[Intel-gfx] [PATCH 17/18] drm/i915: Enable userspace to opt-out of implicit fencing

[Chris Wilson]

Userspace is faced with a dilemma. The kernel requires implicit fencing
to manage resource usage (we always must wait for the GPU to finish
before releasing its PTE) and for third parties. However, userspace may
wish to avoid this serialisation if it is either using explicit fencing
between parties and wants more fine-grained access to buffers (e.g. it
may partition the buffer between uses and track fences on ranges rather
than the implicit fences tracking the whole object). To whit, userspace
needs a mechanism to avoid the kernel's serialisation on its implicit
fences before execbuf execution.

The next question is whether this is an object, execbuf or context flag.
Hybrid users (such as using explicit EGL_ANDROID_native_sync fencing on
shared winsys buffers, but implicit fencing on internal surfaces)
require a per-object level flag. Given that this flag need to be only
set once for the lifetime of the object, this reduces the convenience of
having an execbuf or context level flag (and avoids having multiple
pieces of uABI controlling the same feature).

Incorrect use of this flag will result in rendering corruption and GPU
hangs - but will not result in use-after-free or similar resource
tracking issues.

Serious caveat: write ordering is not strictly correct after setting
this flag on a render target on multiple engines. This affects all
subsequent GEM operations (execbuf, set-domain, pread) and shared
dma-buf operations. A fix is possible - but costly (both in terms of
further ABI changes and runtime overhead).

Testcase: igt/gem_exec_async
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.c            |  3 +++
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 30 ++++++++++++++++--------------
 include/uapi/drm/i915_drm.h                | 24 +++++++++++++++++++++++-
 3 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 449fcfa40319..437ab0695373 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -362,6 +362,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		 */
 		value = i915_gem_mmap_gtt_version();
 		break;
+	case I915_PARAM_HAS_EXEC_ASYNC:
+		value = 1;
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index b63f9327fc40..ca7675c9c1b7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1199,21 +1199,23 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 		struct drm_i915_gem_object *obj = vma->obj;
 		struct reservation_object *resv;
 
-		if (obj->flags & other_rings) {
-			ret = eb_await_bo(req, obj,
-					  obj->base.pending_write_domain);
-			if (ret)
-				return ret;
-		}
+		if ((vma->exec_entry->flags & EXEC_OBJECT_ASYNC) == 0) {
+			if (obj->flags & other_rings) {
+				ret = eb_await_bo(req, obj,
+						  obj->base.pending_write_domain);
+				if (ret)
+					return ret;
+			}
 
-		resv = i915_gem_object_get_dmabuf_resv(obj);
-		if (resv) {
-			ret = i915_sw_fence_await_reservation
-				(&req->submit, resv, &i915_fence_ops,
-				 obj->base.pending_write_domain,
-				 GFP_KERNEL | __GFP_NOWARN);
-			if (ret < 0)
-				return ret;
+			resv = i915_gem_object_get_dmabuf_resv(obj);
+			if (resv) {
+				ret = i915_sw_fence_await_reservation
+					(&req->submit, resv, &i915_fence_ops,
+					 obj->base.pending_write_domain,
+					 GFP_KERNEL | __GFP_NOWARN);
+				if (ret < 0)
+					return ret;
+			}
 		}
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 03725fe89859..730cba23f982 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -388,6 +388,10 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_POOLED_EU	 38
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
+ * synchronisation with implicit fencing on individual objects.
+ */
+#define I915_PARAM_HAS_EXEC_ASYNC	 41
 
 typedef struct drm_i915_getparam {
 	__s32 param;
@@ -729,8 +733,26 @@ struct drm_i915_gem_exec_object2 {
 #define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
 #define EXEC_OBJECT_PINNED		 (1<<4)
 #define EXEC_OBJECT_PAD_TO_SIZE		 (1<<5)
+/* The kernel implicitly tracks GPU activity on all GEM objects, and
+ * synchronises operations with outstanding rendering. This includes
+ * rendering on other devices if exported via dma-buf. However, sometimes
+ * this tracking is too coarse and the user knows better. For example,
+ * if the object is split into non-overlapping ranges shared between different
+ * clients or engines (i.e. suballocating objects), the implicit tracking
+ * by kernel assumes that each operation affects the whole object rather
+ * than an individual range, causing needless synchronisation between clients.
+ *
+ * The kernel maintains the implicit tracking in order to manage resources
+ * used by the GPU - this flag only disables the synchronisation prior to
+ * rendering with this object in this execbuf.
+ *
+ * Opting out of implicit synhronisation requires the user to do its own
+ * explicit tracking to avoid rendering corruption. See, for example,
+ * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
+ */
+#define EXEC_OBJECT_ASYNC		 (1<<6)
 /* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
-#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_PAD_TO_SIZE<<1)
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_ASYNC<<1)
 	__u64 flags;
 
 	union {
-- 
2.9.3