[PATCH v2 0/2] fix gmc page fault on navi1X

[PATCH v2 0/2] fix gmc page fault on navi1X

[xinhui pan]

We hit gmc page fault on navi1X.
UMR tells that the physical address of pte is bad.

Two issues:
1) we did not sync job schedule fence while update mapping.
fix it by adding bo fence to resv after every job submit.

2) we might unref page table bo during update ptes, at the same time, there
is job pending on bo. and submit a job in commit after free bo.
We need free the bo after adding all fence to bo.

change from v1:
fix rebase issue.

xinhui pan (2):
  drm/amdgpu: Add job fence to resv conditionally
  drm/amdgpu: unref the bo after job submit

 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c      | 38 +++++++++++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h      |  5 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c |  9 +++++
 3 files changed, 42 insertions(+), 10 deletions(-)

-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 1/2] drm/amdgpu: Add job fence to resv conditionally

[xinhui pan]

If a job need sync the bo resv, it is likely that bo need the job fence
to sync with others.

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h      | 5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 9 +++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index b5705fcfc935..ca6021b4200b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -226,6 +226,11 @@ struct amdgpu_vm_update_params {
 	 * @num_dw_left: number of dw left for the IB
 	 */
 	unsigned int num_dw_left;
+
+	/**
+	 * @resv: sync the resv and add job fence to it conditionally.
+	 */
+	struct dma_resv *resv;
 };
 
 struct amdgpu_vm_update_funcs {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 4cc7881f438c..0cfac59bff36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -70,6 +70,8 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 
 	p->num_dw_left = ndw;
 
+	p->resv = resv;
+
 	if (!resv)
 		return 0;
 
@@ -111,6 +113,13 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 		swap(p->vm->last_delayed, tmp);
 	dma_fence_put(tmp);
 
+	/* add job fence to resv.
+	 * MM notifier path is an exception as we can not grab the
+	 * resv lock.
+	 */
+	if (!p->direct && p->resv)
+		dma_resv_add_shared_fence(p->resv, f);
+
 	if (fence && !p->direct)
 		swap(*fence, f);
 	dma_fence_put(f);
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 2/2] drm/amdgpu: unref the bo after job submit

[xinhui pan]

Otherwise we might free BOs before job has completed.
We add the fence to BO after commit, so free BOs after that.

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 38 +++++++++++++++++++-------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 73398831196f..bd40a7923b67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -942,13 +942,17 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
  *
  * @entry: PDE to free
  */
-static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry)
+static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry,
+					struct list_head *head)
 {
 	if (entry->base.bo) {
 		entry->base.bo->vm_bo = NULL;
 		list_del(&entry->base.vm_status);
-		amdgpu_bo_unref(&entry->base.bo->shadow);
-		amdgpu_bo_unref(&entry->base.bo);
+		if (!head) {
+			amdgpu_bo_unref(&entry->base.bo->shadow);
+			amdgpu_bo_unref(&entry->base.bo);
+		} else
+			list_add(&entry->base.vm_status, head);
 	}
 	kvfree(entry->entries);
 	entry->entries = NULL;
@@ -965,7 +969,8 @@ static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry)
  */
 static void amdgpu_vm_free_pts(struct amdgpu_device *adev,
 			       struct amdgpu_vm *vm,
-			       struct amdgpu_vm_pt_cursor *start)
+			       struct amdgpu_vm_pt_cursor *start,
+				   struct list_head *head)
 {
 	struct amdgpu_vm_pt_cursor cursor;
 	struct amdgpu_vm_pt *entry;
@@ -973,10 +978,10 @@ static void amdgpu_vm_free_pts(struct amdgpu_device *adev,
 	vm->bulk_moveable = false;
 
 	for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry)
-		amdgpu_vm_free_table(entry);
+		amdgpu_vm_free_table(entry, head);
 
 	if (start)
-		amdgpu_vm_free_table(start->entry);
+		amdgpu_vm_free_table(start->entry, head);
 }
 
 /**
@@ -1428,7 +1433,8 @@ static void amdgpu_vm_fragment(struct amdgpu_vm_update_params *params,
  */
 static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 				 uint64_t start, uint64_t end,
-				 uint64_t dst, uint64_t flags)
+				 uint64_t dst, uint64_t flags,
+				 struct list_head *head)
 {
 	struct amdgpu_device *adev = params->adev;
 	struct amdgpu_vm_pt_cursor cursor;
@@ -1539,7 +1545,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 			 * completely covered by the range and so potentially still in use.
 			 */
 			while (cursor.pfn < frag_start) {
-				amdgpu_vm_free_pts(adev, params->vm, &cursor);
+				amdgpu_vm_free_pts(adev, params->vm, &cursor, head);
 				amdgpu_vm_pt_next(adev, &cursor);
 			}
 
@@ -1582,6 +1588,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	struct amdgpu_vm_update_params params;
 	enum amdgpu_sync_mode sync_mode;
 	int r;
+	struct list_head head;
 
 	memset(&params, 0, sizeof(params));
 	params.adev = adev;
@@ -1589,6 +1596,8 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	params.direct = direct;
 	params.pages_addr = pages_addr;
 
+	INIT_LIST_HEAD(&head);
+
 	/* Implicitly sync to command submissions in the same VM before
 	 * unmapping. Sync to moving fences before mapping.
 	 */
@@ -1617,13 +1626,22 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (r)
 		goto error_unlock;
 
-	r = amdgpu_vm_update_ptes(&params, start, last + 1, addr, flags);
+	r = amdgpu_vm_update_ptes(&params, start, last + 1, addr, flags, &head);
 	if (r)
 		goto error_unlock;
 
 	r = vm->update_funcs->commit(&params, fence);
 
 error_unlock:
+	while (!list_empty(&head)) {
+		struct amdgpu_vm_pt *entry = list_first_entry(&head,
+				struct amdgpu_vm_pt, base.vm_status);
+		list_del(&entry->base.vm_status);
+
+		amdgpu_bo_unref(&entry->base.bo->shadow);
+		amdgpu_bo_unref(&entry->base.bo);
+	}
+
 	amdgpu_vm_eviction_unlock(vm);
 	return r;
 }
@@ -3118,7 +3136,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
 	}
 
-	amdgpu_vm_free_pts(adev, vm, NULL);
+	amdgpu_vm_free_pts(adev, vm, NULL, NULL);
 	amdgpu_bo_unreserve(root);
 	amdgpu_bo_unref(&root);
 	WARN_ON(vm->root.base.bo);
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx