1 files changed, 28 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 368283d53077..5fb3679e4e85 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -910,7 +910,7 @@ static void kfd_process_free_id(struct kfd_process *process)
 {
 	struct kfd_process *primary_process;
 
-	if (process->context_id != KFD_CONTEXT_ID_PRIMARY)
+	if (process->context_id == KFD_CONTEXT_ID_PRIMARY)
 		return;
 
 	primary_process = kfd_lookup_process_by_mm(process->lead_thread->mm);
@@ -1175,10 +1175,12 @@ static void kfd_process_remove_sysfs(struct kfd_process *p)
 	if (!p->kobj)
 		return;
 
-	sysfs_remove_file(p->kobj, &p->attr_pasid);
-	kobject_del(p->kobj_queues);
-	kobject_put(p->kobj_queues);
-	p->kobj_queues = NULL;
+	if (p->kobj_queues) {
+		sysfs_remove_file(p->kobj, &p->attr_pasid);
+		kobject_del(p->kobj_queues);
+		kobject_put(p->kobj_queues);
+		p->kobj_queues = NULL;
+	}
 
 	for (i = 0; i < p->n_pdds; i++) {
 		pdd = p->pdds[i];
@@ -1186,17 +1188,21 @@ static void kfd_process_remove_sysfs(struct kfd_process *p)
 		sysfs_remove_file(p->kobj, &pdd->attr_vram);
 		sysfs_remove_file(p->kobj, &pdd->attr_sdma);
 
-		sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict);
-		if (pdd->dev->kfd2kgd->get_cu_occupancy)
-			sysfs_remove_file(pdd->kobj_stats,
-					  &pdd->attr_cu_occupancy);
-		kobject_del(pdd->kobj_stats);
-		kobject_put(pdd->kobj_stats);
-		pdd->kobj_stats = NULL;
+		if (pdd->kobj_stats) {
+			sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict);
+			if (pdd->dev->kfd2kgd->get_cu_occupancy)
+				sysfs_remove_file(pdd->kobj_stats,
+						  &pdd->attr_cu_occupancy);
+			kobject_del(pdd->kobj_stats);
+			kobject_put(pdd->kobj_stats);
+			pdd->kobj_stats = NULL;
+		}
 	}
 
 	for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) {
 		pdd = p->pdds[i];
+		if (!pdd->kobj_counters)
+			continue;
 
 		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_faults);
 		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_in);
@@ -1254,6 +1260,13 @@ static void kfd_process_wq_release(struct work_struct *work)
 
 	kfd_debugfs_remove_process(p);
 
+	/*
+	 * Remove the proc/sysfs entries before destroying PDDs. The removal path
+	 * walks the PDD array and sysfs callbacks dereference PDD fields, so the
+	 * backing data must remain valid until sysfs removal has completed.
+	 */
+	kfd_process_remove_sysfs(p);
+
 	kfd_process_kunmap_signal_bo(p);
 	kfd_process_free_outstanding_kfd_bos(p);
 	svm_range_list_fini(p);
@@ -1267,11 +1280,6 @@ static void kfd_process_wq_release(struct work_struct *work)
 
 	put_task_struct(p->lead_thread);
 
-	/* the last step is removing process entries under /sys
-	 * to indicate the process has been terminated.
-	 */
-	kfd_process_remove_sysfs(p);
-
 	kfree(p);
 }
 
@@ -1969,7 +1977,7 @@ int kfd_process_evict_queues(struct kfd_process *p, uint32_t trigger)
 		struct kfd_process_device *pdd = p->pdds[i];
 		struct device *dev = pdd->dev->adev->dev;
 
-		kfd_smi_event_queue_eviction(pdd->dev, p->lead_thread->pid,
+		kfd_smi_event_queue_eviction(pdd->dev, p->lead_thread,
 					     trigger);
 
 		r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm,
@@ -1999,7 +2007,7 @@ fail:
 		if (n_evicted == 0)
 			break;
 
-		kfd_smi_event_queue_restore(pdd->dev, p->lead_thread->pid);
+		kfd_smi_event_queue_restore(pdd->dev, p->lead_thread);
 
 		if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm,
 							      &pdd->qpd))
@@ -2022,7 +2030,7 @@ int kfd_process_restore_queues(struct kfd_process *p)
 		struct kfd_process_device *pdd = p->pdds[i];
 		struct device *dev = pdd->dev->adev->dev;
 
-		kfd_smi_event_queue_restore(pdd->dev, p->lead_thread->pid);
+		kfd_smi_event_queue_restore(pdd->dev, p->lead_thread);
 
 		r = pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm,
 							      &pdd->qpd);