linux-dev/drivers/gpu/drm/scheduler, branch master

drm/scheduler: fix fence ref counting

2022-10-25T11:14:36Z

We leaked dependency fences when processes were beeing killed. Additional to that grab a reference to the last scheduled fence. Signed-off-by: Christian König Reviewed-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20220929180151.139751-1-christian.koenig@amd.com

Merge drm/drm-fixes into drm-misc-fixes

2022-10-20T07:09:00Z

Backmerging to get v6.1-rc1. Signed-off-by: Thomas Zimmermann

drm/sched: add DRM_SCHED_FENCE_DONT_PIPELINE flag

2022-10-19T10:42:51Z

Setting this flag on a scheduler fence prevents pipelining of jobs depending on this fence. In other words we always insert a full CPU round trip before dependent jobs are pushed to the pipeline. Signed-off-by: Christian König Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2113#note_1579296 Reviewed-by: Alex Deucher Acked-by: Luben Tuikov Link: https://patchwork.freedesktop.org/patch/msgid/20221014081553.114899-1-christian.koenig@amd.com

Revert "drm/sched: Use parent fence instead of finished"

2022-10-07T02:58:39Z

This reverts commit e4dc45b1848bc6bcac31eb1b4ccdd7f6718b3c86. This is causing instability on Linus' desktop, and I'm seeing oops with VK CTS runs. netconsole got me the following oops: [ 1234.778760] BUG: kernel NULL pointer dereference, address: 0000000000000088 [ 1234.778782] #PF: supervisor read access in kernel mode [ 1234.778787] #PF: error_code(0x0000) - not-present page [ 1234.778791] PGD 0 P4D 0 [ 1234.778798] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 1234.778803] CPU: 7 PID: 805 Comm: systemd-journal Not tainted 6.0.0+ #2 [ 1234.778809] Hardware name: System manufacturer System Product Name/PRIME X370-PRO, BIOS 5603 07/28/2020 [ 1234.778813] RIP: 0010:drm_sched_job_done.isra.0+0xc/0x140 [gpu_sched] [ 1234.778828] Code: aa 0f 1d ce e9 57 ff ff ff 48 89 d7 e8 9d 8f 3f ce e9 4a ff ff ff 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 55 53 48 89 fb <48> 8b af 88 00 00 00 f0 ff 8d f0 00 00 00 48 8b 85 80 01 00 00 f0 [ 1234.778834] RSP: 0000:ffffabe680380de0 EFLAGS: 00010087 [ 1234.778839] RAX: ffffffffc04e9230 RBX: 0000000000000000 RCX: 0000000000000018 [ 1234.778897] RDX: 00000ba278e8977a RSI: ffff953fb288b460 RDI: 0000000000000000 [ 1234.778901] RBP: ffff953fb288b598 R08: 00000000000000e0 R09: ffff953fbd98b808 [ 1234.778905] R10: 0000000000000000 R11: ffffabe680380ff8 R12: ffffabe680380e00 [ 1234.778908] R13: 0000000000000001 R14: 00000000ffffffff R15: ffff953fbd9ec458 [ 1234.778912] FS: 00007f35e7008580(0000) GS:ffff95428ebc0000(0000) knlGS:0000000000000000 [ 1234.778916] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1234.778919] CR2: 0000000000000088 CR3: 000000010147c000 CR4: 00000000003506e0 [ 1234.778924] Call Trace: [ 1234.778981] [ 1234.778989] dma_fence_signal_timestamp_locked+0x6a/0xe0 [ 1234.778999] dma_fence_signal+0x2c/0x50 [ 1234.779005] amdgpu_fence_process+0xc8/0x140 [amdgpu] [ 1234.779234] sdma_v3_0_process_trap_irq+0x70/0x80 [amdgpu] [ 1234.779395] amdgpu_irq_dispatch+0xa9/0x1d0 [amdgpu] [ 1234.779609] amdgpu_ih_process+0x80/0x100 [amdgpu] [ 1234.779783] amdgpu_irq_handler+0x1f/0x60 [amdgpu] [ 1234.779940] __handle_irq_event_percpu+0x46/0x190 [ 1234.779946] handle_irq_event+0x34/0x70 [ 1234.779949] handle_edge_irq+0x9f/0x240 [ 1234.779954] __common_interrupt+0x66/0x100 [ 1234.779960] common_interrupt+0xa0/0xc0 [ 1234.779965] [ 1234.779968] [ 1234.779971] asm_common_interrupt+0x22/0x40 [ 1234.779976] RIP: 0010:finish_mkwrite_fault+0x22/0x110 [ 1234.779981] Code: 1f 84 00 00 00 00 00 90 0f 1f 44 00 00 41 55 41 54 55 48 89 fd 53 48 8b 07 f6 40 50 08 0f 84 eb 00 00 00 48 8b 45 30 48 8b 18 <48> 89 df e8 66 bd ff ff 48 85 c0 74 0d 48 89 c2 83 e2 01 48 83 ea [ 1234.779985] RSP: 0000:ffffabe680bcfd78 EFLAGS: 00000202 Revert it for now and figure it out later. Signed-off-by: Dave Airlie

drm/sched: Use parent fence instead of finished

2022-09-16T13:53:25Z

Using the parent fence instead of the finished fence to get the job status. This change is to avoid GPU scheduler timeout error which can cause GPU reset. Signed-off-by: Arvind Yadav Reviewed-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-6-Arvind.Yadav@amd.com Signed-off-by: Christian König

drm/scheduler: quieten kernel-doc warnings

2022-09-06T20:14:28Z

Fix kernel-doc warnings in gpu_scheduler.h and sched_main.c. Quashes these warnings: include/drm/gpu_scheduler.h:332: warning: missing initial short description on line: * struct drm_sched_backend_ops include/drm/gpu_scheduler.h:412: warning: missing initial short description on line: * struct drm_gpu_scheduler include/drm/gpu_scheduler.h:461: warning: Function parameter or member 'dev' not described in 'drm_gpu_scheduler' drivers/gpu/drm/scheduler/sched_main.c:201: warning: missing initial short description on line: * drm_sched_dependency_optimized drivers/gpu/drm/scheduler/sched_main.c:995: warning: Function parameter or member 'dev' not described in 'drm_sched_init' Fixes: 2d33948e4e00 ("drm/scheduler: add documentation") Fixes: 8ab62eda177b ("drm/sched: Add device pointer to drm_gpu_scheduler") Fixes: 542cff7893a3 ("drm/sched: Avoid lockdep spalt on killing a processes") Signed-off-by: Randy Dunlap Cc: David Airlie Cc: Daniel Vetter Cc: Andrey Grodzovsky Cc: Nayan Deshmukh Cc: Alex Deucher Cc: Christian König Cc: Jiawei Gu Cc: dri-devel@lists.freedesktop.org Acked-by: Christian König Signed-off-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20220404213040.12912-1-rdunlap@infradead.org

drm/sched: move calling drm_sched_entity_select_rq

2022-07-19T15:22:25Z

We already discussed that the call to drm_sched_entity_select_rq() needs to move to drm_sched_job_arm() to be able to set a new scheduler list between _init() and _arm(). This was just not applied for some reason. Signed-off-by: Christian König Reviewed-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20220714103902.7084-2-christian.koenig@amd.com

Merge tag 'amd-drm-next-5.20-2022-07-05' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

2022-07-12T01:07:32Z

amd-drm-next-5.20-2022-07-05: amdgpu: - Various spelling and grammer fixes - Various eDP fixes - Various DMCUB fixes - VCN fixes - GMC 11 fixes - RAS fixes - TMZ support for GC 10.3.7 - GPUVM TLB flush fixes - SMU 13.0.x updates - DCN 3.2 Support - DCN 3.2.1 Support - MES updates - GFX11 modifiers support - USB-C fixes - MMHUB 3.0.1 support - SDMA 6.0 doorbell fixes - Initial devcoredump support - Enable high priority gfx queue on asics which support it - Enable GPU reset for SMU 13.0.4 - OLED display fixes - MPO fixes - DC frame size fixes - ASPM support for PCIE 7.4/7.6 - GPU reset support for SMU 13.0.0 - GFX11 updates - VCN JPEG fix - BACO support for SMU 13.0.7 - VCN instance handling fix - GFX8 GPUVM TLB flush fix - GPU reset rework - VCN 4.0.2 support - GTT size fixes - DP link training fixes - LSDMA 6.0.1 support - Various backlight fixes - Color encoding fixes - Backlight config cleanup - VCN 4.x unified queue cleanup amdkfd: - MMU notifier fixes - Updates for GC 10.3.6 and 10.3.7 - P2P DMA support using dma-buf - Add available memory IOCTL - SDMA 6.0.1 fix - MES fixes - HMM profiler support radeon: - License fix - Backlight config cleanup UAPI: - Add available memory IOCTL to amdkfd Proposed userspace: https://www.mail-archive.com/amd-gfx@lists.freedesktop.org/msg75743.html - HMM profiler support for amdkfd Proposed userspace: https://lists.freedesktop.org/archives/amd-gfx/2022-June/080805.html Signed-off-by: Dave Airlie From: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20220705212633.6037-1-alexander.deucher@amd.com

drm/sched: Partial revert of 'drm/sched: Keep s_fence->parent pointer'

2022-06-28T15:24:31Z

Problem: This patch caused negative refcount as described in [1] because for that case parent fence did not signal by the time of drm_sched_stop and hence kept in pending list the assumption was they will not signal and so fence was put to account for the s_fence->parent refcount but for amdgpu which has embedded HW fence (always same parent fence) drm_sched_fence_release_scheduled was always called and would still drop the count for parent fence once more. For jobs that never signaled this imbalance was masked by refcount bug in amdgpu_fence_driver_clear_job_fences that would not drop refcount on the fences that were removed from fence drive fences array (against prevois insertion into the array in get in amdgpu_fence_emit). Fix: Revert this patch and by setting s_job->s_fence->parent to NULL as before prevent the extra refcount drop in amdgpu when drm_sched_fence_release_scheduled is called on job release. Also - align behaviour in drm_sched_resubmit_jobs_ext with that of drm_sched_main when submitting jobs - take a refcount for the new parent fence pointer and drop refcount for original kref_init for new HW fence creation (or fake new HW fence in amdgpu - see next patch). [1] - https://lore.kernel.org/all/731b7ff1-3cc9-e314-df2a-7c51b76d4db0@amd.com/t/#r00c728fcc069b1276642c325bfa9d82bf8fa21a3 Signed-off-by: Andrey Grodzovsky Tested-by: Yiqing Yao Acked-by: Christian König Signed-off-by: Alex Deucher

drm/scheduler: Don't kill jobs in interrupt context

2022-05-17T14:06:41Z

Interrupt context can't sleep. Drivers like Panfrost and MSM are taking mutex when job is released, and thus, that code can sleep. This results into "BUG: scheduling while atomic" if locks are contented while job is freed. There is no good reason for releasing scheduler's jobs in IRQ context, hence use normal context to fix the trouble. Cc: stable@vger.kernel.org Fixes: 542cff7893a3 ("drm/sched: Avoid lockdep spalt on killing a processes") Signed-off-by: Dmitry Osipenko Signed-off-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/msgid/20220411221536.283312-1-dmitry.osipenko@collabora.com