drm/i915: Allow specification of parallel execbuf

There is a desire to split a task onto two engines and have them run at
the same time, e.g. scanline interleaving to spread the workload evenly.
Through the use of the out-fence from the first execbuf, we can
coordinate secondary execbuf to only become ready simultaneously with
the first, so that with all things idle the second execbufs are executed
in parallel with the first. The key difference here between the new
EXEC_FENCE_SUBMIT and the existing EXEC_FENCE_IN is that the in-fence
waits for the completion of the first request (so that all of its
rendering results are visible to the second execbuf, the more common
userspace fence requirement).

Since we only have a single input fence slot, userspace cannot mix an
in-fence and a submit-fence. It has to use one or the other! This is not
such a harsh requirement, since by virtue of the submit-fence, the
secondary execbuf inherit all of the dependencies from the first
request, and for the application the dependencies should be common
between the primary and secondary execbuf.

Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Testcase: igt/gem_exec_fence/parallel
Link: https://github.com/intel/media-driver/pull/546
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190521211134.16117-10-chris@chris-wilson.co.uk

1 files changed, 24 insertions, 1 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d6c5220addd0..7ce25b54c57b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -2318,6 +2318,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 {
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
+	struct dma_fence *exec_fence = NULL;
 	struct sync_file *out_fence = NULL;
 	int out_fence_fd = -1;
 	int err;
@@ -2360,11 +2361,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			return -EINVAL;
 	}
 
+	if (args->flags & I915_EXEC_FENCE_SUBMIT) {
+		if (in_fence) {
+			err = -EINVAL;
+			goto err_in_fence;
+		}
+
+		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
+		if (!exec_fence) {
+			err = -EINVAL;
+			goto err_in_fence;
+		}
+	}
+
 	if (args->flags & I915_EXEC_FENCE_OUT) {
 		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
 		if (out_fence_fd < 0) {
 			err = out_fence_fd;
-			goto err_in_fence;
+			goto err_exec_fence;
 		}
 	}
 
@@ -2494,6 +2508,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
+	if (exec_fence) {
+		err = i915_request_await_execution(eb.request, exec_fence,
+						   eb.engine->bond_execute);
+		if (err < 0)
+			goto err_request;
+	}
+
 	if (fences) {
 		err = await_fence_array(&eb, fences);
 		if (err)
@@ -2555,6 +2576,8 @@ err_destroy:
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
+err_exec_fence:
+	dma_fence_put(exec_fence);
 err_in_fence:
 	dma_fence_put(in_fence);
 	return err;