1 files changed, 56 insertions, 11 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 57bec08e80c5..111b7f8c617a 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -28,6 +28,7 @@
 
 #include <linux/dma_remapping.h>
 #include <linux/reservation.h>
+#include <linux/sync_file.h>
 #include <linux/uaccess.h>
 
 #include <drm/drmP.h>
@@ -1110,6 +1111,9 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 	list_for_each_entry(vma, vmas, exec_list) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
+		if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC)
+			continue;
+
 		ret = i915_gem_request_await_object
 			(req, obj, obj->base.pending_write_domain);
 		if (ret)
@@ -1180,14 +1184,14 @@ validate_exec_list(struct drm_device *dev,
 			if (exec[i].offset !=
 			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
 				return -EINVAL;
-
-			/* From drm_mm perspective address space is continuous,
-			 * so from this point we're always using non-canonical
-			 * form internally.
-			 */
-			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
 		}
 
+		/* From drm_mm perspective address space is continuous,
+		 * so from this point we're always using non-canonical
+		 * form internally.
+		 */
+		exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
@@ -1591,6 +1595,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct i915_execbuffer_params *params = &params_master;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
 	u32 dispatch_flags;
+	struct dma_fence *in_fence = NULL;
+	struct sync_file *out_fence = NULL;
+	int out_fence_fd = -1;
 	int ret;
 	bool need_relocs;
 
@@ -1634,6 +1641,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		dispatch_flags |= I915_DISPATCH_RS;
 	}
 
+	if (args->flags & I915_EXEC_FENCE_IN) {
+		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
+		if (!in_fence)
+			return -EINVAL;
+	}
+
+	if (args->flags & I915_EXEC_FENCE_OUT) {
+		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
+		if (out_fence_fd < 0) {
+			ret = out_fence_fd;
+			goto err_in_fence;
+		}
+	}
+
 	/* Take a local wakeref for preparing to dispatch the execbuf as
 	 * we expect to access the hardware fairly frequently in the
 	 * process. Upon first dispatch, we acquire another prolonged
@@ -1778,6 +1799,21 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		goto err_batch_unpin;
 	}
 
+	if (in_fence) {
+		ret = i915_gem_request_await_dma_fence(params->request,
+						       in_fence);
+		if (ret < 0)
+			goto err_request;
+	}
+
+	if (out_fence_fd != -1) {
+		out_fence = sync_file_create(&params->request->fence);
+		if (!out_fence) {
+			ret = -ENOMEM;
+			goto err_request;
+		}
+	}
+
 	/* Whilst this request exists, batch_obj will be on the
 	 * active_list, and so will hold the active reference. Only when this
 	 * request is retired will the the batch_obj be moved onto the
@@ -1805,6 +1841,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	ret = execbuf_submit(params, args, &eb->vmas);
 err_request:
 	__i915_add_request(params->request, ret == 0);
+	if (out_fence) {
+		if (ret == 0) {
+			fd_install(out_fence_fd, out_fence->file);
+			args->rsvd2 &= GENMASK_ULL(0, 31); /* keep in-fence */
+			args->rsvd2 |= (u64)out_fence_fd << 32;
+			out_fence_fd = -1;
+		} else {
+			fput(out_fence->file);
+		}
+	}
 
 err_batch_unpin:
 	/*
@@ -1826,6 +1872,10 @@ pre_mutex_err:
 	/* intel_gpu_busy should also get a ref, so it will free when the device
 	 * is really idle. */
 	intel_runtime_pm_put(dev_priv);
+	if (out_fence_fd != -1)
+		put_unused_fd(out_fence_fd);
+err_in_fence:
+	dma_fence_put(in_fence);
 	return ret;
 }
 
@@ -1933,11 +1983,6 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (args->rsvd2 != 0) {
-		DRM_DEBUG("dirty rvsd2 field\n");
-		return -EINVAL;
-	}
-
 	exec2_list = drm_malloc_gfp(args->buffer_count,
 				    sizeof(*exec2_list),
 				    GFP_TEMPORARY);