From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
To: Dave Airlie <airlied@gmail.com>, Simona Vetter <simona.vetter@ffwll.ch>
Cc: "Jani Nikula" <jani.nikula@linux.intel.com>,
"Joonas Lahtinen" <joonas.lahtinen@linux.intel.com>,
"Tvrtko Ursulin" <tursulin@ursulin.net>,
"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
"Thomas Zimmermann" <tzimmermann@suse.de>,
"Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
"Maxime Ripard" <mripard@kernel.org>,
"Matthew Brost" <matthew.brost@intel.com>,
"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
"Oded Gabbay" <ogabbay@kernel.org>,
dri-devel@lists.freedesktop.org, intel-gfx@lists.freedesktop.org,
intel-xe@lists.freedesktop.org, dim-tools@lists.freedesktop.org
Subject: [PULL] drm-xe-next
Date: Thu, 12 Nov 2026 10:42:35 +0100 [thread overview]
Message-ID: <avWKCypDrHj5139M@fedora> (raw)
Hi Dave, Simona!
This week's drm-xe-next PR. Highlights:
Series
------
- drm/xe: Clean up adjust_idledly() and implement Wa_16031259911 (v3)
10/10 patches pushed
Refactors adjust_idledly() (common picosecond unit, early bails, factored
min/max helpers, VF-mode bail-out), syncs Wa_16023105232 with its OOB rule,
fixes GuC regset size accounting for RING_IDLEDLY workarounds, and adds
Wa_16031259911 for graphics IP 35.10/35.11.
(Gustavo Sousa)
- Prepare SR-IOV provisioning for vGPU profiles
5/5 patches pushed
Splits the PF provisioning-mode change and bulk priority provisioning into
static helpers that expect the master mutex held, and makes mode changes,
VF auto-provisioning and unprovisioning run under that mutex, in
preparation for vGPU profile support.
(Piotr Piórkowski, Michal Wajdeczko)
- drm/xe: Clean up the GU_MISC irq handling
3/4 patches pushed (the 4th, "drm/xe: Use intel_display_gse_irq_handler()",
went via drm-intel-next together with its i915 dependency)
Only enables the GSE interrupt when display needs it, extracts
xe_gu_misc_irq_{postinstall,reset}() and renames the display GSE irq
handler.
(Ville Syrjälä)
- drm/xe: Fix tile workaround resume handling and enable Wa_14028586678
2/2 patches pushed
Waits for PCODE init before applying tile workarounds on resume (and
reapplies after D3cold runtime resume), then enables Wa_14028586678 on
Crescent Island.
(Daniel Charles, Fei Yang)
- Optimise suspend handling for CCS iGPU platforms (v2)
2/2 patches pushed
Avoids evicting CCS buffers from TT and skips BO eviction on iGPU for
non-hibernation sleep, since CCS stolen memory persists across them.
(Matthew Auld)
- Fix VF probe issue due to missing LMTT dir ptr (v3)
2/2 patches pushed
Programs the LMTT directory pointer from each GT's init path and uses
multicast writes for early-generation LMTT config, fixing VF probe
failures. (b4 reports the two patches as separate 1-patch threads; the
cover letter describes a two-patch series.)
(Satyanarayana K V P)
Single patches
--------------
- drm: xe: select configfs (Arnd Bergmann)
- drm/xe: Don't ask for bug reports on force probed platforms (Rodrigo Vivi)
- drm/xe: Add support for Wa_14028250015 (Alan Previn)
- drm/xe/xe_pci_error: Wait for pcode init post SBR (Riana Tauro)
- drm/xe/guc: Demote uncorrectable local error log on CRI (Varun Gupta)
The following changes since commit 3b8860fe2581a8db796150728687ba1c6b78ddab:
drm/xe: Unwrap sync fences before adding them as job dependencies (2026-11-04 14:44:09 -0800)
are available in the Git repository at:
https://gitlab.freedesktop.org/drm/xe/kernel.git tags/drm-xe-next-2026-11-12
for you to fetch changes up to be73339dd9d70623b7dbc9c4e3b966824b771069:
drm: xe: select configfs (2026-11-11 13:53:05 -0500)
----------------------------------------------------------------
Driver Changes:
- drm: xe: select configfs (Arnd Bergmann)
- drm/xe: Don't ask for bug reports on force probed platforms (Rodrigo Vivi)
- drm/xe/pf: Split the provisioning mode change function (Michal Wajdeczko)
- drm/xe/pf: Provision VFs under mutex (Piotr Piórkowski)
- drm/xe/pf: Add locked variant of the fair VFs provisioning (Piotr Piórkowski)
- drm/xe/pf: Change provisioning mode under mutex (Michal Wajdeczko)
- drm/xe/pf: Split the bulk priority provisioning function (Michal Wajdeczko)
- drm/xe: Only enable the GSE interrupt when display needs it (Ville Syrjälä)
- drm/xe: Extract xe_gu_misc_irq_{postinstall,reset}() (Ville Syrjälä)
- drm/xe: s/xe_display_irq_enable()/xe_display_gse_irq_handler()/ (Ville Syrjälä)
- drm/xe/pm: skip BO eviction on iGPU for non-hibernation sleep (Matthew Auld)
- drm/xe: only evict CCS buffers from TT on iGPU (Matthew Auld)
- drm/xe: Implement Wa_16031259911 (Gustavo Sousa)
- drm/xe/guc: Increment regset size for RING_IDLEDLY workarounds (Gustavo Sousa)
- drm/xe/guc: Increment regset size for Wa_1607983814 inside hwe loop (Gustavo Sousa)
- drm/xe: Replace MAXCNT comment with a comment on adjust_idledly() (Gustavo Sousa)
- drm/xe: Drop early and redundant workaround checks in adjust_idledly() (Gustavo Sousa)
- drm/xe: Bail from adjust_idledly() if no applicable workaround (Gustavo Sousa)
- drm/xe: Factor out {min,max}_idledly_ps in adjust_idledly() (Gustavo Sousa)
- drm/xe: Use picosecond as common unit in adjust_idledly() (Gustavo Sousa)
- drm/xe: Sync Wa_16023105232 in xe_was to match OOB rule (Gustavo Sousa)
- drm/xe: Bail from adjust_idledly() if in VF mode (Gustavo Sousa)
- drm/xe: Add support for Wa_14028250015 (Alan Previn)
- drm/xe/pf: Use multicast writes for early-generation LMTT config (Satyanarayana K V P)
- drm/xe/pf: Program LMTT directory pointer from each GT's init path (Satyanarayana K V P)
- drm/xe/xe_pci_error: Wait for pcode init post SBR (Riana Tauro)
- drm/xe/guc: Demote uncorrectable local error log on CRI (Varun Gupta)
- drm/xe/cri: Implement Wa_14028586678 (Fei Yang)
- drm/xe/pm: Apply tile workarounds after PCODE initialization (Daniel Charles)
----------------------------------------------------------------
Alan Previn (1):
drm/xe: Add support for Wa_14028250015
Arnd Bergmann (1):
drm: xe: select configfs
Daniel Charles (1):
drm/xe/pm: Apply tile workarounds after PCODE initialization
Fei Yang (1):
drm/xe/cri: Implement Wa_14028586678
Gustavo Sousa (10):
drm/xe: Bail from adjust_idledly() if in VF mode
drm/xe: Sync Wa_16023105232 in xe_was to match OOB rule
drm/xe: Use picosecond as common unit in adjust_idledly()
drm/xe: Factor out {min,max}_idledly_ps in adjust_idledly()
drm/xe: Bail from adjust_idledly() if no applicable workaround
drm/xe: Drop early and redundant workaround checks in adjust_idledly()
drm/xe: Replace MAXCNT comment with a comment on adjust_idledly()
drm/xe/guc: Increment regset size for Wa_1607983814 inside hwe loop
drm/xe/guc: Increment regset size for RING_IDLEDLY workarounds
drm/xe: Implement Wa_16031259911
Matthew Auld (2):
drm/xe: only evict CCS buffers from TT on iGPU
drm/xe/pm: skip BO eviction on iGPU for non-hibernation sleep
Michal Wajdeczko (3):
drm/xe/pf: Split the bulk priority provisioning function
drm/xe/pf: Change provisioning mode under mutex
drm/xe/pf: Split the provisioning mode change function
Piotr Piórkowski (2):
drm/xe/pf: Add locked variant of the fair VFs provisioning
drm/xe/pf: Provision VFs under mutex
Riana Tauro (1):
drm/xe/xe_pci_error: Wait for pcode init post SBR
Rodrigo Vivi (1):
drm/xe: Don't ask for bug reports on force probed platforms
Satyanarayana K V P (2):
drm/xe/pf: Program LMTT directory pointer from each GT's init path
drm/xe/pf: Use multicast writes for early-generation LMTT config
Varun Gupta (1):
drm/xe/guc: Demote uncorrectable local error log on CRI
Ville Syrjälä (3):
drm/xe: s/xe_display_irq_enable()/xe_display_gse_irq_handler()/
drm/xe: Extract xe_gu_misc_irq_{postinstall,reset}()
drm/xe: Only enable the GSE interrupt when display needs it
drivers/gpu/drm/xe/Kconfig | 1 +
drivers/gpu/drm/xe/abi/guc_klvs_abi.h | 1 +
drivers/gpu/drm/xe/display/xe_display.c | 19 +++-
drivers/gpu/drm/xe/display/xe_display.h | 6 +-
drivers/gpu/drm/xe/regs/xe_gt_regs.h | 3 +-
drivers/gpu/drm/xe/regs/xe_mert_regs.h | 4 +
drivers/gpu/drm/xe/xe_bo_evict.c | 66 ++++++++++--
drivers/gpu/drm/xe/xe_configfs.h | 30 ------
drivers/gpu/drm/xe/xe_device_types.h | 2 +
drivers/gpu/drm/xe/xe_device_wa_oob.rules | 1 +
drivers/gpu/drm/xe/xe_gt.c | 14 ++-
drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 69 ++++++-------
drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h | 17 +--
drivers/gpu/drm/xe/xe_guc_ads.c | 21 +++-
drivers/gpu/drm/xe/xe_guc_submit.c | 18 +++-
drivers/gpu/drm/xe/xe_hw_engine.c | 160 ++++++++++++++---------------
drivers/gpu/drm/xe/xe_irq.c | 29 ++++--
drivers/gpu/drm/xe/xe_lmtt.c | 52 +++++++---
drivers/gpu/drm/xe/xe_lmtt.h | 5 +-
drivers/gpu/drm/xe/xe_pci.c | 22 +++-
drivers/gpu/drm/xe/xe_pci_error.c | 6 ++
drivers/gpu/drm/xe/xe_pm.c | 36 +++++--
drivers/gpu/drm/xe/xe_pm.h | 2 +-
drivers/gpu/drm/xe/xe_sriov_pf_provision.c | 100 +++++++++++-------
drivers/gpu/drm/xe/xe_wa.c | 12 ++-
drivers/gpu/drm/xe/xe_wa_oob.rules | 7 +-
drivers/gpu/drm/xe/xe_wedge.c | 8 +-
27 files changed, 437 insertions(+), 274 deletions(-)
next reply other threads:[~2026-11-12 9:43 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-12 9:42 Thomas Hellstrom [this message]
-- strict thread matches above, loose matches on Subject: below --
2026-11-05 15:38 [PULL] drm-xe-next Thomas Hellstrom
2026-10-01 20:57 Matthew Brost
2026-10-01 12:57 Rodrigo Vivi
2026-10-01 21:05 ` Rodrigo Vivi
2026-09-18 19:45 Matthew Brost
2026-09-01 0:26 Matthew Brost
2026-07-30 16:06 Rodrigo Vivi
2026-07-03 18:13 Rodrigo Vivi
2026-05-28 12:57 Thomas Hellstrom
2026-05-21 18:38 Thomas Hellstrom
2026-05-14 13:20 Thomas Hellstrom
2026-04-30 13:00 Thomas Hellstrom
2026-03-27 3:24 Matthew Brost
2026-03-26 4:44 Matthew Brost
2026-03-12 14:57 Matthew Brost
2026-03-02 22:40 Matthew Brost
2026-01-15 16:16 Rodrigo Vivi
2025-12-30 9:58 Thomas Hellstrom
2025-12-19 22:41 Rodrigo Vivi
2025-11-14 10:49 Thomas Hellstrom
2025-11-17 20:56 ` Dave Airlie
2025-11-18 8:34 ` Thomas Hellström
2025-11-05 16:53 Thomas Hellstrom
2025-10-28 11:16 Thomas Hellstrom
2025-10-31 17:46 ` Simona Vetter
2025-10-20 8:31 Thomas Hellstrom
2025-10-24 11:26 ` Simona Vetter
2025-09-19 14:53 Lucas De Marchi
2025-08-29 22:00 Lucas De Marchi
2025-07-15 18:21 Rodrigo Vivi
2025-07-10 22:16 Rodrigo Vivi
2025-07-11 9:12 ` Simona Vetter
2025-07-11 9:25 ` Simona Vetter
2025-06-18 20:05 Rodrigo Vivi
2025-05-08 16:01 Thomas Hellstrom
2025-04-28 16:03 Thomas Hellstrom
2025-04-28 14:27 Thomas Hellstrom
2025-04-28 15:40 ` Thomas Hellström
2025-04-17 10:22 Thomas Hellstrom
2025-03-07 8:02 Lucas De Marchi
2025-03-07 14:51 ` Lucas De Marchi
2025-03-07 19:04 ` Lucas De Marchi
2025-02-24 18:50 Lucas De Marchi
2025-01-10 14:54 Rodrigo Vivi
2025-01-07 19:01 Rodrigo Vivi
2024-12-11 23:27 Rodrigo Vivi
2024-10-31 11:50 Thomas Hellstrom
2024-10-24 17:52 Thomas Hellstrom
2024-10-24 19:22 ` Matthew Brost
2024-10-25 7:30 ` Thomas Hellström
2024-10-25 9:34 ` Jani Nikula
2024-10-25 10:45 ` Thomas Hellström
2024-10-25 22:26 ` Matthew Brost
2024-10-17 9:32 Thomas Hellstrom
2024-10-10 9:56 Thomas Hellstrom
2024-09-06 2:29 Lucas De Marchi
2024-08-28 19:18 Lucas De Marchi
2024-08-22 20:55 Lucas De Marchi
2024-08-27 10:51 ` Daniel Vetter
2024-07-30 22:39 Lucas De Marchi
2024-07-02 19:02 Rodrigo Vivi
2024-07-05 8:18 ` Daniel Vetter
2024-06-26 22:32 Rodrigo Vivi
2024-06-06 21:43 Rodrigo Vivi
2024-04-23 12:54 Thomas Hellstrom
2024-02-26 3:21 Lucas De Marchi
2024-02-26 9:58 ` Daniel Vetter
2024-02-26 10:46 ` Daniel Stone
2024-02-26 14:16 ` Lucas De Marchi
2023-12-15 22:28 Rodrigo Vivi
2023-12-17 12:35 ` Oded Gabbay
2023-12-17 12:35 ` Oded Gabbay
2023-12-18 12:09 ` Oded Gabbay
2023-12-18 12:09 ` Oded Gabbay
2023-12-18 14:27 ` Oded Gabbay
2023-12-18 14:27 ` Oded Gabbay
2023-12-19 7:17 ` Ohad Sharabi
2023-12-19 9:15 ` Dani Liberman
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=avWKCypDrHj5139M@fedora \
--to=thomas.hellstrom@linux.intel.com \
--cc=airlied@gmail.com \
--cc=dim-tools@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=jani.nikula@linux.intel.com \
--cc=joonas.lahtinen@linux.intel.com \
--cc=maarten.lankhorst@linux.intel.com \
--cc=matthew.brost@intel.com \
--cc=mripard@kernel.org \
--cc=ogabbay@kernel.org \
--cc=rodrigo.vivi@intel.com \
--cc=simona.vetter@ffwll.ch \
--cc=tursulin@ursulin.net \
--cc=tzimmermann@suse.de \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.