From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v8 00/12] Fine grained fault locking, threaded prefetch, storm cache
Date: Fri, 24 Jul 2026 16:25:49 -0700 [thread overview]
Message-ID: <20260724232601.1753977-1-matthew.brost@intel.com> (raw)
Fine-grained fault locking provides immediate benefits: it allows page
faults from the same VM to be processed in parallel (unless they target
the same range) and enables a sane multi-threaded prefetch
implementation. UMD prefetch benchmarks see 10% to 50% improvement in
prefetch performance on BMG depending on PCIe bus speed.
Once parallel fault processing is available, the pagefault queue can be
unified into a single queue with multiple workers pulling faults to
process. A single queue then allows a sensible pagefault cache to be
implemented, so that multiple faults targeting the same region can be
batched together and acknowledged in, ideally, a single pass. This saves
CPU cycles during pagefault handling and improves overall throughput of
the fault handler.
Significant improvements in UMD pagefault benchmarks can be seen when
utilizing this caching.
v3:
- Fix kunit build (CI)
v4:
- Actually fix kunit build (CI)
v5:
- Address v4 feedback, rebase, fix several CI bugs
v6:
- Address Sashiko feedback: https://sashiko.dev/#/patchset/20260723214743.1498125-1-matthew.brost%40intel.com
- CI fixes
v7:
- Dedicated prefetch work queue (Sashiko, arch choice)
- Clean up unwind paths (Sashiko)
v8:
- Still fighting valid Sashiko issues (unwind, locking issues, reset flows)
Matt
Matthew Brost (12):
drm/xe: Fine grained page fault locking
drm/xe: Allow prefetch-only VM bind IOCTLs to use VM read lock
drm/xe: Thread prefetch of SVM ranges
drm/xe: Use a single page-fault queue with multiple workers
drm/xe: Add num_pf_work modparam
drm/xe: Engine class and instance into a u8
drm/xe: Track pagefault worker runtime
drm/xe: Chain page faults via queue-resident cache to avoid fault
storms
drm/xe: Add pagefault chaining stats
drm/xe: Add debugfs pagefault_info
drm/xe: batch CT pagefault acks with periodic flush
drm/xe: Track parallel page fault activity in GT stats
drivers/gpu/drm/xe/xe_debugfs.c | 11 +
drivers/gpu/drm/xe/xe_defaults.h | 1 +
drivers/gpu/drm/xe/xe_device.c | 14 +-
drivers/gpu/drm/xe/xe_device_types.h | 23 +-
drivers/gpu/drm/xe/xe_gt_stats.c | 7 +
drivers/gpu/drm/xe/xe_gt_stats_types.h | 22 +
drivers/gpu/drm/xe/xe_guc_ct.c | 95 +++-
drivers/gpu/drm/xe/xe_guc_ct.h | 36 +-
drivers/gpu/drm/xe/xe_guc_pagefault.c | 39 +-
drivers/gpu/drm/xe/xe_guc_types.h | 6 +
drivers/gpu/drm/xe/xe_module.c | 4 +
drivers/gpu/drm/xe/xe_module.h | 1 +
drivers/gpu/drm/xe/xe_pagefault.c | 689 ++++++++++++++++++++----
drivers/gpu/drm/xe/xe_pagefault.h | 74 +++
drivers/gpu/drm/xe/xe_pagefault_types.h | 112 +++-
drivers/gpu/drm/xe/xe_svm.c | 146 +++--
drivers/gpu/drm/xe/xe_svm.h | 59 +-
drivers/gpu/drm/xe/xe_userptr.c | 19 +-
drivers/gpu/drm/xe/xe_vm.c | 285 +++++++---
drivers/gpu/drm/xe/xe_vm_types.h | 42 +-
20 files changed, 1376 insertions(+), 309 deletions(-)
--
2.34.1
next reply other threads:[~2026-07-24 23:26 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-24 23:25 Matthew Brost [this message]
2026-07-24 23:25 ` [PATCH v8 01/12] drm/xe: Fine grained page fault locking Matthew Brost
2026-07-24 23:25 ` [PATCH v8 02/12] drm/xe: Allow prefetch-only VM bind IOCTLs to use VM read lock Matthew Brost
2026-07-27 14:33 ` Francois Dugast
2026-07-24 23:25 ` [PATCH v8 03/12] drm/xe: Thread prefetch of SVM ranges Matthew Brost
2026-07-27 16:41 ` Francois Dugast
2026-07-27 19:21 ` Matthew Brost
2026-07-27 19:46 ` Matthew Brost
2026-07-27 16:49 ` Francois Dugast
2026-07-27 19:11 ` Matthew Brost
2026-07-24 23:25 ` [PATCH v8 04/12] drm/xe: Use a single page-fault queue with multiple workers Matthew Brost
2026-07-24 23:25 ` [PATCH v8 05/12] drm/xe: Add num_pf_work modparam Matthew Brost
2026-07-24 23:25 ` [PATCH v8 06/12] drm/xe: Engine class and instance into a u8 Matthew Brost
2026-07-24 23:25 ` [PATCH v8 07/12] drm/xe: Track pagefault worker runtime Matthew Brost
2026-07-24 23:25 ` [PATCH v8 08/12] drm/xe: Chain page faults via queue-resident cache to avoid fault storms Matthew Brost
2026-07-29 12:31 ` Francois Dugast
2026-07-29 18:20 ` Matthew Brost
2026-08-03 13:58 ` Francois Dugast
2026-07-24 23:25 ` [PATCH v8 09/12] drm/xe: Add pagefault chaining stats Matthew Brost
2026-07-24 23:25 ` [PATCH v8 10/12] drm/xe: Add debugfs pagefault_info Matthew Brost
2026-07-24 23:26 ` [PATCH v8 11/12] drm/xe: batch CT pagefault acks with periodic flush Matthew Brost
2026-08-04 12:55 ` Francois Dugast
2026-07-24 23:26 ` [PATCH v8 12/12] drm/xe: Track parallel page fault activity in GT stats Matthew Brost
2026-07-24 23:32 ` ✗ CI.checkpatch: warning for Fine grained fault locking, threaded prefetch, storm cache (rev8) Patchwork
2026-07-24 23:33 ` ✓ CI.KUnit: success " Patchwork
2026-07-25 0:17 ` ✓ Xe.CI.BAT: " 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=20260724232601.1753977-1-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