Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [RFC PATCH 0/6] Common preempt fences and semantics
@ 2024-11-09 17:29 Matthew Brost
  2024-11-09 17:29 ` [RFC PATCH 1/6] dma-resv: Add DMA_RESV_USAGE_PREEMPT Matthew Brost
                   ` (14 more replies)
  0 siblings, 15 replies; 27+ messages in thread
From: Matthew Brost @ 2024-11-09 17:29 UTC (permalink / raw)
  To: intel-xe, dri-devel
  Cc: simona.vetter, thomas.hellstrom, pstanner, boris.brezillon,
	airlied, ltuikov89, dakr, christian.koenig, mihail.atanassov,
	steven.price, shashank.sharma

The motivation for this series comes from pending UMD submission work by
AMD [1], ARM [3], and the Xe team, who are also beginning to look at
this. Sima has suggested [4] some common driver preemptive fences and
semantics, which we all agree on. This is the first attempt to implement
them, based on Xe's existing long-running preemptive fences.

The semantics are fairly simple: preemptive fences attached to a
dma-resv must wait to enable signaling (and thus preempt device
execution) until all fences in other slots have been signaled. These
semantics are necessary to avoid deadlocks when preempting a device
while a user submission is pending, and resuming device execution
depends on the user submission completing. The semantics align with
Christian's view [5], which I also arrived at independently (with a
little help from Sima).

Implemented via the new dma-resv slot DMA_RESV_USAGE_PREEMPT, a common
embedded base preemptive fence class with driver operations, and updates
to the scheduler to adhere to these semantics. 

The current Xe long-running preemptive fences have been converted to the
new common code, and UMD submission is expected to follow (hopefully)
shortly thereafter in a subsequent series.

Not intended to be presented as the final solution, but rather to
kickstart serious discussions on this topic.

Matt

[1] https://patchwork.freedesktop.org/series/113675/
[2] https://patchwork.freedesktop.org/series/114385/
[3] https://patchwork.freedesktop.org/series/137924/
[4] https://patchwork.kernel.org/project/dri-devel/cover/20240828172605.19176-1-mihail.atanassov@arm.com/#26011577
[5] https://patchwork.kernel.org/project/dri-devel/cover/20240828172605.19176-1-mihail.atanassov@arm.com/#26011853

Matthew Brost (6):
  dma-resv: Add DMA_RESV_USAGE_PREEMPT
  drm/sched: Teach scheduler about DMA_RESV_USAGE_PREEMPT
  dma-fence: Add dma_fence_preempt base class
  drm/sched: Teach scheduler about dma_fence_prempt type
  drm/xe: Use DMA_RESV_USAGE_PREEMPT for preempt fences
  drm/xe: Use dma_fence_preempt base class

 drivers/dma-buf/Makefile                    |   2 +-
 drivers/dma-buf/dma-fence-preempt.c         | 102 ++++++++++++++++++++
 drivers/dma-buf/dma-resv.c                  |  43 ++++++---
 drivers/dma-buf/st-dma-resv.c               |   2 +-
 drivers/gpu/drm/scheduler/sched_entity.c    |  29 +++++-
 drivers/gpu/drm/scheduler/sched_main.c      |  50 +++++++---
 drivers/gpu/drm/xe/xe_bo.c                  |  22 +----
 drivers/gpu/drm/xe/xe_guc_submit.c          |   3 +
 drivers/gpu/drm/xe/xe_hw_engine_group.c     |   4 +-
 drivers/gpu/drm/xe/xe_migrate.c             |   4 +-
 drivers/gpu/drm/xe/xe_preempt_fence.c       |  81 +++++-----------
 drivers/gpu/drm/xe/xe_preempt_fence.h       |   2 +-
 drivers/gpu/drm/xe/xe_preempt_fence_types.h |  11 +--
 drivers/gpu/drm/xe/xe_pt.c                  |  12 +--
 drivers/gpu/drm/xe/xe_vm.c                  |  22 +----
 include/drm/gpu_scheduler.h                 |  15 +++
 include/linux/dma-fence-preempt.h           |  54 +++++++++++
 include/linux/dma-fence.h                   |   1 +
 include/linux/dma-resv.h                    |  24 +++--
 19 files changed, 326 insertions(+), 157 deletions(-)
 create mode 100644 drivers/dma-buf/dma-fence-preempt.c
 create mode 100644 include/linux/dma-fence-preempt.h

-- 
2.34.1


^ permalink raw reply	[flat|nested] 27+ messages in thread

end of thread, other threads:[~2024-11-15 19:38 UTC | newest]

Thread overview: 27+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-11-09 17:29 [RFC PATCH 0/6] Common preempt fences and semantics Matthew Brost
2024-11-09 17:29 ` [RFC PATCH 1/6] dma-resv: Add DMA_RESV_USAGE_PREEMPT Matthew Brost
2024-11-09 17:29 ` [RFC PATCH 2/6] drm/sched: Teach scheduler about DMA_RESV_USAGE_PREEMPT Matthew Brost
2024-11-12  9:06   ` Philipp Stanner
2024-11-12 20:08     ` Matthew Brost
2024-11-13 11:03       ` Philipp Stanner
2024-11-09 17:29 ` [RFC PATCH 3/6] dma-fence: Add dma_fence_preempt base class Matthew Brost
2024-11-09 17:29 ` [RFC PATCH 4/6] drm/sched: Teach scheduler about dma_fence_prempt type Matthew Brost
2024-11-09 17:29 ` [RFC PATCH 5/6] drm/xe: Use DMA_RESV_USAGE_PREEMPT for preempt fences Matthew Brost
2024-11-09 17:29 ` [RFC PATCH 6/6] drm/xe: Use dma_fence_preempt base class Matthew Brost
2024-11-09 17:35 ` ✓ CI.Patch_applied: success for Common preempt fences and semantics Patchwork
2024-11-09 17:35 ` ✗ CI.checkpatch: warning " Patchwork
2024-11-09 17:36 ` ✓ CI.KUnit: success " Patchwork
2024-11-09 17:48 ` ✓ CI.Build: " Patchwork
2024-11-09 17:50 ` ✓ CI.Hooks: " Patchwork
2024-11-09 17:51 ` ✗ CI.checksparse: warning " Patchwork
2024-11-09 18:16 ` ✓ CI.BAT: success " Patchwork
2024-11-10  8:13 ` ✗ CI.FULL: failure " Patchwork
2024-11-11 13:42 ` [RFC PATCH 0/6] " Christian König
2024-11-12  3:29   ` Matthew Brost
2024-11-12 11:09     ` Christian König
2024-11-13  2:27       ` Matthew Brost
2024-11-13  2:30         ` Matthew Brost
2024-11-13  9:02           ` Christian König
2024-11-13 15:34             ` Matthew Brost
2024-11-14  8:38               ` Christian König
2024-11-15 19:38                 ` Matthew Brost

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox