From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 58E84606A336 for ; Thu, 5 Nov 2026 15:38:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=intel.com header.i=@intel.com header.a=rsa-sha256 header.s=Intel header.b=knscMZkI Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id D53821127DC; Thu, 5 Nov 2026 15:38:49 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.17]) by gabe.freedesktop.org (Postfix) with ESMTPS id 518201127CC; Thu, 5 Nov 2026 15:38:43 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1793893123; x=1825429123; h=date:from:to:cc:subject:message-id:mime-version: content-transfer-encoding; bh=wcmEgAmrNqkbPp5ErltyteHVDWi7TjyzI0l2SUKvwgo=; b=knscMZkI2Y9OcO3dviQKUvH+vsFJqo8ACMJMC2+hpgKw27C9fsxZbdZZ OsdAxqUh/SoWWXjxRcH/zba+i9uofIL4EMLQ6C/fSJcsbCYzxSoyLPKWF TmOvoeVc9btJeXa9YOe+5Pq2vSURtiWCtt4kTIF7xBQYvnRbjGoXVjPdj OLABBgHJB6igRzLpWfiUf7lm0wy8oldrbag97Gm3PgVQIj5dGGgQEqhT0 P40fL5xIkcBfS33PQa6oO/R6lQFSeZoU+bhc0TEQgJAoqGAG3iBN1REDw SAdVcZCtc6z8oYKeejLJaMZuUGmiZMQIiH4PzzfPxiw0dAU/t6ofEs5/L A==; X-CSE-ConnectionGUID: UzHd/GfASBOUuK+0NtqmRg== X-CSE-MsgGUID: +h5rI9/pRkukkzZiH6UDbw== X-IronPort-AV: E=McAfee;i="6800,10657,11957"; a="2691456" X-IronPort-AV: E=Sophos;i="6.27,197,1787036400"; d="scan'208";a="2691456" Received: from orviesa006.jf.intel.com ([10.64.159.146]) by fmvoesa111.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 05 Nov 2026 07:38:43 -0800 X-CSE-ConnectionGUID: 2bBNZXhUQ3OFIQ+eWZWirQ== X-CSE-MsgGUID: EGJlVfcgTrG8il3bFYTwGg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.27,197,1787036400"; d="scan'208";a="7097559" Received: from conormcd-mobl2.ger.corp.intel.com (HELO fedora) ([10.245.244.219]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 05 Nov 2026 07:38:39 -0800 Date: Thu, 5 Nov 2026 16:38:17 +0100 From: Thomas Hellstrom To: Dave Airlie , Simona Vetter Cc: Jani Nikula , Joonas Lahtinen , Tvrtko Ursulin , Rodrigo Vivi , Thomas Zimmermann , Maarten Lankhorst , Maxime Ripard , Matthew Brost , Thomas =?iso-8859-1?Q?Hellstr=F6m?= , Oded Gabbay , 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 Message-ID: X-Archived-By: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Intel-gfx" X-Spam-Status: No, score=-13.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH, INCLUDES_PULL_REQUEST,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=unavailable autolearn_force=no version=4.0.1 X-Spam-Checker-Version: SpamAssassin 4.0.1 (2024-03-26) on aws-us-west-2-korg-listserv-alma10-1 Hi Dave, Simona! Here's the first drm-xe-next PR towards 7.5. Highlights: Series ------ - drm/xe/hwmon: Update hwmon thermal mailbox (v14) 16/16 patches pushed Adds CRI-specific temperature sensor handling to xe hwmon: sensor presence checks, platform-reported VRAM thermal channels, PCIe and memory controller temperature support, IEEE-754 / sign-magnitude register decoding, cached availability to cut probe time, and several hwmon fixes (error propagation, pcode power limit handling). (Karthik Poosa) - Convert IO_BUS errors to structured xe_log API (v7) 12/12 patches pushed Converts error reporting in VRAM, LMTT, PCI, PAT, reg_sr, memirq, MMIO, hwmon and GGTT to the structured xe_log API, adding new VRAM, PAT and HWMON driver-hardware components. Also makes xe_pat_init_early() return an error on unknown platforms. (Dnyaneshwar Bhadane) - Add CPER logging support for CRI (v8) 10/10 patches pushed Adds CPER (Common Platform Error Record) logging of RAS errors reported by the device, emitted via a trace event and the xe_log SIGID infrastructure. Also converts correctable, SoC internal, core compute and device memory error reporting to SIGID. (Badal Nilawar) - drm/xe/sysctrl: Clean up error handling in the System Controller mailbox (v9) 10/10 patches pushed Makes error propagation in the sysctrl mailbox driver consistent and uses xe_log_err() for structured reporting. Removes redundant checks, simplifies helpers without an error path and fixes mailbox header handling. (Mallesh Koujalagi) - Introduce xe_wedge (v14) 9/9 patches pushed Consolidates the wedging implementation into a dedicated xe_wedge component and fixes several pre-existing wedge-handling issues (IRQ-safe declare_wedged, runtime PM guards in RAS/AMC/HW error workers, wedge worker flushing before bus reset, GT ordered workqueue). (Raag Jadav) - drm/xe: Capture additional HW register state in devcoredump (v7) 7/7 patches pushed Extends the devcoredump with GuC status/capture registers, GT fuses, GAM page-fault reports and L3 node status on Xe3p, to make hang and fault triage post-mortem dumps self-contained. (Nareshkumar Gollakoti) - Use SIG ID logs for GuC component (v8) 7/7 patches pushed Adds SIG ID logging for GuC CT shutdown, major GuC failures and DMA failures, with cleanups of GuC error codes, separate CRASH/EXCEPTION G2H handlers, and ct_dead_capture available on non-debug configs. (Daniele Ceraolo Spurio, Umesh Nerlige Ramappa) - Add Ocode late binding support for CRI (v7) 6/6 patches pushed Refactors the late-bind PM flow and adds Ocode (OOBMSM telemetry/ manageability) firmware loading on CRI, with status-code string mappings, a flag-to-mask conversion and a firmware leak fix. (Badal Nilawar) - Add support to handle memory double-bit ECC errors (v6) 6/6 patches pushed Adds the firmware commands needed to handle uncorrectable memory double-bit ECC errors: page offline requests and queue/list queries via sysctrl, tracking of firmware-offlined pages, and reporting max_pages to userspace. (Riana Tauro) - Fix memory corruption with unaligned dst in MEM_COPY (v5) 4/4 patches pushed Fixes xe_migrate_access_memory() corruption on BMG when the MATRIX_COPY destination is not pitch aligned, fixes page tracking, optimizes unaligned copies and adds a subtest. (Jan Maslak, Christoph Manszewski) - Split the BO shrinker and adjust batch size (v5) 4/4 patches pushed Sets the shrinker batch size from the average BO size, splits the shrinker into purgeable and non-purgeable ones, tracks populated ttm_tts and no longer aborts the shrinker walk on -EBUSY. (Thomas Hellström) - Split GuC ID space into usable and shareable pools (v7) 4/4 patches pushed Separates GuC IDs usable for submission from IDs shareable with VFs in the ID manager, with dedicated allocation interfaces, accounting and KUnit coverage. (Piotr Piórkowski) - Follow-up fixes for memory page offline (v2) 4/4 patches pushed Addresses review comments on page offline: drops RCU list handling for VRAM bad-page tracking, re-validates external pin under the resv lock, keeps fault injection in the usable range and fixes kernel-doc. (Tejas Upadhyay) - access_memory chunking fixes and tests (no cover letter) 3/3 patches pushed Keeps access_memory chunks within the transfer limit and extends the tests to cover large writes to unaligned BO offsets and short bounce- buffered accesses. (Mika Kuoppala) - drm/xe: Some D3Cold related fixes (v4) 3/3 patches pushed Toggles the D3Cold enable flag on runtime resume, accesses GT MMIO only after pcode init and memsets the g2g buffer on resume. (Vinay Belgaumkar) - drm/xe: Update Wa_14026539277 (v5) 3/3 patches pushed Reverts the old implementation and adds the up-to-date one after the workaround database changed; extracts override_has_cached_pt(). (Gustavo Sousa) - Improve HW reserved PAT checking (v3) 3/3 patches pushed Replaces the !coh_mode based check for HW reserved PAT indices with pat.valid and hardens all PAT index queries accordingly. (Matthew Auld) - Fix kernel crash during driver teardown (v7) 3/3 patches pushed Disables the GT reset worker before engine teardown, protects GuC timeout handling from device unplug and prevents the VF memory IRQ handler from accessing a torn-down engine. (Satyanarayana K V P) - GuC: Compress GuC log and CTB dump with zstd (v11) 3/3 patches pushed Adds a dump cache and zstd compression of large GuC log/CTB snapshot payloads and trims noise in the LRC snapshot output. (Zhanjun Dong, Alan Previn) - drm/xe/sysctrl: Add system controller debugfs (v8) 3/3 patches pushed Adds sysctrl debugfs infrastructure with a loopback test, RAS error injection and a generic mailbox passthrough entry for firmware validation. (Anoop Vijay) - Fix two BO pin/unpin accounting bugs (v3) 2/2 patches pushed Fixes shrinker accounting double-subtraction on nested external pins and a stale pinned_link entry when fb-pin performs the final unpin. (Thomas Hellström) - Don't dereference a NULL resource in xe_evict_flags() (v3) 2/2 patches pushed Skips eviction of a BO without a ttm resource (e.g. imported dma-buf BO being torn down) and adds a regression test. (Niranjana Vishwanathapura) - drm/xe/nvm: Add survivability partition (v3) 2/2 patches pushed (1 xe, 1 mtd: mtd_intel_dg) Defines a survivability partition covering the whole storage so a card in survivability mode can recover from a corrupted partition table. The mtd patch went in via drm with the MTD maintainer's ack. (Alexander Usyskin) - drm/xe/tuning: Fix Xe3p tuning register mismatches 2/2 patches pushed Stops applying obsolete media CCCHKNREG1/L3SQCREG3 tunings from Xe3p onward and restricts the Anyhit NULL-query tuning to render engines. (Nitin Gote) - Intel Xe GPU debug support (eudebug) (v10) 1/27 patches pushed Only the xe-relevant subset was pushed: removes the ifdef in the DRM_GPUVA_OP_DRIVER svm sub-op checking. (Mika Kuoppala) Single patches -------------- - drm/xe/svm: Preserve default PAT index when resetting VMA attributes (Arvind Yadav) - drm/xe/eu_stall: Don't mark stream enabled if enable fails (Fei Yang) - drm/xe/guc: Add WA 14028709524 to disable PRL from VF (Alan Previn) - drm/xe/vf: Move H2G CTB to VRAM on VF (Piotr Piórkowski) - drm/xe/hwmon: Use overflows_type() for temperature range check (Mallesh Koujalagi) - drm/xe/dma-buf: Add xe_dma_buf_to_gem() self-import helper (Niranjana Vishwanathapura) - drm/xe/cri: Add new PCI ID (Balasubramani Vivekanandan) - drm/xe/guc: Do not attribute a TDR disable to a pending suspend (Jagmeet Randhawa) - drm/xe: Rebind BOs evicted before the first LR queue (Arvind Yadav) - drm/xe: Extend Wa_16030224309 to graphics version 35.11 (Tangudu Tilak Tirumalesh) - drm/xe/madvise: use already clamped pat_index (Matthew Auld) - drm/xe: Fix build with DRM_XE=y and CONFIGFS_FS=m (Rodrigo Vivi) - drm/xe/lrc: Restore CTX_CS_INDIRECT_CTX_OFFSET programming for pre-Xe2 (Helen Koike) - drm/xe: Tie BO TTM LRU priority to DONTNEED/WILLNEED madvise state (Matthew Brost) - drm/xe/xe3: Fix OAM stream broken on Xe3+ (Shekhar Chauhan) - drm/xe: Mark xe_vma_ops_alloc() noinline for error injection (Shuicheng Lin) - drm/xe/gsc: Fix NVL-S GSC compatibility number (Daniele Ceraolo Spurio) - drm/xe/uc: Add missing HuC firmware entry for Alderlake-N (Kumar, Sachin) - drm/xe: Bump LRU for external objects on exec and rebind (Thomas Hellström) - drm/xe/oa: Zero OA buffer at allocation (Bommu Krishnaiah) - drm/xe/log: fix documentation title levels (Guillaume Tucker) - drm/xe/ras: Fix sysctrl and drm-ras discrepancy (Raag Jadav) - drm/xe/sysctrl: Add mailbox control state to error messages (Anoop Vijay) - drm/xe: Don't transfer shrinker pages for pinned bos on purgeable state change (Thomas Hellström) - drm/xe/i2c: cancel the client work on remove (Fan Wu) - drm/xe: Don't allow XE_VALIDATION_UNIMPLEMENTED outside of debug builds (Thomas Hellström) - drm/xe/xe3p: Read resource copy presence from fuse register (Matt Roper) - drm/xe: Unwrap sync fences before adding them as job dependencies (Chen, Junjia) The following changes since commit 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4: Linux 7.4-rc1 (2026-11-01 13:26:31 -0800) are available in the Git repository at: https://gitlab.freedesktop.org/drm/xe/kernel.git tags/drm-xe-next-2026-11-05 for you to fetch changes up to 3b8860fe2581a8db796150728687ba1c6b78ddab: drm/xe: Unwrap sync fences before adding them as job dependencies (2026-11-04 14:44:09 -0800) ---------------------------------------------------------------- Cross-subsystem Changes: - mtd: mtd_intel_dg: add survivability partition (Alexander Usyskin) Core Changes: - drm/xe/cri: Add new PCI ID (Balasubramani Vivekanandan) Driver Changes: - drm/xe: Unwrap sync fences before adding them as job dependencies (Chen, Junjia) - drm/xe/svm: Preserve default PAT index when resetting VMA attributes (Arvind Yadav) - drm/xe/guc: capture additional engine state registers (Nareshkumar Gollakoti) - drm/xe: capture L3 node status registers in devcoredump (Nareshkumar Gollakoti) - drm/xe/guc: add TDL, SLICE gfx registers to capture list (Nareshkumar Gollakoti) - drm/xe: dump GAM page fault report registers in devcoredump (Nareshkumar Gollakoti) - drm/xe/guc: Print register addresses in capture snapshot output (Nareshkumar Gollakoti) - drm/xe/devcoredump: Add GuC register snapshot to devcoredump (Nareshkumar Gollakoti) - drm/xe/devcoredump: Capture GT fuse registers in devcoredump (Nareshkumar Gollakoti) - drm/xe/xe_late_bind_fw: Refactor pm flow (Badal Nilawar) - drm/xe/xe_late_bind_fw: Enable late binding support for CRI (Badal Nilawar) - drm/xe/xe_late_bind_fw: Add support to load Ocode firmware (Badal Nilawar) - drm/xe/xe_late_bind_fw: Convert late bind flag to mask (Badal Nilawar) - drm/xe/xe_late_bind_fw: Add string mappings of status codes (Badal Nilawar) - drm/xe/xe_late_bind_fw: Fix firmware leak on missing manifest entry (Badal Nilawar) - drm/xe/eu_stall: Don't mark stream enabled if enable fails (Fei Yang) - drm/xe/guc: Add WA 14028709524 to disable PRL from VF (Alan Previn) - drm/xe/vf: Move H2G CTB to VRAM on VF (Piotr Piórkowski) - drm/xe/hwmon: Use overflows_type() for temperature range check (Mallesh Koujalagi) - drm/xe/dma-buf: Add xe_dma_buf_to_gem() self-import helper (Niranjana Vishwanathapura) - drm/xe/tests: Keep bounce buffered accesses short in access_memory test (Mika Kuoppala) - drm/xe/tests: Cover a large write to an unaligned bo offset (Mika Kuoppala) - drm/xe/migrate: Keep access_memory chunks within the transfer limit (Mika Kuoppala) - drm/xe: Memset g2g buffer on resume (Vinay Belgaumkar) - drm/xe: Access GT MMIO after pcode init (Vinay Belgaumkar) - drm/xe: Toggle the D3Cold enable flag at runtime resume (Vinay Belgaumkar) - drm/xe/xe_ras: Report correctable errors using SIGID (Badal Nilawar) - drm/xe/xe_ras: Report soc internal errors using SIGID (Badal Nilawar) - drm/xe/xe_ras: Report core compute errors using SIGID (Badal Nilawar) - drm/xe/xe_ras: Report device memory errors using SIGID (Badal Nilawar) - drm/xe/cper: Emit cper record to trace buf (Badal Nilawar) - drm/xe/cper: Construct CPER record for hardware errors (Badal Nilawar) - drm/xe/cper: Initialize Intel-specific CPER header (Badal Nilawar) - drm/xe/cper: Retrieve the error counter record for CPER reporting (Badal Nilawar) - drm/xe/cper: Add CPER reporting entry point for xe_log (Badal Nilawar) - drm/xe: Add up-to-date implementation for Wa_14026539277 (Gustavo Sousa) - Revert "drm/xe/nvlp: Implement Wa_14026539277" (Gustavo Sousa) - drm/xe: Extract override_has_cached_pt() (Gustavo Sousa) - drm/xe/guc: Do not attribute a TDR disable to a pending suspend (Jagmeet Randhawa) - drm/xe: Remove ifdef in DRM_GPUVA_OP_DRIVER svm subop checking (Mika Kuoppala) - drm/xe: Rebind BOs evicted before the first LR queue (Arvind Yadav) - drm/xe: Extend Wa_16030224309 to graphics version 35.11 (Tangudu Tilak Tirumalesh) - drm/xe/tuning: Stop applying media CCCHKNREG1 tuning from Xe3p onward (Nitin Gote) - drm/xe/pat: always check is_valid() when querying an index (Matthew Auld) - drm/xe: revamp hw reserved PAT index checking (Matthew Auld) - drm/xe/pat: initialise pat.valid everywhere (Matthew Auld) - drm/xe/ras: Move xe_ras_process_errors() to xe_ras (Raag Jadav) - drm/xe/amc: Guard xe_amc_work() with runtime PM (Raag Jadav) - drm/xe/pci_error: Flush GT wedge worker before bus reset (Raag Jadav) - drm/xe: Make xe_device_declare_wedged() IRQ safe (Raag Jadav) - drm/xe: Move xe_device_wedged_fini() registration to xe_device_probe_early() (Raag Jadav) - drm/xe/hw_error: Guard csc_hw_error_work() with runtime PM (Raag Jadav) - drm/xe: Drop xe_device_set_wedged_method() (Raag Jadav) - drm/xe/gt: Use GT ordered workqueue for wedging (Raag Jadav) - drm/xe/tests: Add xe_migrate_access_memory subtest (Jan Maslak) - drm/xe/xe_migrate: Optimize unaligned access_memory copies (Jan Maslak) - drm/xe/xe_migrate: Align MEM_COPY pitch with destination address (Christoph Manszewski) - drm/xe/xe_migrate: Fix page tracking in access_memory (Christoph Manszewski) - drm/xe/madvise: use already clamped pat_index (Matthew Auld) - drm/xe: Fix build with DRM_XE=y and CONFIGFS_FS=m (Rodrigo Vivi) - drm/xe/lrc: Restore CTX_CS_INDIRECT_CTX_OFFSET programming for pre-Xe2 (Helen Koike) - drm/xe: Tie BO TTM LRU priority to DONTNEED/WILLNEED madvise state (Matthew Brost) - drm/xe/xe3: Fix OAM stream broken on Xe3+ (Shekhar Chauhan) - drm/xe: Mark xe_vma_ops_alloc() noinline for error injection (Shuicheng Lin) - drm/xe: Update non-purgeable shrinker batch size based on average BO size (Thomas Hellström) - drm/xe: Split the bo shrinker into purgeable and non-purgeable shrinkers (Thomas Hellström) - drm/xe: Track number of populated ttm_tts in the shrinker (Thomas Hellström) - drm/xe: Don't abort the shrinker walk on -EBUSY (Thomas Hellström) - drm/xe/guc: Report errors that cause a CT shutdown using SIGID (Daniele Ceraolo Spurio) - drm/xe/guc: Report major GuC failures using SIGID (Daniele Ceraolo Spurio) - drm/xe/uc: Report DMA failure using SIGID (Daniele Ceraolo Spurio) - drm/xe/guc: Cleanup error codes and handling for CT errors (Umesh Nerlige Ramappa) - drm/xe/guc: Make ct_dead_capture available on non-debug config (Umesh Nerlige Ramappa) - drm/xe/guc: Handle CRASH and EXCEPTION G2H with separate helpers (Umesh Nerlige Ramappa) - drm/xe/guc: Use different error codes for GuC load errors (Daniele Ceraolo Spurio) - drm/xe/gsc: Fix NVL-S GSC compatibility number (Daniele Ceraolo Spurio) - drm/xe/pf: Explicitly use shareable GuC IDs for VFs provisioning (Piotr Piórkowski) - drm/xe/guc: Start use explicitly usable GuC IDs for for submission (Piotr Piórkowski) - drm/xe/kunit: Extend GuC ID manager split-pool coverage (Piotr Piórkowski) - drm/xe/guc: Split GuC ID manager into usable and shareable pools (Piotr Piórkowski) - drm/xe/tuning: Restrict Anyhit NULL-query tuning to render engines (Nitin Gote) - drm/xe/hwmon: Propagate all hardware read errors (Karthik Poosa) - drm/xe: Validate thermal sensor count before reads (Karthik Poosa) - drm/xe/hwmon: Simplify temperature channels config (Karthik Poosa) - drm/xe/hwmon: add PCIe temperature support for CRI (Karthik Poosa) - drm/xe/hwmon: Update memory controller temperature offset for CRI (Karthik Poosa) - drm/xe/hwmon: Decode CRI temperature registers as IEEE-754 (Karthik Poosa) - drm/xe/hwmon: Add platform-aware VRAM thermal channel support (Karthik Poosa) - drm/xe/hwmon: use CRI-specific package and VRAM temperature registers (Karthik Poosa) - drm/xe/hwmon: Cache temperature availability to reduce probe time (Karthik Poosa) - drm/xe/hwmon: Consolidate temperature sensor availability checks (Karthik Poosa) - drm/xe/hwmon: Detect unavailable PCIe thermal sensors (Karthik Poosa) - drm/xe/hwmon: Handle unavailable memory controller sensors (Karthik Poosa) - drm/xe/hwmon: Add helpers to validate thermal sensor readings (Karthik Poosa) - drm/xe/hwmon: Fix thermal sensor data handling (Karthik Poosa) - drm/xe/hwmon: Decode mailbox temperature as sign-magnitude (Karthik Poosa) - drm/xe/hwmon: Fix pcode power limit handling (Karthik Poosa) - drm/xe/xe_ras: Track offlined pages by firmware to avoid duplicates (Riana Tauro) - drm/xe/xe_ttm_vram: Report max_pages reported by firmware to userspace (Riana Tauro) - drm/xe/xe_ras: Add function to get maximum pages firmware can store (Riana Tauro) - drm/xe/xe_ras: Add support to query page offline queue and list (Riana Tauro) - drm/xe/xe_ras: Handle page offline requests for device memory ecc errors (Riana Tauro) - drm/xe: Separate drm-ras netlink data from device and firmware RAS state (Riana Tauro) - drm/xe/gt: Disable GT reset worker before engine teardown (Satyanarayana K V P) - drm/xe/guc: Protect timeout handling from device unplug (Satyanarayana K V P) - drm/xe: Prevent VF memory IRQ from accessing a torn-down engine (Satyanarayana K V P) - drm/xe/guc: Add dump_cache to optimize GuC CT/Log compression flow (Alan Previn) - drm/xe/guc: Compress GuC log and CTB dump with zstd (Zhanjun Dong) - drm/xe: Remove extra newlines from LRC snapshot dump (Zhanjun Dong) - drm/xe/vram: Report VRAM errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/vram: Report tile vs device VRAM visibility errors (Dnyaneshwar Bhadane) - drm/xe/lmtt: Report invalidation errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/pci: Report unknown GMDID versions using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/pat: Report missing PAT table using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/pat: Return error from xe_pat_init_early() on unknown platform (Dnyaneshwar Bhadane) - drm/xe/reg_sr: Report save-restore errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/memirq: Report errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/mmio: Report BAR mapping errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/hwmon: Report errors using structured xe_log API (Dnyaneshwar Bhadane) - drm/xe/ggtt: Report GGTT errors using structured logging (Dnyaneshwar Bhadane) - drm/xe/log: Add VRAM, PAT, and HWMON DRIVER_HARDWARE components (Dnyaneshwar Bhadane) - drm/xe/uc: Add missing HuC firmware entry for Alderlake-N (Kumar, Sachin) - drm/xe: Bump LRU for external objects on exec and rebind (Thomas Hellström) - drm/xe/oa: Zero OA buffer at allocation (Bommu Krishnaiah) - drm/xe/tests: add regression for eviction of a BO with no resource (Niranjana Vishwanathapura) - drm/xe: skip eviction of a BO with no resource (Niranjana Vishwanathapura) - drm/xe/log: fix documentation title levels (Guillaume Tucker) - drm/xe/ras: Fix sysctrl and drm-ras discrepancy (Raag Jadav) - drm/xe/sysctrl: Add mailbox control state to error messages (Anoop Vijay) - drm/xe: Don't transfer shrinker pages for pinned bos on purgeable state change (Thomas Hellström) - drm/xe/nvm: define survivability partition (Alexander Usyskin) - drm/xe: Keep VRAM fault injection within the usable range (Tejas Upadhyay) - drm/xe: Drop RCU list handling for VRAM bad-page tracking, use mgr->lock (Tejas Upadhyay) - drm/xe: Re-validate external pin under resv lock before VRAM purge (Tejas Upadhyay) - drm/xe: Clean up kernel-doc typos in VRAM manager (Tejas Upadhyay) - drm/xe/i2c: cancel the client work on remove (Fan Wu) - drm/xe: Don't allow XE_VALIDATION_UNIMPLEMENTED outside of debug builds (Thomas Hellström) - drm/xe/sysctrl: Report 'System Controller event' error using SIGID (Mallesh Koujalagi) - drm/xe/sysctrl: Log group and command ID on mailbox failure (Mallesh Koujalagi) - drm/xe/sysctrl: Improve firmware response error logging (Mallesh Koujalagi) - drm/xe/sysctrl: Replace FIELD_GET() with REG_FIELD_GET() (Mallesh Koujalagi) - drm/xe/sysctrl: Fix mailbox header handling (Mallesh Koujalagi) - drm/xe/sysctrl: Use xe_assert() for payload size validation (Mallesh Koujalagi) - drm/xe/sysctrl: Make sysctrl_read_frame() void (Mallesh Koujalagi) - drm/xe/sysctrl: Make sysctrl_write_frame() void (Mallesh Koujalagi) - drm/xe/sysctrl: Return error codes from sysctrl_wait_bit_set() (Mallesh Koujalagi) - drm/xe/sysctrl: Return error codes from sysctrl_wait_bit_clear() (Mallesh Koujalagi) - drm/xe/xe3p: Read resource copy presence from fuse register (Matt Roper) - drm/xe/sysctrl: Add generic mailbox passthrough debugfs entry (Anoop Vijay) - drm/xe/sysctrl: Add RAS error injection debugfs interface (Anoop Vijay) - drm/xe/sysctrl: Add sysctrl debugfs infrastructure and loopback test interface (Anoop Vijay) - drm/xe: Fix stale pinned_link entry when fb-pin performs the final unpin (Thomas Hellström) - drm/xe: Fix shrinker accounting double-subtraction on nested external pins (Thomas Hellström) - drm/xe/cper: Log CPER records for aggregate counter retrieval (Badal Nilawar) - drm/xe: Introduce xe_wedge (Raag Jadav) ---------------------------------------------------------------- Alan Previn (2): drm/xe/guc: Add dump_cache to optimize GuC CT/Log compression flow drm/xe/guc: Add WA 14028709524 to disable PRL from VF Alexander Usyskin (2): mtd: mtd_intel_dg: add survivability partition drm/xe/nvm: define survivability partition Anoop Vijay (4): drm/xe/sysctrl: Add sysctrl debugfs infrastructure and loopback test interface drm/xe/sysctrl: Add RAS error injection debugfs interface drm/xe/sysctrl: Add generic mailbox passthrough debugfs entry drm/xe/sysctrl: Add mailbox control state to error messages Arvind Yadav (2): drm/xe: Rebind BOs evicted before the first LR queue drm/xe/svm: Preserve default PAT index when resetting VMA attributes Badal Nilawar (16): drm/xe/cper: Add CPER reporting entry point for xe_log drm/xe/cper: Retrieve the error counter record for CPER reporting drm/xe/cper: Initialize Intel-specific CPER header drm/xe/cper: Construct CPER record for hardware errors drm/xe/cper: Log CPER records for aggregate counter retrieval drm/xe/cper: Emit cper record to trace buf drm/xe/xe_ras: Report device memory errors using SIGID drm/xe/xe_ras: Report core compute errors using SIGID drm/xe/xe_ras: Report soc internal errors using SIGID drm/xe/xe_ras: Report correctable errors using SIGID drm/xe/xe_late_bind_fw: Fix firmware leak on missing manifest entry drm/xe/xe_late_bind_fw: Add string mappings of status codes drm/xe/xe_late_bind_fw: Convert late bind flag to mask drm/xe/xe_late_bind_fw: Add support to load Ocode firmware drm/xe/xe_late_bind_fw: Enable late binding support for CRI drm/xe/xe_late_bind_fw: Refactor pm flow Balasubramani Vivekanandan (2): drm/xe/cri: Add new PCI ID drm/xe/cri: Add new PCI ID Bommu Krishnaiah (1): drm/xe/oa: Zero OA buffer at allocation Chen, Junjia (1): drm/xe: Unwrap sync fences before adding them as job dependencies Christoph Manszewski (2): drm/xe/xe_migrate: Fix page tracking in access_memory drm/xe/xe_migrate: Align MEM_COPY pitch with destination address Daniele Ceraolo Spurio (5): drm/xe/gsc: Fix NVL-S GSC compatibility number drm/xe/guc: Use different error codes for GuC load errors drm/xe/uc: Report DMA failure using SIGID drm/xe/guc: Report major GuC failures using SIGID drm/xe/guc: Report errors that cause a CT shutdown using SIGID Dnyaneshwar Bhadane (12): drm/xe/log: Add VRAM, PAT, and HWMON DRIVER_HARDWARE components drm/xe/ggtt: Report GGTT errors using structured logging drm/xe/hwmon: Report errors using structured xe_log API drm/xe/mmio: Report BAR mapping errors using structured xe_log API drm/xe/memirq: Report errors using structured xe_log API drm/xe/reg_sr: Report save-restore errors using structured xe_log API drm/xe/pat: Return error from xe_pat_init_early() on unknown platform drm/xe/pat: Report missing PAT table using structured xe_log API drm/xe/pci: Report unknown GMDID versions using structured xe_log API drm/xe/lmtt: Report invalidation errors using structured xe_log API drm/xe/vram: Report tile vs device VRAM visibility errors drm/xe/vram: Report VRAM errors using structured xe_log API Fan Wu (1): drm/xe/i2c: cancel the client work on remove Fei Yang (1): drm/xe/eu_stall: Don't mark stream enabled if enable fails Guillaume Tucker (1): drm/xe/log: fix documentation title levels Gustavo Sousa (3): drm/xe: Extract override_has_cached_pt() Revert "drm/xe/nvlp: Implement Wa_14026539277" drm/xe: Add up-to-date implementation for Wa_14026539277 Helen Koike (1): drm/xe/lrc: Restore CTX_CS_INDIRECT_CTX_OFFSET programming for pre-Xe2 Jagmeet Randhawa (2): drm/xe/guc: Fix race around q->guc->suspend_pending access drm/xe/guc: Do not attribute a TDR disable to a pending suspend Jan Maslak (2): drm/xe/xe_migrate: Optimize unaligned access_memory copies drm/xe/tests: Add xe_migrate_access_memory subtest Karthik Poosa (16): drm/xe/hwmon: Fix pcode power limit handling drm/xe/hwmon: Decode mailbox temperature as sign-magnitude drm/xe/hwmon: Fix thermal sensor data handling drm/xe/hwmon: Add helpers to validate thermal sensor readings drm/xe/hwmon: Handle unavailable memory controller sensors drm/xe/hwmon: Detect unavailable PCIe thermal sensors drm/xe/hwmon: Consolidate temperature sensor availability checks drm/xe/hwmon: Cache temperature availability to reduce probe time drm/xe/hwmon: use CRI-specific package and VRAM temperature registers drm/xe/hwmon: Add platform-aware VRAM thermal channel support drm/xe/hwmon: Decode CRI temperature registers as IEEE-754 drm/xe/hwmon: Update memory controller temperature offset for CRI drm/xe/hwmon: add PCIe temperature support for CRI drm/xe/hwmon: Simplify temperature channels config drm/xe: Validate thermal sensor count before reads drm/xe/hwmon: Propagate all hardware read errors Kumar, Sachin (1): drm/xe/uc: Add missing HuC firmware entry for Alderlake-N Mallesh Koujalagi (11): drm/xe/sysctrl: Return error codes from sysctrl_wait_bit_clear() drm/xe/sysctrl: Return error codes from sysctrl_wait_bit_set() drm/xe/sysctrl: Make sysctrl_write_frame() void drm/xe/sysctrl: Make sysctrl_read_frame() void drm/xe/sysctrl: Use xe_assert() for payload size validation drm/xe/sysctrl: Fix mailbox header handling drm/xe/sysctrl: Replace FIELD_GET() with REG_FIELD_GET() drm/xe/sysctrl: Improve firmware response error logging drm/xe/sysctrl: Log group and command ID on mailbox failure drm/xe/sysctrl: Report 'System Controller event' error using SIGID drm/xe/hwmon: Use overflows_type() for temperature range check Matt Roper (1): drm/xe/xe3p: Read resource copy presence from fuse register Matthew Auld (4): drm/xe/madvise: use already clamped pat_index drm/xe/pat: initialise pat.valid everywhere drm/xe: revamp hw reserved PAT index checking drm/xe/pat: always check is_valid() when querying an index Matthew Brost (1): drm/xe: Tie BO TTM LRU priority to DONTNEED/WILLNEED madvise state Mika Kuoppala (4): drm/xe: Remove ifdef in DRM_GPUVA_OP_DRIVER svm subop checking drm/xe/migrate: Keep access_memory chunks within the transfer limit drm/xe/tests: Cover a large write to an unaligned bo offset drm/xe/tests: Keep bounce buffered accesses short in access_memory test Nareshkumar Gollakoti (7): drm/xe/devcoredump: Capture GT fuse registers in devcoredump drm/xe/devcoredump: Add GuC register snapshot to devcoredump drm/xe/guc: Print register addresses in capture snapshot output drm/xe: dump GAM page fault report registers in devcoredump drm/xe/guc: add TDL, SLICE gfx registers to capture list drm/xe: capture L3 node status registers in devcoredump drm/xe/guc: capture additional engine state registers Niranjana Vishwanathapura (3): drm/xe: skip eviction of a BO with no resource drm/xe/tests: add regression for eviction of a BO with no resource drm/xe/dma-buf: Add xe_dma_buf_to_gem() self-import helper Nitin Gote (2): drm/xe/tuning: Restrict Anyhit NULL-query tuning to render engines drm/xe/tuning: Stop applying media CCCHKNREG1 tuning from Xe3p onward Piotr Piórkowski (5): drm/xe/guc: Split GuC ID manager into usable and shareable pools drm/xe/kunit: Extend GuC ID manager split-pool coverage drm/xe/guc: Start use explicitly usable GuC IDs for for submission drm/xe/pf: Explicitly use shareable GuC IDs for VFs provisioning drm/xe/vf: Move H2G CTB to VRAM on VF Raag Jadav (10): drm/xe/ras: Fix sysctrl and drm-ras discrepancy drm/xe/gt: Use GT ordered workqueue for wedging drm/xe: Drop xe_device_set_wedged_method() drm/xe/hw_error: Guard csc_hw_error_work() with runtime PM drm/xe: Move xe_device_wedged_fini() registration to xe_device_probe_early() drm/xe: Make xe_device_declare_wedged() IRQ safe drm/xe/pci_error: Flush GT wedge worker before bus reset drm/xe/amc: Guard xe_amc_work() with runtime PM drm/xe: Introduce xe_wedge drm/xe/ras: Move xe_ras_process_errors() to xe_ras Riana Tauro (6): drm/xe: Separate drm-ras netlink data from device and firmware RAS state drm/xe/xe_ras: Handle page offline requests for device memory ecc errors drm/xe/xe_ras: Add support to query page offline queue and list drm/xe/xe_ras: Add function to get maximum pages firmware can store drm/xe/xe_ttm_vram: Report max_pages reported by firmware to userspace drm/xe/xe_ras: Track offlined pages by firmware to avoid duplicates Rodrigo Vivi (1): drm/xe: Fix build with DRM_XE=y and CONFIGFS_FS=m Satyanarayana K V P (3): drm/xe: Prevent VF memory IRQ from accessing a torn-down engine drm/xe/guc: Protect timeout handling from device unplug drm/xe/gt: Disable GT reset worker before engine teardown Shekhar Chauhan (1): drm/xe/xe3: Fix OAM stream broken on Xe3+ Shuicheng Lin (1): drm/xe: Mark xe_vma_ops_alloc() noinline for error injection Tangudu Tilak Tirumalesh (1): drm/xe: Extend Wa_16030224309 to graphics version 35.11 Tejas Upadhyay (4): drm/xe: Clean up kernel-doc typos in VRAM manager drm/xe: Re-validate external pin under resv lock before VRAM purge drm/xe: Drop RCU list handling for VRAM bad-page tracking, use mgr->lock drm/xe: Keep VRAM fault injection within the usable range Thomas Hellström (13): drm/xe: Don't unload the driver until all drm devices are freed drm/xe: Route deferred xe_vma/xe_vm teardown off system_dfl_wq drm/xe: Route execlist exec queue teardown off system_dfl_wq drm/xe: Fix shrinker accounting double-subtraction on nested external pins drm/xe: Fix stale pinned_link entry when fb-pin performs the final unpin drm/xe: Don't allow XE_VALIDATION_UNIMPLEMENTED outside of debug builds drm/xe: Don't transfer shrinker pages for pinned bos on purgeable state change drm/xe: Bump LRU for external objects on exec and rebind drm/xe: Don't abort the shrinker walk on -EBUSY drm/xe: Track number of populated ttm_tts in the shrinker drm/xe: Split the bo shrinker into purgeable and non-purgeable shrinkers drm/xe: Update non-purgeable shrinker batch size based on average BO size Merge drm/drm-next into drm-xe-next Tvrtko Ursulin (1): drm/xe: Do not emit Wa_16010904313 twice Umesh Nerlige Ramappa (3): drm/xe/guc: Handle CRASH and EXCEPTION G2H with separate helpers drm/xe/guc: Make ct_dead_capture available on non-debug config drm/xe/guc: Cleanup error codes and handling for CT errors Vinay Belgaumkar (3): drm/xe: Toggle the D3Cold enable flag at runtime resume drm/xe: Access GT MMIO after pcode init drm/xe: Memset g2g buffer on resume Zhanjun Dong (2): drm/xe: Remove extra newlines from LRC snapshot dump drm/xe/guc: Compress GuC log and CTB dump with zstd .../ABI/testing/sysfs-driver-intel-xe-cper | 18 + Documentation/gpu/xe/xe_device.rst | 2 +- drivers/gpu/drm/xe/Kconfig | 15 + drivers/gpu/drm/xe/Kconfig.profile | 12 + drivers/gpu/drm/xe/Makefile | 5 + drivers/gpu/drm/xe/abi/uc_fw_abi.h | 11 +- drivers/gpu/drm/xe/abi/xe_log_abi.h | 3 + drivers/gpu/drm/xe/abi/xe_sigid_abi.h | 16 +- drivers/gpu/drm/xe/regs/xe_engine_regs.h | 24 + drivers/gpu/drm/xe/regs/xe_gt_regs.h | 20 +- drivers/gpu/drm/xe/regs/xe_guc_regs.h | 5 + drivers/gpu/drm/xe/regs/xe_lrc_layout.h | 3 + drivers/gpu/drm/xe/regs/xe_pcode_regs.h | 4 + drivers/gpu/drm/xe/tests/xe_dma_buf.c | 89 +++ .../gpu/drm/xe/tests/xe_gt_sriov_pf_config_kunit.c | 5 + drivers/gpu/drm/xe/tests/xe_guc_id_mgr_test.c | 689 +++++++++++++++++++-- drivers/gpu/drm/xe/tests/xe_kunit_helpers.c | 3 +- drivers/gpu/drm/xe/tests/xe_migrate.c | 366 +++++++++++ drivers/gpu/drm/xe/xe_amc.c | 11 +- drivers/gpu/drm/xe/xe_bo.c | 58 +- drivers/gpu/drm/xe/xe_bo_types.h | 8 +- drivers/gpu/drm/xe/xe_configfs.h | 2 +- drivers/gpu/drm/xe/xe_cper.c | 322 ++++++++++ drivers/gpu/drm/xe/xe_cper.h | 37 ++ drivers/gpu/drm/xe/xe_cper_types.h | 110 ++++ drivers/gpu/drm/xe/xe_debugfs.c | 70 +-- drivers/gpu/drm/xe/xe_devcoredump.c | 353 ++++++++++- drivers/gpu/drm/xe/xe_devcoredump_types.h | 67 ++ drivers/gpu/drm/xe/xe_device.c | 257 ++------ drivers/gpu/drm/xe/xe_device.h | 16 +- drivers/gpu/drm/xe/xe_device_sysfs.c | 50 ++ drivers/gpu/drm/xe/xe_device_types.h | 51 +- drivers/gpu/drm/xe/xe_device_wa_oob.rules | 1 - drivers/gpu/drm/xe/xe_dma_buf.c | 38 +- drivers/gpu/drm/xe/xe_dma_buf.h | 2 + drivers/gpu/drm/xe/xe_drm_ras.c | 33 +- drivers/gpu/drm/xe/xe_drm_ras_types.h | 3 - drivers/gpu/drm/xe/xe_eu_stall.c | 6 +- drivers/gpu/drm/xe/xe_execlist.c | 6 +- drivers/gpu/drm/xe/xe_ggtt.c | 9 +- drivers/gpu/drm/xe/xe_gpu_scheduler_types.h | 5 +- drivers/gpu/drm/xe/xe_gsc.c | 4 +- drivers/gpu/drm/xe/xe_gt.c | 121 ++-- drivers/gpu/drm/xe/xe_gt.h | 3 +- drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 21 +- drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c | 1 + drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 3 +- drivers/gpu/drm/xe/xe_gt_types.h | 9 + drivers/gpu/drm/xe/xe_guc.c | 76 ++- drivers/gpu/drm/xe/xe_guc.h | 3 +- drivers/gpu/drm/xe/xe_guc_capture.c | 86 ++- drivers/gpu/drm/xe/xe_guc_ct.c | 355 +++++++---- drivers/gpu/drm/xe/xe_guc_ct.h | 4 +- drivers/gpu/drm/xe/xe_guc_ct_types.h | 3 + drivers/gpu/drm/xe/xe_guc_exec_queue_types.h | 5 +- drivers/gpu/drm/xe/xe_guc_id_mgr.c | 469 +++++++++++--- drivers/gpu/drm/xe/xe_guc_id_mgr.h | 31 +- drivers/gpu/drm/xe/xe_guc_log.c | 222 ++++++- drivers/gpu/drm/xe/xe_guc_log.h | 11 +- drivers/gpu/drm/xe/xe_guc_log_types.h | 20 + drivers/gpu/drm/xe/xe_guc_pc.c | 11 +- drivers/gpu/drm/xe/xe_guc_rc.c | 5 +- drivers/gpu/drm/xe/xe_guc_submit.c | 155 +++-- drivers/gpu/drm/xe/xe_guc_submit.h | 2 +- drivers/gpu/drm/xe/xe_guc_tlb_inval.c | 3 +- drivers/gpu/drm/xe/xe_guc_types.h | 8 +- drivers/gpu/drm/xe/xe_hw_engine.c | 54 +- drivers/gpu/drm/xe/xe_hw_error.c | 8 +- drivers/gpu/drm/xe/xe_hwmon.c | 618 +++++++++++++----- drivers/gpu/drm/xe/xe_irq.c | 3 + drivers/gpu/drm/xe/xe_late_bind_fw.c | 150 ++++- drivers/gpu/drm/xe/xe_late_bind_fw.h | 4 +- drivers/gpu/drm/xe/xe_late_bind_fw_types.h | 6 +- drivers/gpu/drm/xe/xe_lmtt.c | 10 +- drivers/gpu/drm/xe/xe_log.c | 5 +- drivers/gpu/drm/xe/xe_lrc.c | 12 +- drivers/gpu/drm/xe/xe_memirq.c | 10 +- drivers/gpu/drm/xe/xe_mert.c | 5 +- drivers/gpu/drm/xe/xe_migrate.c | 180 +++++- drivers/gpu/drm/xe/xe_mmio.c | 12 +- drivers/gpu/drm/xe/xe_module.c | 24 +- drivers/gpu/drm/xe/xe_nvm.c | 13 +- drivers/gpu/drm/xe/xe_oa.c | 24 +- drivers/gpu/drm/xe/xe_pagefault.c | 8 - drivers/gpu/drm/xe/xe_pagefault_types.h | 3 - drivers/gpu/drm/xe/xe_pat.c | 131 +++- drivers/gpu/drm/xe/xe_pat.h | 29 +- drivers/gpu/drm/xe/xe_pci.c | 23 +- drivers/gpu/drm/xe/xe_pci_error.c | 13 +- drivers/gpu/drm/xe/xe_pci_types.h | 4 +- drivers/gpu/drm/xe/xe_pcode_api.h | 2 - drivers/gpu/drm/xe/xe_pm.c | 18 +- drivers/gpu/drm/xe/xe_pt.c | 2 - drivers/gpu/drm/xe/xe_ras.c | 469 ++++++++++++-- drivers/gpu/drm/xe/xe_ras.h | 7 +- drivers/gpu/drm/xe/xe_ras_types.h | 85 +++ drivers/gpu/drm/xe/xe_reg_sr.c | 11 +- drivers/gpu/drm/xe/xe_shrinker.c | 218 +++++-- drivers/gpu/drm/xe/xe_shrinker.h | 7 +- drivers/gpu/drm/xe/xe_sriov_pf.c | 3 +- drivers/gpu/drm/xe/xe_survivability_mode.c | 4 +- drivers/gpu/drm/xe/xe_svm.c | 1 + drivers/gpu/drm/xe/xe_sync.c | 33 +- drivers/gpu/drm/xe/xe_sysctrl.c | 32 + drivers/gpu/drm/xe/xe_sysctrl.h | 1 + drivers/gpu/drm/xe/xe_sysctrl_debugfs.c | 500 +++++++++++++++ drivers/gpu/drm/xe/xe_sysctrl_debugfs.h | 14 + drivers/gpu/drm/xe/xe_sysctrl_event.c | 14 +- drivers/gpu/drm/xe/xe_sysctrl_mailbox.c | 140 +++-- drivers/gpu/drm/xe/xe_sysctrl_mailbox.h | 6 +- drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h | 55 ++ drivers/gpu/drm/xe/xe_sysctrl_types.h | 47 ++ drivers/gpu/drm/xe/xe_trace_cper.c | 9 + drivers/gpu/drm/xe/xe_trace_cper.h | 65 ++ drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 68 +- drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 6 +- drivers/gpu/drm/xe/xe_tuning.c | 4 +- drivers/gpu/drm/xe/xe_uc.c | 21 +- drivers/gpu/drm/xe/xe_uc.h | 3 +- drivers/gpu/drm/xe/xe_uc_fw.c | 16 +- drivers/gpu/drm/xe/xe_validation.h | 2 + drivers/gpu/drm/xe/xe_vm.c | 38 +- drivers/gpu/drm/xe/xe_vm_madvise.c | 17 +- drivers/gpu/drm/xe/xe_vram.c | 38 +- drivers/gpu/drm/xe/xe_wa_oob.rules | 4 +- drivers/gpu/drm/xe/xe_wedge.c | 262 ++++++++ drivers/gpu/drm/xe/xe_wedge.h | 24 + drivers/gpu/drm/xe/xe_wedge_types.h | 44 ++ drivers/mtd/devices/mtd_intel_dg.c | 65 +- include/drm/intel/pciids.h | 4 +- include/linux/intel_dg_nvm_aux.h | 1 + 131 files changed, 6754 insertions(+), 1391 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-xe-cper create mode 100644 drivers/gpu/drm/xe/xe_cper.c create mode 100644 drivers/gpu/drm/xe/xe_cper.h create mode 100644 drivers/gpu/drm/xe/xe_cper_types.h create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_debugfs.c create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_debugfs.h create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.c create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.h create mode 100644 drivers/gpu/drm/xe/xe_wedge.c create mode 100644 drivers/gpu/drm/xe/xe_wedge.h create mode 100644 drivers/gpu/drm/xe/xe_wedge_types.h