Skip to content

drm/msm: sparse / "VM_BIND" support

Rob Clark dri-devel linux-arm-kernel linux-arm-msm linux-iommu linux-media lkml 7 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v5 Latest40 patches 14 repliesIn review
  2. v4 posting 3/340 patches 24 repliesSuperseded
  3. v4 posting 2/311 of 40 patches 20 repliesSuperseded
Earlier versions · 4
VersionPostedPatchesRepliesStatus
v4 posting 1/322 of 33 patches4 repliesSuperseded
v333 patches5 repliesSuperseded
v234 patches10 repliesSuperseded
v1 RFC24 patches0 repliesSuperseded

Changes in v5 from the cover letter

- Improved drm/sched enqueue_credit comments, and better define the return from drm_sched_entity_push_job()
- Improve DRM_GPUVM_VA_WEAK_REF comments, and additional WARN_ON()s to make it clear that some of the gpuvm functionality is not available in this mode.
- Link to v4: https://lore.kernel.org/all/[email protected]/

Patches in v5 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/40drm/gpuvm: Don't require obj lock in destructor pathdrivers/gpu/drm/drm_gpuvm.c+5 -25 replies
2/40drm/gpuvm: Allow VAs to hold soft reference to BOsdrivers/gpu/drm/drm_gpuvm.c include/drm/drm_gpuvm.h+49 -73 replies
3/40drm/gem: Add ww_acquire_ctx support to drm_gem_lru_scan()drivers/gpu/drm/drm_gem.c drivers/gpu/drm/msm/msm_gem_shrinker.c include/drm/drm_gem.h+30 -180 replies
4/40drm/sched: Add enqueue credit limitdrivers/gpu/drm/scheduler/sched_entity.c drivers/gpu/drm/scheduler/sched_main.c include/drm/gpu_scheduler.h+43 -30 replies
5/40iommu/io-pgtable-arm: Add quirk to quiet WARN_ON()drivers/iommu/io-pgtable-arm.c include/linux/io-pgtable.h+22 -130 replies
6/40drm/msm: Rename msm_file_private -> msm_contextdrivers/gpu/drm/msm/adreno/a6xx_gpu.c drivers/gpu/drm/msm/adreno/adreno_gpu.c drivers/gpu/drm/msm/adreno/adreno_gpu.h +6 more+49 -510 replies
7/40drm/msm: Improve msm_context commentsdrivers/gpu/drm/msm/msm_gpu.h+29 -150 replies
8/40drm/msm: Rename msm_gem_address_space -> msm_gem_vmdrivers/gpu/drm/msm/adreno/a2xx_gpu.c drivers/gpu/drm/msm/adreno/a3xx_gpu.c drivers/gpu/drm/msm/adreno/a4xx_gpu.c +38 more+349 -3540 replies
9/40drm/msm: Remove vram carveout supportdrivers/gpu/drm/msm/adreno/a2xx_gpu.c drivers/gpu/drm/msm/adreno/a3xx_gpu.c drivers/gpu/drm/msm/adreno/a4xx_gpu.c +11 more+19 -3090 replies
10/40drm/msm: Collapse vma allocation and initializationdrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_vma.c+20 -500 replies
11/40drm/msm: Collapse vma close and deletedrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem_vma.c+5 -130 replies
12/40drm/msm: Don't close VMAs on purgedrivers/gpu/drm/msm/msm_gem.c+1 -10 replies
13/40drm/msm: drm_gpuvm conversiondrivers/gpu/drm/msm/Kconfig drivers/gpu/drm/msm/adreno/a2xx_gpu.c drivers/gpu/drm/msm/adreno/a6xx_gmu.c +9 more+271 -1340 replies
14/40drm/msm: Convert vm lockingdrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_shrinker.c +2 more+150 -380 replies
15/40drm/msm: Use drm_gpuvm types moredrivers/gpu/drm/msm/adreno/a2xx_gpu.c drivers/gpu/drm/msm/adreno/a5xx_gpu.c drivers/gpu/drm/msm/adreno/a6xx_gmu.c +24 more+190 -2040 replies
16/40drm/msm: Split out helper to get iommu prot flagsdrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h+11 -20 replies
17/40drm/msm: Add mmu support for non-zero offsetdrivers/gpu/drm/msm/adreno/a2xx_gpummu.c drivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h +3 more+36 -140 replies
18/40drm/msm: Add PRR supportdrivers/gpu/drm/msm/adreno/adreno_gpu.c drivers/gpu/drm/msm/msm_iommu.c include/uapi/drm/msm_drm.h+73 -10 replies
19/40drm/msm: Rename msm_gem_vma_purge() -> _unmap()drivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_vma.c+4 -40 replies
20/40drm/msm: Drop queued submits on lastclose()drivers/gpu/drm/msm/msm_drv.c drivers/gpu/drm/msm/msm_gpu.h drivers/gpu/drm/msm/msm_ringbuffer.c+15 -00 replies
21/40drm/msm: Lazily create context VMdrivers/gpu/drm/msm/adreno/a6xx_gpu.c drivers/gpu/drm/msm/adreno/adreno_gpu.c drivers/gpu/drm/msm/msm_drv.c +2 more+43 -140 replies
22/40drm/msm: Add opt-in for VM_BINDdrivers/gpu/drm/msm/adreno/a6xx_gpu.c drivers/gpu/drm/msm/adreno/adreno_gpu.c drivers/gpu/drm/msm/msm_drv.c +4 more+99 -80 replies
23/40drm/msm: Mark VM as unusable on GPU hangsdrivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_submit.c drivers/gpu/drm/msm/msm_gpu.c+34 -20 replies
24/40drm/msm: Add _NO_SHARE flagdrivers/gpu/drm/msm/msm_drv.h drivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem_prime.c +1 more+53 -00 replies
25/40drm/msm: Crashdump prep for sparse mappingsdrivers/gpu/drm/msm/msm_gpu.c+10 -70 replies
26/40drm/msm: rd dumping prep for sparse mappingsdrivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_rd.c+17 -310 replies
27/40drm/msm: Crashdec support for sparsedrivers/gpu/drm/msm/msm_gpu.c+72 -240 replies
28/40drm/msm: rd dumping support for sparsedrivers/gpu/drm/msm/msm_rd.c+33 -150 replies
29/40drm/msm: Extract out syncobj helpersdrivers/gpu/drm/msm/Makefile drivers/gpu/drm/msm/msm_gem_submit.c drivers/gpu/drm/msm/msm_syncobj.c +2 more+235 -1930 replies
30/40drm/msm: Use DMA_RESV_USAGE_BOOKKEEP/KERNELdrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem_shrinker.c+4 -40 replies
31/40drm/msm: Add VM_BIND submitqueuedrivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_submit.c drivers/gpu/drm/msm/msm_gem_vma.c +3 more+197 -250 replies
32/40drm/msm: Support IO_PGTABLE_QUIRK_NO_WARN_ONdrivers/gpu/drm/msm/adreno/a6xx_gpu.c drivers/gpu/drm/msm/msm_iommu.c drivers/gpu/drm/msm/msm_mmu.h+20 -70 replies
33/40drm/msm: Support pgtable preallocationdrivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_iommu.c drivers/gpu/drm/msm/msm_mmu.h+225 -10 replies
34/40drm/msm: Split out map/unmap opsdrivers/gpu/drm/msm/msm_gem_vma.c+56 -70 replies
35/40drm/msm: Add VM_BIND ioctldrivers/gpu/drm/msm/msm_drv.c drivers/gpu/drm/msm/msm_drv.h drivers/gpu/drm/msm/msm_gem.c +4 more+1185 -330 replies
36/40drm/msm: Add VM logging for VM_BIND updatesdrivers/gpu/drm/msm/adreno/adreno_gpu.c drivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_vma.c +2 more+202 -130 replies
37/40drm/msm: Add VMA unmap reasondrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h drivers/gpu/drm/msm/msm_gem_vma.c+23 -120 replies
38/40drm/msm: Add mmu prealloc tracepointdrivers/gpu/drm/msm/msm_gpu_trace.h drivers/gpu/drm/msm/msm_iommu.c+18 -00 replies
39/40drm/msm: use trylock for debugfsdrivers/gpu/drm/msm/msm_gem.c drivers/gpu/drm/msm/msm_gem.h+8 -10 replies
40/40drm/msm: Bump UAPI versiondrivers/gpu/drm/msm/msm_drv.c+2 -10 replies

Reviews trailers per patch

4 of 40 patches have a Reviewed-by or Acked-by.

PatchRobin MurphyDmitry Baryshkov
1/40
2/40
3/40
4/40
5/40A-b
6/40R-b
7/40R-b
8/40R-b
9/40
10/40
11/40
12/40
13/40
14/40
15/40
16/40
17/40
18/40
19/40
20/40
21/40
22/40
23/40
24/40
25/40
26/40
27/40
28/40
29/40
30/40
31/40
32/40
33/40
34/40
35/40
36/40
37/40
38/40
39/40
40/40

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v5 thread

Cover letter [PATCH v5 00/40] drm/msm: sparse / "VM_BIND" support

From: Rob Clark <[email protected]>

Conversion to DRM GPU VA Manager[1], and adding support for Vulkan Sparse Memory[2] in the form of:

1. A new VM_BIND submitqueue type for executing VM MSM_SUBMIT_BO_OP_MAP/ MAP_NULL/UNMAP commands

2. A new VM_BIND ioctl to allow submitting batches of one or more MAP/MAP_NULL/UNMAP commands to a VM_BIND submitqueue

I did not implement support for synchronous VM_BIND commands. Since userspace could just immediately wait for the SUBMIT to complete, I don't think we need this extra complexity in the kernel. Synchronous/immediate VM_BIND operations could be implemented with a 2nd VM_BIND submitqueue.

The corresponding mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32533

Changes in v5:
- Improved drm/sched enqueue_credit comments, and better define the return from drm_sched_entity_push_job()
- Improve DRM_GPUVM_VA_WEAK_REF comments, and additional WARN_ON()s to make it clear that some of the gpuvm functionality is not available in this mode.
- Link to v4: https://lore.kernel.org/all/[email protected]/

Changes in v4:
- Various locking/etc fixes
- Optimize the pgtable preallocation. If userspace sorts the VM_BIND ops then the kernel detects ops that fall into the same 2MB last level PTD to avoid duplicate page preallocation.
- Add way to throttle pushing jobs to the scheduler, to cap the amount of potentially temporary prealloc'd pgtable pages.
- Add vm_log to devcoredump for debugging. If the vm_log_shift module param is set, keep a log of the last 1<<vm_log_shift VM updates for easier debugging of faults/crashes.
- Link to v3: https://lore.kernel.org/all/[email protected]/

Changes in v3:
- Switched to seperate VM_BIND ioctl. This makes the UABI a bit cleaner, but OTOH the userspace code was cleaner when the end result of either type of VkQueue lead to the same ioctl. So I'm a bit on the fence.
- Switched to doing the gpuvm bookkeeping synchronously, and only deferring the pgtable updates. This avoids needing to hold any resv locks in the fence signaling path, resolving the last shrinker related lockdep complaints. OTOH it means userspace can trigger invalid pgtable updates with multiple VM_BIND queues. In this case, we ensure that unmaps happen completely (to prevent userspace from using this to access free'd pages), mark the context as unusable, and move on with life.
- Link to v2: https://lore.kernel.org/all/[email protected]/

Changes in v2:
- Dropped Bibek Kumar Patro's arm-smmu patches[3], which have since been
merged.
- Pre-allocate all the things, and drop HACK patch which disabled shrinker.
This includes ensuring that vm_bo objects are allocated up front, pre-
allocating VMA objects, and pre-allocating pages used for pgtable updates.
The latter utilizes io_pgtable_cfg callbacks for pgtable alloc/free, that
were initially added for panthor.
- Add back support for BO dumping for devcoredump.
- Link to v1 (RFC): https://lore.kernel.org/dri-devel/[email protected]/T/#t

[1] https://www.kernel.org/doc/html/next/gpu/drm-mm.html#drm-gpuvm
[2] https://docs.vulkan.org/spec/latest/chapters/sparsemem.html
[3] https://patchwork.kernel.org/project/linux-arm-kernel/list/?series=909700

Rob Clark (40):
drm/gpuvm: Don't require obj lock in destructor path drm/gpuvm: Allow VAs to hold soft reference to BOs drm/gem: Add ww_acquire_ctx support to drm_gem_lru_scan() drm/sched: Add enqueue credit limit iommu/io-pgtable-arm: Add quirk to quiet WARN_ON() drm/msm: Rename msm_file_private -> msm_context drm/msm: Improve msm_context comments
drm/msm: Rename msm_gem_address_space -> msm_gem_vm drm/msm: Remove vram carveout support
drm/msm: Collapse vma allocation and initialization drm/msm: Collapse vma close and delete
drm/msm: Don't close VMAs on purge
drm/msm: drm_gpuvm conversion
drm/msm: Convert vm locking
drm/msm: Use drm_gpuvm types more
drm/msm: Split out helper to get iommu prot flags drm/msm: Add mmu support for non-zero offset drm/msm: Add PRR support
drm/msm: Rename msm_gem_vma_purge() -> _unmap() drm/msm: Drop queued submits on lastclose() drm/msm: Lazily create context VM
drm/msm: Add opt-in for VM_BIND
drm/msm: Mark VM as unusable on GPU hangs drm/msm: Add _NO_SHARE flag
drm/msm: Crashdump prep for sparse mappings drm/msm: rd dumping prep for sparse mappings drm/msm: Crashdec support for sparse
drm/msm: rd dumping support for sparse
drm/msm: Extract out syncobj helpers
drm/msm: Use DMA_RESV_USAGE_BOOKKEEP/KERNEL drm/msm: Add VM_BIND submitqueue
drm/msm: Support IO_PGTABLE_QUIRK_NO_WARN_ON drm/msm: Support pgtable preallocation
drm/msm: Split out map/unmap ops
drm/msm: Add VM_BIND ioctl
drm/msm: Add VM logging for VM_BIND updates drm/msm: Add VMA unmap reason
drm/msm: Add mmu prealloc tracepoint
drm/msm: use trylock for debugfs
drm/msm: Bump UAPI version

 drivers/gpu/drm/drm_gem.c                     |   14 +-
 drivers/gpu/drm/drm_gpuvm.c                   |   38 +-
 drivers/gpu/drm/msm/Kconfig                   |    1 +
 drivers/gpu/drm/msm/Makefile                  |    1 +
 drivers/gpu/drm/msm/adreno/a2xx_gpu.c         |   25 +-
 drivers/gpu/drm/msm/adreno/a2xx_gpummu.c      |    5 +-
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c         |   17 +-
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c         |   17 +-
 drivers/gpu/drm/msm/adreno/a5xx_debugfs.c     |    4 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c         |   22 +-
 drivers/gpu/drm/msm/adreno/a5xx_power.c       |    2 +-
 drivers/gpu/drm/msm/adreno/a5xx_preempt.c     |   10 +-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c         |   32 +-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.h         |    2 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c         |   49 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c   |    6 +-
 drivers/gpu/drm/msm/adreno/a6xx_preempt.c     |   10 +-
 drivers/gpu/drm/msm/adreno/adreno_device.c    |    4 -
 drivers/gpu/drm/msm/adreno/adreno_gpu.c       |   99 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.h       |   23 +-
 .../drm/msm/disp/dpu1/dpu_encoder_phys_wb.c   |   14 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c   |   18 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h   |    2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |   18 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c     |   14 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h     |    4 +-
 drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c     |    6 +-
 drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c      |   28 +-
 drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c    |   12 +-
 drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c     |    4 +-
 drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c      |   19 +-
 drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c    |   12 +-
 drivers/gpu/drm/msm/dsi/dsi_host.c            |   14 +-
 drivers/gpu/drm/msm/msm_drv.c                 |  184 +--
 drivers/gpu/drm/msm/msm_drv.h                 |   35 +-
 drivers/gpu/drm/msm/msm_fb.c                  |   18 +-
 drivers/gpu/drm/msm/msm_fbdev.c               |    2 +-
 drivers/gpu/drm/msm/msm_gem.c                 |  494 +++---
 drivers/gpu/drm/msm/msm_gem.h                 |  247 ++-
 drivers/gpu/drm/msm/msm_gem_prime.c           |   15 +
 drivers/gpu/drm/msm/msm_gem_shrinker.c        |  104 +-
 drivers/gpu/drm/msm/msm_gem_submit.c          |  295 ++--
 drivers/gpu/drm/msm/msm_gem_vma.c             | 1471 ++++++++++++++++-
 drivers/gpu/drm/msm/msm_gpu.c                 |  211 ++-
 drivers/gpu/drm/msm/msm_gpu.h                 |  144 +-
 drivers/gpu/drm/msm/msm_gpu_trace.h           |   14 +
 drivers/gpu/drm/msm/msm_iommu.c               |  302 +++-
 drivers/gpu/drm/msm/msm_kms.c                 |   18 +-
 drivers/gpu/drm/msm/msm_kms.h                 |    2 +-
 drivers/gpu/drm/msm/msm_mmu.h                 |   38 +-
 drivers/gpu/drm/msm/msm_rd.c                  |   62 +-
 drivers/gpu/drm/msm/msm_ringbuffer.c          |   10 +-
 drivers/gpu/drm/msm/msm_submitqueue.c         |   96 +-
 drivers/gpu/drm/msm/msm_syncobj.c             |  172 ++
 drivers/gpu/drm/msm/msm_syncobj.h             |   37 +
 drivers/gpu/drm/scheduler/sched_entity.c      |   19 +-
 drivers/gpu/drm/scheduler/sched_main.c        |    3 +
 drivers/iommu/io-pgtable-arm.c                |   27 +-
 include/drm/drm_gem.h                         |   10 +-
 include/drm/drm_gpuvm.h                       |   19 +-
 include/drm/gpu_scheduler.h                   |   24 +-
 include/linux/io-pgtable.h                    |    8 +
 include/uapi/drm/msm_drm.h                    |  149 +-
 63 files changed, 3526 insertions(+), 1250 deletions(-)
 create mode 100644 drivers/gpu/drm/msm/msm_syncobj.c
 create mode 100644 drivers/gpu/drm/msm/msm_syncobj.h
Signature · 1 line
2.49.0