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/gfx_v6_0.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/gfx_v6_0.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 33 |
1 files changed, 17 insertions, 16 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index c41219e23151..da6caff78c22 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -1285,7 +1285,7 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) } static void gfx_v6_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, - u32 sh_num, u32 instance) + u32 sh_num, u32 instance, int xcc_id) { u32 data; @@ -1438,12 +1438,12 @@ static void gfx_v6_0_write_harvested_raster_configs(struct amdgpu_device *adev, } /* GRBM_GFX_INDEX has a different offset on SI */ - gfx_v6_0_select_se_sh(adev, se, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, se, 0xffffffff, 0xffffffff, 0); WREG32(mmPA_SC_RASTER_CONFIG, raster_config_se); } /* GRBM_GFX_INDEX has a different offset on SI */ - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); } static void gfx_v6_0_setup_rb(struct amdgpu_device *adev) @@ -1459,14 +1459,14 @@ static void gfx_v6_0_setup_rb(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff, 0); data = gfx_v6_0_get_rb_active_bitmap(adev); active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * rb_bitmap_width_per_sh); } } - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); adev->gfx.config.backend_enable_mask = active_rbs; adev->gfx.config.num_rbs = hweight32(active_rbs); @@ -1487,7 +1487,7 @@ static void gfx_v6_0_setup_rb(struct amdgpu_device *adev) /* cache the values for userspace */ for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff, 0); adev->gfx.config.rb_config[i][j].rb_backend_disable = RREG32(mmCC_RB_BACKEND_DISABLE); adev->gfx.config.rb_config[i][j].user_rb_backend_disable = @@ -1496,7 +1496,7 @@ static void gfx_v6_0_setup_rb(struct amdgpu_device *adev) RREG32(mmPA_SC_RASTER_CONFIG); } } - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); mutex_unlock(&adev->grbm_idx_mutex); } @@ -1535,7 +1535,7 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff, 0); data = RREG32(mmSPI_STATIC_THREAD_MGMT_3); active_cu = gfx_v6_0_get_cu_enabled(adev); @@ -1550,7 +1550,7 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) } } } - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); mutex_unlock(&adev->grbm_idx_mutex); } @@ -2391,7 +2391,7 @@ static void gfx_v6_0_enable_lbpw(struct amdgpu_device *adev, bool enable) WREG32_FIELD(RLC_LB_CNTL, LOAD_BALANCE_ENABLE, enable ? 1 : 0); if (!enable) { - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); WREG32(mmSPI_LB_CU_MASK, 0x00ff); } } @@ -2968,7 +2968,7 @@ static void wave_read_regs(struct amdgpu_device *adev, uint32_t simd, *(out++) = RREG32(mmSQ_IND_DATA); } -static void gfx_v6_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields) +static void gfx_v6_0_read_wave_data(struct amdgpu_device *adev, uint32_t xcc_id, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields) { /* type 0 wave data */ dst[(*no_fields)++] = 0; @@ -2993,7 +2993,7 @@ static void gfx_v6_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, u dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_MODE); } -static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd, +static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t xcc_id, uint32_t simd, uint32_t wave, uint32_t start, uint32_t size, uint32_t *dst) { @@ -3003,7 +3003,7 @@ static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd, } static void gfx_v6_0_select_me_pipe_q(struct amdgpu_device *adev, - u32 me, u32 pipe, u32 q, u32 vm) + u32 me, u32 pipe, u32 q, u32 vm, u32 xcc_id) { DRM_INFO("Not implemented\n"); } @@ -3028,6 +3028,7 @@ static int gfx_v6_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + adev->gfx.xcc_mask = 1; adev->gfx.num_gfx_rings = GFX6_NUM_GFX_RINGS; adev->gfx.num_compute_rings = min(amdgpu_gfx_get_num_kcq(adev), GFX6_NUM_COMPUTE_RINGS); @@ -3073,7 +3074,7 @@ static int gfx_v6_0_sw_init(void *handle) ring = &adev->gfx.gfx_ring[i]; ring->ring_obj = NULL; sprintf(ring->name, "gfx"); - r = amdgpu_ring_init(adev, ring, 1024, + r = amdgpu_ring_init(adev, ring, 2048, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, AMDGPU_RING_PRIO_DEFAULT, NULL); @@ -3571,7 +3572,7 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev) mask = 1; ao_bitmap = 0; counter = 0; - gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff, 0); if (i < 4 && j < 2) gfx_v6_0_set_user_cu_inactive_bitmap( adev, disable_masks[i * 2 + j]); @@ -3593,7 +3594,7 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev) } } - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0); mutex_unlock(&adev->grbm_idx_mutex); cu_info->number = active_cu_number; |