kernel/linux.git/drivers/gpu/drm/xe, branch v6.12.102

gpu: Move DRM buddy allocator one level up (part two)

2026-08-03T09:17:33+00:00

[ Upstream commit ba110db8e1bc206c13fd7d985e79b033f53bfdea ] Move the DRM buddy allocator one level up so that it can be used by GPU drivers (example, nova-core) that have usecases other than DRM (such as VFIO vGPU support). Modify the API, structures and Kconfigs to use "gpu_buddy" terminology. Adapt the drivers and tests to use the new API. The commit cannot be split due to bisectability, however no functional change is intended. Verified by running K-UNIT tests and build tested various configurations. Signed-off-by: Joel Fernandes Reviewed-by: Dave Airlie [airlied: I've split this into two so git can find copies easier. I've also just nuked drm_random library, that stuff needs to be done elsewhere and only the buddy tests seem to be using it]. Signed-off-by: Dave Airlie Stable-dep-of: 56bc6384314f ("gpu/buddy: bail out of try_harder when alignment cannot be honoured") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

drm/xe: Fix PTE index in xe_vm_populate_pgtable() for chunked binds

2026-08-03T09:17:16+00:00

commit 34a4dd45cf210c04fee773b0dbc350aec285f03c upstream. xe_vm_populate_pgtable() indexed the source PTE array (update->pt_entries) by the per-call loop counter, assuming each call starts at the first entry of the update. That holds for the CPU bind path (xe_migrate_update_pgtables_cpu), which populates a whole update in a single call, but not for the GPU bind path: write_pgtable() splits an update into MAX_PTE_PER_SDI (510) sized MI_STORE_DATA_IMM chunks, invoking the populate callback once per chunk with an advancing qword_ofs but a fresh command- buffer destination pointer. As a result, every chunk after the first re-read pt_entries from index 0 instead of from its true offset, so PTEs beyond the first 510 entries of a single update were programmed with the wrong physical pages, shifting the mapping by exactly MAX_PTE_PER_SDI pages. This stayed latent because a single update only exceeds 510 qwords when a large (e.g. 2M) region is bound as individual 4K PTEs rather than a single huge-page entry, which happens when the backing store is sufficiently fragmented. It was surfaced by the BO defrag path, which deliberately rebinds such fragmented ranges via the GPU bind path, producing deterministic data corruption offset by 510 pages. Index pt_entries by the chunk's absolute offset relative to update->ofs so both the CPU and GPU paths pick the correct entries. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: stable@vger.kernel.org Assisted-by: GitHub_Copilot:claude-opus-4.8 Signed-off-by: Matthew Brost Reviewed-by: Matthew Auld Link: https://patch.msgid.link/20260702012434.3861171-1-matthew.brost@intel.com (cherry picked from commit e6f2d0b757c4fb577a513c577140109d1d292a9a) Signed-off-by: Thomas Hellström Signed-off-by: Greg Kroah-Hartman

drm/xe/wopcm: fix WOPCM size for LNL+

2026-08-03T09:17:05+00:00

[ Upstream commit ad87e2476b3b246580f407afc8ffa91d621bc849 ] Starting on LNL the WOPCM size is 8MB instead of 4, so we need to avoid using the [0, 8MB) range of the GGTT as that can be unaccessible from the microcontrollers. Note that the proper long-term fix here is to read the WOPCM size from the HW, but that is a more serious rework that would be difficult to backport, so we can do that as a follow-up. Fixes: 9c57bc08652a ("drm/xe/lnl: Drop force_probe requirement") Signed-off-by: Daniele Ceraolo Spurio Cc: Rodrigo Vivi Cc: Shuicheng Lin Cc: Matt Roper Reviewed-by: Shuicheng Lin Link: https://patch.msgid.link/20260713221758.3285744-2-daniele.ceraolospurio@intel.com (cherry picked from commit 3033b0b24ed0e2f5e56bdd4d9c183417c365a45b) Signed-off-by: Thomas Hellström Signed-off-by: Sasha Levin

PCI: Fix restoring BARs on BAR resize rollback path

2026-07-24T14:11:48+00:00

[ Upstream commit 337b1b566db087347194e4543ddfdfa5645275cc ] BAR resize operation is implemented in the pci_resize_resource() and pbus_reassign_bridge_resources() functions. pci_resize_resource() can be called either from __resource_resize_store() from sysfs or directly by the driver for the Endpoint Device. The pci_resize_resource() requires that caller has released the device resources that share the bridge window with the BAR to be resized as otherwise the bridge window is pinned in place and cannot be changed. pbus_reassign_bridge_resources() rolls back resources if the resize operation fails, but rollback is performed only for the bridge windows. Because releasing the device resources are done by the caller of the BAR resize interface, these functions performing the BAR resize do not have access to the device resources as they were before the resize. pbus_reassign_bridge_resources() could try __pci_bridge_assign_resources() after rolling back the bridge windows as they were, however, it will not guarantee the resource are assigned due to differences in how FW and the kernel assign the resources (alignment of the start address and tail). To perform rollback robustly, the BAR resize interface has to be altered to also release the device resources that share the bridge window with the BAR to be resized. Also, remove restoring from the entries failed list as saved list should now contain both the bridge windows and device resources so the extra restore is duplicated work. Some drivers (currently only amdgpu) want to prevent releasing some resources. Add exclude_bars param to pci_resize_resource() and make amdgpu pass its register BAR (BAR 2 or 5), which should never be released during resize operation. Normally 64-bit prefetchable resources do not share a bridge window with the 32-bit only register BAR, but there are various fallbacks in the resource assignment logic which may make the resources share the bridge window in rare cases. This change (together with the driver side changes) is to counter the resource releases that had to be done to prevent resource tree corruption in the ("PCI: Release assigned resource before restoring them") change. As such, it likely restores functionality in cases where device resources were released to avoid resource tree conflicts which appeared to be "working" when such conflicts were not correctly detected by the kernel. Reported-by: Simon Richter Link: https://lore.kernel.org/linux-pci/f9a8c975-f5d3-4dd2-988e-4371a1433a60@hogyros.de/ Reported-by: Alex Bennée Link: https://lore.kernel.org/linux-pci/874irqop6b.fsf@draig.linaro.org/ Signed-off-by: Ilpo Järvinen [bhelgaas: squash amdgpu BAR selection from https: //lore.kernel.org/r/20251114103053.13778-1-ilpo.jarvinen@linux.intel.com] Signed-off-by: Bjorn Helgaas Tested-by: Alex Bennée # AVA, AMD GPU Reviewed-by: Christian König Link: https://patch.msgid.link/20251113162628.5946-7-ilpo.jarvinen@linux.intel.com Stable-dep-of: ee7471fe968d ("PCI: Skip Resizable BAR restore on read error") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

drm/xe: remove duplicate include

2026-07-24T14:11:25+00:00

[ Upstream commit 91426ce50d14a49bde53b3ad1e48393556ba92cd ] xe_pci.c includes twice, separated only by the include. Drop the redundant second include; this is a non-functional cleanup flagged by scripts/checkincludes.pl. Fixes: 6cad22853cb8 ("drm/xe/kunit: Add stub to read_gmdid") Signed-off-by: Anas Khan Link: https://patch.msgid.link/20260702112820.34675-1-anxkhn28@gmail.com Signed-off-by: Rodrigo Vivi (cherry picked from commit 84ed5b0a925721aaf069d36e18a99db966ff4e80) Signed-off-by: Thomas Hellström Signed-off-by: Sasha Levin

drm/xe/pf: Don't attempt to process FAST_REQ or EVENT relays

2026-07-24T14:11:21+00:00

[ Upstream commit ed8b0d731892c68b41ecbd27c952af284816dec1 ] Currently defined VF/PF relay actions use regular REQUEST messages only and the PF shouldn't attempt to handle FAST_REQUEST nor EVENT messages as this would result in breaking the VFPF ABI protocol and also might trigger an assert on the PF side. Fixes: 98e62805921c ("drm/xe/pf: Add SR-IOV GuC Relay PF services") Signed-off-by: Michal Wajdeczko Reviewed-by: Michał Winiarski Link: https://patch.msgid.link/20260527183735.22616-1-michal.wajdeczko@intel.com (cherry picked from commit 1714d360fc5ae2e0886a69e979095d9c7ff3568a) Signed-off-by: Thomas Hellström Signed-off-by: Sasha Levin

drm/xe/hw_engine: Fix double-free of managed BO in error path

2026-07-24T14:11:21+00:00

[ Upstream commit 7ac3cae7a251d28e9079de07a991bd4eb2bb7fd8 ] The error path in hw_engine_init() explicitly frees a BO allocated with xe_managed_bo_create_pin_map() via xe_bo_unpin_map_no_vm(). Since the managed BO already has a devm cleanup action registered, this causes a double-free when devm unwinds during probe failure. Remove the explicit free and let devm handle it, consistent with all other xe_managed_bo_create_pin_map() callers. Fixes: 0e1a47fcabc8 ("drm/xe: Add a helper for DRM device-lifetime BO create") Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Zongyao Bai Link: https://patch.msgid.link/20260626210631.3887291-1-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit e459a3bdeb117be496d7f229e2ea1f6c9fe4080b) Signed-off-by: Thomas Hellström Signed-off-by: Sasha Levin

drm/xe/pt: Fix NULL pointer dereference in xe_pt_zap_ptes_entry()

2026-07-24T14:11:21+00:00

[ Upstream commit 3feeb667197bd58a17f4edfdbcad249ffcb3c864 ] The page-table walk framework may pass a NULL *child pointer for unpopulated entries. xe_pt_zap_ptes_entry() called container_of(*child) before checking for NULL, then dereferenced the result, causing a crash. Move the container_of() call after a NULL guard, so the function returns early instead of proceeding with an invalid pointer. XE_WARN_ON is kept to help root cause the issue, but we now bail instead of crashing the driver. v2: Comment that triggering XE_WARN_ON is unexpected behavior (Matt Brost) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Matthew Brost Cc: Thomas Hellström Reviewed-by: Matthew Brost Link: https://lore.kernel.org/r/20260616081756.286918-1-francois.dugast@intel.com Signed-off-by: Francois Dugast (cherry picked from commit b9297d19d9df5d4b6c994648570c5dcd1cac68ff) Signed-off-by: Thomas Hellström Signed-off-by: Sasha Levin

drm/xe/display: fix oops in suspend/shutdown without display

2026-07-04T11:43:23+00:00

[ Upstream commit 68938cc08e23a94fd881e845837ff918de005ce7 ] The xe driver keeps track of whether to probe display, and whether display hardware is there, using xe->info.probe_display. It gets set to false if there's no display after intel_display_device_probe(). However, the display may also be disabled via fuses, detected at a later time in intel_display_device_info_runtime_init(). In this case, the xe driver does for_each_intel_crtc() on uninitialized mode config in xe_display_flush_cleanup_work(), leading to a NULL pointer dereference, and generally calls display code with display info cleared. Check for intel_display_device_present() after intel_display_device_info_runtime_init(), and reset xe->info.probe_display as necessary. Also do unset_display_features() for completeness, although display runtime init has already done that. This will need to be unified across all cases later. Move intel_display_device_info_runtime_init() call slightly earlier, similar to i915, to avoid a bunch of unnecessary setup for no display cases. Note #1: The xe driver has no business doing low level display plumbing like for_each_intel_crtc() to begin with. It all needs to happen in display code. Note #2: The actual bug is present already in commit 44e694958b95 ("drm/xe/display: Implement display support"), but the oops was likely introduced later at commit ddf6492e0e50 ("drm/xe/display: Make display suspend/resume work on discrete"). Fixes: 44e694958b95 ("drm/xe/display: Implement display support") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/7904 Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/6150 Cc: stable@vger.kernel.org # v6.8+ Reviewed-by: Suraj Kandpal Link: https://patch.msgid.link/20260515160920.1082842-1-jani.nikula@intel.com Signed-off-by: Jani Nikula (cherry picked from commit 7c3eb9f47533220888a67266448185fd0775d4da) Signed-off-by: Matthew Brost Signed-off-by: Sasha Levin

drm/xe: Clear pending_disable before signaling suspend fence

2026-06-19T11:42:35+00:00

commit 54f2a0442a30fe7a0f6bc8345e81f8b2db8effbd upstream. In the schedule-disable done path for suspend, we signal the suspend fence before clearing pending_disable. That wakeup can let suspend_wait complete and resume be queued immediately. The resume path may then reach enable_scheduling() while pending_disable is still set and hit the !exec_queue_pending_disable(q) assertion. Fix this by clearing pending_disable before signaling the suspend fence, so any resumed transition observes a consistent state. Fixes: 87651f31ae4e ("drm/xe/guc_submit: fix race around suspend_pending") Cc: stable@vger.kernel.org # v7.0+ Signed-off-by: Tangudu Tilak Tirumalesh Reviewed-by: Thomas Hellstrom Signed-off-by: Daniele Ceraolo Spurio Link: https://patch.msgid.link/20260603065217.3131066-3-tilak.tirumalesh.tangudu@intel.com (cherry picked from commit 4b1ae138b0e103d753773956a84eebc2edbf62c4) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman