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/mes_v11_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/mes_v11_0.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 59 |
1 files changed, 34 insertions, 25 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 45280f047180..1bdaa00c0b46 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -164,7 +164,7 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, { struct amdgpu_device *adev = mes->adev; union MESAPI__ADD_QUEUE mes_add_queue_pkt; - struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0]; + struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB(0)]; uint32_t vm_cntx_cntl = hub->vm_cntx_cntl; memset(&mes_add_queue_pkt, 0, sizeof(mes_add_queue_pkt)); @@ -202,17 +202,14 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.gws_size = input->gws_size; mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; + mes_add_queue_pkt.trap_en = input->trap_en; + mes_add_queue_pkt.skip_process_ctx_clear = input->skip_process_ctx_clear; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; mes_add_queue_pkt.gds_size = input->queue_size; - if (!(((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 4) && - (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) && - (adev->ip_versions[GC_HWIP][0] <= IP_VERSION(11, 0, 3)))) - mes_add_queue_pkt.trap_en = 1; - /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; mes_add_queue_pkt.gds_size = input->queue_size; @@ -339,6 +336,19 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes, misc_pkt.wait_reg_mem.reg_offset1 = input->wrm_reg.reg0; misc_pkt.wait_reg_mem.reg_offset2 = input->wrm_reg.reg1; break; + case MES_MISC_OP_SET_SHADER_DEBUGGER: + misc_pkt.opcode = MESAPI_MISC__SET_SHADER_DEBUGGER; + misc_pkt.set_shader_debugger.process_context_addr = + input->set_shader_debugger.process_context_addr; + misc_pkt.set_shader_debugger.flags.u32all = + input->set_shader_debugger.flags.u32all; + misc_pkt.set_shader_debugger.spi_gdbg_per_vmid_cntl = + input->set_shader_debugger.spi_gdbg_per_vmid_cntl; + memcpy(misc_pkt.set_shader_debugger.tcp_watch_cntl, + input->set_shader_debugger.tcp_watch_cntl, + sizeof(misc_pkt.set_shader_debugger.tcp_watch_cntl)); + misc_pkt.set_shader_debugger.trap_en = input->set_shader_debugger.trap_en; + break; default: DRM_ERROR("unsupported misc op (%d) \n", input->op); return -EINVAL; @@ -704,6 +714,8 @@ static int mes_v11_0_mqd_init(struct amdgpu_ring *ring) uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr; uint32_t tmp; + memset(mqd, 0, sizeof(*mqd)); + mqd->header = 0xC0310800; mqd->compute_pipelinestat_enable = 0x00000001; mqd->compute_static_thread_mgmt_se0 = 0xffffffff; @@ -797,6 +809,7 @@ static int mes_v11_0_mqd_init(struct amdgpu_ring *ring) mqd->cp_hqd_iq_timer = regCP_HQD_IQ_TIMER_DEFAULT; mqd->cp_hqd_quantum = regCP_HQD_QUANTUM_DEFAULT; + amdgpu_device_flush_hdp(ring->adev, NULL); return 0; } @@ -864,8 +877,8 @@ static void mes_v11_0_queue_init_register(struct amdgpu_ring *ring) static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev) { - struct amdgpu_kiq *kiq = &adev->gfx.kiq; - struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring; + struct amdgpu_kiq *kiq = &adev->gfx.kiq[0]; + struct amdgpu_ring *kiq_ring = &adev->gfx.kiq[0].ring; int r; if (!kiq->pmf || !kiq->pmf->kiq_map_queues) @@ -879,12 +892,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev) kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring); - r = amdgpu_ring_test_ring(kiq_ring); - if (r) { - DRM_ERROR("kfq enable failed\n"); - kiq_ring->sched.ready = false; - } - return r; + return amdgpu_ring_test_helper(kiq_ring); } static int mes_v11_0_queue_init(struct amdgpu_device *adev, @@ -894,7 +902,7 @@ static int mes_v11_0_queue_init(struct amdgpu_device *adev, int r; if (pipe == AMDGPU_MES_KIQ_PIPE) - ring = &adev->gfx.kiq.ring; + ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) ring = &adev->mes.ring; else @@ -961,9 +969,9 @@ static int mes_v11_0_kiq_ring_init(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - spin_lock_init(&adev->gfx.kiq.ring_lock); + spin_lock_init(&adev->gfx.kiq[0].ring_lock); - ring = &adev->gfx.kiq.ring; + ring = &adev->gfx.kiq[0].ring; ring->me = 3; ring->pipe = 1; @@ -989,7 +997,7 @@ static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev, struct amdgpu_ring *ring; if (pipe == AMDGPU_MES_KIQ_PIPE) - ring = &adev->gfx.kiq.ring; + ring = &adev->gfx.kiq[0].ring; else if (pipe == AMDGPU_MES_SCHED_PIPE) ring = &adev->mes.ring; else @@ -999,6 +1007,7 @@ static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev, return 0; r = amdgpu_bo_create_kernel(adev, mqd_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT, &ring->mqd_obj, &ring->mqd_gpu_addr, &ring->mqd_ptr); if (r) { @@ -1074,15 +1083,15 @@ static int mes_v11_0_sw_fini(void *handle) amdgpu_ucode_release(&adev->mes.fw[pipe]); } - amdgpu_bo_free_kernel(&adev->gfx.kiq.ring.mqd_obj, - &adev->gfx.kiq.ring.mqd_gpu_addr, - &adev->gfx.kiq.ring.mqd_ptr); + amdgpu_bo_free_kernel(&adev->gfx.kiq[0].ring.mqd_obj, + &adev->gfx.kiq[0].ring.mqd_gpu_addr, + &adev->gfx.kiq[0].ring.mqd_ptr); amdgpu_bo_free_kernel(&adev->mes.ring.mqd_obj, &adev->mes.ring.mqd_gpu_addr, &adev->mes.ring.mqd_ptr); - amdgpu_ring_fini(&adev->gfx.kiq.ring); + amdgpu_ring_fini(&adev->gfx.kiq[0].ring); amdgpu_ring_fini(&adev->mes.ring); if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { @@ -1175,7 +1184,7 @@ static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev) mes_v11_0_enable(adev, true); - mes_v11_0_kiq_setting(&adev->gfx.kiq.ring); + mes_v11_0_kiq_setting(&adev->gfx.kiq[0].ring); r = mes_v11_0_queue_init(adev, AMDGPU_MES_KIQ_PIPE); if (r) @@ -1196,7 +1205,7 @@ static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev) } if (amdgpu_sriov_vf(adev)) { - mes_v11_0_kiq_dequeue(&adev->gfx.kiq.ring); + mes_v11_0_kiq_dequeue(&adev->gfx.kiq[0].ring); mes_v11_0_kiq_clear(adev); } @@ -1244,7 +1253,7 @@ static int mes_v11_0_hw_init(void *handle) * MES uses KIQ ring exclusively so driver cannot access KIQ ring * with MES enabled. */ - adev->gfx.kiq.ring.sched.ready = false; + adev->gfx.kiq[0].ring.sched.ready = false; adev->mes.ring.sched.ready = true; return 0; |