linux/drivers/gpu/drm/xe, branch for-next

drm/xe: Mark ComputeCS read mode as UC on iGPU

2025-01-16T19:03:11Z

RING_CMD_CCTL read index should be UC on iGPU parts due to L3 caching structure. Having this as WB blocks ULLS from being enabled. Change to UC to unblock ULLS on iGPU. v2: - Drop internal communications commnet, bspec is updated Cc: Balasubramani Vivekanandan Cc: Michal Mrozek Cc: Paulo Zanoni Cc: José Roberto de Souza Cc: stable@vger.kernel.org Fixes: 328e089bfb37 ("drm/xe: Leverage ComputeCS read L3 caching") Signed-off-by: Matthew Brost Acked-by: Michal Mrozek Reviewed-by: Stuart Summers Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20250114002507.114087-1-matthew.brost@intel.com (cherry picked from commit 758debf35b9cda5450e40996991a6e4b222899bd) Signed-off-by: Thomas Hellström

drm/xe/oa: Add missing VISACTL mux registers

2025-01-15T10:32:50Z

Add missing VISACTL mux registers required for some OA config's (e.g. RenderPipeCtrl). Fixes: cdf02fe1a94a ("drm/xe/oa/uapi: Add/remove OA config perf ops") Cc: stable@vger.kernel.org Signed-off-by: Ashutosh Dixit Reviewed-by: Umesh Nerlige Ramappa Link: https://patchwork.freedesktop.org/patch/msgid/20250111021539.2920346-1-ashutosh.dixit@intel.com (cherry picked from commit c26f22dac3449d8a687237cdfc59a6445eb8f75a) Signed-off-by: Thomas Hellström

drm/xe: make change ccs_mode a synchronous action

2025-01-15T10:32:50Z

If ccs_mode is being modified via /sys/class/drm/cardX/device/tileY/gtY/ccs_mode the asynchronous reset is triggered and the write returns immediately. With that some test receive false information about number of CCS engines or even fail if they proceed without delay after changing the ccs_mode. Changing the ccs_mode change from async to sync to prevent failures in tests. Signed-off-by: Maciej Patelczyk Reviewed-by: Lucas De Marchi Fixes: f3bc5bb4d53d ("drm/xe: Allow userspace to configure CCS mode") Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20241211111727.1481476-3-maciej.patelczyk@intel.com Signed-off-by: Nirmoy Das (cherry picked from commit 480fb9806e2e073532f7786166287114c696b340) Signed-off-by: Thomas Hellström

drm/xe: introduce xe_gt_reset and xe_gt_wait_for_reset

2025-01-15T10:32:50Z

Add synchronous version gt reset as there are few places where it is expected. Also add a wait helper to wait until gt reset is done. Signed-off-by: Maciej Patelczyk Reviewed-by: Lucas De Marchi Fixes: f3bc5bb4d53d ("drm/xe: Allow userspace to configure CCS mode") Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20241211111727.1481476-2-maciej.patelczyk@intel.com Signed-off-by: Nirmoy Das (cherry picked from commit 155c77f45f63dd58a37eeb0896b0b140ab785836) Signed-off-by: Thomas Hellström

drm/xe/guc: Adding steering info support for GuC register lists

2025-01-15T10:32:50Z

The guc_mmio_reg interface supports steering, but it is currently not implemented. This will allow the GuC to control steering of MMIO registers after save-restore and avoid reading from fused off MCR register instances. Fixes: 9c57bc08652a ("drm/xe/lnl: Drop force_probe requirement") Signed-off-by: Jesus Narvaez Cc: Matt Roper Cc: Lucas De Marchi Cc: Daniele Ceraolo Spurio Reviewed-by: Jonathan Cavitt Signed-off-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20241212190100.3768068-1-jesus.narvaez@intel.com (cherry picked from commit ee5a1321df90891d59d83b7c9d5b6c5b755d059d) Signed-off-by: Thomas Hellström

drm/xe/dg1: Fix power gate sequence.

2025-01-09T09:38:56Z

sub-pipe PG is not present on DG1. Setting these bits can disable other power gates and cause GPU hangs on video playbacks. VLK: 16314, 4304 Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13381 Cc: Vinay Belgaumkar Cc: Himal Prasad Ghimiray Reviewed-by: Himal Prasad Ghimiray Link: https://patchwork.freedesktop.org/patch/msgid/20241219235536.454270-1-rodrigo.vivi@intel.com Signed-off-by: Rodrigo Vivi (cherry picked from commit 2f12e9c029315c1400059b2e7fdf53117c09c3a9) Signed-off-by: Thomas Hellström

drm/xe: Fix tlb invalidation when wedging

2025-01-09T09:38:56Z

If GuC fails to load, the driver wedges, but in the process it tries to do stuff that may not be initialized yet. This moves the xe_gt_tlb_invalidation_init() to be done earlier: as its own doc says, it's a software-only initialization and should had been named with the _early() suffix. Move it to be called by xe_gt_init_early(), so the locks and seqno are initialized, avoiding a NULL ptr deref when wedging: xe 0000:03:00.0: [drm] *ERROR* GT0: load failed: status: Reset = 0, BootROM = 0x50, UKernel = 0x00, MIA = 0x00, Auth = 0x01 xe 0000:03:00.0: [drm] *ERROR* GT0: firmware signature verification failed xe 0000:03:00.0: [drm] *ERROR* CRITICAL: Xe has declared device 0000:03:00.0 as wedged. ... BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 9 UID: 0 PID: 3908 Comm: modprobe Tainted: G U W 6.13.0-rc4-xe+ #3 Tainted: [U]=USER, [W]=WARN Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-S ADP-S DDR5 UDIMM CRB, BIOS ADLSFWI1.R00.3275.A00.2207010640 07/01/2022 RIP: 0010:xe_gt_tlb_invalidation_reset+0x75/0x110 [xe] This can be easily triggered by poking the GuC binary to force a signature failure. There will still be an extra message, xe 0000:03:00.0: [drm] *ERROR* GT0: GuC mmio request 0x4100: no reply 0x4100 but that's better than a NULL ptr deref. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3956 Fixes: c9474b726b93 ("drm/xe: Wedge the entire device") Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20250103001111.331684-2-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 5001ef3af8f2c972d6fd9c5221a8457556f8bea6) Signed-off-by: Thomas Hellström

xe/oa: Fix query mode of operation for OAR/OAC

2025-01-02T18:01:21Z

This is a set of squashed commits to facilitate smooth applying to stable. Each commit message is retained for reference. 1) Allow a GGTT mapped batch to be submitted to user exec queue For a OA use case, one of the HW registers needs to be modified by submitting an MI_LOAD_REGISTER_IMM command to the users exec queue, so that the register is modified in the user's hardware context. In order to do this a batch that is mapped in GGTT, needs to be submitted to the user exec queue. Since all user submissions use q->vm and hence PPGTT, add some plumbing to enable submission of batches mapped in GGTT. v2: ggtt is zero-initialized, so no need to set it false (Matt Brost) 2) xe/oa: Use MI_LOAD_REGISTER_IMMEDIATE to enable OAR/OAC To enable OAR/OAC, a bit in RING_CONTEXT_CONTROL needs to be set. Setting this bit cause the context image size to change and if not done correct, can cause undesired hangs. Current code uses a separate exec_queue to modify this bit and is error-prone. As per HW recommendation, submit MI_LOAD_REGISTER_IMM to the target hardware context to modify the relevant bit. In v2 version, an attempt to submit everything to the user-queue was made, but it failed the unprivileged-single-ctx-counters test. It appears that the OACTXCONTROL must be modified from a remote context. In v3 version, all context specific register configurations were moved to use LOAD_REGISTER_IMMEDIATE and that seems to work well. This is a cleaner way, since we can now submit all configuration to user exec_queue and the fence handling is simplified. v2: (Matt) - set job->ggtt to true if create job is successful - unlock vm on job error (Ashutosh) - don't wait on job submission - use kernel exec queue where possible v3: (Ashutosh) - Fix checkpatch issues - Remove extra spaces/new-lines - Add Fixes: and Cc: tags - Reset context control bit when OA stream is closed - Submit all config via MI_LOAD_REGISTER_IMMEDIATE (Umesh) - Update commit message for v3 experiment - Squash patches for easier port to stable v4: (Ashutosh) - No need to pass q to xe_oa_submit_bb - Do not support exec queues with width > 1 - Fix disabling of CTX_CTRL_OAC_CONTEXT_ENABLE v5: (Ashutosh) - Drop reg_lri related comments - Use XE_OA_SUBMIT_NO_DEPS in xe_oa_load_with_lri Fixes: 8135f1c09dd2 ("drm/xe/oa: Don't reset OAC_CONTEXT_ENABLE on OA stream close") Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Matthew Brost # commit 1 Reviewed-by: Ashutosh Dixit Cc: stable@vger.kernel.org Reviewed-by: Jonathan Cavitt Signed-off-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20241220171919.571528-2-umesh.nerlige.ramappa@intel.com (cherry picked from commit 55039832f98c7e05f1cf9e0d8c12b2490abd0f16) Signed-off-by: Thomas Hellström

drm/xe: Fix fault on fd close after unbind

2024-12-23T15:19:52Z

If userspace holds an fd open, unbinds the device and then closes it, the driver shouldn't try to access the hardware. Protect it by using drm_dev_enter()/drm_dev_exit(). This fixes the following page fault: <6> [IGT] xe_wedged: exiting, ret=98 <1> BUG: unable to handle page fault for address: ffffc901bc5e508c <1> #PF: supervisor read access in kernel mode <1> #PF: error_code(0x0000) - not-present page ... <4> xe_lrc_update_timestamp+0x1c/0xd0 [xe] <4> xe_exec_queue_update_run_ticks+0x50/0xb0 [xe] <4> xe_exec_queue_fini+0x16/0xb0 [xe] <4> __guc_exec_queue_fini_async+0xc4/0x190 [xe] <4> guc_exec_queue_fini_async+0xa0/0xe0 [xe] <4> guc_exec_queue_fini+0x23/0x40 [xe] <4> xe_exec_queue_destroy+0xb3/0xf0 [xe] <4> xe_file_close+0xd4/0x1a0 [xe] <4> drm_file_free+0x210/0x280 [drm] <4> drm_close_helper.isra.0+0x6d/0x80 [drm] <4> drm_release_noglobal+0x20/0x90 [drm] Fixes: 514447a12190 ("drm/xe: Stop accumulating LRC timestamp on job_free") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3421 Reviewed-by: Umesh Nerlige Ramappa Link: https://patchwork.freedesktop.org/patch/msgid/20241218053122.2730195-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 4ca1fd418338d4d135428a0eb1e16e3b3ce17ee8) Signed-off-by: Thomas Hellström

drm/xe/pf: Use correct function to check LMEM provisioning

2024-12-23T15:19:52Z

There is a typo in function call and instead of VF LMEM we were looking at VF GGTT provisioning. Fix that. Fixes: 234670cea9a2 ("drm/xe/pf: Skip fair VFs provisioning if already provisioned") Signed-off-by: Michal Wajdeczko Cc: Piotr Piórkowski Reviewed-by: Himal Prasad Ghimiray Link: https://patchwork.freedesktop.org/patch/msgid/20241216223253.819-1-michal.wajdeczko@intel.com (cherry picked from commit a8d0aa0e7fcd20c9f1992688c0f0d07a68287403) Signed-off-by: Thomas Hellström