Merge tag 'amd-drm-fixes-5.19-2022-07-20' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-5.19-2022-07-20:

amdgpu:
- Drop redundant buffer cleanup that can lead to a segfault
- Add a bo_list mutex to avoid possible list corruption in CS

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220720210917.6202-1-alexander.deucher@amd.com

5 files changed, 38 insertions, 18 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6b6d46e29e6e8b..4608599ba6bb54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1364,16 +1364,10 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				    struct amdgpu_vm *vm)
 {
 	struct amdkfd_process_info *process_info = vm->process_info;
-	struct amdgpu_bo *pd = vm->root.bo;
 
 	if (!process_info)
 		return;
 
-	/* Release eviction fence from PD */
-	amdgpu_bo_reserve(pd, false);
-	amdgpu_bo_fence(pd, NULL, false);
-	amdgpu_bo_unreserve(pd);
-
 	/* Update process info */
 	mutex_lock(&process_info->lock);
 	process_info->n_vms--;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 714178f1b6c6ed..2168163aad2d38 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -40,7 +40,7 @@ static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu)
 {
 	struct amdgpu_bo_list *list = container_of(rcu, struct amdgpu_bo_list,
 						   rhead);
-
+	mutex_destroy(&list->bo_list_mutex);
 	kvfree(list);
 }
 
@@ -136,6 +136,7 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 
 	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
 
+	mutex_init(&list->bo_list_mutex);
 	*result = list;
 	return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 529d52a204cf4a..9caea1688fc322 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -47,6 +47,10 @@ struct amdgpu_bo_list {
 	struct amdgpu_bo *oa_obj;
 	unsigned first_userptr;
 	unsigned num_entries;
+
+	/* Protect access during command submission.
+	 */
+	struct mutex bo_list_mutex;
 };
 
 int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index b28af04b0c3e93..d8f1335bc68f41 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -519,6 +519,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			return r;
 	}
 
+	mutex_lock(&p->bo_list->bo_list_mutex);
+
 	/* One for TTM and one for the CS job */
 	amdgpu_bo_list_for_each_entry(e, p->bo_list)
 		e->tv.num_shared = 2;
@@ -651,6 +653,7 @@ out_free_user_pages:
 			kvfree(e->user_pages);
 			e->user_pages = NULL;
 		}
+		mutex_unlock(&p->bo_list->bo_list_mutex);
 	}
 	return r;
 }
@@ -690,9 +693,11 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 {
 	unsigned i;
 
-	if (error && backoff)
+	if (error && backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
+		mutex_unlock(&parser->bo_list->bo_list_mutex);
+	}
 
 	for (i = 0; i < parser->num_post_deps; i++) {
 		drm_syncobj_put(parser->post_deps[i].syncobj);
@@ -832,12 +837,16 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			continue;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
-		if (r)
+		if (r) {
+			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
+		}
 
 		r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update);
-		if (r)
+		if (r) {
+			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
+		}
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
@@ -1278,6 +1287,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	mutex_unlock(&p->adev->notifier_lock);
+	mutex_unlock(&p->bo_list->bo_list_mutex);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 93ac33a8de9aab..3087dd1a1856cd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1653,7 +1653,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
 	adev->dm.crc_rd_wrk = amdgpu_dm_crtc_secure_display_create_work();
 #endif
-	if (dc_enable_dmub_notifications(adev->dm.dc)) {
+	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
 		init_completion(&adev->dm.dmub_aux_transfer_done);
 		adev->dm.dmub_notify = kzalloc(sizeof(struct dmub_notification), GFP_KERNEL);
 		if (!adev->dm.dmub_notify) {
@@ -1689,6 +1689,13 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		goto error;
 	}
 
+	/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
+	 * It is expected that DMUB will resend any pending notifications at this point, for
+	 * example HPD from DPIA.
+	 */
+	if (dc_is_dmub_outbox_supported(adev->dm.dc))
+		dc_enable_dmub_outbox(adev->dm.dc);
+
 	/* create fake encoders for MST */
 	dm_dp_create_fake_mst_encoders(adev);
 
@@ -2678,9 +2685,6 @@ static int dm_resume(void *handle)
 		 */
 		link_enc_cfg_copy(adev->dm.dc->current_state, dc_state);
 
-		if (dc_enable_dmub_notifications(adev->dm.dc))
-			amdgpu_dm_outbox_init(adev);
-
 		r = dm_dmub_hw_init(adev);
 		if (r)
 			DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
@@ -2698,6 +2702,11 @@ static int dm_resume(void *handle)
 			}
 		}
 
+		if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+			amdgpu_dm_outbox_init(adev);
+			dc_enable_dmub_outbox(adev->dm.dc);
+		}
+
 		WARN_ON(!dc_commit_state(dm->dc, dc_state));
 
 		dm_gpureset_commit_state(dm->cached_dc_state, dm);
@@ -2719,13 +2728,15 @@ static int dm_resume(void *handle)
 	/* TODO: Remove dc_state->dccg, use dc->dccg directly. */
 	dc_resource_state_construct(dm->dc, dm_state->context);
 
-	/* Re-enable outbox interrupts for DPIA. */
-	if (dc_enable_dmub_notifications(adev->dm.dc))
-		amdgpu_dm_outbox_init(adev);
-
 	/* Before powering on DC we need to re-initialize DMUB. */
 	dm_dmub_hw_resume(adev);
 
+	/* Re-enable outbox interrupts for DPIA. */
+	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		amdgpu_dm_outbox_init(adev);
+		dc_enable_dmub_outbox(adev->dm.dc);
+	}
+
 	/* power on hardware */
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);