diff options
| author | Matthew Brost <matthew.brost@intel.com> | 2023-12-05 21:39:54 +0300 |
|---|---|---|
| committer | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2023-12-21 19:46:09 +0300 |
| commit | eb9702ad29863c1ae41d17d8504c7444f280dfff (patch) | |
| tree | 797ec928e909153489844a892caa6c56984e9bd4 /drivers/gpu/drm/xe/xe_exec_queue_types.h | |
| parent | f5783b5026f76083ef4c53f6240619bd5c7bb9a5 (diff) | |
| download | linux-eb9702ad29863c1ae41d17d8504c7444f280dfff.tar.xz | |
drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs
The idea being out-syncs can signal indicating all previous operations
on the bind queue are complete. An example use case of this would be
support for implementing vkQueueWaitIdle easily.
All in-syncs are waited on before signaling out-syncs. This is
implemented by forming a composite software fence of in-syncs and
installing this fence in the out-syncs and exec queue last fence slot.
The last fence must be added as a dependency for jobs on user exec
queues as it is possible for the last fence to be a composite software
fence (unordered, ioctl with zero bb or binds) rather than hardware
fence (ordered, previous job on queue).
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Diffstat (limited to 'drivers/gpu/drm/xe/xe_exec_queue_types.h')
| -rw-r--r-- | drivers/gpu/drm/xe/xe_exec_queue_types.h | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 6826feb650f3..c7aefa1c8c31 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -66,8 +66,9 @@ struct xe_exec_queue { struct xe_hw_fence_irq *fence_irq; /** - * @last_fence: last fence on engine, protected by vm->lock in write - * mode if bind engine + * @last_fence: last fence on exec queue, protected by vm->lock in write + * mode if bind exec queue, protected by dma resv lock if non-bind exec + * queue */ struct dma_fence *last_fence; |