1 files changed, 58 insertions, 53 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 142f89462aa4..b4a0db24f4dd 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -115,36 +115,20 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 	return 0;
 }
 
-static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
+static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
-	bool sync_to_ring[RADEON_NUM_RINGS] = { };
-	bool need_sync = false;
-	int i, r;
+	int i;
 
 	for (i = 0; i < p->nrelocs; i++) {
-		struct radeon_fence *fence;
+		struct radeon_fence *a, *b;
 
 		if (!p->relocs[i].robj || !p->relocs[i].robj->tbo.sync_obj)
 			continue;
 
-		fence = p->relocs[i].robj->tbo.sync_obj;
-		if (fence->ring != p->ring && !radeon_fence_signaled(fence)) {
-			sync_to_ring[fence->ring] = true;
-			need_sync = true;
-		}
-	}
-
-	if (!need_sync) {
-		return 0;
-	}
-
-	r = radeon_semaphore_create(p->rdev, &p->ib.semaphore);
-	if (r) {
-		return r;
+		a = p->relocs[i].robj->tbo.sync_obj;
+		b = p->ib.sync_to[a->ring];
+		p->ib.sync_to[a->ring] = radeon_fence_later(a, b);
 	}
-
-	return radeon_semaphore_sync_rings(p->rdev, p->ib.semaphore,
-					   sync_to_ring, p->ring);
 }
 
 /* XXX: note that this is called from the legacy UMS CS ioctl as well */
@@ -294,6 +278,30 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 	return 0;
 }
 
+static void radeon_bo_vm_fence_va(struct radeon_cs_parser *parser,
+				  struct radeon_fence *fence)
+{
+	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
+	struct radeon_vm *vm = &fpriv->vm;
+	struct radeon_bo_list *lobj;
+
+	if (parser->chunk_ib_idx == -1) {
+		return;
+	}
+	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) {
+		return;
+	}
+
+	list_for_each_entry(lobj, &parser->validated, tv.head) {
+		struct radeon_bo_va *bo_va;
+		struct radeon_bo *rbo = lobj->bo;
+
+		bo_va = radeon_bo_va(rbo, vm);
+		radeon_fence_unref(&bo_va->fence);
+		bo_va->fence = radeon_fence_ref(fence);
+	}
+}
+
 /**
  * cs_parser_fini() - clean parser states
  * @parser:	parser structure holding parsing context.
@@ -306,11 +314,14 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 {
 	unsigned i;
 
-	if (!error)
+	if (!error) {
+		/* fence all bo va before ttm_eu_fence_buffer_objects so bo are still reserved */
+		radeon_bo_vm_fence_va(parser, parser->ib.fence);
 		ttm_eu_fence_buffer_objects(&parser->validated,
 					    parser->ib.fence);
-	else
+	} else {
 		ttm_eu_backoff_reservation(&parser->validated);
+	}
 
 	if (parser->relocs != NULL) {
 		for (i = 0; i < parser->nrelocs; i++) {
@@ -368,16 +379,13 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		DRM_ERROR("Invalid command stream !\n");
 		return r;
 	}
-	r = radeon_cs_sync_rings(parser);
-	if (r) {
-		DRM_ERROR("Failed to synchronize rings !\n");
-	}
+	radeon_cs_sync_rings(parser);
 	parser->ib.vm_id = 0;
-	r = radeon_ib_schedule(rdev, &parser->ib);
+	r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
 	}
-	return 0;
+	return r;
 }
 
 static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
@@ -407,7 +415,6 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 
 	if (parser->chunk_ib_idx == -1)
 		return 0;
-
 	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0)
 		return 0;
 
@@ -459,6 +466,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		return r;
 	}
 
+	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
 	r = radeon_vm_bind(rdev, vm);
 	if (r) {
@@ -468,30 +476,26 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	if (r) {
 		goto out;
 	}
-	r = radeon_cs_sync_rings(parser);
-	if (r) {
-		DRM_ERROR("Failed to synchronize rings !\n");
-	}
+	radeon_cs_sync_rings(parser);
+
+	parser->ib.vm_id = vm->id;
+	/* ib pool is bind at 0 in virtual address space,
+	 * so gpu_addr is the offset inside the pool bo
+	 */
+	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
 		parser->const_ib.vm_id = vm->id;
-		/* ib pool is bind at 0 in virtual address space to gpu_addr is the
-		 * offset inside the pool bo
+		/* ib pool is bind at 0 in virtual address space,
+		 * so gpu_addr is the offset inside the pool bo
 		 */
 		parser->const_ib.gpu_addr = parser->const_ib.sa_bo->soffset;
-		r = radeon_ib_schedule(rdev, &parser->const_ib);
-		if (r)
-			goto out;
+		r = radeon_ib_schedule(rdev, &parser->ib, &parser->const_ib);
+	} else {
+		r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	}
 
-	parser->ib.vm_id = vm->id;
-	/* ib pool is bind at 0 in virtual address space to gpu_addr is the
-	 * offset inside the pool bo
-	 */
-	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
-	parser->ib.is_const_ib = false;
-	r = radeon_ib_schedule(rdev, &parser->ib);
 out:
 	if (!r) {
 		if (vm->fence) {
@@ -499,7 +503,8 @@ out:
 		}
 		vm->fence = radeon_fence_ref(parser->ib.fence);
 	}
-	mutex_unlock(&fpriv->vm.mutex);
+	mutex_unlock(&vm->mutex);
+	mutex_unlock(&rdev->vm_manager.lock);
 	return r;
 }
 
@@ -519,9 +524,9 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	struct radeon_cs_parser parser;
 	int r;
 
-	radeon_mutex_lock(&rdev->cs_mutex);
+	down_read(&rdev->exclusive_lock);
 	if (!rdev->accel_working) {
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		up_read(&rdev->exclusive_lock);
 		return -EBUSY;
 	}
 	/* initialize parser */
@@ -534,8 +539,8 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
 		radeon_cs_parser_fini(&parser, r);
+		up_read(&rdev->exclusive_lock);
 		r = radeon_cs_handle_lockup(rdev, r);
-		radeon_mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
 	r = radeon_cs_parser_relocs(&parser);
@@ -543,8 +548,8 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to parse relocation %d!\n", r);
 		radeon_cs_parser_fini(&parser, r);
+		up_read(&rdev->exclusive_lock);
 		r = radeon_cs_handle_lockup(rdev, r);
-		radeon_mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
 	r = radeon_cs_ib_chunk(rdev, &parser);
@@ -557,8 +562,8 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	}
 out:
 	radeon_cs_parser_fini(&parser, r);
+	up_read(&rdev->exclusive_lock);
 	r = radeon_cs_handle_lockup(rdev, r);
-	radeon_mutex_unlock(&rdev->cs_mutex);
 	return r;
 }