[PATCH 1/5] drm/amdkfd: svm range restore work deadlock when process exit

[Philip Yang <Philip.Yang@xxxxxxx>]

kfd_process_notifier_release flush svm_range_restore_work may cause
deadlock, because svm_range_restore_work calls
svm_range_list_lock_and_flush_work which takes mmap write lock. Move
flush svm_range_restore_work to kfd_process_wq_release to avoid
deadlock. Then svm_range_restore_work needs taking mm ref.

Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
Reported-by: Ruili Ji <ruili.ji@xxxxxxx>
---
 drivers/gpu/drm/amd/amdkfd/kfd_process.c |  1 -
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 14 ++++++++------
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d1145da5348f..74f162887d3b 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 f2805ba74c80..37b3191615b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1643,13 +1643,13 @@ 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)
+	/* Avoid mm is gone 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);
@@ -1703,6 +1703,7 @@ 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) {
@@ -2830,6 +2831,8 @@ 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);
 
@@ -2840,7 +2843,6 @@ 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);
-- 
2.17.1