diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
| commit | 901bdf5ea1a836400ee69aa32b04e9c209271ec7 (patch) | |
| tree | ccb1851c8a71e776dbccf1ccae132dc9b5f093c6 /drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | |
| parent | ba57b9b11f78530146f02b776854b2b6b6d344a4 (diff) | |
| parent | 3b718dcaf163d17fe907ea098c8449e0cd6bc271 (diff) | |
| download | lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.tar.gz lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.zip | |
Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.5-2023-06-02:
amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates
amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions
radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero
ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()
UAPI:
- Add new ctx query flag to better handle GPU resets
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3
amd-drm-next-6.5-2023-06-09:
amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class
amdkfd:
- Add debugger support for gdb
radeon:
- Fix possible UAF
drm:
- Add Colorspace functionality
UAPI:
- Add debugger interface for enabling gdb
Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 47 |
1 files changed, 38 insertions, 9 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 2eb2c66843a8..6e1d331af01f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -112,6 +112,9 @@ static int amdgpu_cs_p1_ib(struct amdgpu_cs_parser *p, if (r < 0) return r; + if (num_ibs[r] >= amdgpu_ring_max_ibs(chunk_ib->ip_type)) + return -EINVAL; + ++(num_ibs[r]); p->gang_leader_idx = r; return 0; @@ -192,7 +195,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, uint64_t *chunk_array_user; uint64_t *chunk_array; uint32_t uf_offset = 0; - unsigned int size; + size_t size; int ret; int i; @@ -285,6 +288,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: + case AMDGPU_CHUNK_ID_CP_GFX_SHADOW: break; default: @@ -393,7 +397,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p, { struct drm_amdgpu_cs_chunk_dep *deps = chunk->kdata; struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - unsigned num_deps; + unsigned int num_deps; int i, r; num_deps = chunk->length_dw * 4 / @@ -464,7 +468,7 @@ static int amdgpu_cs_p2_syncobj_in(struct amdgpu_cs_parser *p, struct amdgpu_cs_chunk *chunk) { struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata; - unsigned num_deps; + unsigned int num_deps; int i, r; num_deps = chunk->length_dw * 4 / @@ -482,7 +486,7 @@ static int amdgpu_cs_p2_syncobj_timeline_wait(struct amdgpu_cs_parser *p, struct amdgpu_cs_chunk *chunk) { struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata; - unsigned num_deps; + unsigned int num_deps; int i, r; num_deps = chunk->length_dw * 4 / @@ -502,7 +506,7 @@ static int amdgpu_cs_p2_syncobj_out(struct amdgpu_cs_parser *p, struct amdgpu_cs_chunk *chunk) { struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata; - unsigned num_deps; + unsigned int num_deps; int i; num_deps = chunk->length_dw * 4 / @@ -536,7 +540,7 @@ static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p, struct amdgpu_cs_chunk *chunk) { struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata; - unsigned num_deps; + unsigned int num_deps; int i; num_deps = chunk->length_dw * 4 / @@ -575,6 +579,26 @@ static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p, return 0; } +static int amdgpu_cs_p2_shadow(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_cp_gfx_shadow *shadow = chunk->kdata; + int i; + + if (shadow->flags & ~AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW) + return -EINVAL; + + for (i = 0; i < p->gang_size; ++i) { + p->jobs[i]->shadow_va = shadow->shadow_va; + p->jobs[i]->csa_va = shadow->csa_va; + p->jobs[i]->gds_va = shadow->gds_va; + p->jobs[i]->init_shadow = + shadow->flags & AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW; + } + + return 0; +} + static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p) { unsigned int ce_preempt = 0, de_preempt = 0; @@ -617,6 +641,11 @@ static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p) if (r) return r; break; + case AMDGPU_CHUNK_ID_CP_GFX_SHADOW: + r = amdgpu_cs_p2_shadow(p, chunk); + if (r) + return r; + break; } } @@ -729,6 +758,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, if (used_vis_vram < total_vis_vram) { u64 free_vis_vram = total_vis_vram - used_vis_vram; + adev->mm_stats.accum_us_vis = min(adev->mm_stats.accum_us_vis + increment_us, us_upper_bound); @@ -1047,9 +1077,8 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p, /* the IB should be reserved at this point */ r = amdgpu_bo_kmap(aobj, (void **)&kptr); - if (r) { + if (r) return r; - } kptr += va_start - (m->start * AMDGPU_GPU_PAGE_SIZE); @@ -1356,7 +1385,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, /* Cleanup the parser structure */ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) { - unsigned i; + unsigned int i; amdgpu_sync_free(&parser->sync); for (i = 0; i < parser->num_post_deps; i++) { |