drm/virtio: Support sync objects

Add sync object DRM UAPI support to VirtIO-GPU driver. Sync objects
support is needed by native context VirtIO-GPU Mesa drivers, it also will
be used by Venus and Virgl contexts.

Reviewed-by; Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Tested-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> # amdgpu nctx
Tested-by: Rob Clark <robdclark@gmail.com> # freedreno nctx
Reviewed-by: Rob Clark <robdclark@gmail.com>
Acked-by: Gurchetan Singh <gurchetansingh@chromium.org>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230416115237.798604-4-dmitry.osipenko@collabora.com

drivers/gpu/drm/virtio/virtgpu_drv.c

@@ -176,7 +176,8 @@ static const struct drm_driver driver = {
 	 * If KMS is disabled DRIVER_MODESET and DRIVER_ATOMIC are masked
 	 * out via drm_device::driver_features:
 	 */
-	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC,
+	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC |
+			   DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE,
 	.open = virtio_gpu_driver_open,
 	.postclose = virtio_gpu_driver_postclose,
 

drivers/gpu/drm/virtio/virtgpu_submit.c

@@ -14,11 +14,24 @@
 #include <linux/uaccess.h>
 
 #include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
 #include <drm/virtgpu_drm.h>
 
 #include "virtgpu_drv.h"
 
+struct virtio_gpu_submit_post_dep {
+	struct drm_syncobj *syncobj;
+	struct dma_fence_chain *chain;
+	u64 point;
+};
+
 struct virtio_gpu_submit {
+	struct virtio_gpu_submit_post_dep *post_deps;
+	unsigned int num_out_syncobjs;
+
+	struct drm_syncobj **in_syncobjs;
+	unsigned int num_in_syncobjs;
+
 	struct virtio_gpu_object_array *buflist;
 	struct drm_virtgpu_execbuffer *exbuf;
 	struct virtio_gpu_fence *out_fence;
@@ -59,6 +72,203 @@ static int virtio_gpu_dma_fence_wait(struct virtio_gpu_submit *submit,
 	return 0;
 }
 
+static void virtio_gpu_free_syncobjs(struct drm_syncobj **syncobjs,
+				     u32 nr_syncobjs)
+{
+	u32 i = nr_syncobjs;
+
+	while (i--) {
+		if (syncobjs[i])
+			drm_syncobj_put(syncobjs[i]);
+	}
+
+	kvfree(syncobjs);
+}
+
+static int
+virtio_gpu_parse_deps(struct virtio_gpu_submit *submit)
+{
+	struct drm_virtgpu_execbuffer *exbuf = submit->exbuf;
+	struct drm_virtgpu_execbuffer_syncobj syncobj_desc;
+	size_t syncobj_stride = exbuf->syncobj_stride;
+	u32 num_in_syncobjs = exbuf->num_in_syncobjs;
+	struct drm_syncobj **syncobjs;
+	int ret = 0, i;
+
+	if (!num_in_syncobjs)
+		return 0;
+
+	/*
+	 * kvalloc at first tries to allocate memory using kmalloc and
+	 * falls back to vmalloc only on failure. It also uses __GFP_NOWARN
+	 * internally for allocations larger than a page size, preventing
+	 * storm of KMSG warnings.
+	 */
+	syncobjs = kvcalloc(num_in_syncobjs, sizeof(*syncobjs), GFP_KERNEL);
+	if (!syncobjs)
+		return -ENOMEM;
+
+	for (i = 0; i < num_in_syncobjs; i++) {
+		u64 address = exbuf->in_syncobjs + i * syncobj_stride;
+		struct dma_fence *fence;
+
+		memset(&syncobj_desc, 0, sizeof(syncobj_desc));
+
+		if (copy_from_user(&syncobj_desc,
+				   u64_to_user_ptr(address),
+				   min(syncobj_stride, sizeof(syncobj_desc)))) {
+			ret = -EFAULT;
+			break;
+		}
+
+		if (syncobj_desc.flags & ~VIRTGPU_EXECBUF_SYNCOBJ_FLAGS) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = drm_syncobj_find_fence(submit->file, syncobj_desc.handle,
+					     syncobj_desc.point, 0, &fence);
+		if (ret)
+			break;
+
+		ret = virtio_gpu_dma_fence_wait(submit, fence);
+
+		dma_fence_put(fence);
+		if (ret)
+			break;
+
+		if (syncobj_desc.flags & VIRTGPU_EXECBUF_SYNCOBJ_RESET) {
+			syncobjs[i] = drm_syncobj_find(submit->file,
+						       syncobj_desc.handle);
+			if (!syncobjs[i]) {
+				ret = -EINVAL;
+				break;
+			}
+		}
+	}
+
+	if (ret) {
+		virtio_gpu_free_syncobjs(syncobjs, i);
+		return ret;
+	}
+
+	submit->num_in_syncobjs = num_in_syncobjs;
+	submit->in_syncobjs = syncobjs;
+
+	return ret;
+}
+
+static void virtio_gpu_reset_syncobjs(struct drm_syncobj **syncobjs,
+				      u32 nr_syncobjs)
+{
+	u32 i;
+
+	for (i = 0; i < nr_syncobjs; i++) {
+		if (syncobjs[i])
+			drm_syncobj_replace_fence(syncobjs[i], NULL);
+	}
+}
+
+static void
+virtio_gpu_free_post_deps(struct virtio_gpu_submit_post_dep *post_deps,
+			  u32 nr_syncobjs)
+{
+	u32 i = nr_syncobjs;
+
+	while (i--) {
+		kfree(post_deps[i].chain);
+		drm_syncobj_put(post_deps[i].syncobj);
+	}
+
+	kvfree(post_deps);
+}
+
+static int virtio_gpu_parse_post_deps(struct virtio_gpu_submit *submit)
+{
+	struct drm_virtgpu_execbuffer *exbuf = submit->exbuf;
+	struct drm_virtgpu_execbuffer_syncobj syncobj_desc;
+	struct virtio_gpu_submit_post_dep *post_deps;
+	u32 num_out_syncobjs = exbuf->num_out_syncobjs;
+	size_t syncobj_stride = exbuf->syncobj_stride;
+	int ret = 0, i;
+
+	if (!num_out_syncobjs)
+		return 0;
+
+	post_deps = kvcalloc(num_out_syncobjs, sizeof(*post_deps), GFP_KERNEL);
+	if (!post_deps)
+		return -ENOMEM;
+
+	for (i = 0; i < num_out_syncobjs; i++) {
+		u64 address = exbuf->out_syncobjs + i * syncobj_stride;
+
+		memset(&syncobj_desc, 0, sizeof(syncobj_desc));
+
+		if (copy_from_user(&syncobj_desc,
+				   u64_to_user_ptr(address),
+				   min(syncobj_stride, sizeof(syncobj_desc)))) {
+			ret = -EFAULT;
+			break;
+		}
+
+		post_deps[i].point = syncobj_desc.point;
+
+		if (syncobj_desc.flags) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (syncobj_desc.point) {
+			post_deps[i].chain = dma_fence_chain_alloc();
+			if (!post_deps[i].chain) {
+				ret = -ENOMEM;
+				break;
+			}
+		}
+
+		post_deps[i].syncobj = drm_syncobj_find(submit->file,
+							syncobj_desc.handle);
+		if (!post_deps[i].syncobj) {
+			kfree(post_deps[i].chain);
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	if (ret) {
+		virtio_gpu_free_post_deps(post_deps, i);
+		return ret;
+	}
+
+	submit->num_out_syncobjs = num_out_syncobjs;
+	submit->post_deps = post_deps;
+
+	return 0;
+}
+
+static void
+virtio_gpu_process_post_deps(struct virtio_gpu_submit *submit)
+{
+	struct virtio_gpu_submit_post_dep *post_deps = submit->post_deps;
+
+	if (post_deps) {
+		struct dma_fence *fence = &submit->out_fence->f;
+		u32 i;
+
+		for (i = 0; i < submit->num_out_syncobjs; i++) {
+			if (post_deps[i].chain) {
+				drm_syncobj_add_point(post_deps[i].syncobj,
+						      post_deps[i].chain,
+						      fence, post_deps[i].point);
+				post_deps[i].chain = NULL;
+			} else {
+				drm_syncobj_replace_fence(post_deps[i].syncobj,
+							  fence);
+			}
+		}
+	}
+}
+
 static int virtio_gpu_fence_event_create(struct drm_device *dev,
 					 struct drm_file *file,
 					 struct virtio_gpu_fence *fence,
@@ -118,6 +328,10 @@ static int virtio_gpu_init_submit_buflist(struct virtio_gpu_submit *submit)
 
 static void virtio_gpu_cleanup_submit(struct virtio_gpu_submit *submit)
 {
+	virtio_gpu_reset_syncobjs(submit->in_syncobjs, submit->num_in_syncobjs);
+	virtio_gpu_free_syncobjs(submit->in_syncobjs, submit->num_in_syncobjs);
+	virtio_gpu_free_post_deps(submit->post_deps, submit->num_out_syncobjs);
+
 	if (!IS_ERR(submit->buf))
 		kvfree(submit->buf);
 
@@ -172,6 +386,7 @@ static int virtio_gpu_init_submit(struct virtio_gpu_submit *submit,
 		drm_fence_event = false;
 
 	if ((exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) ||
+	    exbuf->num_out_syncobjs ||
 	    exbuf->num_bo_handles ||
 	    drm_fence_event)
 		out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
@@ -291,6 +506,14 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto cleanup;
 
+	ret = virtio_gpu_parse_post_deps(&submit);
+	if (ret)
+		goto cleanup;
+
+	ret = virtio_gpu_parse_deps(&submit);
+	if (ret)
+		goto cleanup;
+
 	/*
 	 * Await in-fences in the end of the job submission path to
 	 * optimize the path by proceeding directly to the submission
@@ -311,6 +534,7 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	 * the job submission path.
 	 */
 	virtio_gpu_install_out_fence_fd(&submit);
+	virtio_gpu_process_post_deps(&submit);
 	virtio_gpu_complete_submit(&submit);
 cleanup:
 	virtio_gpu_cleanup_submit(&submit);

include/uapi/drm/virtgpu_drm.h

@@ -64,6 +64,16 @@ struct drm_virtgpu_map {
 	__u32 pad;
 };
 
+#define VIRTGPU_EXECBUF_SYNCOBJ_RESET		0x01
+#define VIRTGPU_EXECBUF_SYNCOBJ_FLAGS ( \
+		VIRTGPU_EXECBUF_SYNCOBJ_RESET | \
+		0)
+struct drm_virtgpu_execbuffer_syncobj {
+	__u32 handle;
+	__u32 flags;
+	__u64 point;
+};
+
 /* fence_fd is modified on success if VIRTGPU_EXECBUF_FENCE_FD_OUT flag is set. */
 struct drm_virtgpu_execbuffer {
 	__u32 flags;
@@ -73,7 +83,11 @@ struct drm_virtgpu_execbuffer {
 	__u32 num_bo_handles;
 	__s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */
 	__u32 ring_idx; /* command ring index (see VIRTGPU_EXECBUF_RING_IDX) */
-	__u32 pad;
+	__u32 syncobj_stride; /* size of @drm_virtgpu_execbuffer_syncobj */
+	__u32 num_in_syncobjs;
+	__u32 num_out_syncobjs;
+	__u64 in_syncobjs;
+	__u64 out_syncobjs;
 };
 
 #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */