[Intel-gfx] [PATCH 28/36] drm/i915/gem: Allow combining submit-fences with syncobj

[Chris Wilson <chris@chris-wilson.co.uk>]

We allow exported sync_file fences to be used as submit fences, but they
are not the only source of user fences. We also accept an array of
syncobj, and as with sync_file these are dma_fences underneath and so
feature the same set of controls. The submit-fence allows for a request
to be scheduled at the same time as the signaler, rather than as normal
after. Userspace can combine submit-fence with its own semaphores for
intra-batch scheduling.

Not exposing submit-fences to syncobj was at the time just a matter of
pragmatic expediency.

Fixes: a88b6e4cbafd ("drm/i915: Allow specification of parallel execbuf")
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4854
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 14 +++++++----
 drivers/gpu/drm/i915/i915_request.c           | 25 +++++++++++++++++++
 include/uapi/drm/i915_drm.h                   |  7 +++---
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 4fddbe34efa6..cb4872ccfe58 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2397,7 +2397,7 @@ static void
 __free_fence_array(struct drm_syncobj **fences, unsigned int n)
 {
 	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+		drm_syncobj_put(ptr_mask_bits(fences[n], 3));
 	kvfree(fences);
 }
 
@@ -2454,7 +2454,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		fences[n] = ptr_pack_bits(syncobj, fence.flags, 3);
 	}
 
 	return fences;
@@ -2485,7 +2485,7 @@ await_fence_array(struct i915_execbuffer *eb,
 		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(fences[n], &flags, 3);
 		if (!(flags & I915_EXEC_FENCE_WAIT))
 			continue;
 
@@ -2509,7 +2509,11 @@ await_fence_array(struct i915_execbuffer *eb,
 			spin_unlock(&syncobj->lock);
 		}
 
-		err = i915_request_await_dma_fence(eb->request, fence);
+		if (flags & I915_EXEC_FENCE_WAIT_SUBMIT)
+			err = i915_request_await_execution(eb->request, fence,
+							   eb->engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb->request, fence);
 		dma_fence_put(fence);
 		if (err < 0)
 			return err;
@@ -2530,7 +2534,7 @@ signal_fence_array(struct i915_execbuffer *eb,
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(fences[n], &flags, 3);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 02747c171c54..a570a1f43d70 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1385,6 +1385,27 @@ __i915_request_await_proxy(struct i915_request *rq,
 	return 0;
 }
 
+static int execution_proxy(struct await_proxy *ap)
+{
+	return i915_request_await_execution(ap->request, ap->fence, ap->data);
+}
+
+static int
+i915_request_await_proxy_execution(struct i915_request *rq,
+				   struct dma_fence *fence,
+				   void (*hook)(struct i915_request *rq,
+						struct dma_fence *signal))
+{
+	/*
+	 * We have to wait until the real request is known in order to
+	 * be able to hook into its execution, as opposed to waiting for
+	 * its completion.
+	 */
+	return __i915_request_await_proxy(rq, fence,
+					  i915_fence_timeout(rq->i915),
+					  execution_proxy, hook);
+}
+
 int
 i915_request_await_execution(struct i915_request *rq,
 			     struct dma_fence *fence,
@@ -1424,6 +1445,10 @@ i915_request_await_execution(struct i915_request *rq,
 			ret = __i915_request_await_execution(rq,
 							     to_request(fence),
 							     hook);
+		else if (dma_fence_is_proxy(fence))
+			ret = i915_request_await_proxy_execution(rq,
+								 fence,
+								 hook);
 		else
 			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 14b67cd6b54b..704dd0e3bc1d 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1040,9 +1040,10 @@ struct drm_i915_gem_exec_fence {
 	 */
 	__u32 handle;
 
-#define I915_EXEC_FENCE_WAIT            (1<<0)
-#define I915_EXEC_FENCE_SIGNAL          (1<<1)
-#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+#define I915_EXEC_FENCE_WAIT            (1u << 0)
+#define I915_EXEC_FENCE_SIGNAL          (1u << 1)
+#define I915_EXEC_FENCE_WAIT_SUBMIT     (1u << 2)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_WAIT_SUBMIT << 1))
 	__u32 flags;
 };
 
-- 
2.20.1

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