diff options
Diffstat (limited to 'drivers/gpu')
91 files changed, 1178 insertions, 381 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c index 6a364357522b..b0299d861903 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c @@ -92,7 +92,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) return NULL; fence = container_of(f, struct amdgpu_amdkfd_fence, base); - if (f->ops == &amdkfd_fence_ops) + if (rcu_access_pointer(f->ops) == &amdkfd_fence_ops) return fence; return NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 35fe2c974699..f0f516a79424 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -3096,7 +3096,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * process_info->eviction_fence = new_fence; replace_eviction_fence(ef, dma_fence_get(&new_fence->base)); } else { - WARN_ONCE(*ef != &process_info->eviction_fence->base, + WARN_ONCE(rcu_access_pointer(*ef) != &process_info->eviction_fence->base, "KFD eviction fence doesn't match KGD process_info"); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index e714cee2997a..5445f75741b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1177,19 +1177,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); } - if (adev->debug_vm) { - /* Invalidate all BOs to test for userspace bugs */ - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct amdgpu_bo *bo = e->bo; - - /* ignore duplicates */ - if (!bo) - continue; - - amdgpu_vm_bo_invalidate(bo, false); - } - } - return 0; } @@ -1378,6 +1365,8 @@ 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) { + struct amdgpu_device *adev = parser->adev; + struct amdgpu_bo_list_entry *e; unsigned int i; amdgpu_sync_free(&parser->sync); @@ -1393,8 +1382,21 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) if (parser->ctx) amdgpu_ctx_put(parser->ctx); - if (parser->bo_list) + if (parser->bo_list) { + if (adev->debug_vm) { + /* Invalidate all BOs to test for userspace bugs */ + amdgpu_bo_list_for_each_entry(e, parser->bo_list) { + struct amdgpu_bo *bo = e->bo; + + /* ignore duplicates */ + if (!bo) + continue; + + amdgpu_vm_bo_invalidate(bo, false); + } + } amdgpu_bo_list_put(parser->bo_list); + } for (i = 0; i < parser->nchunks; i++) kvfree(parser->chunks[i].kdata); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 389bad724273..df2588642817 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -43,6 +43,11 @@ #if defined(CONFIG_DEBUG_FS) +/* Encode milliwatts in the raw Q24.8 sensor report format used by UMR. */ +#define AMDGPU_DEBUGFS_PWR_MW_TO_Q24_8(power_mw) \ + DIV_ROUND_CLOSEST_ULL((u64)(power_mw) * BIT(8), \ + MILLIWATT_PER_WATT) + /** * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes * @@ -1104,6 +1109,10 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf, return r; } + if (idx == AMDGPU_PP_SENSOR_GPU_AVG_POWER || + idx == AMDGPU_PP_SENSOR_GPU_INPUT_POWER) + values[0] = AMDGPU_DEBUGFS_PWR_MW_TO_Q24_8(values[0]); + if (size > valuesize) { amdgpu_virt_disable_access_debugfs(adev); return -EINVAL; @@ -1319,8 +1328,8 @@ err: * @size: Number of bytes to read * @pos: Offset to seek to * - * Read the last residency value logged. It doesn't auto update, one needs to - * stop logging before getting the current value. + * Read a live GFXOFF residency sample from firmware. One needs to start logging + * before getting the current value. */ static ssize_t amdgpu_debugfs_gfxoff_residency_read(struct file *f, char __user *buf, size_t size, loff_t *pos) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 2860f12915c0..5e83edbd313b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -2304,6 +2304,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &psp_v14_0_ip_block); break; case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 5): case IP_VERSION(15, 0, 9): amdgpu_device_ip_block_add(adev, &psp_v15_0_ip_block); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 4c0c77eafbd1..1aed121f4ddb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2908,6 +2908,19 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return 0; } +static void amdgpu_restore_umd_profile_pstate_after_runpm(struct amdgpu_device *adev) +{ + enum amd_dpm_forced_level level; + uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD | + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK | + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK | + AMD_DPM_FORCED_LEVEL_PROFILE_PEAK; + + level = amdgpu_dpm_get_performance_level(adev); + if (level & profile_mode_mask) + amdgpu_asic_update_umd_stable_pstate(adev, true); +} + static int amdgpu_pmops_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2952,6 +2965,8 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) if (adev->pm.rpm_mode == AMDGPU_RUNPM_PX) drm_dev->switch_power_state = DRM_SWITCH_POWER_ON; + + amdgpu_restore_umd_profile_pstate_after_runpm(adev); adev->in_runpm = false; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 71272f40feef..8bb9c198ddec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1210,7 +1210,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return -EINVAL; } } - ui32 >>= 8; + ui32 /= MILLIWATT_PER_WATT; break; case AMDGPU_INFO_SENSOR_GPU_INPUT_POWER: /* get input GPU power */ @@ -1219,7 +1219,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) (void *)&ui32, &ui32_size)) { return -EINVAL; } - ui32 >>= 8; + ui32 /= MILLIWATT_PER_WATT; break; case AMDGPU_INFO_SENSOR_VDDNB: /* get VDDNB in millivolts */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index e0c0d7872e45..7139cb3b2db5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -275,6 +275,7 @@ static int psp_early_init(struct amdgpu_ip_block *ip_block) psp->boot_time_tmr = false; break; case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 5): case IP_VERSION(15, 0, 9): psp_v15_0_0_set_psp_funcs(psp); psp->boot_time_tmr = false; @@ -1222,6 +1223,33 @@ int psp_memory_partition(struct psp_context *psp, int mode) return ret; } +int psp_set_mmhub_eco_sec_level(struct amdgpu_device *adev) +{ + int ret; + struct psp_context *psp = &adev->psp; + struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp); + + cmd->cmd_id = GFX_CMD_ID_SET_MMHUB_ECO_SEC_LEVEL; + + ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); + if (ret) { + dev_err(psp->adev->dev, + "PSP request failed to set mmuhub eco sec level with ret=%d\n", ret); + release_psp_cmd_buf(psp); + return ret; + } + + if (cmd->resp.status) { + dev_err(psp->adev->dev, + "MMHUB ECO SEC LEVEL command 0x%x failed, PSP response status: 0x%X\n", + cmd->cmd_id, cmd->resp.status); + ret = -EIO; + } + release_psp_cmd_buf(psp); + + return ret; +} + static int psp_ptl_fmt_verify(struct psp_context *psp, enum amdgpu_ptl_fmt fmt, uint32_t *ptl_fmt) { @@ -3476,8 +3504,10 @@ static int psp_load_non_psp_fw(struct psp_context *psp) amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 0) || amdgpu_ip_version(adev, MP0_HWIP, 0) == - IP_VERSION(15, 0, 8) || + IP_VERSION(15, 0, 5) || amdgpu_ip_version(adev, MP0_HWIP, 0) == + IP_VERSION(15, 0, 8) || + amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 9)) && (ucode->ucode_id == AMDGPU_UCODE_ID_SDMA1 || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA2 || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 2d838b1b2b11..3d7744d60fac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -656,5 +656,6 @@ int amdgpu_psp_reg_program_no_ring(struct psp_context *psp, uint32_t val, void amdgpu_psp_debugfs_init(struct amdgpu_device *adev); int amdgpu_psp_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type *type); +int psp_set_mmhub_eco_sec_level(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index eb8bbfc7e6d9..5fc91f45db5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2173,6 +2173,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) gtt_size = configured_size; } + /* Cap GTT so that it does not exceed total physical RAM. */ + if (adev->flags & AMD_IS_APU) { + u64 phys_ram = (u64)totalram_pages() << PAGE_SHIFT; + + if (gtt_size > phys_ram) { + gtt_size = phys_ram; + dev_info(adev->dev, + "Capping GTT to %uM to not exceed available system memory\n", + (unsigned int)(gtt_size / (1024 * 1024))); + } + } + /* Initialize GTT memory pool */ r = amdgpu_gtt_mgr_init(adev, gtt_size); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 572f2949cb64..3efe1ae27386 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -965,6 +965,7 @@ amdgpu_userq_vm_validate(struct amdgpu_userq_mgr *uq_mgr) struct amdgpu_vm *vm = &fpriv->vm; unsigned long key, tmp_key; struct amdgpu_bo_va *bo_va; + struct amdgpu_usermode_queue *queue; struct amdgpu_bo *bo; struct drm_exec exec; struct xarray xa; @@ -1080,6 +1081,24 @@ retry_lock: dma_fence_wait(bo_va->last_pt_update, false); dma_fence_wait(vm->last_update, false); + xa_for_each(&uq_mgr->userq_xa, tmp_key, queue) { + bo = queue->wptr_obj.obj; + if (!bo) { + ret = -EINVAL; + goto unlock_all; + } + + ret = amdgpu_ttm_alloc_gart(&bo->tbo); + if (unlikely(ret)) { + drm_file_err(uq_mgr->file, + "failed to bind wptr bo to gart on resume, qid=%lu ret=%d\n", + tmp_key, ret); + goto unlock_all; + } + + queue->wptr_obj.gpu_addr = amdgpu_bo_gpu_offset(bo); + } + ret = amdgpu_evf_mgr_rearm(&fpriv->evf_mgr, &exec); if (ret) drm_file_err(uq_mgr->file, "Failed to replace eviction fence\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f224d33c4bc4..dc6a9d7dd0b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1553,6 +1553,8 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, struct amdgpu_sync sync; int r; + if (list_empty(&vm->freed)) + return 0; /* * Implicitly sync to command submissions in the same VM before diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index d80f01c0e754..b02561f41b58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -379,7 +379,7 @@ struct amd_sriov_msg_vf2pf_info { struct { uint8_t id; uint32_t version; - } ucode_info[AMD_SRIOV_MSG_RESERVE_UCODE]; + } __packed ucode_info[AMD_SRIOV_MSG_RESERVE_UCODE]; uint64_t dummy_page_addr; /* FB allocated for guest MES to record UQ info */ uint64_t mes_info_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c index e7546816baba..2c3e6d9f52a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c @@ -399,6 +399,25 @@ static void jpeg_v5_3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) } /** + * jpeg_v5_3_0_set_mmhub_eco_sec_level - set jpeg sec lvl reg + * + * @adev: amdgpu_device pointer + * + * request psp to set secure lvl + */ +static int jpeg_v5_3_0_set_mmhub_eco_sec_level(struct amdgpu_device *adev) +{ + int r = 0; + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + /* Request to PSP to program JPEG secure lvl */ + r = psp_set_mmhub_eco_sec_level(adev); + } + + return r; +} + +/** * jpeg_v5_3_0_start - start JPEG block * * @adev: amdgpu_device pointer @@ -423,6 +442,11 @@ static int jpeg_v5_3_0_start(struct amdgpu_device *adev) if (r) return r; + /* program JPEG secure lvl register */ + r = jpeg_v5_3_0_set_mmhub_eco_sec_level(adev); + if (r) + return r; + /* JPEG disable CGC */ jpeg_v5_3_0_disable_clock_gating(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index 16625c31bfd3..4e44a581a78a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -70,27 +70,23 @@ mes_userq_create_wptr_mapping(struct amdgpu_device *adev, ret = -EINVAL; goto fail_map; } - - /* TODO use eviction fence instead of pinning. */ - ret = amdgpu_bo_pin(wptr_obj->obj, AMDGPU_GEM_DOMAIN_GTT); + /* Keep WPTR BO under eviction-fence control instead of pinning. */ + ret = amdgpu_evf_mgr_attach_fence(&uq_mgr_to_fpriv(uq_mgr)->evf_mgr, wptr_obj->obj); if (ret) { - DRM_ERROR("Failed to pin wptr bo. ret %d\n", ret); + DRM_ERROR("Failed to attach eviction fence to wptr bo. ret %d\n", ret); goto fail_map; } ret = amdgpu_ttm_alloc_gart(&wptr_obj->obj->tbo); if (ret) { - DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret); - goto fail_alloc_gart; + DRM_ERROR("Failed to bind wptr bo to GART. ret %d\n", ret); + goto fail_map; } queue->wptr_obj.gpu_addr = amdgpu_bo_gpu_offset(wptr_obj->obj); drm_exec_fini(&exec); return 0; - -fail_alloc_gart: - amdgpu_bo_unpin(wptr_obj->obj); fail_map: amdgpu_bo_unref(&wptr_obj->obj); fail_lock: @@ -468,9 +464,6 @@ static void mes_userq_mqd_destroy(struct amdgpu_usermode_queue *queue) amdgpu_bo_free_kernel(&queue->mqd.obj, &queue->mqd.gpu_addr, &queue->mqd.cpu_ptr); - amdgpu_bo_reserve(queue->wptr_obj.obj, true); - amdgpu_bo_unpin(queue->wptr_obj.obj); - amdgpu_bo_unreserve(queue->wptr_obj.obj); amdgpu_bo_unref(&queue->wptr_obj.obj); } diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c index c78f0598637f..000516b5845a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c @@ -30,70 +30,76 @@ #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h" #include <uapi/linux/kfd_ioctl.h> -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL_nbif_4_10 0x4f0aeb -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL1_nbif_4_10 0x4f0aec -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL1_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL_nbif_4_10 0x4f0aed -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL1_nbif_4_10 0x4f0aee -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL1_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL_nbif_4_10 0x4f0aef -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL1_nbif_4_10 0x4f0af0 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL1_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL_nbif_4_10 0x4f0af1 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL1_nbif_4_10 0x4f0af2 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL1_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL_nbif_4_10 0x4f0af3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL1_nbif_4_10 0x4f0af4 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL1_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL_nbif_4_10 0x4f0af5 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL_nbif_4_10_BASE_IDX 3 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL1_nbif_4_10 0x4f0af6 -#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL1_nbif_4_10_BASE_IDX 3 -#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbif_4_10 0x0021 -#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbif_4_10_BASE_IDX 2 - -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_HIGH_nbio_7_11_5 0x8e13 -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_HIGH_nbio_7_11_5_BASE_IDX 5 -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_LOW_nbio_7_11_5 0x8e14 -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_LOW_nbio_7_11_5_BASE_IDX 5 -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_CNTL_nbio_7_11_5 0x8e15 -#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_CNTL_nbio_7_11_5_BASE_IDX 5 - -#define regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5 0x8e4d -#define regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 5 -#define regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5 0x8e4e -#define regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 5 - -#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5 0xd000 -#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5_BASE_IDX 5 - -#define regBIF_BX0_BIF_FB_EN_nbio_7_11_5 0x8e20 -#define regBIF_BX0_BIF_FB_EN_nbio_7_11_5_BASE_IDX 5 - -#define regBIF_BX0_INTERRUPT_CNTL_nbio_7_11_5 0x8e11 -#define regBIF_BX0_INTERRUPT_CNTL_nbio_7_11_5_BASE_IDX 5 -#define regBIF_BX0_INTERRUPT_CNTL2_nbio_7_11_5 0x8e12 -#define regBIF_BX0_INTERRUPT_CNTL2_nbio_7_11_5_BASE_IDX 5 - -#define regBIF_BX_PF0_GPU_HDP_FLUSH_REQ_nbio_7_11_5 0x8e26 -#define regBIF_BX_PF0_GPU_HDP_FLUSH_REQ_nbio_7_11_5_BASE_IDX 5 -#define regBIF_BX_PF0_GPU_HDP_FLUSH_DONE_nbio_7_11_5 0x8e27 -#define regBIF_BX_PF0_GPU_HDP_FLUSH_DONE_nbio_7_11_5_BASE_IDX 5 - -#define regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5 0x8e17 -#define regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 5 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL_nbif_4_10 0x4f0aeb +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL1_nbif_4_10 0x4f0aec +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_0_CTRL1_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL_nbif_4_10 0x4f0aed +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL1_nbif_4_10 0x4f0aee +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_1_CTRL1_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL_nbif_4_10 0x4f0aef +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL1_nbif_4_10 0x4f0af0 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_2_CTRL1_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL_nbif_4_10 0x4f0af1 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL1_nbif_4_10 0x4f0af2 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_3_CTRL1_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL_nbif_4_10 0x4f0af3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL1_nbif_4_10 0x4f0af4 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_4_CTRL1_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL_nbif_4_10 0x4f0af5 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL_nbif_4_10_BASE_IDX 3 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL1_nbif_4_10 0x4f0af6 +#define regGDC_S2A0_S2A_DOORBELL_ENTRY_5_CTRL1_nbif_4_10_BASE_IDX 3 +#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbif_4_10 0x0021 +#define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbif_4_10_BASE_IDX 2 + +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_HIGH_nbio_7_11_5 0x8e13 +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_HIGH_nbio_7_11_5_BASE_IDX 5 +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_LOW_nbio_7_11_5 0x8e14 +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_BASE_LOW_nbio_7_11_5_BASE_IDX 5 +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_CNTL_nbio_7_11_5 0x8e15 +#define regBIF_BX_PF0_DOORBELL_SELFRING_GPA_APER_CNTL_nbio_7_11_5_BASE_IDX 5 + +#define regBIF_BX1_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5 0x012d +#define regBIF_BX1_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 2 +#define regBIF_BX1_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5 0x012e +#define regBIF_BX1_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 2 + +#define regRCC_STRAP1_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5 0x0021 +#define regRCC_STRAP1_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5_BASE_IDX 2 + +#define regBIF_BX1_BIF_FB_EN_nbio_7_11_5 0x0100 +#define regBIF_BX1_BIF_FB_EN_nbio_7_11_5_BASE_IDX 2 + +#define regBIF_BX1_INTERRUPT_CNTL_nbio_7_11_5 0x00f1 +#define regBIF_BX1_INTERRUPT_CNTL_nbio_7_11_5_BASE_IDX 2 +#define regBIF_BX1_INTERRUPT_CNTL2_nbio_7_11_5 0x00f2 +#define regBIF_BX1_INTERRUPT_CNTL2_nbio_7_11_5_BASE_IDX 2 + +#define regBIF_BX_PF1_GPU_HDP_FLUSH_REQ_nbio_7_11_5 0x0106 +#define regBIF_BX_PF1_GPU_HDP_FLUSH_REQ_nbio_7_11_5_BASE_IDX 2 +#define regBIF_BX_PF1_GPU_HDP_FLUSH_DONE_nbio_7_11_5 0x0107 +#define regBIF_BX_PF1_GPU_HDP_FLUSH_DONE_nbio_7_11_5_BASE_IDX 2 + +#define regBIF_BX_PF1_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5 0x00f7 +#define regBIF_BX_PF1_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5_BASE_IDX 2 + +//BIF_BX1_BIF_FB_EN +#define BIF_BX1_BIF_FB_EN__FB_READ_EN__SHIFT_nbio_7_11_5 0x0 +#define BIF_BX1_BIF_FB_EN__FB_WRITE_EN__SHIFT_nbio_7_11_5 0x1 +#define BIF_BX1_BIF_FB_EN__FB_READ_EN_MASK_nbio_7_11_5 0x00000001L +#define BIF_BX1_BIF_FB_EN__FB_WRITE_EN_MASK_nbio_7_11_5 0x00000002L static void nbif_v6_3_1_remap_hdp_registers(struct amdgpu_device *adev) { if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) { - WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5, + WREG32_SOC15(NBIO, 0, regBIF_BX1_REMAP_HDP_MEM_FLUSH_CNTL_nbio_7_11_5, adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL); - WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5, + WREG32_SOC15(NBIO, 0, regBIF_BX1_REMAP_HDP_REG_FLUSH_CNTL_nbio_7_11_5, adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL); } else { WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL, @@ -110,7 +116,7 @@ static u32 nbif_v6_3_1_get_rev_id(struct amdgpu_device *adev) if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 4)) tmp = RREG32_SOC15(NBIO, 0, regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbif_4_10); else if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) - tmp = RREG32_SOC15(NBIO, 0, regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5); + tmp = RREG32_SOC15(NBIO, 0, regRCC_STRAP1_RCC_DEV0_EPF0_STRAP0_nbio_7_11_5); else tmp = RREG32_SOC15(NBIO, 0, regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0); @@ -124,11 +130,11 @@ static void nbif_v6_3_1_mc_access_enable(struct amdgpu_device *adev, bool enable { if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) { if (enable) - WREG32_SOC15(NBIO, 0, regBIF_BX0_BIF_FB_EN_nbio_7_11_5, - BIF_BX0_BIF_FB_EN__FB_READ_EN_MASK | - BIF_BX0_BIF_FB_EN__FB_WRITE_EN_MASK); + WREG32_SOC15(NBIO, 0, regBIF_BX1_BIF_FB_EN_nbio_7_11_5, + BIF_BX1_BIF_FB_EN__FB_READ_EN_MASK_nbio_7_11_5 | + BIF_BX1_BIF_FB_EN__FB_WRITE_EN_MASK_nbio_7_11_5); else - WREG32_SOC15(NBIO, 0, regBIF_BX0_BIF_FB_EN_nbio_7_11_5, 0); + WREG32_SOC15(NBIO, 0, regBIF_BX1_BIF_FB_EN_nbio_7_11_5, 0); } else { if (enable) WREG32_SOC15(NBIO, 0, regBIF_BX0_BIF_FB_EN, @@ -383,12 +389,12 @@ static void nbif_v6_3_1_ih_control(struct amdgpu_device *adev) /* setup interrupt control */ if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) - WREG32_SOC15(NBIO, 0, regBIF_BX0_INTERRUPT_CNTL2_nbio_7_11_5, + WREG32_SOC15(NBIO, 0, regBIF_BX1_INTERRUPT_CNTL2_nbio_7_11_5, adev->dummy_page_addr >> 8); else WREG32_SOC15(NBIO, 0, regBIF_BX0_INTERRUPT_CNTL2, adev->dummy_page_addr >> 8); - interrupt_cntl = RREG32_SOC15(NBIO, 0, regBIF_BX0_INTERRUPT_CNTL_nbio_7_11_5); + interrupt_cntl = RREG32_SOC15(NBIO, 0, regBIF_BX1_INTERRUPT_CNTL_nbio_7_11_5); /* * BIF_BX0_INTERRUPT_CNTL__IH_DUMMY_RD_OVERRIDE_MASK=0 - dummy read disabled with msi, enabled without msi * BIF_BX0_INTERRUPT_CNTL__IH_DUMMY_RD_OVERRIDE_MASK=1 - dummy read controlled by IH_DUMMY_RD_EN @@ -401,7 +407,7 @@ static void nbif_v6_3_1_ih_control(struct amdgpu_device *adev) IH_REQ_NONSNOOP_EN, 0); if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) - WREG32_SOC15(NBIO, 0, regBIF_BX0_INTERRUPT_CNTL_nbio_7_11_5, interrupt_cntl); + WREG32_SOC15(NBIO, 0, regBIF_BX1_INTERRUPT_CNTL_nbio_7_11_5, interrupt_cntl); else WREG32_SOC15(NBIO, 0, regBIF_BX0_INTERRUPT_CNTL, interrupt_cntl); } @@ -427,7 +433,7 @@ nbif_v6_3_1_get_clockgating_state(struct amdgpu_device *adev, static u32 nbif_v6_3_1_get_hdp_flush_req_offset(struct amdgpu_device *adev) { if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) - return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_GPU_HDP_FLUSH_REQ_nbio_7_11_5); + return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF1_GPU_HDP_FLUSH_REQ_nbio_7_11_5); else return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_GPU_HDP_FLUSH_REQ); } @@ -435,7 +441,7 @@ static u32 nbif_v6_3_1_get_hdp_flush_req_offset(struct amdgpu_device *adev) static u32 nbif_v6_3_1_get_hdp_flush_done_offset(struct amdgpu_device *adev) { if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) - return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_GPU_HDP_FLUSH_DONE_nbio_7_11_5); + return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF1_GPU_HDP_FLUSH_DONE_nbio_7_11_5); else return SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_GPU_HDP_FLUSH_DONE); } @@ -622,7 +628,7 @@ static void nbif_v6_3_1_set_reg_remap(struct amdgpu_device *adev) } else { if (amdgpu_ip_version(adev, NBIO_HWIP, 0) == IP_VERSION(7, 11, 5)) adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, - regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5) << 2; + regBIF_BX_PF1_HDP_MEM_COHERENCY_FLUSH_CNTL_nbio_7_11_5) << 2; else adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index ac34bac3c839..ad618b78685f 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -110,6 +110,7 @@ enum psp_gfx_cmd_id GFX_CMD_ID_PERF_HW = 0x0000004C, /* performance monitor */ GFX_CMD_ID_FB_FW_RESERV_ADDR = 0x00000050, /* Query FW reservation addr */ GFX_CMD_ID_FB_FW_RESERV_EXT_ADDR = 0x00000051, /* Query FW reservation extended addr */ + GFX_CMD_ID_SET_MMHUB_ECO_SEC_LEVEL = 0x0000005D, /* Set MMHUB ECO sec lvls on VCN block */ }; /* PSP boot config sub-commands */ diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c index 2a4d91368ac6..abaa40b6def9 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c @@ -33,9 +33,22 @@ MODULE_FIRMWARE("amdgpu/psp_15_0_0_toc.bin"); MODULE_FIRMWARE("amdgpu/psp_15_0_0_ta.bin"); +MODULE_FIRMWARE("amdgpu/psp_15_0_5_toc.bin"); +MODULE_FIRMWARE("amdgpu/psp_15_0_5_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_15_0_9_toc.bin"); MODULE_FIRMWARE("amdgpu/psp_15_0_9_ta.bin"); +#define regMPASP_PCRU0_MPASP_C2PMSG_64 0x4280 +#define regMPASP_PCRU0_MPASP_C2PMSG_64_BASE_IDX 2 +#define regMPASP_PCRU0_MPASP_C2PMSG_67 0x4283 +#define regMPASP_PCRU0_MPASP_C2PMSG_67_BASE_IDX 2 +#define regMPASP_PCRU0_MPASP_C2PMSG_69 0x4285 +#define regMPASP_PCRU0_MPASP_C2PMSG_69_BASE_IDX 2 +#define regMPASP_PCRU0_MPASP_C2PMSG_70 0x4286 +#define regMPASP_PCRU0_MPASP_C2PMSG_70_BASE_IDX 2 +#define regMPASP_PCRU0_MPASP_C2PMSG_71 0x4287 +#define regMPASP_PCRU0_MPASP_C2PMSG_71_BASE_IDX 2 + static int psp_v15_0_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; @@ -71,14 +84,25 @@ static int psp_v15_0_0_ring_stop(struct psp_context *psp, ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_101), 0x80000000, 0x80000000, false); } else { - /* Write the ring destroy command*/ - WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, - GFX_CTRL_CMD_ID_DESTROY_RINGS); - /* there might be handshake issue with hardware which needs delay */ - mdelay(20); - /* Wait for response flag (bit 31) */ - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), - 0x80000000, 0x80000000, false); + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 5)) { + /* Write the ring destroy command*/ + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_64, + GFX_CTRL_CMD_ID_DESTROY_RINGS); + /* there might be handshake issue with hardware which needs delay */ + mdelay(20); + /* Wait for response flag (bit 31) */ + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_64), + 0x80000000, 0x80000000, false); + } else { + /* Write the ring destroy command*/ + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, + GFX_CTRL_CMD_ID_DESTROY_RINGS); + /* there might be handshake issue with hardware which needs delay */ + mdelay(20); + /* Wait for response flag (bit 31) */ + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), + 0x80000000, 0x80000000, false); + } } return ret; @@ -118,9 +142,10 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp, 0x80000000, 0x8000FFFF, false); } else { - /* Wait for sOS ready for ring creation */ - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), - 0x80000000, 0x80000000, false); + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 5)) { + /* Wait for sOS ready for ring creation */ + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_64), + 0x80000000, 0x80000000, false); if (ret) { DRM_ERROR("Failed to wait for trust OS ready for ring creation\n"); return ret; @@ -128,6 +153,35 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp, /* Write low address of the ring to C2PMSG_69 */ psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_69, psp_ring_reg); + /* Write high address of the ring to C2PMSG_70 */ + psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr); + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_70, psp_ring_reg); + /* Write size of ring to C2PMSG_71 */ + psp_ring_reg = ring->ring_size; + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_71, psp_ring_reg); + /* Write the ring initialization command to C2PMSG_64 */ + psp_ring_reg = ring_type; + psp_ring_reg = psp_ring_reg << 16; + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_64, psp_ring_reg); + + /* there might be handshake issue with hardware which needs delay */ + mdelay(20); + + /* Wait for response flag (bit 31) in C2PMSG_64 */ + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_64), + 0x80000000, 0x8000FFFF, false); + } else { + /* Wait for sOS ready for ring creation */ + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), + 0x80000000, 0x80000000, false); + if (ret) { + DRM_ERROR("Failed to wait for trust OS ready for ring creation\n"); + return ret; + } + + /* Write low address of the ring to C2PMSG_69 */ + psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_69, psp_ring_reg); /* Write high address of the ring to C2PMSG_70 */ psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr); @@ -146,6 +200,7 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp, /* Wait for response flag (bit 31) in C2PMSG_64 */ ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), 0x80000000, 0x8000FFFF, false); + } } return ret; @@ -176,8 +231,12 @@ static uint32_t psp_v15_0_0_ring_get_wptr(struct psp_context *psp) if (amdgpu_sriov_vf(adev)) data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102); - else - data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67); + else { + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 5)) + data = RREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_67); + else + data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67); + } return data; } @@ -190,8 +249,12 @@ static void psp_v15_0_0_ring_set_wptr(struct psp_context *psp, uint32_t value) WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102, value); WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD); - } else - WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value); + } else { + if (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 5)) + WREG32_SOC15(MP0, 0, regMPASP_PCRU0_MPASP_C2PMSG_67, value); + else + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value); + } } static const struct psp_funcs psp_v15_0_0_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index e0b80abcd075..e9d51e992a8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -406,6 +406,7 @@ soc21_asic_reset_method(struct amdgpu_device *adev) case IP_VERSION(14, 0, 4): case IP_VERSION(14, 0, 5): case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 5): case IP_VERSION(15, 0, 9): return AMD_RESET_METHOD_MODE2; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 45580e9c4e0c..886e2c2074a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -796,6 +796,27 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, } /** + * vcn_v5_0_0_set_mmhub_eco_sec_level - set vcn sec lvl reg + * + * @adev: amdgpu_device pointer + * + * request psp to set sec lvl + */ +static int vcn_v5_0_0_set_mmhub_eco_sec_level(struct amdgpu_device *adev) +{ + int r = 0; + + if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(5, 3, 0)) { + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + /* Request to PSP to program VCN secure lvl */ + r = psp_set_mmhub_eco_sec_level(adev); + } + } + + return r; +} + +/** * vcn_v5_0_0_start - VCN start * * @vinst: VCN instance @@ -819,6 +840,11 @@ static int vcn_v5_0_0_start(struct amdgpu_vcn_inst *vinst) fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + /* program VCN secure lvl register */ + r = vcn_v5_0_0_set_mmhub_eco_sec_level(adev); + if (r) + return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) return vcn_v5_0_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index c7edebd2fd8a..e1689b3d2add 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -3109,10 +3109,14 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v goto out; } - /* Check if target is still PTRACED. */ + /* + * Verify debugger has permission to debug target process. + * For cross-process debugging, require active ptrace relationship. + * This applies to ALL operations to prevent unauthorized interference. + */ rcu_read_lock(); - if (target != p && args->op != KFD_IOC_DBG_TRAP_DISABLE - && ptrace_parent(target->lead_thread) != current) { + if (target != p && ptrace_parent(target->lead_thread) != current + && target->debugger_process != p) { pr_err("PID %i is not PTRACED and cannot be debugged\n", args->pid); r = -EPERM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 2a239f45fc24..6e0df685503d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1412,6 +1412,15 @@ int kfd_parse_crat_table(void *crat_image, struct list_head *device_list, break; } + /* Validate subtype fits within remaining image */ + if ((char *)sub_type_hdr + sub_type_hdr->length > + (char *)crat_image + image_len) { + pr_warn("CRAT subtype length %u exceeds image bounds\n", + sub_type_hdr->length); + ret = -EINVAL; + break; + } + if (sub_type_hdr->flags & CRAT_SUBTYPE_FLAGS_ENABLED) { ret = kfd_parse_subtype(sub_type_hdr, device_list); if (ret) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 2e97da597b3d..f705c61bdb1d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -524,6 +524,9 @@ int kfd_criu_restore_event(struct file *devkfd, ret = create_other_event(p, ev, &ev_priv->event_id); break; + default: + ret = -EINVAL; + break; } mutex_unlock(&p->event_mutex); @@ -545,15 +548,27 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, int ret = 0; struct kfd_event *ev; uint32_t ev_id; + uint32_t num_events; - uint32_t num_events = kfd_get_num_events(p); + /* Serialize the count and the walk below against concurrent event + * create/destroy. Those paths take only p->event_mutex, not the + * p->mutex held by the CRIU checkpoint caller, so without this the + * event_idr can grow between kfd_get_num_events() and the loop and the + * walk writes past the ev_privs allocation. + */ + mutex_lock(&p->event_mutex); - if (!num_events) + num_events = kfd_get_num_events(p); + if (!num_events) { + mutex_unlock(&p->event_mutex); return 0; + } ev_privs = kvzalloc(num_events * sizeof(*ev_privs), GFP_KERNEL); - if (!ev_privs) + if (!ev_privs) { + mutex_unlock(&p->event_mutex); return -ENOMEM; + } idr_for_each_entry(&p->event_idr, ev, ev_id) { @@ -594,6 +609,8 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, i++; } + mutex_unlock(&p->event_mutex); + ret = copy_to_user(user_priv_data + *priv_data_offset, ev_privs, num_events * sizeof(*ev_privs)); if (ret) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 9ccbc6e5b27b..503176f00204 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -383,7 +383,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, false); if (retval) { dev_err(dev->adev->dev, "failed to allocate process context bo\n"); - return retval; + goto err_allocate_pqn; } memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index 98a5512b701b..b249e7d1af48 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -288,7 +288,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope } err = kfd_queue_buffer_get(vm, (void *)properties->eop_ring_buffer_address, &properties->eop_buf_bo, - ALIGN(properties->eop_ring_buffer_size, PAGE_SIZE)); + ALIGN((u64)properties->eop_ring_buffer_size, PAGE_SIZE)); if (err) goto out_err_unreserve; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index eaf19ec843e8..1820547b1dde 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9903,25 +9903,6 @@ static void remove_stream(struct amdgpu_device *adev, acrtc->enabled = false; } -static void prepare_flip_isr(struct amdgpu_crtc *acrtc) -{ - - assert_spin_locked(&acrtc->base.dev->event_lock); - WARN_ON(acrtc->event); - - acrtc->event = acrtc->base.state->event; - - /* Set the flip status */ - acrtc->pflip_status = AMDGPU_FLIP_SUBMITTED; - - /* Mark this event as consumed */ - acrtc->base.state->event = NULL; - - drm_dbg_state(acrtc->base.dev, - "crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", - acrtc->crtc_id); -} - static void update_freesync_state_on_stream( struct amdgpu_display_manager *dm, struct dm_crtc_state *new_crtc_state, @@ -10274,17 +10255,47 @@ static void dm_arm_vblank_event(struct amdgpu_crtc *acrtc, return; if (pflip_update) { - drm_crtc_vblank_get(&acrtc->base); WARN_ON(acrtc->pflip_status != AMDGPU_FLIP_NONE); - /* Arm flip completion handling and event delivery after programming. */ - prepare_flip_isr(acrtc); + WARN_ON(acrtc->event); + + acrtc->pflip_status = AMDGPU_FLIP_SUBMITTED; + acrtc->event = acrtc->base.state->event; + acrtc->base.state->event = NULL; + + drm_dbg_state(acrtc->base.dev, + "crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", + acrtc->crtc_id); } else if (cursor_update) { - drm_crtc_vblank_get(&acrtc->base); acrtc->event = acrtc->base.state->event; acrtc->base.state->event = NULL; } } +/** + * dm_arm_vblank_event_pre_programming - Prepare for programming + * @acrtc: The amdgpu CRTC to prepare + * @acrtc_state: The new CRTC state + * @pflip_update: Whether a page flip is being programmed + * @cursor_update: Whether a cursor update is being programmed + * + * Grab a reference on the vblank counter if a page flip or cursor update is to + * be programmed. Do this before programming so the HW is not in any + * idle-optimized state (such as PSR). + */ +static void dm_arm_vblank_event_pre_programming(struct amdgpu_crtc *acrtc, + struct dm_crtc_state *acrtc_state, + bool pflip_update, + bool cursor_update) +{ + assert_spin_locked(&acrtc->base.dev->event_lock); + + if (!acrtc->base.state->event || acrtc_state->active_planes == 0) + return; + + if (pflip_update || cursor_update) + drm_crtc_vblank_get(&acrtc->base); +} + static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, struct drm_device *dev, struct amdgpu_display_manager *dm, @@ -10550,16 +10561,19 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state, } } - /* - * DCE depends on a combination of GRPH_FLIP, VLINE0, and VUPDATE for - * event delivery. Only GRPH_FLIP handler can send pflip events, and it - * only fires if HW latched to the flip. Maintain legacy behavior by - * arming event before programming. - */ - if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) == 0) { - scoped_guard(spinlock_irqsave, &pcrtc->dev->event_lock) { + scoped_guard(spinlock_irqsave, &pcrtc->dev->event_lock) { + dm_arm_vblank_event_pre_programming(acrtc_attach, acrtc_state, + pflip_present, + cursor_update); + /* + * DCE depends on a combination of GRPH_FLIP, VLINE0, and + * VUPDATE for event delivery. Only GRPH_FLIP handler can send + * pflip events, and it only fires if HW latched to the flip. + * Maintain legacy behavior by arming event before programming. + */ + if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) == 0) { dm_arm_vblank_event(acrtc_attach, acrtc_state, - pflip_present, cursor_update); + pflip_present, cursor_update); } } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index ecb8493ec523..8e3862f6dac2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -45,9 +45,7 @@ clk_src->base.ctx #define DC_LOGGER \ - calc_pll_cs->ctx->logger -#define DC_LOGGER_INIT() \ - struct calc_pll_clock_source *calc_pll_cs = &clk_src->calc_pll + CTX->logger #undef FN #define FN(reg_name, field_name) \ @@ -287,6 +285,7 @@ static bool calc_pll_dividers_in_range( } static uint32_t calculate_pixel_clock_pll_dividers( + struct dce110_clk_src *clk_src, struct calc_pll_clock_source *calc_pll_cs, struct pll_settings *pll_settings) { @@ -474,7 +473,7 @@ static uint32_t dce110_get_pix_clk_dividers_helper ( { uint32_t field = 0; uint32_t pll_calc_error = MAX_PLL_CALC_ERROR; - DC_LOGGER_INIT(); + /* Check if reference clock is external (not pcie/xtalin) * HW Dce80 spec: * 00 - PCIE_REFCLK, 01 - XTALIN, 02 - GENERICA, 03 - GENERICB @@ -517,12 +516,14 @@ static uint32_t dce110_get_pix_clk_dividers_helper ( /*Calculate Dividers by HDMI object, no SS case or SS case */ pll_calc_error = calculate_pixel_clock_pll_dividers( + clk_src, &clk_src->calc_pll_hdmi, pll_settings); else /*Calculate Dividers by default object, no SS case or SS case */ pll_calc_error = calculate_pixel_clock_pll_dividers( + clk_src, &clk_src->calc_pll, pll_settings); @@ -568,7 +569,6 @@ static uint32_t dce110_get_pix_clk_dividers( { struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); uint32_t pll_calc_error = MAX_PLL_CALC_ERROR; - DC_LOGGER_INIT(); if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { @@ -600,7 +600,6 @@ static uint32_t dce112_get_pix_clk_dividers( struct pll_settings *pll_settings) { struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); - DC_LOGGER_INIT(); if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { @@ -1442,8 +1441,6 @@ static uint32_t dcn3_get_pix_clk_dividers( unsigned long long actual_pix_clk_100Hz = pix_clk_params ? pix_clk_params->requested_pix_clk_100hz : 0; struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); - DC_LOGGER_INIT(); - if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { DC_LOG_ERROR( @@ -1513,7 +1510,6 @@ static const struct clock_source_funcs dce110_clk_src_funcs = { .get_dp_dto_frequency_100hz = get_dp_dto_frequency_100hz }; - static void get_ss_info_from_atombios( struct dce110_clk_src *clk_src, enum as_signal_type as_signal, @@ -1526,7 +1522,7 @@ static void get_ss_info_from_atombios( struct spread_spectrum_info *ss_info_cur; struct spread_spectrum_data *ss_data_cur; uint32_t i; - DC_LOGGER_INIT(); + if (ss_entries_num == NULL) { DC_LOG_SYNC( "Invalid entry !!!\n"); @@ -1657,6 +1653,7 @@ static void ss_info_from_atombios_create( } static bool calc_pll_max_vco_construct( + struct dce110_clk_src *clk_src, struct calc_pll_clock_source *calc_pll_cs, struct calc_pll_clock_source_init_data *init_data) { @@ -1808,6 +1805,7 @@ bool dce110_clk_src_construct( ss_info_from_atombios_create(clk_src); if (!calc_pll_max_vco_construct( + clk_src, &clk_src->calc_pll, &calc_pll_cs_init_data)) { ASSERT_CRITICAL(false); @@ -1822,7 +1820,7 @@ bool dce110_clk_src_construct( if (!calc_pll_max_vco_construct( - &clk_src->calc_pll_hdmi, &calc_pll_cs_init_data_hdmi)) { + clk_src, &clk_src->calc_pll_hdmi, &calc_pll_cs_init_data_hdmi)) { ASSERT_CRITICAL(false); goto unexpected_failure; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/dml21_utils.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/dml21_utils.c index 835fece1d46a..50e445275b14 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/dml21_utils.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/dml21_utils.c @@ -359,14 +359,13 @@ void dml21_handle_phantom_streams_planes(const struct dc *dc, struct dc_state *c main_plane = main_stream_status->plane_states[dc_plane_index]; /* create phantom planes for subvp enabled plane */ - dml21_add_phantom_plane(dml_ctx, - dc, - context, - phantom_stream, - main_plane, - &dml_ctx->v21.mode_programming.programming->plane_programming[dml_plane_index]); - - phantoms_added = true; + if (dml21_add_phantom_plane(dml_ctx, + dc, + context, + phantom_stream, + main_plane, + &dml_ctx->v21.mode_programming.programming->plane_programming[dml_plane_index])) + phantoms_added = true; } } } diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn4_calcs.c index f338e733318e..b4e2264ef408 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn4_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/dml21/src/dml2_core/dml2_core_dcn4_calcs.c @@ -2452,7 +2452,7 @@ static void calculate_mcache_row_bytes( DML_ASSERT(*p->num_mcaches > 0); } -static void calculate_mcache_setting( +static bool calculate_mcache_setting( struct dml2_core_internal_scratch *scratch, struct dml2_core_calcs_calculate_mcache_setting_params *p) { @@ -2478,7 +2478,7 @@ static void calculate_mcache_setting( *p->lc_comb_mcache = 0; if (!p->dcc_enable) - return; + return true; l->is_dual_plane = dml_is_420(p->source_format) || p->source_format == dml2_rgbe_alpha; @@ -2515,7 +2515,14 @@ static void calculate_mcache_setting( l->l_p.mvmpg_per_mcache_lb = &l->mvmpg_per_mcache_lb_l; calculate_mcache_row_bytes(scratch, &l->l_p); - DML_ASSERT(*p->num_mcaches_l > 0); + if (*p->num_mcaches_l == 0 || + (p->surf_vert ? l->mvmpg_height_l : l->mvmpg_width_l) == 0) { + DML_LOG_VERBOSE("DML::%s: degenerate luma viewport (num_mcaches_l=%u mvmpg_%s_l=%u) — mode not supported\n", + __func__, *p->num_mcaches_l, + p->surf_vert ? "height" : "width", + p->surf_vert ? l->mvmpg_height_l : l->mvmpg_width_l); + return false; + } if (l->is_dual_plane) { l->c_p.num_chans = p->num_chans; @@ -2551,7 +2558,14 @@ static void calculate_mcache_setting( l->c_p.mvmpg_per_mcache_lb = &l->mvmpg_per_mcache_lb_c; calculate_mcache_row_bytes(scratch, &l->c_p); - DML_ASSERT(*p->num_mcaches_c > 0); + if (*p->num_mcaches_c == 0 || + (p->surf_vert ? l->mvmpg_height_c : l->mvmpg_width_c) == 0) { + DML_LOG_VERBOSE("DML::%s: degenerate chroma viewport (num_mcaches_c=%u mvmpg_%s_c=%u) — mode not supported\n", + __func__, *p->num_mcaches_c, + p->surf_vert ? "height" : "width", + p->surf_vert ? l->mvmpg_height_c : l->mvmpg_width_c); + return false; + } } // Sharing for iMALL access @@ -2661,6 +2675,7 @@ static void calculate_mcache_setting( *p->mcache_shift_granularity_l = l->mvmpg_access_width_l; *p->mcache_shift_granularity_c = l->mvmpg_access_width_c; + return true; } static void calculate_mall_bw_overhead_factor( @@ -9457,7 +9472,10 @@ static bool dml_core_mode_support(struct dml2_core_calcs_mode_support_ex *in_out calculate_mcache_setting_params->mall_comb_mcache_c = &mode_lib->ms.mall_comb_mcache_c[k]; calculate_mcache_setting_params->lc_comb_mcache = &mode_lib->ms.lc_comb_mcache[k]; - calculate_mcache_setting(&mode_lib->scratch, calculate_mcache_setting_params); + if (!calculate_mcache_setting(&mode_lib->scratch, calculate_mcache_setting_params)) { + mode_lib->ms.support.ModeSupport = false; + return false; + } } calculate_mall_bw_overhead_factor( @@ -10933,7 +10951,8 @@ static bool dml_core_mode_programming(struct dml2_core_calcs_mode_programming_ex calculate_mcache_setting_params->mall_comb_mcache_l = &mode_lib->mp.mall_comb_mcache_l[k]; calculate_mcache_setting_params->mall_comb_mcache_c = &mode_lib->mp.mall_comb_mcache_c[k]; calculate_mcache_setting_params->lc_comb_mcache = &mode_lib->mp.lc_comb_mcache[k]; - calculate_mcache_setting(&mode_lib->scratch, calculate_mcache_setting_params); + if (!calculate_mcache_setting(&mode_lib->scratch, calculate_mcache_setting_params)) + return false; } calculate_mall_bw_overhead_factor( diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 042602c50e35..53fffe58602f 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1337,8 +1337,27 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) { - if (pipe_ctx != NULL && pipe_ctx->stream_res.stream_enc != NULL) + if (pipe_ctx == NULL || pipe_ctx->stream_res.stream_enc == NULL) + return; + + if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute(pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for three frames to make sure AV mute is sent out. + * Some HDMI sinks need additional GCP packets to properly + * process the mute state, especially after link re-establishment + * with HDMI 2.0 scrambling enabled. + */ + if (enable && pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) { + int i; + + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + for (i = 0; i < 3; i++) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } + } } enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index a7c85a2302ab..2d3587a31bc8 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -847,13 +847,19 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) pipe_ctx->stream_res.stream_enc, enable); - /* Wait for two frame to make sure AV mute is sent out */ + /* Wait for three frames to make sure AV mute is sent out. + * Some HDMI sinks need additional GCP packets to properly + * process the mute state, especially after link re-establishment + * with HDMI 2.0 scrambling enabled. + */ if (enable && pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) { + int i; + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + for (i = 0; i < 3; i++) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } } } } diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 42e7f0e9b3ce..ca5997748799 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -384,7 +384,7 @@ static bool write_i2c_retimer_vga( for (size_t i = 0; i < ARRAY_SIZE(vga_data); i++) { if (!write_i2c_retimer_offset_value(link, address, vga_data[i][0], vga_data[i][1])) { - DC_LOG_ERROR("Set retimer failed, vga index: %zu\n", i); + DC_LOG_DEBUG("Set retimer failed, vga index: %zu\n", i); return false; } } @@ -405,7 +405,7 @@ static bool write_i2c_retimer_byte( return true; if (!write_i2c_retimer_offset_value(link, address, index, value)) { - DC_LOG_ERROR("Set retimer failed, 3g index: 0x%x, value: 0x%x\n", index, value); + DC_LOG_DEBUG("Set retimer failed, 3g index: 0x%x, value: 0x%x\n", index, value); return false; } @@ -421,14 +421,14 @@ static bool write_i2c_retimer_byte( if (!link_query_ddc_data( link->ddc, address, &offset, 1, &value, 1 )) { - DC_LOG_ERROR("Set retimer failed, link_query_ddc_data\n"); + DC_LOG_DEBUG("Set retimer failed, link_query_ddc_data\n"); return false; } } value |= apply_rx_tx_change; if (!write_i2c_retimer_offset_value(link, address, offset, value)) { - DC_LOG_ERROR("Set retimer failed, 3g offset: 0x%x, value: 0x%x\n", offset, value); + DC_LOG_DEBUG("Set retimer failed, 3g offset: 0x%x, value: 0x%x\n", offset, value); return false; } } @@ -449,7 +449,7 @@ static bool write_i2c_retimer_setting( uint8_t value = settings->reg_settings[i].i2c_reg_val; if (!write_i2c_retimer_byte(link, address, index, value)) { - DC_LOG_ERROR("Set retimer failed, index: %zu\n", i); + DC_LOG_DEBUG("Set retimer failed, index: %zu\n", i); return false; } } @@ -460,7 +460,7 @@ static bool write_i2c_retimer_setting( uint8_t value = settings->reg_settings_6g[i].i2c_reg_val; if (!write_i2c_retimer_byte(link, address, index, value)) { - DC_LOG_ERROR("Set retimer failed, 6g index: %zu\n", i); + DC_LOG_DEBUG("Set retimer failed, 6g index: %zu\n", i); return false; } } @@ -492,7 +492,7 @@ static bool write_i2c_default_retimer_setting( for (size_t i = 0; i < ARRAY_SIZE(data); i++) { if (!write_i2c_retimer_offset_value(link, address, data[i][0], data[i][1])) { - DC_LOG_ERROR("Set default retimer failed, index: %zu\n", i); + DC_LOG_DEBUG("Set default retimer failed, index: %zu\n", i); return false; } } @@ -524,7 +524,7 @@ static bool write_i2c_redriver_setting( ); if (!success) - DC_LOG_ERROR("Set redriver failed"); + DC_LOG_DEBUG("Set redriver failed"); return success; } diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 6371f292f2d8..606d48115301 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -24,6 +24,8 @@ #ifndef __KGD_PP_INTERFACE_H__ #define __KGD_PP_INTERFACE_H__ +#include <linux/units.h> + extern const struct amdgpu_ip_block_version pp_smu_ip_block; extern const struct amdgpu_ip_block_version smu_v11_0_ip_block; extern const struct amdgpu_ip_block_version smu_v12_0_ip_block; @@ -150,8 +152,8 @@ enum amd_pp_sensors { AMDGPU_PP_SENSOR_MEM_TEMP, AMDGPU_PP_SENSOR_VCE_POWER, AMDGPU_PP_SENSOR_UVD_POWER, - AMDGPU_PP_SENSOR_GPU_AVG_POWER, - AMDGPU_PP_SENSOR_GPU_INPUT_POWER, + AMDGPU_PP_SENSOR_GPU_AVG_POWER, /* milliwatts */ + AMDGPU_PP_SENSOR_GPU_INPUT_POWER, /* milliwatts */ AMDGPU_PP_SENSOR_SS_APU_SHARE, AMDGPU_PP_SENSOR_SS_DGPU_SHARE, AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK, diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index f76ba6753551..e5e89294958a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -1183,20 +1183,36 @@ int amdgpu_dpm_dispatch_task(struct amdgpu_device *adev, return ret; } -int amdgpu_dpm_get_pp_table(struct amdgpu_device *adev, char **table) +static bool amdgpu_dpm_is_pp_table_allowed(struct amdgpu_device *adev) +{ + return !amdgpu_sriov_vf(adev) && + !(adev->flags & AMD_IS_APU) && + !adev->scpm_enabled; +} + +int amdgpu_dpm_get_pp_table(struct amdgpu_device *adev, char *table, + size_t size) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + char *pptable = NULL; int ret = 0; - if (!table) + if ((!table && size) || (table && !size)) return -EINVAL; - if (amdgpu_sriov_vf(adev) || !pp_funcs->get_pp_table || adev->scpm_enabled) + if (!amdgpu_dpm_is_pp_table_allowed(adev) || + !pp_funcs->get_pp_table) return -EOPNOTSUPP; mutex_lock(&adev->pm.mutex); ret = pp_funcs->get_pp_table(adev->powerplay.pp_handle, - table); + &pptable); + if (ret > 0 && !pptable) { + ret = -EINVAL; + } else if (ret > 0 && table) { + ret = min_t(size_t, ret, size); + memcpy(table, pptable, ret); + } mutex_unlock(&adev->pm.mutex); return ret; @@ -1426,17 +1442,23 @@ int amdgpu_dpm_set_power_profile_mode(struct amdgpu_device *adev, return ret; } -int amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void **table) +ssize_t amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void *buf, + size_t size) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - int ret = 0; + void *table; + ssize_t ret; if (!pp_funcs->get_gpu_metrics) return 0; mutex_lock(&adev->pm.mutex); ret = pp_funcs->get_gpu_metrics(adev->powerplay.pp_handle, - table); + &table); + if (ret > 0) { + ret = min_t(ssize_t, ret, size); + memcpy(buf, table, ret); + } mutex_unlock(&adev->pm.mutex); return ret; @@ -1703,7 +1725,8 @@ int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev, if (!buf || !size) return -EINVAL; - if (amdgpu_sriov_vf(adev) || !pp_funcs->set_pp_table || adev->scpm_enabled) + if (!amdgpu_dpm_is_pp_table_allowed(adev) || + !pp_funcs->set_pp_table) return -EOPNOTSUPP; mutex_lock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 97da01aff76c..85b089a3dc41 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -41,8 +41,6 @@ #define DEVICE_ATTR_IS(_name) (attr_id == device_attr_id__##_name) -#define power_2_mwatt(power) (((power) >> 8) * 1000 + ((power) & 0xff)) - struct od_attribute { struct kobj_attribute attribute; struct list_head entry; @@ -564,25 +562,19 @@ static ssize_t amdgpu_get_pp_table(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - char *table = NULL; int size, ret; ret = amdgpu_pm_get_access_if_active(adev); if (ret) return ret; - size = amdgpu_dpm_get_pp_table(adev, &table); + size = amdgpu_dpm_get_pp_table(adev, buf, PAGE_SIZE - 1); amdgpu_pm_put_access(adev); if (size <= 0) return size; - if (size >= PAGE_SIZE) - size = PAGE_SIZE - 1; - - memcpy(buf, table, size); - return size; } @@ -1780,7 +1772,6 @@ static ssize_t amdgpu_get_gpu_metrics(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - void *gpu_metrics; ssize_t size = 0; int ret; @@ -1788,15 +1779,10 @@ static ssize_t amdgpu_get_gpu_metrics(struct device *dev, if (ret) return ret; - size = amdgpu_dpm_get_gpu_metrics(adev, &gpu_metrics); + size = amdgpu_dpm_get_gpu_metrics(adev, buf, PAGE_SIZE - 1); if (size <= 0) goto out; - if (size >= PAGE_SIZE) - size = PAGE_SIZE - 1; - - memcpy(buf, gpu_metrics, size); - out: amdgpu_pm_put_access(adev); @@ -2726,10 +2712,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_table)) { int ret; - char *tmp = NULL; - ret = amdgpu_dpm_get_pp_table(adev, &tmp); - if (ret == -EOPNOTSUPP || !tmp) + ret = amdgpu_dpm_get_pp_table(adev, NULL, 0); + if (ret <= 0) *states = ATTR_STATE_UNSUPPORTED; else *states = ATTR_STATE_SUPPORTED; @@ -3364,7 +3349,7 @@ static int amdgpu_hwmon_get_power(struct device *dev, return r; /* convert to microwatts */ - return power_2_mwatt(query) * 1000; + return query * 1000; } static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, @@ -4932,7 +4917,7 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a seq_printf(m, "\t%u mV (VDDNB)\n", value); size = sizeof(uint32_t); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) { - mwatt = power_2_mwatt(query); + mwatt = query; centiwatt = DIV_ROUND_CLOSEST(mwatt, 10); if (adev->flags & AMD_IS_APU) seq_printf(m, "\t%u.%02u W (average SoC including CPU)\n", centiwatt / 100, centiwatt % 100); @@ -4941,7 +4926,7 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a } size = sizeof(uint32_t); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) { - mwatt = power_2_mwatt(query); + mwatt = query; centiwatt = DIV_ROUND_CLOSEST(mwatt, 10); if (adev->flags & AMD_IS_APU) seq_printf(m, "\t%u.%02u W (current SoC including CPU)\n", centiwatt / 100, centiwatt % 100); diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index aa3f427819a0..8d1b097a3c3c 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -487,7 +487,8 @@ int amdgpu_dpm_get_pp_num_states(struct amdgpu_device *adev, int amdgpu_dpm_dispatch_task(struct amdgpu_device *adev, enum amd_pp_task task_id, enum amd_pm_state_type *user_state); -int amdgpu_dpm_get_pp_table(struct amdgpu_device *adev, char **table); +int amdgpu_dpm_get_pp_table(struct amdgpu_device *adev, char *table, + size_t size); int amdgpu_dpm_set_fine_grain_clk_vol(struct amdgpu_device *adev, uint32_t type, long *input, @@ -517,7 +518,8 @@ int amdgpu_dpm_get_power_profile_mode(struct amdgpu_device *adev, char *buf); int amdgpu_dpm_set_power_profile_mode(struct amdgpu_device *adev, long *input, uint32_t size); -int amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void **table); +ssize_t amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void *buf, + size_t size); ssize_t amdgpu_dpm_get_xcp_metrics(struct amdgpu_device *adev, int xcp_id, void *table); ssize_t amdgpu_dpm_get_temp_metrics(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index bc82ba2e4c9b..f8a5648095d1 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -4062,7 +4062,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query) (adev->asic_type != CHIP_FIJI) && (adev->asic_type != CHIP_TONGA)) { smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0, &tmp); - *query = tmp; + *query = PP_PWR_Q24_8_TO_MW(tmp); if (tmp != 0) return 0; @@ -4081,7 +4081,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query) if (tmp != 0) break; } - *query = tmp; + *query = PP_PWR_Q24_8_TO_MW(tmp); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 4b92b52aba2b..c283309efe87 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3934,8 +3934,8 @@ static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr, if (ret) return ret; - /* SMC returning actual watts, keep consistent with legacy asics, low 8 bit as 8 fractional bits */ - *query = value << 8; + /* SMC returns whole Watts, while power sensors use milliwatts. */ + *query = value * MILLIWATT_PER_WATT; return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 69a9074058ce..b466b08e4a67 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -1419,7 +1419,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query) if (ret) return ret; - *query = metrics_table.CurrSocketPower << 8; + *query = metrics_table.CurrSocketPower * MILLIWATT_PER_WATT; return ret; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 7b8f4c1b80eb..e9c194056e32 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -2154,12 +2154,13 @@ static int vega20_get_gpu_power(struct pp_hwmgr *hwmgr, int idx, switch (idx) { case AMDGPU_PP_SENSOR_GPU_AVG_POWER: if (hwmgr->smu_version == 0x282e00) - *query = metrics_table.AverageSocketPower << 8; + *query = metrics_table.AverageSocketPower * + MILLIWATT_PER_WATT; else ret = -EOPNOTSUPP; break; case AMDGPU_PP_SENSOR_GPU_INPUT_POWER: - *query = metrics_table.CurrSocketPower << 8; + *query = metrics_table.CurrSocketPower * MILLIWATT_PER_WATT; break; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index ca71efaa1656..368200f7cf16 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -35,6 +35,11 @@ struct pp_hwmgr; struct phm_fan_speed_info; struct pp_atomctrl_voltage_table; +/* Decode legacy unsigned Q24.8 watts to internal milliwatts. */ +#define PP_PWR_Q24_8_TO_MW(power) \ + DIV_ROUND_CLOSEST_ULL((u64)(power) * MILLIWATT_PER_WATT, \ + BIT(8)) + #define VOLTAGE_SCALE 4 #define VOLTAGE_VID_OFFSET_SCALE1 625 #define VOLTAGE_VID_OFFSET_SCALE2 100 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index e3a89e9a9df4..64a64973fb86 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1348,7 +1348,7 @@ struct pptable_funcs { u32 (*set_gfx_off_residency)(struct smu_context *smu, bool start); /** - * @get_gfx_off_residency: Average GFXOFF residency % during the logging interval + * @get_gfx_off_residency: Live GFXOFF residency percentage */ u32 (*get_gfx_off_residency)(struct smu_context *smu, uint32_t *residency); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu15_driver_if_v15_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu15_driver_if_v15_0_0.h index 47ddf533b08f..a5d3e8d88860 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu15_driver_if_v15_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu15_driver_if_v15_0_0.h @@ -144,6 +144,44 @@ typedef struct { uint32_t MaxGfxClk; } DpmClocks_t; +//Freq in MHz +//Voltage in milli volts with 2 fractional bits +typedef struct { + uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS]; + uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS]; + uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS]; + uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS]; + + uint32_t VPEClocks[NUM_VPE_DPM_LEVELS]; + uint32_t FclkClocks_Freq[NUM_FCLK_DPM_LEVELS]; + uint32_t FclkClocks_Voltage[NUM_FCLK_DPM_LEVELS]; + uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS]; + MemPstateTable_t MemPstateTable[NUM_MEM_PSTATE_LEVELS]; + + uint8_t NumDcfClkLevelsEnabled; + uint8_t NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk + uint8_t NumSocClkLevelsEnabled; + + uint8_t VpeClkLevelsEnabled; + + uint8_t NumMemPstatesEnabled; + uint8_t NumFclkLevelsEnabled; + uint8_t Spare1; + uint8_t Spare2; + + uint8_t Spare3; + uint8_t Spare4; + uint8_t Spare5[2]; + + uint32_t MinGfxClk; + uint32_t MaxGfxClk; + + uint32_t Spare6[8]; + uint32_t Spare7[8]; + uint32_t Spare8[8]; + uint32_t Spare9[8]; +} DpmClocks_t_v15_0_5; + typedef struct { uint16_t CoreFrequency[16]; //Target core frequency [MHz] uint16_t CorePower[16]; //CAC calculated core power [mW] diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v11_5_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v11_5_ppsmc.h index 7471e2df2828..4206514765cd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v11_5_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v11_5_ppsmc.h @@ -110,8 +110,10 @@ #define PPSMC_MSG_GetSlowPPTLimit 0x4C #define PPSMC_MSG_GetGfxOffStatus 0x50 #define PPSMC_MSG_GetGfxOffEntryCount 0x51 -#define PPSMC_MSG_LogGfxOffResidency 0x52 -#define PPSMC_Message_Count 0x53 +#define PPSMC_MSG_GfxOffResidencyLogReadSample 0x52 +#define PPSMC_MSG_StopGfxOffResidencyLogging 0x53 +#define PPSMC_MSG_StartGfxOffResidencyLogging 0x56 +#define PPSMC_Message_Count 0x57 //Argument for PPSMC_MSG_GfxDeviceDriverReset enum { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 636ff90923d9..acf03838d49d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -252,7 +252,9 @@ __SMU_DUMMY_MAP(DriverMode2Reset), \ __SMU_DUMMY_MAP(GetGfxOffStatus), \ __SMU_DUMMY_MAP(GetGfxOffEntryCount), \ - __SMU_DUMMY_MAP(LogGfxOffResidency), \ + __SMU_DUMMY_MAP(StartGfxOffResidencyLogging), \ + __SMU_DUMMY_MAP(GfxOffResidencyLogReadSample), \ + __SMU_DUMMY_MAP(StopGfxOffResidencyLogging), \ __SMU_DUMMY_MAP(SetNumBadMemoryPagesRetired), \ __SMU_DUMMY_MAP(SetBadMemoryPagesRetiredFlagsPerChannel), \ __SMU_DUMMY_MAP(AllowGpo), \ diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v15_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v15_0.h index e6fd8be2cc4a..0fa32fd041da 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v15_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v15_0.h @@ -26,7 +26,7 @@ #include "amdgpu_smu.h" #define SMU15_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU15_DRIVER_IF_VERSION_SMU_V15_0 0x7 +#define SMU15_DRIVER_IF_VERSION_SMU_V15_0 0x9 #define FEATURE_MASK(feature) (1ULL << feature) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 54d3dba7d354..cfad8cd74773 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -658,7 +658,7 @@ static int arcturus_get_smu_metrics_data(struct smu_context *smu, *value = metrics->VcnActivityPercentage; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c index e6e009df9840..bb9620666dae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c @@ -158,12 +158,10 @@ cyan_skillfish_get_smu_metrics_data(struct smu_context *smu, *value = metrics->Current.MemclkFrequency; break; case METRICS_CURR_SOCKETPOWER: - *value = (metrics->Current.CurrentSocketPower << 8) / - 1000; + *value = metrics->Current.CurrentSocketPower; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->Average.CurrentSocketPower << 8) / - 1000; + *value = metrics->Average.CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->Current.GfxTemperature / 100 * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index cd0457e13f54..6dfc3b585c6b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -602,7 +602,7 @@ static int navi10_get_legacy_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * @@ -691,7 +691,7 @@ static int navi10_get_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * @@ -777,7 +777,7 @@ static int navi12_get_legacy_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * @@ -866,7 +866,7 @@ static int navi12_get_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index f799e489b481..dccca6ddd5ad 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -855,9 +855,10 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = use_metrics_v3 ? metrics_v3->AverageSocketPower << 8 : - use_metrics_v2 ? metrics_v2->AverageSocketPower << 8 : - metrics->AverageSocketPower << 8; + *value = use_metrics_v3 ? metrics_v3->AverageSocketPower : + use_metrics_v2 ? metrics_v2->AverageSocketPower : + metrics->AverageSocketPower; + *value *= MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = (use_metrics_v3 ? metrics_v3->TemperatureEdge : diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 016a5c893fee..3e3c68448ba9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -72,6 +72,12 @@ static const struct smu_feature_bits vangogh_dpm_features = { } }; +/* + * SMU support new GFXOFF residency log interface since version 4.63.62.00, + * use this to get live readings of GFXOFF residency + */ +#define SUPPORT_LIVE_RESIDENCY_MSG_VERSION 0x043f3e00 + static struct cmn2asic_msg_mapping vangogh_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 0), @@ -142,7 +148,9 @@ static struct cmn2asic_msg_mapping vangogh_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(GetSlowPPTLimit, PPSMC_MSG_GetSlowPPTLimit, 0), MSG_MAP(GetGfxOffStatus, PPSMC_MSG_GetGfxOffStatus, 0), MSG_MAP(GetGfxOffEntryCount, PPSMC_MSG_GetGfxOffEntryCount, 0), - MSG_MAP(LogGfxOffResidency, PPSMC_MSG_LogGfxOffResidency, 0), + MSG_MAP(StartGfxOffResidencyLogging, PPSMC_MSG_StartGfxOffResidencyLogging, 0), + MSG_MAP(GfxOffResidencyLogReadSample, PPSMC_MSG_GfxOffResidencyLogReadSample, 0), + MSG_MAP(StopGfxOffResidencyLogging, PPSMC_MSG_StopGfxOffResidencyLogging, 0), }; static struct cmn2asic_mapping vangogh_feature_mask_map[SMU_FEATURE_COUNT] = { @@ -310,8 +318,7 @@ static int vangogh_get_legacy_smu_metrics_data(struct smu_context *smu, *value = metrics->UvdActivity / 100; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / - 1000 ; + *value = metrics->CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * @@ -379,12 +386,10 @@ static int vangogh_get_smu_metrics_data(struct smu_context *smu, *value = metrics->Current.UvdActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->Average.CurrentSocketPower << 8) / - 1000; + *value = metrics->Average.CurrentSocketPower; break; case METRICS_CURR_SOCKETPOWER: - *value = (metrics->Current.CurrentSocketPower << 8) / - 1000; + *value = metrics->Current.CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->Current.GfxTemperature / 100 * @@ -2449,19 +2454,32 @@ static int vangogh_set_power_limit(struct smu_context *smu, static u32 vangogh_set_gfxoff_residency(struct smu_context *smu, bool start) { int ret = 0; - u32 residency; struct amdgpu_device *adev = smu->adev; if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return 0; - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_LogGfxOffResidency, - start, &residency); - if (ret) - return ret; + if (smu->smc_fw_version < SUPPORT_LIVE_RESIDENCY_MSG_VERSION) { + u32 residency; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxOffResidencyLogReadSample, + start, &residency); + if (ret) + return ret; - if (!start) - adev->gfx.gfx_off_residency = residency; + if (!start) + adev->gfx.gfx_off_residency = residency; + } else { + if (start) { + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_StartGfxOffResidencyLogging, NULL); + if (ret) + return ret; + } else { + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_StopGfxOffResidencyLogging, NULL); + if (ret) + return ret; + } + } return ret; } @@ -2478,11 +2496,20 @@ static u32 vangogh_set_gfxoff_residency(struct smu_context *smu, bool start) */ static u32 vangogh_get_gfxoff_residency(struct smu_context *smu, uint32_t *residency) { + int ret = 0; struct amdgpu_device *adev = smu->adev; - *residency = adev->gfx.gfx_off_residency; + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) + return 0; + + if (smu->smc_fw_version < SUPPORT_LIVE_RESIDENCY_MSG_VERSION) { + *residency = adev->gfx.gfx_off_residency; + } else { + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GfxOffResidencyLogReadSample, + residency); + } - return 0; + return ret; } /** diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 75335da224c7..175c44190caa 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1215,9 +1215,10 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(12, 0, 0)) && (adev->pm.fw_version >= 0x373200))) - *value = metrics->CurrentSocketPower << 8; + *value = metrics->CurrentSocketPower * + MILLIWATT_PER_WATT; else - *value = (metrics->CurrentSocketPower << 8) / 1000; + *value = metrics->CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = (metrics->GfxTemperature / 100) * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 9d8b1227388f..18c0b43b93b9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -677,7 +677,8 @@ static int aldebaran_get_smu_metrics_data(struct smu_context *smu, case METRICS_AVERAGE_SOCKETPOWER: /* Valid power data is available only from primary die */ if (aldebaran_is_primary(smu)) - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * + MILLIWATT_PER_WATT; else ret = -EOPNOTSUPP; break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index acbd7046d8a5..0be34fbdac26 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -807,7 +807,7 @@ static int smu_v13_0_0_get_smu_metrics_data(struct smu_context *smu, metrics->Vcn1ActivityPercentage); break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->AvgTemperature[TEMP_EDGE] * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c index fe929bd89058..8d476a60d62f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c @@ -434,7 +434,8 @@ int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); break; case METRICS_CURR_SOCKETPOWER: - *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + *value = SMUQ10_ROUND(metrics->SocketPower) * + MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_HOTSPOT: *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index ba91bf590eed..a9d558f5b739 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -338,10 +338,10 @@ static int smu_v13_0_4_get_smu_metrics_data(struct smu_context *smu, *value = metrics->UvdActivity / 100; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->AverageSocketPower << 8) / 1000; + *value = metrics->AverageSocketPower; break; case METRICS_CURR_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; + *value = metrics->CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 27372a60e83d..f95b15af436d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -295,7 +295,7 @@ static int smu_v13_0_5_get_smu_metrics_data(struct smu_context *smu, *value = metrics->UvdActivity / 100; break; case METRICS_CURR_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; + *value = metrics->CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index b12388134489..41608574bc61 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1321,7 +1321,8 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, *value = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization, version)); break; case METRICS_CURR_SOCKETPOWER: - *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower, version)) << 8; + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower, version)) * + MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_HOTSPOT: *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature, version)) * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 42c9ceeb4f7d..5d11ed8be4c3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -817,7 +817,7 @@ static int smu_v13_0_7_get_smu_metrics_data(struct smu_context *smu, *value = smu_safe_u16_nn(metrics->AverageUclkActivity); break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->AvgTemperature[TEMP_EDGE] * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 7bf88ffd311b..edc3fedca9f8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -372,7 +372,7 @@ static int yellow_carp_get_smu_metrics_data(struct smu_context *smu, *value = metrics->UvdActivity / 100; break; case METRICS_CURR_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; + *value = metrics->CurrentSocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index 3d73f2050bbe..568665265a13 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -312,8 +312,7 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu, break; case METRICS_AVERAGE_SOCKETPOWER: case METRICS_CURR_SOCKETPOWER: - *value = (metrics->SocketPower / 1000 << 8) + - (metrics->SocketPower % 1000 / 10); + *value = metrics->SocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index a6a88e7b2668..bd054cbfbae0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -695,7 +695,7 @@ static int smu_v14_0_2_get_smu_metrics_data(struct smu_context *smu, metrics->Vcn1ActivityPercentage); break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + *value = metrics->AverageSocketPower * MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->AvgTemperature[TEMP_EDGE] * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c index bb8d09e73c7d..0da1ffb3a567 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c @@ -168,7 +168,7 @@ static int smu_v15_0_0_init_smc_tables(struct smu_context *smu) SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t), + SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t_v15_0_5), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); @@ -178,7 +178,7 @@ static int smu_v15_0_0_init_smc_tables(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - smu_table->clocks_table = kzalloc_obj(DpmClocks_t); + smu_table->clocks_table = kzalloc_obj(DpmClocks_t_v15_0_5); if (!smu_table->clocks_table) goto err1_out; @@ -378,8 +378,7 @@ static int smu_v15_0_0_get_smu_metrics_data(struct smu_context *smu, break; case METRICS_AVERAGE_SOCKETPOWER: case METRICS_CURR_SOCKETPOWER: - *value = (metrics->SocketPower / 1000 << 8) + - (metrics->SocketPower % 1000 / 10); + *value = metrics->SocketPower; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->GfxTemperature / 100 * @@ -752,11 +751,48 @@ static int smu_v15_0_0_get_dpm_freq_by_index(struct smu_context *smu, return 0; } +static int smu_v15_0_5_get_dpm_freq_by_index(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t dpm_level, + uint32_t *freq) +{ + DpmClocks_t_v15_0_5 *clk_table = smu->smu_table.clocks_table; + + if (!clk_table || clk_type >= SMU_CLK_COUNT) + return -EINVAL; + + switch (clk_type) { + case SMU_SOCCLK: + if (dpm_level >= clk_table->NumSocClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->SocClocks[dpm_level]; + break; + case SMU_UCLK: + case SMU_MCLK: + if (dpm_level >= clk_table->NumMemPstatesEnabled) + return -EINVAL; + *freq = clk_table->MemPstateTable[dpm_level].MemClk; + break; + case SMU_FCLK: + if (dpm_level >= clk_table->NumFclkLevelsEnabled) + return -EINVAL; + *freq = clk_table->FclkClocks_Freq[dpm_level]; + break; + default: + return -EINVAL; + } + + return 0; +} + static int smu_v15_0_common_get_dpm_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t dpm_level, uint32_t *freq) { + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 5)) + smu_v15_0_5_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq); + else smu_v15_0_0_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq); return 0; @@ -907,12 +943,116 @@ failed: return ret; } +static int smu_v15_0_5_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + DpmClocks_t_v15_0_5 *clk_table = smu->smu_table.clocks_table; + uint32_t clock_limit; + uint32_t max_dpm_level, min_dpm_level; + int ret = 0; + + if (!smu_v15_0_0_clk_dpm_is_enabled(smu, clk_type)) { + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + clock_limit = smu->smu_table.boot_values.uclk; + break; + case SMU_FCLK: + clock_limit = smu->smu_table.boot_values.fclk; + break; + case SMU_GFXCLK: + case SMU_SCLK: + clock_limit = smu->smu_table.boot_values.gfxclk; + break; + case SMU_SOCCLK: + clock_limit = smu->smu_table.boot_values.socclk; + break; + default: + clock_limit = 0; + break; + } + + /* clock in Mhz unit */ + if (min) + *min = clock_limit / 100; + if (max) + *max = clock_limit / 100; + + return 0; + } + + if (max) { + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + *max = clk_table->MaxGfxClk; + break; + case SMU_MCLK: + case SMU_UCLK: + max_dpm_level = 0; + break; + case SMU_FCLK: + max_dpm_level = clk_table->NumFclkLevelsEnabled - 1; + break; + case SMU_SOCCLK: + max_dpm_level = clk_table->NumSocClkLevelsEnabled - 1; + break; + default: + ret = -EINVAL; + goto failed; + } + + if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { + ret = smu_v15_0_common_get_dpm_freq_by_index(smu, clk_type, + max_dpm_level, max); + if (ret) + goto failed; + } + } + + if (min) { + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + *min = clk_table->MinGfxClk; + break; + case SMU_MCLK: + case SMU_UCLK: + min_dpm_level = clk_table->NumMemPstatesEnabled - 1; + break; + case SMU_FCLK: + min_dpm_level = 0; + break; + case SMU_SOCCLK: + min_dpm_level = 0; + break; + default: + ret = -EINVAL; + goto failed; + } + + if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { + ret = smu_v15_0_common_get_dpm_freq_by_index(smu, clk_type, + min_dpm_level, min); + if (ret) + goto failed; + } + } + +failed: + return ret; +} + static int smu_v15_0_common_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max) { - if (clk_type != SMU_VCLK1 && clk_type != SMU_DCLK1) + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 5)) + smu_v15_0_5_get_dpm_ultimate_freq(smu, clk_type, min, max); + else if (clk_type != SMU_VCLK1 && clk_type != SMU_DCLK1) smu_v15_0_0_get_dpm_ultimate_freq(smu, clk_type, min, max); return 0; @@ -986,11 +1126,36 @@ static int smu_v15_0_0_get_dpm_level_count(struct smu_context *smu, return 0; } +static int smu_v15_0_5_get_dpm_level_count(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *count) +{ + DpmClocks_t_v15_0_5 *clk_table = smu->smu_table.clocks_table; + + switch (clk_type) { + case SMU_SOCCLK: + *count = clk_table->NumSocClkLevelsEnabled; + break; + case SMU_MCLK: + *count = clk_table->NumMemPstatesEnabled; + break; + case SMU_FCLK: + *count = clk_table->NumFclkLevelsEnabled; + break; + default: + break; + } + + return 0; +} + static int smu_v15_0_common_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *count) { - if (clk_type != SMU_VCLK1 && clk_type != SMU_DCLK1) + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 5)) + smu_v15_0_5_get_dpm_level_count(smu, clk_type, count); + else if (clk_type != SMU_VCLK1 && clk_type != SMU_DCLK1) smu_v15_0_0_get_dpm_level_count(smu, clk_type, count); return 0; @@ -1363,9 +1528,24 @@ static int smu_v15_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *sm return 0; } +static int smu_v15_0_5_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) +{ + DpmClocks_t_v15_0_5 *clk_table = smu->smu_table.clocks_table; + + smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; + smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; + smu->gfx_actual_hard_min_freq = 0; + smu->gfx_actual_soft_max_freq = 0; + + return 0; +} + static int smu_v15_0_common_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) { - smu_v15_0_0_set_fine_grain_gfx_freq_parameters(smu); + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 5)) + smu_v15_0_5_set_fine_grain_gfx_freq_parameters(smu); + else + smu_v15_0_0_set_fine_grain_gfx_freq_parameters(smu); return 0; } @@ -1405,9 +1585,36 @@ static int smu_v15_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks return 0; } +static int smu_v15_0_5_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table) +{ + DpmClocks_t_v15_0_5 *clk_table = smu->smu_table.clocks_table; + uint8_t idx; + + /* + * Only the Clock information of SOC and + * VPE is copied to provide VPE DPM settings for use. + */ + for (idx = 0; idx < NUM_SOCCLK_DPM_LEVELS; idx++) { + clock_table->SocClocks[idx].Freq = + (idx < clk_table->NumSocClkLevelsEnabled) ? clk_table->SocClocks[idx]:0; + clock_table->SocClocks[idx].Vol = 0; + } + + for (idx = 0; idx < NUM_VPE_DPM_LEVELS; idx++) { + clock_table->VPEClocks[idx].Freq = + (idx < clk_table->VpeClkLevelsEnabled) ? clk_table->VPEClocks[idx]:0; + clock_table->VPEClocks[idx].Vol = 0; + } + + return 0; +} + static int smu_v15_0_common_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table) { - smu_v15_0_0_get_dpm_table(smu, clock_table); + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 5)) + smu_v15_0_5_get_dpm_table(smu, clock_table); + else + smu_v15_0_0_get_dpm_table(smu, clock_table); return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c index 2105a1d7bb34..118eda5429ff 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c @@ -411,7 +411,8 @@ static int smu_v15_0_8_get_smu_metrics_data(struct smu_context *smu, *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); break; case METRICS_CURR_SOCKETPOWER: - *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + *value = SMUQ10_ROUND(metrics->SocketPower) * + MILLIWATT_PER_WATT; break; case METRICS_TEMPERATURE_HOTSPOT: *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c index 16c0631adeb1..6b128fabe3a9 100644 --- a/drivers/gpu/drm/bridge/display-connector.c +++ b/drivers/gpu/drm/bridge/display-connector.c @@ -40,6 +40,13 @@ static int display_connector_attach(struct drm_bridge *bridge, return flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR ? 0 : -EINVAL; } +static void display_connector_destroy(struct drm_bridge *bridge) +{ + struct display_connector *conn = to_display_connector(bridge); + + i2c_put_adapter(conn->bridge.ddc); +} + static enum drm_connector_status display_connector_detect(struct drm_bridge *bridge) { struct display_connector *conn = to_display_connector(bridge); @@ -177,6 +184,7 @@ static u32 *display_connector_get_input_bus_fmts(struct drm_bridge *bridge, static const struct drm_bridge_funcs display_connector_bridge_funcs = { .attach = display_connector_attach, + .destroy = display_connector_destroy, .detect = display_connector_bridge_detect, .edid_read = display_connector_edid_read, .atomic_get_output_bus_fmts = display_connector_get_output_bus_fmts, @@ -403,9 +411,6 @@ static void display_connector_remove(struct platform_device *pdev) regulator_disable(conn->supply); drm_bridge_remove(&conn->bridge); - - if (!IS_ERR(conn->bridge.ddc)) - i2c_put_adapter(conn->bridge.ddc); } static const struct of_device_id display_connector_match[] = { diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index 9c31e14cc413..e623ccb4c1d8 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -3686,6 +3686,18 @@ int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int bw; u8 buf; + if (!drm_dp_is_branch(dpcd)) + return 0; + + if (dpcd[DP_DPCD_REV] < 0x11) + return 0; + + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 0; + + if ((port_cap[0] & DP_DS_PORT_TYPE_MASK) != DP_DS_PORT_TYPE_HDMI) + return 0; + buf = port_cap[2]; bw = buf & DP_PCON_MAX_FRL_BW; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 6296635c4e79..95008e0c0eb8 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3501,6 +3501,8 @@ static void intel_ddi_enable_hdmi(struct intel_atomic_state *state, } intel_ddi_buf_enable(encoder, buf_ctl); + + intel_hdmi_poll_for_scrambling_enable(crtc_state, connector); } static void intel_ddi_enable(struct intel_atomic_state *state, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 7ff5712f8b19..5733d2e7ac7f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4242,7 +4242,14 @@ static int intel_dp_hdmi_sink_max_frl(struct intel_dp *intel_dp) rate_per_lane = info->hdmi.max_frl_rate_per_lane; max_frl_rate = max_lanes * rate_per_lane; - if (info->hdmi.dsc_cap.v_1p2) { + /* + * The sink's DSC max FRL rate only applies to compressed video + * transport, which requires a DSC 1.2 encoder in the PCON. Without + * one the HDMI link always carries uncompressed video, for which + * the regular max FRL rate is the limit. + */ + if (drm_dp_pcon_enc_is_dsc_1_2(intel_dp->pcon_dsc_dpcd) && + info->hdmi.dsc_cap.v_1p2) { max_dsc_lanes = info->hdmi.dsc_cap.max_lanes; dsc_rate_per_lane = info->hdmi.dsc_cap.max_frl_rate_per_lane; if (max_dsc_lanes && dsc_rate_per_lane) diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 9076c2b176ec..b9d11fb8559d 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2729,6 +2729,32 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *_ } /* + * HDMI 2.0 spec, section 6.1.3.1 (Scrambling Control): after + * enabling Scrambling_Enable and starting scrambled video + * transmission, poll Scrambling_Status for up to 200 ms. + */ +void +intel_hdmi_poll_for_scrambling_enable(const struct intel_crtc_state *crtc_state, + struct drm_connector *_connector) +{ + struct intel_connector *connector = to_intel_connector(_connector); + struct intel_display *display = to_intel_display(crtc_state); + bool scrambling_enabled = false; + int ret; + + if (!crtc_state->hdmi_scrambling) + return; + + /* Poll for a max of 200 msec as per HDMI spec */ + ret = poll_timeout_us(scrambling_enabled = drm_scdc_get_scrambling_status(&connector->base), + scrambling_enabled, 1000, 200 * 1000, false); + if (ret) + drm_dbg_kms(display->drm, + "[CONNECTOR:%d:%s] Timed out waiting for scrambling enable\n", + connector->base.base.id, connector->base.name); +} + +/* * intel_hdmi_handle_sink_scrambling: handle sink scrambling/clock ratio setup * @encoder: intel_encoder * @connector: drm_connector diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index be2fad57e4ad..0fa3661568e8 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -70,5 +70,7 @@ void hsw_read_infoframe(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, unsigned int type, void *frame, ssize_t len); +void intel_hdmi_poll_for_scrambling_enable(const struct intel_crtc_state *crtc_state, + struct drm_connector *_connector); #endif /* __INTEL_HDMI_H__ */ diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c index 941c017399fc..d13726401d92 100644 --- a/drivers/gpu/drm/imagination/pvr_queue.c +++ b/drivers/gpu/drm/imagination/pvr_queue.c @@ -726,8 +726,6 @@ static void pvr_queue_submit_job_to_cccb(struct pvr_job *job) cmd->partial_render_geom_frag_fence.value = job->done_fence->seqno - 1; } - trace_pvr_job_submit_fw(job); - /* Submit job to FW */ pvr_cccb_write_command_with_header(cccb, job->fw_ccb_cmd_type, job->cmd_len, job->cmd, job->id, job->id); @@ -802,6 +800,9 @@ static struct dma_fence *pvr_queue_run_job(struct drm_sched_job *sched_job) job->hwrt, frag_job->fw_ccb_cmd_type == ROGUE_FWIF_CCB_CMD_TYPE_FRAG_PR); + + trace_pvr_job_submit_fw(geom_job); + trace_pvr_job_submit_fw(frag_job); } else { struct pvr_queue *queue = container_of(job->base.sched, struct pvr_queue, scheduler); @@ -809,6 +810,8 @@ static struct dma_fence *pvr_queue_run_job(struct drm_sched_job *sched_job) pvr_cccb_send_kccb_kick(pvr_dev, &queue->cccb, pvr_context_get_fw_addr(job->ctx) + queue->ctx_offset, job->hwrt); + + trace_pvr_job_submit_fw(job); } return dma_fence_get(job->done_fence); diff --git a/drivers/gpu/drm/imagination/pvr_trace.h b/drivers/gpu/drm/imagination/pvr_trace.h index ffbbde3b2bcc..943d6b2418cb 100644 --- a/drivers/gpu/drm/imagination/pvr_trace.h +++ b/drivers/gpu/drm/imagination/pvr_trace.h @@ -41,6 +41,17 @@ TRACE_EVENT(pvr_job_submit_ioctl, __entry->count) ); +#define PVR_JOB_GET_HWRT_FW_ADDR(job) \ + ({ \ + struct pvr_job *_job = (job); \ + u32 _hwrt_fw_addr = 0; \ + \ + if (_job && _job->hwrt) \ + pvr_fw_object_get_fw_addr(_job->hwrt->fw_obj, &_hwrt_fw_addr); \ + \ + _hwrt_fw_addr; \ + }) + #define PVR_JOB_TYPE_TO_STR(val) \ __print_symbolic(val, \ { DRM_PVR_JOB_TYPE_GEOMETRY, "geometry" }, \ @@ -64,9 +75,7 @@ TRACE_EVENT(pvr_job_create, __entry->ctx = job->ctx; __entry->fw_obj = job->ctx->fw_obj; pvr_fw_object_get_fw_addr(job->ctx->fw_obj, &__entry->fw_addr); - __entry->hwrt_addr = job->hwrt ? - job->hwrt->fw_obj->fw_addr_offset : - 0; + __entry->hwrt_addr = PVR_JOB_GET_HWRT_FW_ADDR(job); __entry->job = job; __entry->job_type = job->type; __entry->sync_op_count = sync_op_count;), @@ -82,6 +91,7 @@ TRACE_EVENT(pvr_job_create, ); #undef PVR_JOB_TYPE_TO_STR +#undef PVR_JOB_GET_HWRT_FW_ADDR TRACE_EVENT(pvr_job_submit_fw, TP_PROTO(struct pvr_job *job), diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 8e552cdc3b53..97e3ff412e6e 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -154,10 +154,10 @@ static void mtk_crtc_reset(struct drm_crtc *crtc) { struct mtk_crtc_state *state; - if (crtc->state) + if (crtc->state) { __drm_atomic_helper_crtc_destroy_state(crtc->state); - - kfree(to_mtk_crtc_state(crtc->state)); + kfree(to_mtk_crtc_state(crtc->state)); + } crtc->state = NULL; state = kzalloc_obj(*state); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index c0af3e3b51d5..6a259872b0a9 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -625,6 +625,7 @@ static void mtk_disp_ovl_adaptor_master_unbind(struct device *dev) struct mtk_disp_ovl_adaptor *priv = dev_get_drvdata(dev); priv->children_bound = false; + component_unbind_all(dev, priv->mmsys_dev); } static const struct component_master_ops mtk_disp_ovl_adaptor_master_ops = { @@ -651,12 +652,15 @@ static int mtk_disp_ovl_adaptor_probe(struct platform_device *pdev) priv->mmsys_dev = pdev->dev.platform_data; - component_master_add_with_match(dev, &mtk_disp_ovl_adaptor_master_ops, match); + ret = component_master_add_with_match(dev, &mtk_disp_ovl_adaptor_master_ops, match); + if (ret) + return dev_err_probe(dev, ret, "Failed to add component master\n"); pm_runtime_enable(dev); ret = component_add(dev, &mtk_disp_ovl_adaptor_comp_ops); if (ret != 0) { + component_master_del(dev, &mtk_disp_ovl_adaptor_master_ops); pm_runtime_disable(dev); return dev_err_probe(dev, ret, "Failed to add component\n"); } @@ -666,6 +670,7 @@ static int mtk_disp_ovl_adaptor_probe(struct platform_device *pdev) static void mtk_disp_ovl_adaptor_remove(struct platform_device *pdev) { + component_del(&pdev->dev, &mtk_disp_ovl_adaptor_comp_ops); component_master_del(&pdev->dev, &mtk_disp_ovl_adaptor_master_ops); pm_runtime_disable(&pdev->dev); } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index eb325e68aa59..49dfc0f825cb 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -743,8 +743,6 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi) mtk_dsi_set_vm_cmd(dsi); mtk_dsi_config_vdo_timing(dsi); mtk_dsi_set_interrupt_enable(dsi); - mtk_dsi_lane_ready(dsi); - mtk_dsi_clk_hs_mode(dsi, 1); return 0; err_disable_engine_clk: @@ -858,6 +856,9 @@ static void mtk_dsi_bridge_atomic_pre_enable(struct drm_bridge *bridge, ret = mtk_dsi_poweron(dsi); if (ret < 0) drm_err(drm, "failed to power on dsi\n"); + + mtk_dsi_lane_ready(dsi); + mtk_dsi_clk_hs_mode(dsi, 1); } static void mtk_dsi_bridge_atomic_post_disable(struct drm_bridge *bridge, diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_common.c b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c index a049489daa2d..042b98e5a519 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_common.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c @@ -290,6 +290,13 @@ static int mtk_hdmi_get_cec_dev(struct mtk_hdmi *hdmi, struct device *dev, struc return 0; } +static void mtk_hdmi_put_adapter(void *_adap) +{ + struct i2c_adapter *adap = _adap; + + i2c_put_adapter(adap); +} + static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, struct platform_device *pdev, const char * const *clk_names, size_t num_clocks) { @@ -328,12 +335,12 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, struct platform_device if (!i2c_np) return dev_err_probe(dev, -EINVAL, "No ddc-i2c-bus in connector\n"); - hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np); + hdmi->ddc_adpt = of_get_i2c_adapter_by_node(i2c_np); of_node_put(i2c_np); if (!hdmi->ddc_adpt) return dev_err_probe(dev, -EPROBE_DEFER, "Failed to get ddc i2c adapter by node\n"); - ret = devm_add_action_or_reset(dev, mtk_hdmi_put_device, &hdmi->ddc_adpt->dev); + ret = devm_add_action_or_reset(dev, mtk_hdmi_put_adapter, hdmi->ddc_adpt); if (ret) return ret; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c index 7bbf463056c9..ffe456238a2b 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c @@ -1499,13 +1499,6 @@ static int mtk_hdmi_v2_probe(struct platform_device *pdev) return 0; } -static void mtk_hdmi_v2_remove(struct platform_device *pdev) -{ - struct mtk_hdmi *hdmi = platform_get_drvdata(pdev); - - i2c_put_adapter(hdmi->ddc_adpt); -} - static const struct of_device_id mtk_drm_hdmi_v2_of_ids[] = { { .compatible = "mediatek,mt8188-hdmi-tx", .data = &mtk_hdmi_conf_mt8188 }, { .compatible = "mediatek,mt8195-hdmi-tx", .data = &mtk_hdmi_conf_mt8195 }, @@ -1515,7 +1508,6 @@ MODULE_DEVICE_TABLE(of, mtk_drm_hdmi_v2_of_ids); static struct platform_driver mtk_hdmi_v2_driver = { .probe = mtk_hdmi_v2_probe, - .remove = mtk_hdmi_v2_remove, .driver = { .name = "mediatek-drm-hdmi-v2", .of_match_table = mtk_drm_hdmi_v2_of_ids, diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index 90f59d782a80..e45933e333b5 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -545,6 +545,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, struct panthor_fw_binary_section_entry_hdr hdr; struct panthor_fw_section *section; u32 section_size; + u32 data_size; u32 name_len; int ret; @@ -595,6 +596,13 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, return -EINVAL; } + section_size = hdr.va.end - hdr.va.start; + data_size = hdr.data.end - hdr.data.start; + if (data_size > section_size) { + drm_err(&ptdev->base, "Firmware corrupted, section data exceeds section size\n"); + return -EINVAL; + } + name_len = iter->size - iter->offset; section = drmm_kzalloc(&ptdev->base, sizeof(*section), GFP_KERNEL); @@ -603,7 +611,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, list_add_tail(§ion->node, &ptdev->fw->sections); section->flags = hdr.flags; - section->data.size = hdr.data.end - hdr.data.start; + section->data.size = data_size; if (section->data.size > 0) { void *data = drmm_kmalloc(&ptdev->base, section->data.size, GFP_KERNEL); @@ -626,7 +634,6 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, section->name = name; } - section_size = hdr.va.end - hdr.va.start; if (section_size) { u32 cache_mode = hdr.flags & CSF_FW_BINARY_IFACE_ENTRY_CACHE_MODE_MASK; struct panthor_gem_object *bo; @@ -857,18 +864,24 @@ out: * iface_fw_to_cpu_addr() - Turn an MCU address into a CPU address * @ptdev: Device. * @mcu_va: MCU address. + * @size: Size of the object pointed to by @mcu_va. * - * Return: NULL if the address is not part of the shared section, non-NULL otherwise. + * Return: NULL if the object is not part of the shared section, non-NULL otherwise. */ -static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va) +static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va, size_t size) { u64 shared_mem_start = panthor_kernel_bo_gpuva(ptdev->fw->shared_section->mem); - u64 shared_mem_end = shared_mem_start + - panthor_kernel_bo_size(ptdev->fw->shared_section->mem); - if (mcu_va < shared_mem_start || mcu_va >= shared_mem_end) + size_t shared_mem_size = panthor_kernel_bo_size(ptdev->fw->shared_section->mem); + u64 offset; + + if (mcu_va < shared_mem_start) + return NULL; + + offset = mcu_va - shared_mem_start; + if (offset > shared_mem_size || size > shared_mem_size - offset) return NULL; - return ptdev->fw->shared_section->mem->kmap + (mcu_va - shared_mem_start); + return ptdev->fw->shared_section->mem->kmap + offset; } static int panthor_init_cs_iface(struct panthor_device *ptdev, @@ -890,8 +903,10 @@ static int panthor_init_cs_iface(struct panthor_device *ptdev, spin_lock_init(&cs_iface->lock); cs_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset; - cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va); - cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va); + cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va, + sizeof(*cs_iface->input)); + cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va, + sizeof(*cs_iface->output)); if (!cs_iface->input || !cs_iface->output) { drm_err(&ptdev->base, "Invalid stream control interface input/output VA"); @@ -941,8 +956,10 @@ static int panthor_init_csg_iface(struct panthor_device *ptdev, spin_lock_init(&csg_iface->lock); csg_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset; - csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va); - csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va); + csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va, + sizeof(*csg_iface->input)); + csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va, + sizeof(*csg_iface->output)); if (csg_iface->control->stream_num < MIN_CS_PER_CSG || csg_iface->control->stream_num > MAX_CS_PER_CSG) @@ -999,8 +1016,10 @@ static int panthor_fw_init_ifaces(struct panthor_device *ptdev) return -EINVAL; } - glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va); - glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va); + glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va, + sizeof(*glb_iface->input)); + glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va, + sizeof(*glb_iface->output)); if (!glb_iface->input || !glb_iface->output) { drm_err(&ptdev->base, "Invalid global control interface input/output VA"); return -EINVAL; diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 8e5141bb5075..7877d493d80e 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -104,7 +104,7 @@ vc4_overflow_mem_work(struct work_struct *work) vc4->bin_alloc_overflow = BIT(bin_bo_slot); V3D_WRITE(V3D_BPOA, bo->base.dma_addr + bin_bo_slot * vc4->bin_alloc_size); - V3D_WRITE(V3D_BPOS, bo->base.base.size); + V3D_WRITE(V3D_BPOS, vc4->bin_alloc_size); V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM); V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM); spin_unlock_irqrestore(&vc4->job_lock, irqflags); diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c index 7f2fadfde7a8..d2a65c968b1f 100644 --- a/drivers/gpu/drm/vc4/vc4_validate.c +++ b/drivers/gpu/drm/vc4/vc4_validate.c @@ -385,6 +385,23 @@ validate_tile_binning_config(VALIDATE_ARGS) return -EINVAL; } + /* The tile state data array is 48 bytes per tile, and we put it at + * the start of a BO containing both it and the tile alloc. + */ + tile_state_size = 48 * tile_count; + + /* Since the tile alloc array will follow us, align. */ + tile_state_size = roundup(tile_state_size, 4096); + + /* Reject configurations whose tile state would leave no room for + * the tile alloc pool that follows it in the slot. + */ + if (tile_state_size >= vc4->bin_alloc_size) { + DRM_DEBUG("Tile binning config of %dx%d too large\n", + exec->bin_tiles_x, exec->bin_tiles_y); + return -EINVAL; + } + bin_slot = vc4_v3d_get_bin_slot(vc4); if (bin_slot < 0) { if (bin_slot != -EINTR && bin_slot != -ERESTARTSYS) { @@ -400,13 +417,13 @@ validate_tile_binning_config(VALIDATE_ARGS) exec->bin_slots |= BIT(bin_slot); bin_addr = vc4->bin_bo->base.dma_addr + bin_slot * vc4->bin_alloc_size; - /* The tile state data array is 48 bytes per tile, and we put it at - * the start of a BO containing both it and the tile alloc. - */ - tile_state_size = 48 * tile_count; + exec->tile_alloc_offset = bin_addr + tile_state_size; - /* Since the tile alloc array will follow us, align. */ - exec->tile_alloc_offset = bin_addr + roundup(tile_state_size, 4096); + /* The TSDA area must be zeroed out before use, otherwise the PTB might + * consume a stale tile state. + */ + memset(vc4->bin_bo->base.vaddr + bin_slot * vc4->bin_alloc_size, 0, + tile_state_size); *(uint8_t *)(validated + 14) = ((flags & ~(VC4_BIN_CONFIG_ALLOC_INIT_BLOCK_SIZE_MASK | diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 2421b0dd057c..f9042bafdc93 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -547,14 +547,17 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile, if (IS_ERR(dma_buf)) return PTR_ERR(dma_buf); - if (dma_buf->ops != &tdev->ops) - return -ENOSYS; + if (dma_buf->ops != &tdev->ops) { + ret = -ENOSYS; + goto out; + } prime = (struct ttm_prime_object *) dma_buf->priv; base = &prime->base; *handle = base->handle; ret = ttm_ref_object_add(tfile, base, NULL, false); +out: dma_buf_put(dma_buf); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index 135b75a3e013..56f965ec99dc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -30,6 +30,7 @@ #include "vmwgfx_bo.h" #include <linux/highmem.h> +#include <linux/overflow.h> /* * Template that implements find_first_diff() for a generic @@ -463,19 +464,42 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, container_of(dst->tbo.bdev, struct vmw_private, bdev); size_t dst_size = dst->tbo.resource->size; size_t src_size = src->tbo.resource->size; + size_t dst_end, src_end; struct iosys_map dst_map = {0}; struct iosys_map src_map = {0}; + bool dst_mapped = false; + bool src_mapped = false; int ret, i; int x_in_bytes; u8 *vsrc; u8 *vdst; + if (!height || !width_in_bytes) + return 0; + + if (!dst_stride || !src_stride) + return -EINVAL; + if (dst_stride < width_in_bytes || src_stride < width_in_bytes) + return -EINVAL; + if (check_mul_overflow((size_t)dst_stride, (size_t)height - 1, &dst_end) || + check_add_overflow(dst_end, (size_t)width_in_bytes, &dst_end) || + check_add_overflow((size_t)dst_offset, dst_end, &dst_end) || + dst_end > dst_size || + check_mul_overflow((size_t)src_stride, (size_t)height - 1, &src_end) || + check_add_overflow(src_end, (size_t)width_in_bytes, &src_end) || + check_add_overflow((size_t)src_offset, src_end, &src_end) || + src_end > src_size) { + drm_dbg_driver(&vmw->drm, "Out-of-bounds external BO copy\n"); + return -EINVAL; + } + vsrc = map_external(src, &src_map); if (!vsrc) { drm_dbg_driver(&vmw->drm, "Wasn't able to map src\n"); ret = -ENOMEM; goto out; } + src_mapped = true; vdst = map_external(dst, &dst_map); if (!vdst) { @@ -483,16 +507,13 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, ret = -ENOMEM; goto out; } + dst_mapped = true; vsrc += src_offset; vdst += dst_offset; - if (src_stride == dst_stride) { - dst_size -= dst_offset; - src_size -= src_offset; - memcpy(vdst, vsrc, - min(dst_stride * height, min(dst_size, src_size))); + if (src_stride == dst_stride && width_in_bytes == dst_stride) { + memcpy(vdst, vsrc, dst_stride * (size_t)height); } else { - WARN_ON(dst_stride < width_in_bytes); for (i = 0; i < height; ++i) { memcpy(vdst, vsrc, width_in_bytes); vsrc += src_stride; @@ -508,8 +529,10 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, ret = 0; out: - unmap_external(src, &src_map); - unmap_external(dst, &dst_map); + if (src_mapped) + unmap_external(src, &src_map); + if (dst_mapped) + unmap_external(dst, &dst_map); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c index b010fc7ca68e..d1e7df500190 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c @@ -432,6 +432,7 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps) u32 size = vmw_cursor_mob_size(vps->cursor.update_type, vps->base.crtc_w, vps->base.crtc_h); struct vmw_bo *vbo = vps->cursor.mob; + void *map; if (!vbo) return -EINVAL; @@ -446,11 +447,15 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps) if (unlikely(ret != 0)) return -ENOMEM; - vmw_bo_map_and_cache(vbo); + map = vmw_bo_map_and_cache(vbo); + if (!map) { + vmw_bo_unmap(vbo); + ret = -ENOMEM; + } ttm_bo_unreserve(&vbo->tbo); - return 0; + return ret; } /** @@ -663,9 +668,15 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane, !vmw_cursor_buffer_changed(vps, old_vps)) { vps->cursor.update_type = VMW_CURSOR_UPDATE_NONE; - } else { - vmw_cursor_mob_get(vcp, vps); - vmw_cursor_mob_map(vps); + } else if (vps->cursor.update_type == + VMW_CURSOR_UPDATE_MOB && + (vmw_cursor_mob_get(vcp, vps) || + vmw_cursor_mob_map(vps))) { + /* + * Reset the cursor to avoid crashes later. + */ + vps->cursor.update_type = + VMW_CURSOR_UPDATE_NONE; } } } @@ -732,6 +743,34 @@ int vmw_cursor_plane_atomic_check(struct drm_plane *plane, "surface not suitable for cursor\n"); return -EINVAL; } + } else if (update_type == VMW_CURSOR_UPDATE_GB_ONLY || + update_type == VMW_CURSOR_UPDATE_MOB) { + u32 cursor_max_dim = + vmw_read(vmw, SVGA_REG_CURSOR_MAX_DIMENSION); + + if (new_state->crtc_w > cursor_max_dim || + new_state->crtc_h > cursor_max_dim) { + drm_warn(&vmw->drm, + "Cursor dimensions (%d, %d) exceed device max %u\n", + new_state->crtc_w, new_state->crtc_h, + cursor_max_dim); + return -EINVAL; + } + + if (update_type == VMW_CURSOR_UPDATE_MOB) { + u32 mob_max_size = + vmw_read(vmw, SVGA_REG_MOB_MAX_SIZE); + u64 mob_size = (u64)new_state->crtc_w * + new_state->crtc_h * sizeof(u32) + + sizeof(SVGAGBCursorHeader); + + if (mob_size > mob_max_size) { + drm_warn(&vmw->drm, + "Cursor MOB size %llu exceeds device max %u\n", + mob_size, mob_max_size); + return -EINVAL; + } + } } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index e1f18020170a..a9136a6523cb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1272,9 +1272,13 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXBindQuery); + struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); struct vmw_bo *vmw_bo; int ret; + if (!ctx_node) + return -EINVAL; + cmd = container_of(header, typeof(*cmd), header); /* @@ -1288,7 +1292,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, return ret; sw_context->dx_query_mob = vmw_bo; - sw_context->dx_query_ctx = sw_context->dx_ctx_node->ctx; + sw_context->dx_query_ctx = ctx_node->ctx; return 0; } @@ -1506,6 +1510,12 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, bool dirty; cmd = container_of(header, typeof(*cmd), header); + + if (unlikely(header->size < sizeof(cmd->body) + sizeof(*suffix))) { + VMW_DEBUG_USER("Illegal SVGA_3D_CMD_SURFACE_DMA size.\n"); + return -EINVAL; + } + suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->body + header->size - sizeof(*suffix)); @@ -1567,11 +1577,17 @@ static int vmw_cmd_draw(struct vmw_private *dev_priv, uint32_t maxnum; int ret; + cmd = container_of(header, typeof(*cmd), header); + + if (unlikely(header->size < sizeof(cmd->body))) { + VMW_DEBUG_USER("Illegal DRAW_PRIMITIVES header size.\n"); + return -EINVAL; + } + ret = vmw_cmd_cid_check(dev_priv, sw_context, header); if (unlikely(ret != 0)) return ret; - cmd = container_of(header, typeof(*cmd), header); maxnum = (header->size - sizeof(cmd->body)) / sizeof(*decl); if (unlikely(cmd->body.numVertexDecls > maxnum)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 4ef84ff9b638..384c6736cf6b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -367,13 +367,24 @@ void vmw_fence_fifo_down(struct vmw_fence_manager *fman) ret = vmw_fence_obj_wait(fence, false, false, VMW_FENCE_WAIT_TIMEOUT); + spin_lock(&fman->lock); if (unlikely(ret != 0)) { + bool cookie = dma_fence_begin_signalling(); + list_del_init(&fence->head); - dma_fence_signal(&fence->base); + if (fence->waiter_added) { + vmw_seqno_waiter_remove(fman->dev_priv); + fence->waiter_added = false; + } + dma_fence_signal_locked(&fence->base); + dma_fence_end_signalling(cookie); } BUG_ON(!list_empty(&fence->head)); + spin_unlock(&fman->lock); + dma_fence_put(&fence->base); + spin_lock(&fman->lock); } spin_unlock(&fman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 45561bc1c9ef..8ab88f388652 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -311,7 +311,7 @@ void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res) return; cur = max(res_start, dirty->start); - res_end = max(res_end, dirty->end); + res_end = min(res_end, dirty->end); while (cur < res_end) { unsigned long num; @@ -347,7 +347,7 @@ void vmw_bo_dirty_clear(struct vmw_bo *vbo) return; cur = max(res_start, dirty->start); - res_end = max(res_end, dirty->end); + res_end = min(res_end, dirty->end); while (cur < res_end) { unsigned long num; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 388011696941..e3a187a2c7a1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -136,7 +136,7 @@ static void vmw_resource_release(struct kref *kref) val_buf.num_shared = 0; res->func->unbind(res, false, &val_buf); } - res->guest_memory_size = false; + res->guest_memory_dirty = false; vmw_resource_mob_detach(res); if (res->dirty) res->func->dirty_free(res); @@ -773,7 +773,7 @@ void vmw_resource_unbind_list(struct vmw_bo *vbo) if (!WARN_ON_ONCE(!res->func->unbind)) (void) res->func->unbind(res, res->res_dirty, &val_buf); - res->guest_memory_size = true; + res->guest_memory_dirty = true; res->res_dirty = false; vmw_resource_mob_detach(res); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index eca4e3e97eb4..39811cf19db1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -25,6 +25,8 @@ * **************************************************************************/ +#include <linux/overflow.h> + #include <drm/ttm/ttm_placement.h> #include "vmwgfx_binding.h" @@ -685,7 +687,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data, static int vmw_user_shader_alloc(struct vmw_private *dev_priv, struct vmw_bo *buffer, size_t shader_size, - size_t offset, + u64 offset, SVGA3dShaderType shader_type, uint8_t num_input_sig, uint8_t num_output_sig, @@ -739,7 +741,7 @@ out: static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv, struct vmw_bo *buffer, size_t shader_size, - size_t offset, + u64 offset, SVGA3dShaderType shader_type) { struct vmw_shader *shader; @@ -768,7 +770,7 @@ out_err: static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, enum drm_vmw_shader_type shader_type_drm, - u32 buffer_handle, size_t size, size_t offset, + u32 buffer_handle, size_t size, u64 offset, uint8_t num_input_sig, uint8_t num_output_sig, uint32_t *shader_handle) { @@ -779,13 +781,16 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, int ret; if (buffer_handle != SVGA3D_INVALID_ID) { + u64 end; + ret = vmw_user_bo_lookup(file_priv, buffer_handle, &buffer); if (unlikely(ret != 0)) { VMW_DEBUG_USER("Couldn't find buffer for shader creation.\n"); return ret; } - if ((u64)buffer->tbo.base.size < (u64)size + (u64)offset) { + if (check_add_overflow((u64)size, (u64)offset, &end) || + end > buffer->tbo.base.size) { VMW_DEBUG_USER("Illegal buffer- or shader size.\n"); ret = -EINVAL; goto out_bad_arg; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 35dc94c3db39..45fde7ec514f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -309,7 +309,8 @@ int vmw_validation_add_resource(struct vmw_validation_context *ctx, } node->res = vmw_resource_reference_unless_doomed(res); if (!node->res) { - hash_del_rcu(&node->hash.head); + if (ctx->sw_context) + hash_del_rcu(&node->hash.head); return -ESRCH; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c index 7b8163b5e501..3d0d5dfa869f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c @@ -206,14 +206,14 @@ vmw_vkms_init(struct vmw_private *vmw) vmw->vkms_enabled = false; ret = vmw_host_get_guestinfo(GUESTINFO_VBLANK, buffer, &buf_len); - if (ret || buf_len > max_buf_len) - return; - buffer[buf_len] = '\0'; + if (!ret && buf_len <= max_buf_len) { + buffer[buf_len] = '\0'; - ret = kstrtobool(buffer, &vmw->vkms_enabled); - if (!ret && vmw->vkms_enabled) { - ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS); - vmw->vkms_enabled = (ret == 0); + ret = kstrtobool(buffer, &vmw->vkms_enabled); + if (!ret && vmw->vkms_enabled) { + ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS); + vmw->vkms_enabled = (ret == 0); + } } vmw->crc_workq = alloc_ordered_workqueue("vmwgfx_crc_generator", 0); @@ -228,7 +228,8 @@ vmw_vkms_init(struct vmw_private *vmw) void vmw_vkms_cleanup(struct vmw_private *vmw) { - destroy_workqueue(vmw->crc_workq); + if (vmw->crc_workq) + destroy_workqueue(vmw->crc_workq); } bool diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 39c9c8f0ea2d..d0a1e6c2b55f 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -443,10 +443,6 @@ static bool xe_pt_hugepte_possible(u64 addr, u64 next, unsigned int level, if (!xe_pt_covers(addr, next, level, &xe_walk->base)) return false; - /* Does the DMA segment cover the whole pte? */ - if (next - xe_walk->va_curs_start > xe_walk->curs->size) - return false; - /* null VMA's and purged BO's do not have dma addresses */ if (xe_vma_is_null(xe_walk->vma) || (bo && xe_bo_is_purged(bo))) return true; @@ -455,6 +451,10 @@ static bool xe_pt_hugepte_possible(u64 addr, u64 next, unsigned int level, if (xe_walk->clear_pt) return true; + /* Does the DMA segment cover the whole pte? */ + if (next - xe_walk->va_curs_start > xe_walk->curs->size) + return false; + /* Is the DMA address huge PTE size aligned? */ size = next - addr; dma = addr - xe_walk->va_curs_start + xe_res_dma(xe_walk->curs); @@ -775,8 +775,11 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, } xe_walk.needs_64K = (vm->flags & XE_VM_FLAG_64K); - if (clear_pt) + if (clear_pt) { + xe_assert(xe, !range); + curs.size = xe_vma_size(vma); goto walk_pt; + } if (vma->gpuva.flags & XE_VMA_ATOMIC_PTE_BIT) { xe_walk.default_vram_pte = xe_atomic_for_vram(vm, vma) ? XE_USM_PPGTT_PTE_AE : 0; |