The Vulkan timeline semaphores allow signaling to happen on the point
of the timeline without all of the its dependencies to be created.
The current 2 implementations (AMD/Intel) of the Vulkan spec on top of
the Linux kernel are using a thread to wait on the dependencies of a
given point to materialize and delay actual submission to the kernel
driver until the wait completes.
If a binary semaphore is submitted for signaling along the side of a
timeline semaphore waiting for completion that means that the drm
syncobj associated with that binary semaphore will not have a DMA
fence associated with it by the time vkQueueSubmit() returns. This and
the fact that a binary semaphore can be signaled and unsignaled as
before its DMA fences materialize mean that we cannot just rely on the
fence within the syncobj but we also need a sideband payload verifying
that the fence in the syncobj matches the last submission from the
Vulkan API point of view.
This change adds a sideband payload that is incremented with signaled
syncobj when vkQueueSubmit() is called. The next vkQueueSubmit()
waiting on a the syncobj will read the sideband payload and wait for a
fence chain element with a seqno superior or equal to the sideband
payload value to be added into the fence chain and use that fence to
trigger the submission on the kernel driver.
v2: Use a separate ioctl to get/set the sideband value (Christian)
Signed-off-by: Lionel Landwerlin <lionel.g.landwer...@intel.com>
Cc: Christian Koenig <christian.koe...@amd.com>
Cc: Jason Ekstrand <ja...@jlekstrand.net>
Cc: David(ChunMing) Zhou <david1.z...@amd.com>
---
drivers/gpu/drm/drm_internal.h | 2 ++
drivers/gpu/drm/drm_ioctl.c | 3 ++
drivers/gpu/drm/drm_syncobj.c | 63 +++++++++++++++++++++++++++++++---
include/drm/drm_syncobj.h | 9 +++++
include/uapi/drm/drm.h | 5 ++-
5 files changed, 77 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 51a2055c8f18..de5267711a7c 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -208,6 +208,8 @@ int drm_syncobj_timeline_signal_ioctl(struct drm_device
*dev, void *data,
struct drm_file *file_private);
int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_private);
+int drm_syncobj_sideband_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file_private);
/* drm_framebuffer.c */
void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent,
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index f675a3bb2c88..7fd99533f78f 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -703,6 +703,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
DRM_RENDER_ALLOW),
DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl,
DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIDEBAND, drm_syncobj_sideband_ioctl,
+ DRM_RENDER_ALLOW),
+
DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl,
0),
DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE,
drm_crtc_queue_sequence_ioctl, 0),
DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl,
DRM_MASTER),
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index b927e482e554..66f4f91baa6d 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1150,8 +1150,10 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void
*data,
if (ret < 0)
return ret;
- for (i = 0; i < args->count_handles; i++)
+ for (i = 0; i < args->count_handles; i++) {
drm_syncobj_replace_fence(syncobjs[i], NULL);
+ syncobjs[i]->sideband_payload = 0;
+ }
drm_syncobj_array_free(syncobjs, args->count_handles);
@@ -1205,7 +1207,7 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE))
return -EOPNOTSUPP;
- if (args->pad != 0)
+ if (args->flags != 0)
return -EINVAL;
if (args->count_handles == 0)
@@ -1276,7 +1278,7 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void
*data,
if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE))
return -EOPNOTSUPP;
- if (args->pad != 0)
+ if (args->flags != 0)
return -EINVAL;
if (args->count_handles == 0)
@@ -1312,15 +1314,68 @@ int drm_syncobj_query_ioctl(struct drm_device *dev,
void *data,
point = dma_fence_is_signaled(last_signaled) ?
last_signaled->seqno :
to_dma_fence_chain(last_signaled)->prev_seqno;
- dma_fence_put(last_signaled);
+ dma_fence_put(last_signaled);
