[Intel-gfx] [RFC PATCH 000/162] DG1 + LMEM enabling
Matthew Auld
matthew.auld at intel.com
Fri Nov 27 12:04:36 UTC 2020
This series includes a version of Maarten' series[1], which converts more of the
driver locking over to dma-resv. On top of this we now implement things like
LMEM eviction, which has a dependency on this new locking design.
In terms of new uAPI we have gem_create_ext, which offers extensions support for
gem_create. For now the only extension we add is giving userspace the ability to
optionally provide a priority list of potential placements for the object. The
other bit of new uAPI is the query interface for memory regions, which describes
the supported memory regions for the device. What this reports can then be fed
into gem_create_ext to specify where an object might reside, like device local
memory. Note that the class/instance complexity in the uAPI is not very relevant
for DG1, but is in preparation for the Xe HP multi-tile architecture with
multiple memory regions.
The series still includes relocation support, but that's purely for CI, until we
have completed all the IGT rework[2] and so will not be merged. Likewise for
pread/pwrite, which will also be dropped from DG1+.
[1] https://patchwork.freedesktop.org/series/82337/
[2] https://patchwork.freedesktop.org/series/82954/
Abdiel Janulgue (3):
drm/i915/query: Expose memory regions through the query uAPI
drm/i915: Provide a way to disable PCIe relaxed write ordering
drm/i915: Reintroduce mem->reserved
Animesh Manna (2):
drm/i915/lmem: reset the lmem buffer created by fbdev
drm/i915/dsb: Enable lmem for dsb
Anshuman Gupta (1):
drm/i915/oprom: Basic sanitization
Anusha Srivatsa (1):
drm/i915/lmem: Bypass aperture when lmem is available
Bommu Krishnaiah (1):
drm/i915/gem: Update shmem available memory
CQ Tang (13):
drm/i915/dg1: Fix occasional migration error
drm/i915: i915 returns -EBUSY on thread contention
drm/i915: setup GPU device lmem region
drm/i915: Fix object page offset within a region
drm/i915: add i915_gem_object_is_devmem() function
drm/i915: finish memory region support for stolen objects.
drm/i915: Create stolen memory region from local memory
drm/i915/dg1: intel_memory_region_evict() changes for eviction
drm/i915/dg1: i915_gem_object_memcpy(..) infrastructure
drm/i915/dg1: Eviction logic
drm/i915/dg1: Add enable_eviction modparam
drm/i915/dg1: Add lmem_size modparam
drm/i915: need consider system BO snoop for dgfx
Chris Wilson (2):
drm/i915/gt: Move move context layout registers and offsets to
lrc_reg.h
drm/i915/gt: Rename lrc.c to execlists_submission.c
Clint Taylor (3):
drm/i915/dg1: Read OPROM via SPI controller
drm/i915/dg1: Compute MEM Bandwidth using MCHBAR
drm/i915/dg1: Double memory bandwidth available
Daniele Ceraolo Spurio (5):
drm/i915: split gen8+ flush and bb_start emission functions to their
own file
drm/i915: split wa_bb code to its own file
drm/i915: Make intel_init_workaround_bb more compatible with ww
locking.
drm/i915/guc: put all guc objects in lmem when available
drm/i915: WA for zero memory channel
Imre Deak (1):
drm/i915/dg1: Reserve first 1MB of local memory
Kui Wen (1):
drm/i915/dg1: Do not check r->sgt.pfn for NULL
Lucas De Marchi (2):
drm/i915: move eviction to prepare hook
drm/i915/dg1: allow pci to auto probe
Maarten Lankhorst (60):
drm/i915: Pin timeline map after first timeline pin, v5.
drm/i915: Move cmd parser pinning to execbuffer
drm/i915: Add missing -EDEADLK handling to execbuf pinning, v2.
drm/i915: Ensure we hold the object mutex in pin correctly v2
drm/i915: Add gem object locking to madvise.
drm/i915: Move HAS_STRUCT_PAGE to obj->flags
drm/i915: Rework struct phys attachment handling
drm/i915: Convert i915_gem_object_attach_phys() to ww locking, v2.
drm/i915: make lockdep slightly happier about execbuf.
drm/i915: Disable userptr pread/pwrite support.
drm/i915: No longer allow exporting userptr through dma-buf
drm/i915: Reject more ioctls for userptr
drm/i915: Reject UNSYNCHRONIZED for userptr, v2.
drm/i915: Make compilation of userptr code depend on MMU_NOTIFIER.
drm/i915: Fix userptr so we do not have to worry about obj->mm.lock,
v5.
drm/i915: Flatten obj->mm.lock
drm/i915: Populate logical context during first pin.
drm/i915: Make ring submission compatible with obj->mm.lock removal,
v2.
drm/i915: Handle ww locking in init_status_page
drm/i915: Rework clflush to work correctly without obj->mm.lock.
drm/i915: Pass ww ctx to intel_pin_to_display_plane
drm/i915: Add object locking to vm_fault_cpu
drm/i915: Move pinning to inside engine_wa_list_verify()
drm/i915: Take reservation lock around i915_vma_pin.
drm/i915: Make __engine_unpark() compatible with ww locking v2
drm/i915: Take obj lock around set_domain ioctl
drm/i915: Defer pin calls in buffer pool until first use by caller.
drm/i915: Fix pread/pwrite to work with new locking rules.
drm/i915: Fix workarounds selftest, part 1
drm/i915: Add igt_spinner_pin() to allow for ww locking around
spinner.
drm/i915: Add ww locking around vm_access()
drm/i915: Increase ww locking for perf.
drm/i915: Lock ww in ucode objects correctly
drm/i915: Add ww locking to dma-buf ops.
drm/i915: Add missing ww lock in intel_dsb_prepare.
drm/i915: Fix ww locking in shmem_create_from_object
drm/i915: Use a single page table lock for each gtt.
drm/i915/selftests: Prepare huge_pages testcases for obj->mm.lock
removal.
drm/i915/selftests: Prepare client blit for obj->mm.lock removal.
drm/i915/selftests: Prepare coherency tests for obj->mm.lock removal.
drm/i915/selftests: Prepare context tests for obj->mm.lock removal.
drm/i915/selftests: Prepare dma-buf tests for obj->mm.lock removal.
drm/i915/selftests: Prepare execbuf tests for obj->mm.lock removal.
drm/i915/selftests: Prepare mman testcases for obj->mm.lock removal.
drm/i915/selftests: Prepare object tests for obj->mm.lock removal.
drm/i915/selftests: Prepare object blit tests for obj->mm.lock
removal.
drm/i915/selftests: Prepare igt_gem_utils for obj->mm.lock removal
drm/i915/selftests: Prepare context selftest for obj->mm.lock removal
drm/i915/selftests: Prepare hangcheck for obj->mm.lock removal
drm/i915/selftests: Prepare execlists for obj->mm.lock removal
drm/i915/selftests: Prepare mocs tests for obj->mm.lock removal
drm/i915/selftests: Prepare ring submission for obj->mm.lock removal
drm/i915/selftests: Prepare timeline tests for obj->mm.lock removal
drm/i915/selftests: Prepare i915_request tests for obj->mm.lock
removal
drm/i915/selftests: Prepare memory region tests for obj->mm.lock
removal
drm/i915/selftests: Prepare cs engine tests for obj->mm.lock removal
drm/i915/selftests: Prepare gtt tests for obj->mm.lock removal
drm/i915: Finally remove obj->mm.lock.
drm/i915: Keep userpointer bindings if seqcount is unchanged, v2.
drm/i915: Implement eviction locking v2
Matt Roper (1):
drm/i915/lmem: Fail driver init if LMEM training failed
Matthew Auld (19):
drm/i915/selftest: also consider non-contiguous objects
drm/i915/selftest: assert we get 2M GTT pages
drm/i915/selftest: handle local-memory in perf_memcpy
HAX drm/i915/lmem: support CPU relocations
HAX drm/i915/lmem: support pread and pwrite
drm/i915: introduce kernel blitter_context
drm/i915/region: support basic eviction
drm/i915: support basic object migration
drm/i915/uapi: introduce drm_i915_gem_create_ext
drm/i915: setup the LMEM region
drm/i915/gtt: map the PD up front
drm/i915/gtt/dgfx: place the PD in LMEM
drm/i915/gtt: make flushing conditional
drm/i915/gtt/dg1: add PTE_LM plumbing for PPGTT
drm/i915/gtt/dg1: add PTE_LM plumbing for GGTT
drm/i915: allocate context from LMEM
drm/i915: move engine scratch to LMEM
drm/i915/lmem: support optional CPU clearing for special internal use
drm/i915: drop fake lmem
Michael J. Ruhl (2):
drm/i915/dmabuf: Disallow LMEM objects from dma-buf
drm/i915/dg1: Introduce dmabuf mmap to LMEM
Michel Thierry (2):
drm/i915/lmem: allocate cmd ring in lmem
drm/i915/lmem: allocate HWSP in lmem
Mohammed Khajapasha (2):
drm/i915/fbdev: Use lmem physical addresses for fb_mmap() on discrete
drm/i915: Return error value when bo not in LMEM for discrete
Prathap Kumar Valsan (2):
drm/i915: Store gt in memory region
drm/i915/pm: suspend and restore ppgtt mapping
Ramalingam C (6):
drm/i915: define intel_partial_pages_for_sg_table
drm/i915: create and destroy dummy vma
drm/i915: blt copy between objs using pre-created vma windows
drm/i915: window_blt_copy is used for swapin and swapout
drm/i915: Lmem eviction statistics by category
drm/i915/gem/selftest: test and measure window based blt cpy
Stuart Summers (1):
drm/i915: Allow non-uniform subslices in gen12+
Sudeep Dutt (2):
drm/i915/dg1: Track swap in/out stats via debugfs
drm/i915/dg1: Measure swap in/out timing stats
Thomas Hellström (15):
HAX drm/i915: Work around the selftest timeline lock splat workaround
drm/i915: Introduce drm_i915_lock_isolated
drm/i915: Lock hwsp objects isolated for pinning at create time
drm/i915: Prepare for obj->mm.lock removal
drm/i915: Avoid some false positives in assert_object_held()
drm/i915: Reference contending lock objects
drm/i915: Break out dma_resv ww locking utilities to separate files
drm/i915: Introduce a for_i915_gem_ww(){}
drm/i915: Untangle the vma pages_mutex
drm/i915: Add blit functions that can be called from within a WW
transaction
drm/i915: Delay publishing objects on the eviction lists
drm/i915: Perform execbuffer object locking as a separate step
drm/i915: Support ww eviction
drm/i915: Use a ww transaction in the fault handler
drm/i915: Use a ww transaction in i915_gem_object_pin_map_unlocked()
Tvrtko Ursulin (4):
drm/i915/dg1: Eliminate eviction mutex
drm/i915/dg1: Keep engine awake across whole blit
drm/i915/dg1: Add dedicated context for blitter eviction
drm/i915: Improve accuracy of eviction stats
Venkata Ramana Nayana (8):
drm/i915: suspend/resume eviction
drm/i915: Reset blitter context when unpark engine
drm/i915/gt: Allocate default ctx objects in SMEM
drm/i915: suspend/resume enable blitter eviction
drm/i915: suspend/resume handling of perma-pinned objects
drm/i915: Support ww locks in suspend/resume
drm/i915/dg1: Fix mapping type for default state object
drm/i915/dg1: Fix GPU hang due to shmemfs page drop
Venkata Sandeep Dhanalakota (2):
drm/i915: Update the helper to set correct mapping
drm/i915/lmem: Limit block size to 4G
Zbigniew Kempczyński (1):
drm/i915: Distinction of memory regions
drivers/gpu/drm/i915/Kconfig.debug | 11 +
drivers/gpu/drm/i915/Makefile | 7 +-
drivers/gpu/drm/i915/display/intel_bios.c | 75 +-
drivers/gpu/drm/i915/display/intel_bw.c | 64 +-
drivers/gpu/drm/i915/display/intel_display.c | 80 +-
drivers/gpu/drm/i915/display/intel_display.h | 2 +-
drivers/gpu/drm/i915/display/intel_dsb.c | 9 +-
drivers/gpu/drm/i915/display/intel_fbc.c | 20 +-
drivers/gpu/drm/i915/display/intel_fbdev.c | 54 +-
drivers/gpu/drm/i915/display/intel_opregion.c | 169 ++++
drivers/gpu/drm/i915/display/intel_opregion.h | 31 +-
drivers/gpu/drm/i915/display/intel_overlay.c | 34 +-
drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 15 +-
drivers/gpu/drm/i915/gem/i915_gem_context.c | 1 +
drivers/gpu/drm/i915/gem/i915_gem_create.c | 398 ++++++++
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 123 ++-
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 52 +-
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 302 +++++-
drivers/gpu/drm/i915/gem/i915_gem_fence.c | 95 --
drivers/gpu/drm/i915/gem/i915_gem_internal.c | 6 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 254 ++++-
drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 22 +
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 187 ++--
drivers/gpu/drm/i915/gem/i915_gem_mman.h | 11 +
drivers/gpu/drm/i915/gem/i915_gem_object.c | 711 +++++++++++++-
drivers/gpu/drm/i915/gem/i915_gem_object.h | 206 +++-
.../gpu/drm/i915/gem/i915_gem_object_blt.c | 101 +-
.../gpu/drm/i915/gem/i915_gem_object_blt.h | 10 +
.../gpu/drm/i915/gem/i915_gem_object_types.h | 46 +-
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 140 ++-
drivers/gpu/drm/i915/gem/i915_gem_phys.c | 110 +--
drivers/gpu/drm/i915/gem/i915_gem_region.c | 234 ++++-
drivers/gpu/drm/i915/gem/i915_gem_region.h | 3 +-
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 46 +-
drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 52 +-
drivers/gpu/drm/i915/gem/i915_gem_shrinker.h | 6 +-
drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 247 +++--
drivers/gpu/drm/i915/gem/i915_gem_stolen.h | 10 +-
drivers/gpu/drm/i915/gem/i915_gem_tiling.c | 2 -
drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 870 ++++++-----------
.../drm/i915/gem/selftests/huge_gem_object.c | 4 +-
.../gpu/drm/i915/gem/selftests/huge_pages.c | 60 +-
.../i915/gem/selftests/i915_gem_client_blt.c | 8 +-
.../i915/gem/selftests/i915_gem_coherency.c | 18 +-
.../drm/i915/gem/selftests/i915_gem_context.c | 21 +-
.../drm/i915/gem/selftests/i915_gem_dmabuf.c | 2 +-
.../i915/gem/selftests/i915_gem_execbuffer.c | 2 +-
.../drm/i915/gem/selftests/i915_gem_mman.c | 33 +-
.../drm/i915/gem/selftests/i915_gem_object.c | 2 +-
.../i915/gem/selftests/i915_gem_object_blt.c | 172 +++-
.../drm/i915/gem/selftests/i915_gem_phys.c | 10 +-
.../drm/i915/gem/selftests/igt_gem_utils.c | 2 +-
drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 11 +-
drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 393 ++++++++
drivers/gpu/drm/i915/gt/gen8_engine_cs.h | 26 +
drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 91 +-
drivers/gpu/drm/i915/gt/gen8_ppgtt.h | 2 +
drivers/gpu/drm/i915/gt/intel_context.c | 3 +-
drivers/gpu/drm/i915/gt/intel_context.h | 2 +
drivers/gpu/drm/i915/gt/intel_context_sseu.c | 2 +-
drivers/gpu/drm/i915/gt/intel_context_types.h | 13 +-
drivers/gpu/drm/i915/gt/intel_engine.h | 4 +
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 125 ++-
drivers/gpu/drm/i915/gt/intel_engine_pm.c | 14 +-
drivers/gpu/drm/i915/gt/intel_engine_types.h | 2 +
.../drm/i915/gt/intel_engine_workaround_bb.c | 364 +++++++
.../drm/i915/gt/intel_engine_workaround_bb.h | 14 +
...tel_lrc.c => intel_execlists_submission.c} | 899 +++---------------
.../drm/i915/gt/intel_execlists_submission.h | 66 ++
drivers/gpu/drm/i915/gt/intel_ggtt.c | 93 +-
drivers/gpu/drm/i915/gt/intel_gt.c | 14 +-
.../gpu/drm/i915/gt/intel_gt_buffer_pool.c | 47 +-
.../gpu/drm/i915/gt/intel_gt_buffer_pool.h | 5 +
.../drm/i915/gt/intel_gt_buffer_pool_types.h | 1 +
drivers/gpu/drm/i915/gt/intel_gt_irq.c | 1 +
drivers/gpu/drm/i915/gt/intel_gtt.c | 105 +-
drivers/gpu/drm/i915/gt/intel_gtt.h | 23 +-
drivers/gpu/drm/i915/gt/intel_lrc.h | 128 ---
drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 39 +
drivers/gpu/drm/i915/gt/intel_mocs.c | 2 +-
drivers/gpu/drm/i915/gt/intel_ppgtt.c | 20 +-
drivers/gpu/drm/i915/gt/intel_renderstate.c | 2 +-
drivers/gpu/drm/i915/gt/intel_renderstate.h | 1 +
drivers/gpu/drm/i915/gt/intel_ring.c | 24 +-
.../gpu/drm/i915/gt/intel_ring_submission.c | 184 ++--
drivers/gpu/drm/i915/gt/intel_sseu.c | 6 +-
drivers/gpu/drm/i915/gt/intel_timeline.c | 121 ++-
drivers/gpu/drm/i915/gt/intel_timeline.h | 1 +
.../gpu/drm/i915/gt/intel_timeline_types.h | 1 +
drivers/gpu/drm/i915/gt/intel_workarounds.c | 24 +-
drivers/gpu/drm/i915/gt/mock_engine.c | 24 +-
drivers/gpu/drm/i915/gt/selftest_context.c | 5 +-
drivers/gpu/drm/i915/gt/selftest_engine_cs.c | 4 +-
.../{selftest_lrc.c => selftest_execlists.c} | 37 +-
drivers/gpu/drm/i915/gt/selftest_hangcheck.c | 8 +-
drivers/gpu/drm/i915/gt/selftest_mocs.c | 2 +-
drivers/gpu/drm/i915/gt/selftest_reset.c | 5 +-
.../drm/i915/gt/selftest_ring_submission.c | 4 +-
drivers/gpu/drm/i915/gt/selftest_timeline.c | 100 +-
.../gpu/drm/i915/gt/selftest_workarounds.c | 101 +-
drivers/gpu/drm/i915/gt/shmem_utils.c | 11 +-
drivers/gpu/drm/i915/gt/uc/intel_guc.c | 13 +-
drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c | 1 +
drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c | 11 +-
drivers/gpu/drm/i915/gt/uc/intel_guc_log.c | 4 +-
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 1 +
drivers/gpu/drm/i915/gt/uc/intel_huc.c | 18 +-
drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 37 +-
drivers/gpu/drm/i915/gvt/dmabuf.c | 2 +-
drivers/gpu/drm/i915/gvt/mmio_context.h | 2 +
drivers/gpu/drm/i915/gvt/scheduler.c | 1 +
drivers/gpu/drm/i915/i915_active.c | 20 +-
drivers/gpu/drm/i915/i915_cmd_parser.c | 104 +-
drivers/gpu/drm/i915/i915_debugfs.c | 42 +-
drivers/gpu/drm/i915/i915_drv.c | 277 +++++-
drivers/gpu/drm/i915/i915_drv.h | 57 +-
drivers/gpu/drm/i915/i915_gem.c | 418 +++-----
drivers/gpu/drm/i915/i915_gem.h | 12 -
drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
drivers/gpu/drm/i915/i915_gem_ww.c | 93 ++
drivers/gpu/drm/i915/i915_gem_ww.h | 53 ++
drivers/gpu/drm/i915/i915_gpu_error.c | 4 +-
drivers/gpu/drm/i915/i915_memcpy.c | 2 +-
drivers/gpu/drm/i915/i915_memcpy.h | 2 +-
drivers/gpu/drm/i915/i915_mm.c | 2 +-
drivers/gpu/drm/i915/i915_params.c | 11 +-
drivers/gpu/drm/i915/i915_params.h | 3 +-
drivers/gpu/drm/i915/i915_pci.c | 5 +-
drivers/gpu/drm/i915/i915_perf.c | 57 +-
drivers/gpu/drm/i915/i915_query.c | 62 ++
drivers/gpu/drm/i915/i915_reg.h | 17 +
drivers/gpu/drm/i915/i915_selftest.h | 2 +
drivers/gpu/drm/i915/i915_vma.c | 154 ++-
drivers/gpu/drm/i915/i915_vma.h | 28 +-
drivers/gpu/drm/i915/intel_memory_region.c | 229 ++++-
drivers/gpu/drm/i915/intel_memory_region.h | 53 +-
drivers/gpu/drm/i915/intel_region_lmem.c | 168 ++--
drivers/gpu/drm/i915/intel_region_lmem.h | 3 +-
drivers/gpu/drm/i915/intel_uncore.c | 12 +
drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 100 +-
.../drm/i915/selftests/i915_live_selftests.h | 1 +
drivers/gpu/drm/i915/selftests/i915_perf.c | 3 +-
drivers/gpu/drm/i915/selftests/i915_request.c | 10 +-
drivers/gpu/drm/i915/selftests/igt_spinner.c | 136 ++-
drivers/gpu/drm/i915/selftests/igt_spinner.h | 5 +
.../drm/i915/selftests/intel_memory_region.c | 442 ++++++++-
drivers/gpu/drm/i915/selftests/mock_region.c | 4 +-
include/uapi/drm/i915_drm.h | 118 +++
148 files changed, 7813 insertions(+), 3312 deletions(-)
create mode 100644 drivers/gpu/drm/i915/gem/i915_gem_create.c
delete mode 100644 drivers/gpu/drm/i915/gem/i915_gem_fence.c
create mode 100644 drivers/gpu/drm/i915/gt/gen8_engine_cs.c
create mode 100644 drivers/gpu/drm/i915/gt/gen8_engine_cs.h
create mode 100644 drivers/gpu/drm/i915/gt/intel_engine_workaround_bb.c
create mode 100644 drivers/gpu/drm/i915/gt/intel_engine_workaround_bb.h
rename drivers/gpu/drm/i915/gt/{intel_lrc.c => intel_execlists_submission.c} (87%)
create mode 100644 drivers/gpu/drm/i915/gt/intel_execlists_submission.h
delete mode 100644 drivers/gpu/drm/i915/gt/intel_lrc.h
rename drivers/gpu/drm/i915/gt/{selftest_lrc.c => selftest_execlists.c} (99%)
create mode 100644 drivers/gpu/drm/i915/i915_gem_ww.c
create mode 100644 drivers/gpu/drm/i915/i915_gem_ww.h
--
2.26.2
More information about the Intel-gfx
mailing list