work_timer+0x10e/0x190
cancel_delayed_work_sync+0x13/0x20
kfd_process_notifier_release+0x98/0x2a0 [amdgpu]
__mmu_notifier_release+0x74/0x1f0
exit_mmap+0x170/0x200
mmput+0x5d/0x130
svm_range_deferred_list_work+0x104/0x230 [amdgpu]
process_one_work+0x220/0x3c0
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
Reported-by: Ruili Ji <ruili.ji@xxxxxxx>
Tested-by: Ruili Ji <ruili.ji@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 1 -
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 15 +++++++++------
2 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index b993011cfa64..990228711108 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1150,7 +1150,6 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
cancel_delayed_work_sync(&p->eviction_work);
cancel_delayed_work_sync(&p->restore_work);
- cancel_delayed_work_sync(&p->svms.restore_work);
mutex_lock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index ea1c5aaf659a..a1b0c6bda803 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1589,13 +1589,14 @@ static void svm_range_restore_work(struct work_struct *work)
pr_debug("restore svm ranges\n");
- /* kfd_process_notifier_release destroys this worker thread. So during
- * the lifetime of this thread, kfd_process and mm will be valid.
- */
p = container_of(svms, struct kfd_process, svms);
- mm = p->mm;
- if (!mm)
+
+ /* Keep mm reference when svm_range_validate_and_map ranges */
+ mm = get_task_mm(p->lead_thread);
+ if (!mm) {
+ pr_debug("svms 0x%p process mm gone\n", svms);
return;
+ }
svm_range_list_lock_and_flush_work(svms, mm);
mutex_lock(&svms->lock);
@@ -1649,6 +1650,7 @@ static void svm_range_restore_work(struct work_struct *work)
out_reschedule:
mutex_unlock(&svms->lock);
mmap_write_unlock(mm);
+ mmput(mm);
/* If validation failed, reschedule another attempt */
if (evicted_ranges) {
@@ -2779,6 +2781,8 @@ void svm_range_list_fini(struct kfd_process *p)
pr_debug("pasid 0x%x svms 0x%p\n", p->pasid, &p->svms);
+ cancel_delayed_work_sync(&p->svms.restore_work);
+
/* Ensure list work is finished before process is destroyed */
flush_work(&p->svms.deferred_list_work);
@@ -2789,7 +2793,6 @@ void svm_range_list_fini(struct kfd_process *p)
atomic_inc(&p->svms.drain_pagefaults);
svm_range_drain_retry_fault(&p->svms);
-
list_for_each_entry_safe(prange, next, &p->svms.list, list) {
svm_range_unlink(prange);
svm_range_remove_notifier(prange);
--
2.34.1
