@@ -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,
@@ -13,11 +13,26 @@
#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;
+ uint64_t 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;
+ uint64_t *in_fence_ids;
+ unsigned int num_in_fence_ids;
+
struct virtio_gpu_object_array *buflist;
struct drm_virtgpu_execbuffer *exbuf;
struct virtio_gpu_fence *out_fence;
@@ -33,9 +48,10 @@ struct virtio_gpu_submit {
static int virtio_gpu_do_fence_wait(struct virtio_gpu_submit *submit,
struct dma_fence *dma_fence)
{
+ struct dma_fence *in_fence = dma_fence_chain_contained(dma_fence);
uint32_t context = submit->fence_ctx + submit->ring_idx;
- if (dma_fence_match_context(dma_fence, context))
+ if (dma_fence_match_context(in_fence, context))
return 0;
return dma_fence_wait(dma_fence, true);
@@ -56,6 +72,186 @@ static int virtio_gpu_dma_fence_wait(struct virtio_gpu_submit *submit,
return 0;
}
+static void virtio_gpu_free_syncobjs(struct drm_syncobj **syncobjs,
+ uint32_t nr_syncobjs)
+{
+ uint32_t i = nr_syncobjs;
+
+ while (syncobjs && i--) {
+ if (syncobjs[i])
+ drm_syncobj_put(syncobjs[i]);
+ }
+
+ kfree(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;
+ struct drm_syncobj **syncobjs;
+ int ret = 0, i;
+
+ if (!submit->num_in_syncobjs)
+ return 0;
+
+ syncobjs = kcalloc(submit->num_in_syncobjs, sizeof(*syncobjs),
+ GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+ if (!syncobjs)
+ return -ENOMEM;
+
+ for (i = 0; i < submit->num_in_syncobjs; i++) {
+ uint64_t address = exbuf->in_syncobjs + i * syncobj_stride;
+ struct dma_fence *fence;
+
+ 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->in_syncobjs = syncobjs;
+
+ return ret;
+}
+
+static void virtio_gpu_reset_syncobjs(struct drm_syncobj **syncobjs,
+ uint32_t nr_syncobjs)
+{
+ uint32_t i;
+
+ for (i = 0; syncobjs && 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,
+ uint32_t nr_syncobjs)
+{
+ uint32_t i = nr_syncobjs;
+
+ while (post_deps && i--) {
+ kfree(post_deps[i].chain);
+ drm_syncobj_put(post_deps[i].syncobj);
+ }
+
+ kfree(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;
+ size_t syncobj_stride = exbuf->syncobj_stride;
+ int ret = 0, i;
+
+ if (!submit->num_out_syncobjs)
+ return 0;
+
+ post_deps = kcalloc(submit->num_out_syncobjs, sizeof(*post_deps),
+ GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+ if (!post_deps)
+ return -ENOMEM;
+
+ for (i = 0; i < submit->num_out_syncobjs; i++) {
+ uint64_t address = exbuf->out_syncobjs + i * syncobj_stride;
+
+ 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) {
+ ret = -EINVAL;
+ break;
+ }
+ }
+
+ if (ret) {
+ virtio_gpu_free_post_deps(post_deps, i);
+ return ret;
+ }
+
+ 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;
+ struct dma_fence *fence = &submit->out_fence->f;
+ uint32_t i;
+
+ for (i = 0; post_deps && 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,
@@ -119,6 +315,11 @@ 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);
+ kfree(submit->in_fence_ids);
+
if (!IS_ERR(submit->buf))
kvfree(submit->buf);
@@ -164,6 +365,8 @@ static int virtio_gpu_init_submit(struct virtio_gpu_submit *submit,
return err;
}
+ submit->num_out_syncobjs = exbuf->num_out_syncobjs;
+ submit->num_in_syncobjs = exbuf->num_in_syncobjs;
submit->out_fence = out_fence;
submit->fence_ctx = fence_ctx;
submit->ring_idx = ring_idx;
@@ -282,6 +485,14 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
if (ret)
goto cleanup;
+ ret = virtio_gpu_parse_deps(&submit);
+ if (ret)
+ goto cleanup;
+
+ ret = virtio_gpu_parse_post_deps(&submit);
+ if (ret)
+ goto cleanup;
+
ret = virtio_gpu_install_out_fence_fd(&submit);
if (ret)
goto cleanup;
@@ -291,6 +502,7 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
goto cleanup;
virtio_gpu_submit(&submit);
+ virtio_gpu_process_post_deps(&submit);
cleanup:
virtio_gpu_cleanup_submit(&submit);
@@ -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;
+ __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 */