Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v10 00/34] VF migration redesign
Date: Wed,  8 Oct 2025 14:44:58 -0700	[thread overview]
Message-ID: <20251008214532.3442967-1-matthew.brost@intel.com> (raw)

Rather than modifying buffers in place using GGTT addresses during VF
migration, this approach relies on the submission backend's stop/start
mechanism to issue fixups. The patch titled "Document GuC Submission
Backend" provides a detailed explanation of the design.

Testing was performed using an out-of-tree PF/VFIO driver with manual
triggering of VF migration while IGT test cases are running.

IGT test cases:

- A new series [1] that exercises active contexts, job resubmission, and
  compressd memory.

- A new test [2] that actively creates / destroys queue on each
  submission

- xe_exec_threads basic sections, which test context registration loss,
  schedule enable loss, and job resubmission.

- xe_exec_threads balancer sections, which follow the same flows as the 
  basic sections but include a work queue (GGTT address shift).

- xe_exec_threads compute mode user pointer invalidation sections, which
  exercise the same flow as the basic sections, plus replaying
  suspend/resume flows.

All code paths in "Replay GuC submission state on pause/unpause" that
replay state have been manually verified via debug messages "Add debug
prints for GuC replaying state during VF recovery".

v2:
 - Fix lockdep splat
 - Fix checkpatch
 - Fix PTL issue with LRC W/A buffer
 - Fix race creating / destroying queues across migration exposed by [2]
 - Include a version of Satya's patches in [3] which enable CCS save /
   restore across VF migration /w GGTT shift
v3:
 - Address feedback
 - Fix preempt fence mode deadlock /w work queues + VF recovery (Testing)
 - Add NULL checks to scratch LRC allocation
v4:
 - Fix CI failure
 - Remove config lock
v5:
 - Fix CI failures related to lockdep
 - Address various comments
v6:
 - Rebase for CI
v7:
 - Rework GGTT locking for shift
 - Address comments
 - Fix probe on non-migration VFs
v8:
 - Split a patch, address a nit
 - Fix probe on non-memirq VFs
v9:
 - Split GGTT race patch
v10:
 - Fix nits, kernel doc for CI

Matt

Matthew Brost (32):
  drm/xe: Add NULL checks to scratch LRC allocation
  drm/xe: Save off position in ring in which a job was programmed
  drm/xe/guc: Track pending-enable source in submission state
  drm/xe: Track LR jobs in DRM scheduler pending list
  drm/xe: Return first unsignaled job first pending job helper
  drm/xe: Don't change LRC ring head on job resubmission
  drm/xe: Make LRC W/A scratch buffer usage consistent
  drm/xe/vf: Add xe_gt_recovery_pending helper
  drm/xe/vf: Make VF recovery run on per-GT worker
  drm/xe/vf: Abort H2G sends during VF post-migration recovery
  drm/xe/vf: Remove memory allocations from VF post migration recovery
  drm/xe: Move GGTT lock init to alloc
  drm/xe/vf: Move LMEM config to tile layer
  drm/xe/vf: Close multi-GT GGTT shift race
  drm/xe/vf: Teardown VF post migration worker on driver unload
  drm/xe/vf: Don't allow GT reset to be queued during VF post migration
    recovery
  drm/xe/vf: Wakeup in GuC backend on VF post migration recovery
  drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs
    supporting migration
  drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register
  drm/xe/vf: Flush and stop CTs in VF post migration recovery
  drm/xe/vf: Reset TLB invalidations during VF post migration recovery
  drm/xe/vf: Kickstart after resfix in VF post migration recovery
  drm/xe: Add CTB_H2G_BUFFER_OFFSET define
  drm/xe/vf: Start CTs before resfix VF post migration recovery
  drm/xe/vf: Abort VF post migration recovery on failure
  drm/xe/vf: Replay GuC submission state on pause / unpause
  drm/xe: Move queue init before LRC creation
  drm/xe/vf: Add debug prints for GuC replaying state during VF recovery
  drm/xe/vf: Workaround for race condition in GuC firmware during VF
    pause
  drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF
  drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL
  drm/xe/vf: Rebase CCS save/restore BB GGTT addresses

Satyanarayana K V P (2):
  drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups
  drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC

 drivers/gpu/drm/xe/xe_device_types.h         |   5 +
 drivers/gpu/drm/xe/xe_exec.c                 |  12 +-
 drivers/gpu/drm/xe/xe_exec_queue.c           |  64 ++-
 drivers/gpu/drm/xe/xe_exec_queue.h           |   2 -
 drivers/gpu/drm/xe/xe_exec_queue_types.h     |   3 +
 drivers/gpu/drm/xe/xe_execlist.c             |   2 +-
 drivers/gpu/drm/xe/xe_ggtt.c                 |  39 +-
 drivers/gpu/drm/xe/xe_gpu_scheduler.c        |  27 +-
 drivers/gpu/drm/xe/xe_gpu_scheduler.h        |  29 +-
 drivers/gpu/drm/xe/xe_gt.c                   |  39 +-
 drivers/gpu/drm/xe/xe_gt.h                   |  13 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c          | 470 +++++++++++++----
 drivers/gpu/drm/xe/xe_gt_sriov_vf.h          |  11 +-
 drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h    |  34 +-
 drivers/gpu/drm/xe/xe_guc.c                  |   2 +-
 drivers/gpu/drm/xe/xe_guc_ct.c               | 124 ++++-
 drivers/gpu/drm/xe/xe_guc_ct.h               |  11 +
 drivers/gpu/drm/xe/xe_guc_exec_queue_types.h |  15 +
 drivers/gpu/drm/xe/xe_guc_submit.c           | 528 ++++++++++++++++---
 drivers/gpu/drm/xe/xe_guc_submit.h           |   5 +-
 drivers/gpu/drm/xe/xe_lrc.c                  |  15 +-
 drivers/gpu/drm/xe/xe_lrc.h                  |  10 +
 drivers/gpu/drm/xe/xe_memirq.c               |  48 +-
 drivers/gpu/drm/xe/xe_memirq.h               |   2 +
 drivers/gpu/drm/xe/xe_migrate.c              |  28 +-
 drivers/gpu/drm/xe/xe_pci.c                  |   2 +
 drivers/gpu/drm/xe/xe_pci_types.h            |   1 +
 drivers/gpu/drm/xe/xe_preempt_fence.c        |  11 +
 drivers/gpu/drm/xe/xe_ring_ops.c             |  23 +-
 drivers/gpu/drm/xe/xe_sched_job_types.h      |   9 +
 drivers/gpu/drm/xe/xe_sriov_vf.c             | 240 ---------
 drivers/gpu/drm/xe/xe_sriov_vf.h             |   1 -
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c         |  28 +
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.h         |   1 +
 drivers/gpu/drm/xe/xe_sriov_vf_types.h       |   4 -
 drivers/gpu/drm/xe/xe_tile_sriov_vf.c        | 112 +++-
 drivers/gpu/drm/xe/xe_tile_sriov_vf.h        |   9 +-
 drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h  |  23 +
 drivers/gpu/drm/xe/xe_vm.c                   |  26 +-
 drivers/gpu/drm/xe/xe_vram.c                 |   6 +-
 40 files changed, 1430 insertions(+), 604 deletions(-)
 create mode 100644 drivers/gpu/drm/xe/xe_tile_sriov_vf_types.h

-- 
2.34.1


             reply	other threads:[~2025-10-08 21:45 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-08 21:44 Matthew Brost [this message]
2025-10-08 21:44 ` [PATCH v10 01/34] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-10-08 21:45 ` [PATCH v10 02/34] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-10-08 21:45 ` [PATCH v10 03/34] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-10-08 21:45 ` [PATCH v10 04/34] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-10-08 21:45 ` [PATCH v10 05/34] drm/xe: Return first unsignaled job first pending job helper Matthew Brost
2025-10-08 21:45 ` [PATCH v10 06/34] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-10-08 21:45 ` [PATCH v10 07/34] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-10-08 21:45 ` [PATCH v10 08/34] drm/xe/vf: Add xe_gt_recovery_pending helper Matthew Brost
2025-10-08 21:45 ` [PATCH v10 09/34] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-10-08 21:45 ` [PATCH v10 10/34] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 11/34] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 12/34] drm/xe: Move GGTT lock init to alloc Matthew Brost
2025-10-08 21:45 ` [PATCH v10 13/34] drm/xe/vf: Move LMEM config to tile layer Matthew Brost
2025-10-08 21:45 ` [PATCH v10 14/34] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-10-08 21:45 ` [PATCH v10 15/34] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-10-08 21:45 ` [PATCH v10 16/34] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 17/34] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-10-08 21:45 ` [PATCH v10 18/34] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-08 21:45 ` [PATCH v10 19/34] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-10-08 21:45 ` [PATCH v10 20/34] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 21/34] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-08 21:45 ` [PATCH v10 22/34] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-10-08 21:45 ` [PATCH v10 23/34] drm/xe: Add CTB_H2G_BUFFER_OFFSET define Matthew Brost
2025-10-08 21:45 ` [PATCH v10 24/34] drm/xe/vf: Start CTs before resfix VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 25/34] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-08 21:45 ` [PATCH v10 26/34] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-13 11:54   ` Raag Jadav
2025-10-08 21:45 ` [PATCH v10 27/34] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-08 21:45 ` [PATCH v10 28/34] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 29/34] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-08 21:45 ` [PATCH v10 30/34] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-08 21:45 ` [PATCH v10 31/34] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-10-08 21:45 ` [PATCH v10 32/34] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-10-08 21:45 ` [PATCH v10 33/34] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-10-08 21:45 ` [PATCH v10 34/34] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-10-08 21:53 ` ✗ CI.checkpatch: warning for VF migration redesign (rev10) Patchwork
2025-10-08 21:54 ` ✓ CI.KUnit: success " Patchwork
2025-10-08 22:35 ` ✓ Xe.CI.BAT: " Patchwork
2025-10-09  2:36 ` ✗ Xe.CI.Full: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20251008214532.3442967-1-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox