Merge tag 'drm-xe-next-fixes-2024-03-14' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Driver changes:

- Invalidate userptr VMA on page pin fault, allowing userspace
  to free userptr while still having bindings
- Fail early on sysfs file creation error
- Skip VMA pinning on xe_exec with num_batch_buffer == 0

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/c4epi2j6anpc77z73zbgibxg7bxsmmkb522aa7tyei6oa6uunn@3oad4cgomd5a

6 files changed, 55 insertions, 35 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 952496c6260d..826c8b389672 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -235,6 +235,29 @@ retry:
 			goto err_unlock_list;
 	}
 
+	if (!args->num_batch_buffer) {
+		err = xe_vm_lock(vm, true);
+		if (err)
+			goto err_unlock_list;
+
+		if (!xe_vm_in_lr_mode(vm)) {
+			struct dma_fence *fence;
+
+			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
+			if (IS_ERR(fence)) {
+				err = PTR_ERR(fence);
+				goto err_unlock_list;
+			}
+			for (i = 0; i < num_syncs; i++)
+				xe_sync_entry_signal(&syncs[i], NULL, fence);
+			xe_exec_queue_last_fence_set(q, vm, fence);
+			dma_fence_put(fence);
+		}
+
+		xe_vm_unlock(vm);
+		goto err_unlock_list;
+	}
+
 	vm_exec.vm = &vm->gpuvm;
 	vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
 	if (xe_vm_in_lr_mode(vm)) {
@@ -254,24 +277,6 @@ retry:
 		goto err_exec;
 	}
 
-	if (!args->num_batch_buffer) {
-		if (!xe_vm_in_lr_mode(vm)) {
-			struct dma_fence *fence;
-
-			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
-			if (IS_ERR(fence)) {
-				err = PTR_ERR(fence);
-				goto err_exec;
-			}
-			for (i = 0; i < num_syncs; i++)
-				xe_sync_entry_signal(&syncs[i], NULL, fence);
-			xe_exec_queue_last_fence_set(q, vm, fence);
-			dma_fence_put(fence);
-		}
-
-		goto err_exec;
-	}
-
 	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
 		err = -EWOULDBLOCK;	/* Aliased to -EAGAIN */
 		skip_retry = true;
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 73c535193a98..241c294270d9 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type)
 static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
 {
 	return BIT(tile->id) & vma->tile_present &&
-		!(BIT(tile->id) & vma->usm.tile_invalidated);
+		!(BIT(tile->id) & vma->tile_invalidated);
 }
 
 static bool vma_matches(struct xe_vma *vma, u64 page_addr)
@@ -226,7 +226,7 @@ retry_userptr:
 
 	if (xe_vma_is_userptr(vma))
 		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
-	vma->usm.tile_invalidated &= ~BIT(tile->id);
+	vma->tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
 	drm_exec_fini(&exec);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 3b97633d81d8..d82c138f1ece 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -464,7 +464,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate,
 	     TP_ARGS(vma)
 );
 
-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate,
+DEFINE_EVENT(xe_vma, xe_vma_invalidate,
 	     TP_PROTO(struct xe_vma *vma),
 	     TP_ARGS(vma)
 );
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index e3bde897f6e8..3dd8bb64bb00 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -708,6 +708,7 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
+	xe_assert(vm->xe, !xe_vm_in_fault_mode(vm));
 	lockdep_assert_held_write(&vm->lock);
 
 	/* Collect invalidated userptrs */
@@ -724,11 +725,27 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
-		if (err < 0)
-			return err;
+		if (err == -EFAULT) {
+			list_del_init(&uvma->userptr.repin_link);
 
-		list_del_init(&uvma->userptr.repin_link);
-		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
+			/* Wait for pending binds */
+			xe_vm_lock(vm, false);
+			dma_resv_wait_timeout(xe_vm_resv(vm),
+					      DMA_RESV_USAGE_BOOKKEEP,
+					      false, MAX_SCHEDULE_TIMEOUT);
+
+			err = xe_vm_invalidate_vma(&uvma->vma);
+			xe_vm_unlock(vm);
+			if (err)
+				return err;
+		} else {
+			if (err < 0)
+				return err;
+
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->vma.combined_links.rebind,
+				       &vm->rebind_list);
+		}
 	}
 
 	return 0;
@@ -1987,7 +2004,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 			return err;
 	}
 
-	if (vma->tile_mask != (vma->tile_present & ~vma->usm.tile_invalidated)) {
+	if (vma->tile_mask != (vma->tile_present & ~vma->tile_invalidated)) {
 		return xe_vm_bind(vm, vma, q, xe_vma_bo(vma), syncs, num_syncs,
 				  true, first_op, last_op);
 	} else {
@@ -3185,9 +3202,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	u8 id;
 	int ret;
 
-	xe_assert(xe, xe_vm_in_fault_mode(xe_vma_vm(vma)));
 	xe_assert(xe, !xe_vma_is_null(vma));
-	trace_xe_vma_usm_invalidate(vma);
+	trace_xe_vma_invalidate(vma);
 
 	/* Check that we don't race with page-table updates */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
@@ -3225,7 +3241,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 		}
 	}
 
-	vma->usm.tile_invalidated = vma->tile_mask;
+	vma->tile_invalidated = vma->tile_mask;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 292f8cadb40f..713996f7dc59 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -83,11 +83,8 @@ struct xe_vma {
 		struct work_struct destroy_work;
 	};
 
-	/** @usm: unified shared memory state */
-	struct {
-		/** @tile_invalidated: VMA has been invalidated */
-		u8 tile_invalidated;
-	} usm;
+	/** @tile_invalidated: VMA has been invalidated */
+	u8 tile_invalidated;
 
 	/** @tile_mask: Tile mask of where to create binding for this VMA */
 	u8 tile_mask;
diff --git a/drivers/gpu/drm/xe/xe_vram_freq.c b/drivers/gpu/drm/xe/xe_vram_freq.c
index 079cc283a186..c5f6b5a5d117 100644
--- a/drivers/gpu/drm/xe/xe_vram_freq.c
+++ b/drivers/gpu/drm/xe/xe_vram_freq.c
@@ -111,8 +111,10 @@ void xe_vram_freq_sysfs_init(struct xe_tile *tile)
 		return;
 
 	kobj = kobject_create_and_add("memory", tile->sysfs);
-	if (!kobj)
+	if (!kobj) {
 		drm_warn(&xe->drm, "failed to add memory directory, err: %d\n", -ENOMEM);
+		return;
+	}
 
 	err = sysfs_create_group(kobj, &freq_group_attrs);
 	if (err) {