2 files changed, 44 insertions, 28 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index ac005796b71c..7708d90b9da9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 	pqm_uninit(&p->pqm);
 
 	/* Iterate over all process device data structure and check
-	 * if we should reset all wavefronts */
-	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+	 * if we should delete debug managers and reset all wavefronts
+	 */
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+		if ((pdd->dev->dbgmgr) &&
+				(pdd->dev->dbgmgr->pasid == p->pasid))
+			kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
+
 		if (pdd->reset_wavefronts) {
 			pr_warn("amdkfd: Resetting all wave fronts\n");
 			dbgdev_wave_reset_wavefronts(pdd->dev, p);
 			pdd->reset_wavefronts = false;
 		}
+	}
 
 	mutex_unlock(&p->mutex);
 
@@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 
+	/*
+	 * Look for the process that matches the pasid. If there is no such
+	 * process, we either released it in amdkfd's own notifier, or there
+	 * is a bug. Unfortunately, there is no way to tell...
+	 */
 	hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes)
-		if (p->pasid == pasid)
-			break;
+		if (p->pasid == pasid) {
 
-	srcu_read_unlock(&kfd_processes_srcu, idx);
+			srcu_read_unlock(&kfd_processes_srcu, idx);
 
-	BUG_ON(p->pasid != pasid);
+			pr_debug("Unbinding process %d from IOMMU\n", pasid);
 
-	mutex_lock(&p->mutex);
+			mutex_lock(&p->mutex);
 
-	if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
-		kfd_dbgmgr_destroy(dev->dbgmgr);
+			if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
+				kfd_dbgmgr_destroy(dev->dbgmgr);
 
-	pqm_uninit(&p->pqm);
+			pqm_uninit(&p->pqm);
 
-	pdd = kfd_get_process_device_data(dev, p);
+			pdd = kfd_get_process_device_data(dev, p);
 
-	if (!pdd) {
-		mutex_unlock(&p->mutex);
-		return;
-	}
+			if (!pdd) {
+				mutex_unlock(&p->mutex);
+				return;
+			}
 
-	if (pdd->reset_wavefronts) {
-		dbgdev_wave_reset_wavefronts(pdd->dev, p);
-		pdd->reset_wavefronts = false;
-	}
+			if (pdd->reset_wavefronts) {
+				dbgdev_wave_reset_wavefronts(pdd->dev, p);
+				pdd->reset_wavefronts = false;
+			}
 
-	/*
-	 * Just mark pdd as unbound, because we still need it to call
-	 * amd_iommu_unbind_pasid() in when the process exits.
-	 * We don't call amd_iommu_unbind_pasid() here
-	 * because the IOMMU called us.
-	 */
-	pdd->bound = false;
+			/*
+			 * Just mark pdd as unbound, because we still need it
+			 * to call amd_iommu_unbind_pasid() in when the
+			 * process exits.
+			 * We don't call amd_iommu_unbind_pasid() here
+			 * because the IOMMU called us.
+			 */
+			pdd->bound = false;
 
-	mutex_unlock(&p->mutex);
+			mutex_unlock(&p->mutex);
+
+			return;
+		}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
 }
 
 struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 74909e72a009..884c96f50c3d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -666,7 +666,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.simd_count);
 
 	if (dev->mem_bank_count < dev->node_props.mem_banks_count) {
-		pr_warn("kfd: mem_banks_count truncated from %d to %d\n",
+		pr_info_once("kfd: mem_banks_count truncated from %d to %d\n",
 				dev->node_props.mem_banks_count,
 				dev->mem_bank_count);
 		sysfs_show_32bit_prop(buffer, "mem_banks_count",