diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
94 files changed, 1655 insertions, 1816 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 130060834b4e..48bd660ddb85 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1050,6 +1050,10 @@ bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { if (adev->flags & AMD_IS_APU) return false; + + if (amdgpu_sriov_vf(adev)) + return false; + return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cbd593f7d553..2170db83e41d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1728,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr); if (user_addr) { - pr_debug("creating userptr BO for user_addr = %llu\n", user_addr); + pr_debug("creating userptr BO for user_addr = %llx\n", user_addr); ret = init_user_pages(*mem, user_addr, criu_resume); if (ret) goto allocate_init_user_pages_failed; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f095a2513aff..25e1f5ed7ead 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2365,8 +2365,16 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) } adev->ip_blocks[i].status.sw = true; - /* need to do gmc hw init early so we can allocate gpu mem */ - if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) { + /* need to do common hw init early so everything is set up for gmc */ + r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev); + if (r) { + DRM_ERROR("hw_init %d failed %d\n", i, r); + goto init_failed; + } + adev->ip_blocks[i].status.hw = true; + } else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + /* need to do gmc hw init early so we can allocate gpu mem */ /* Try to reserve bad pages early */ if (amdgpu_sriov_vf(adev)) amdgpu_virt_exchange_data(adev); @@ -3052,8 +3060,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) int i, r; static enum amd_ip_block_type ip_order[] = { - AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; @@ -3144,7 +3152,8 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev) continue; if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC || - adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) { + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH || + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP && amdgpu_sriov_vf(adev))) { r = adev->ip_blocks[i].version->funcs->resume(adev); if (r) { @@ -4056,12 +4065,20 @@ static void amdgpu_device_evict_resources(struct amdgpu_device *adev) int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) { struct amdgpu_device *adev = drm_to_adev(dev); + int r = 0; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; adev->in_suspend = true; + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_fini_data_exchange(adev); + r = amdgpu_virt_request_full_gpu(adev, false); + if (r) + return r; + } + if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3)) DRM_WARN("smart shift update failed\n"); @@ -4085,6 +4102,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) amdgpu_device_ip_suspend_phase2(adev); + if (amdgpu_sriov_vf(adev)) + amdgpu_virt_release_full_gpu(adev, false); + return 0; } @@ -4103,6 +4123,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) struct amdgpu_device *adev = drm_to_adev(dev); int r = 0; + if (amdgpu_sriov_vf(adev)) { + r = amdgpu_virt_request_full_gpu(adev, true); + if (r) + return r; + } + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; @@ -4117,6 +4143,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) } r = amdgpu_device_ip_resume(adev); + + /* no matter what r is, always need to properly release full GPU */ + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_init_data_exchange(adev); + amdgpu_virt_release_full_gpu(adev, true); + } + if (r) { dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r); return r; @@ -5524,7 +5557,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev, ~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1); resource_size_t aper_limit = adev->gmc.aper_base + adev->gmc.aper_size - 1; - bool p2p_access = !(pci_p2pdma_distance_many(adev->pdev, + bool p2p_access = !adev->gmc.xgmi.connected_to_cpu && + !(pci_p2pdma_distance_many(adev->pdev, &peer_adev->dev, 1, true) < 0); return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index c20922a5af9f..23998f727c7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,6 +38,8 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> @@ -498,6 +500,12 @@ static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .create_handle = drm_gem_fb_create_handle, }; +static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { + .destroy = drm_gem_fb_destroy, + .create_handle = drm_gem_fb_create_handle, + .dirty = drm_atomic_helper_dirtyfb, +}; + uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags) { @@ -1100,7 +1108,10 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, if (ret) goto err; - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (drm_drv_uses_atomic_modeset(dev)) + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic); + else + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); if (ret) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 8adeb7469f1e..d0d99ed607dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -400,7 +400,6 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring) /* We are not protected by ring lock when reading the last sequence * but it's ok to report slightly wrong fence count here. */ - amdgpu_fence_process(ring); emitted = 0x100000000ull; emitted -= atomic_read(&ring->fence_drv.last_seq); emitted += READ_ONCE(ring->fence_drv.sync_seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c index ecada5eadfe3..e325150879df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c @@ -66,10 +66,15 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev) return true; case CHIP_SIENNA_CICHLID: if (strnstr(atom_ctx->vbios_version, "D603", + sizeof(atom_ctx->vbios_version))) { + if (strnstr(atom_ctx->vbios_version, "D603GLXE", sizeof(atom_ctx->vbios_version))) - return true; - else + return false; + else + return true; + } else { return false; + } default: return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 23a696d38390..de5b936b016d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -304,6 +304,10 @@ struct amdgpu_gfx { uint32_t rlc_srlg_feature_version; uint32_t rlc_srls_fw_version; uint32_t rlc_srls_feature_version; + uint32_t rlcp_ucode_version; + uint32_t rlcp_ucode_feature_version; + uint32_t rlcv_ucode_version; + uint32_t rlcv_ucode_feature_version; uint32_t mec_feature_version; uint32_t mec2_feature_version; bool mec_fw_write_wait; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index b1099ee79c50..c2fd6f3076a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -159,7 +159,10 @@ void amdgpu_job_free(struct amdgpu_job *job) amdgpu_sync_free(&job->sync); amdgpu_sync_free(&job->sched_sync); - dma_fence_put(&job->hw_fence); + if (!job->hw_fence.ops) + kfree(job); + else + dma_fence_put(&job->hw_fence); } int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index fe82b8b19a4e..0c546245793b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -181,6 +181,9 @@ int amdgpu_mes_init(struct amdgpu_device *adev) for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) { if (adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(6, 0, 0)) adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc; + /* zero sdma_hqd_mask for non-existent engine */ + else if (adev->sdma.num_instances == 1) + adev->mes.sdma_hqd_mask[i] = i ? 0 : 0xfc; else adev->mes.sdma_hqd_mask[i] = 0xfc; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 7b46f6bf4187..ad980f4b66e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -222,6 +222,8 @@ struct mes_add_queue_input { uint64_t tba_addr; uint64_t tma_addr; uint32_t is_kfd_process; + uint32_t is_aql_queue; + uint32_t queue_size; }; struct mes_remove_queue_input { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 1036446abc30..c9dec2434f37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -486,11 +486,14 @@ static int psp_sw_fini(void *handle) release_firmware(psp->ta_fw); psp->ta_fw = NULL; } - if (adev->psp.cap_fw) { + if (psp->cap_fw) { release_firmware(psp->cap_fw); psp->cap_fw = NULL; } - + if (psp->toc_fw) { + release_firmware(psp->toc_fw); + psp->toc_fw = NULL; + } if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) || adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7)) psp_sysfs_fini(adev); @@ -753,7 +756,7 @@ static int psp_tmr_init(struct psp_context *psp) } pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE(psp->adev), + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, AMDGPU_GEM_DOMAIN_VRAM, &psp->tmr_bo, &psp->tmr_mc_addr, pptr); @@ -2401,7 +2404,7 @@ static int psp_load_smu_fw(struct psp_context *psp) static bool fw_load_skip_check(struct psp_context *psp, struct amdgpu_firmware_info *ucode) { - if (!ucode->fw) + if (!ucode->fw || !ucode->ucode_size) return true; if (ucode->ucode_id == AMDGPU_UCODE_ID_SMC && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index c32b74bd970f..e593e8c2a54d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -36,6 +36,7 @@ #define PSP_CMD_BUFFER_SIZE 0x1000 #define PSP_1_MEG 0x100000 #define PSP_TMR_SIZE(adev) ((adev)->asic_type == CHIP_ALDEBARAN ? 0x800000 : 0x400000) +#define PSP_TMR_ALIGNMENT 0x100000 #define PSP_FW_NAME_LEN 0x24 enum psp_shared_mem_size { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ff5361f5c2d4..12c6f97945a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev) amdgpu_ras_query_error_status(adev, &info); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && - adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) && + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) { if (amdgpu_ras_reset_error_status(adev, info.head.block)) dev_warn(adev->dev, "Failed to reset error counter and error status"); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index 6373bfb47d55..e23f6192c50e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -272,3 +272,267 @@ void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev) &adev->gfx.rlc.cp_table_gpu_addr, (void **)&adev->gfx.rlc.cp_table_ptr); } + +static int amdgpu_gfx_rlc_init_microcode_v2_0(struct amdgpu_device *adev) +{ + const struct common_firmware_header *common_hdr; + const struct rlc_firmware_header_v2_0 *rlc_hdr; + struct amdgpu_firmware_info *info; + unsigned int *tmp; + unsigned int i; + + rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; + + adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); + adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); + adev->gfx.rlc.save_and_restore_offset = + le32_to_cpu(rlc_hdr->save_and_restore_offset); + adev->gfx.rlc.clear_state_descriptor_offset = + le32_to_cpu(rlc_hdr->clear_state_descriptor_offset); + adev->gfx.rlc.avail_scratch_ram_locations = + le32_to_cpu(rlc_hdr->avail_scratch_ram_locations); + adev->gfx.rlc.reg_restore_list_size = + le32_to_cpu(rlc_hdr->reg_restore_list_size); + adev->gfx.rlc.reg_list_format_start = + le32_to_cpu(rlc_hdr->reg_list_format_start); + adev->gfx.rlc.reg_list_format_separate_start = + le32_to_cpu(rlc_hdr->reg_list_format_separate_start); + adev->gfx.rlc.starting_offsets_start = + le32_to_cpu(rlc_hdr->starting_offsets_start); + adev->gfx.rlc.reg_list_format_size_bytes = + le32_to_cpu(rlc_hdr->reg_list_format_size_bytes); + adev->gfx.rlc.reg_list_size_bytes = + le32_to_cpu(rlc_hdr->reg_list_size_bytes); + adev->gfx.rlc.register_list_format = + kmalloc(adev->gfx.rlc.reg_list_format_size_bytes + + adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL); + if (!adev->gfx.rlc.register_list_format) { + dev_err(adev->dev, "failed to allocate memory for rlc register_list_format\n"); + return -ENOMEM; + } + + tmp = (unsigned int *)((uintptr_t)rlc_hdr + + le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); + for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++) + adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]); + + adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i; + + tmp = (unsigned int *)((uintptr_t)rlc_hdr + + le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); + for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) + adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_G; + info->fw = adev->gfx.rlc_fw; + if (info->fw) { + common_hdr = (const struct common_firmware_header *)info->fw->data; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(common_hdr->ucode_size_bytes), PAGE_SIZE); + } + } + + return 0; +} + +static void amdgpu_gfx_rlc_init_microcode_v2_1(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_1 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver); + adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver); + adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes); + adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes); + adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver); + adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver); + adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes); + adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes); + adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver); + adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver); + adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes); + adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes); + adev->gfx.rlc.reg_list_format_direct_reg_list_length = + le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.save_restore_list_gpm_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.save_restore_list_srm_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_2(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_2 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); + adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); + adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); + adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.rlc_iram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.rlc_dram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_3(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_3 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data; + adev->gfx.rlcp_ucode_version = le32_to_cpu(rlc_hdr->rlcp_ucode_version); + adev->gfx.rlcp_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcp_ucode_feature_version); + adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes); + adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes); + + adev->gfx.rlcv_ucode_version = le32_to_cpu(rlc_hdr->rlcv_ucode_version); + adev->gfx.rlcv_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcv_ucode_feature_version); + adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes); + adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.rlcp_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_P; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.rlcv_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_V; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_4(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_4 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_4 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.global_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->global_tap_delays_ucode_size_bytes); + adev->gfx.rlc.global_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->global_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se0_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se0_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se1_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se1_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se2_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se2_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se3_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se3_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + } +} + +int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev, + uint16_t version_major, + uint16_t version_minor) +{ + int err; + + if (version_major < 2) { + /* only support rlc_hdr v2.x and onwards */ + dev_err(adev->dev, "unsupported rlc fw hdr\n"); + return -EINVAL; + } + + /* is_rlc_v2_1 is still used in APU code path */ + if (version_major == 2 && version_minor == 1) + adev->gfx.rlc.is_rlc_v2_1 = true; + + if (version_minor >= 0) { + err = amdgpu_gfx_rlc_init_microcode_v2_0(adev); + if (err) { + dev_err(adev->dev, "fail to init rlc v2_0 microcode\n"); + return err; + } + } + if (version_minor >= 1) + amdgpu_gfx_rlc_init_microcode_v2_1(adev); + if (version_minor >= 2) + amdgpu_gfx_rlc_init_microcode_v2_2(adev); + if (version_minor == 3) + amdgpu_gfx_rlc_init_microcode_v2_3(adev); + if (version_minor == 4) + amdgpu_gfx_rlc_init_microcode_v2_4(adev); + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index 03ac36b2c2cf..23f060db9255 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -267,5 +267,7 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev); int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev); void amdgpu_gfx_rlc_setup_cp_table(struct amdgpu_device *adev); void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev); - +int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev, + uint16_t version_major, + uint16_t version_minor); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index ebed3f5226db..59edf32f775e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -260,8 +260,12 @@ struct rlc_firmware_header_v2_2 { /* version_major=2, version_minor=3 */ struct rlc_firmware_header_v2_3 { struct rlc_firmware_header_v2_2 v2_2; + uint32_t rlcp_ucode_version; + uint32_t rlcp_ucode_feature_version; uint32_t rlcp_ucode_size_bytes; uint32_t rlcp_ucode_offset_bytes; + uint32_t rlcv_ucode_version; + uint32_t rlcv_ucode_feature_version; uint32_t rlcv_ucode_size_bytes; uint32_t rlcv_ucode_offset_bytes; }; @@ -390,6 +394,7 @@ union amdgpu_firmware_header { struct rlc_firmware_header_v2_1 rlc_v2_1; struct rlc_firmware_header_v2_2 rlc_v2_2; struct rlc_firmware_header_v2_3 rlc_v2_3; + struct rlc_firmware_header_v2_4 rlc_v2_4; struct sdma_firmware_header_v1_0 sdma; struct sdma_firmware_header_v1_1 sdma_v1_1; struct sdma_firmware_header_v2_0 sdma_v2_0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f36e4f08db6d..0b52af415b28 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -191,7 +191,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) fw_name = FIRMWARE_VCN4_0_2; if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = false; + adev->vcn.indirect_sram = true; break; case IP_VERSION(4, 0, 4): fw_name = FIRMWARE_VCN4_0_4; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 59cac347baa3..690fd4f639f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2484,8 +2484,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, /* Intentionally setting invalid PTE flag * combination to force a no-retry-fault */ - flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE | - AMDGPU_PTE_TF; + flags = AMDGPU_PTE_SNOOPED | AMDGPU_PTE_PRT; value = 0; } else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) { /* Redirect the access to the dummy page */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index a2a4dc1844c0..a3cd5c1e8529 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4274,35 +4274,45 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) } - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS]; - info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE); + if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE); + } - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS]; - info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE); + if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE); + } - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS]; - info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE); + if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE); + } - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS]; - info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE); + if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE); + } - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS]; - info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE); + if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE); + } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f6b1bb40e503..daf8ba8235cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -474,49 +474,6 @@ static void gfx_v11_0_free_microcode(struct amdgpu_device *adev) kfree(adev->gfx.rlc.register_list_format); } -static void gfx_v11_0_init_rlc_ext_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_1 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver); - adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver); - adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes); - adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes); - adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver); - adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver); - adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes); - adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes); - adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver); - adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver); - adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes); - adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes); - adev->gfx.rlc.reg_list_format_direct_reg_list_length = - le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); -} - -static void gfx_v11_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_2 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); - adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); - adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); - adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); -} - -static void gfx_v11_0_init_rlcp_rlcv_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_3 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes); - adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes); - adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes); - adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes); -} - static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) { char fw_name[40]; @@ -527,8 +484,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) const struct gfx_firmware_header_v1_0 *cp_hdr; const struct gfx_firmware_header_v2_0 *cp_hdr_v2_0; const struct rlc_firmware_header_v2_0 *rlc_hdr; - unsigned int *tmp = NULL; - unsigned int i = 0; uint16_t version_major; uint16_t version_minor; @@ -583,58 +538,14 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) if (err) goto out; err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + if (err) + goto out; rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); - - adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); - adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); - adev->gfx.rlc.save_and_restore_offset = - le32_to_cpu(rlc_hdr->save_and_restore_offset); - adev->gfx.rlc.clear_state_descriptor_offset = - le32_to_cpu(rlc_hdr->clear_state_descriptor_offset); - adev->gfx.rlc.avail_scratch_ram_locations = - le32_to_cpu(rlc_hdr->avail_scratch_ram_locations); - adev->gfx.rlc.reg_restore_list_size = - le32_to_cpu(rlc_hdr->reg_restore_list_size); - adev->gfx.rlc.reg_list_format_start = - le32_to_cpu(rlc_hdr->reg_list_format_start); - adev->gfx.rlc.reg_list_format_separate_start = - le32_to_cpu(rlc_hdr->reg_list_format_separate_start); - adev->gfx.rlc.starting_offsets_start = - le32_to_cpu(rlc_hdr->starting_offsets_start); - adev->gfx.rlc.reg_list_format_size_bytes = - le32_to_cpu(rlc_hdr->reg_list_format_size_bytes); - adev->gfx.rlc.reg_list_size_bytes = - le32_to_cpu(rlc_hdr->reg_list_size_bytes); - adev->gfx.rlc.register_list_format = - kmalloc(adev->gfx.rlc.reg_list_format_size_bytes + - adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL); - if (!adev->gfx.rlc.register_list_format) { - err = -ENOMEM; + err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor); + if (err) goto out; - } - - tmp = (unsigned int *)((uintptr_t)rlc_hdr + - le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); - for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++) - adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]); - - adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i; - - tmp = (unsigned int *)((uintptr_t)rlc_hdr + - le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); - for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) - adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); - - if (version_major == 2) { - if (version_minor >= 1) - gfx_v11_0_init_rlc_ext_microcode(adev); - if (version_minor >= 2) - gfx_v11_0_init_rlc_iram_dram_microcode(adev); - if (version_minor == 3) - gfx_v11_0_init_rlcp_rlcv_microcode(adev); - } } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix); @@ -769,60 +680,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) adev->firmware.fw_size += ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); } - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_G; - info->fw = adev->gfx.rlc_fw; - if (info->fw) { - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - } - if (adev->gfx.rlc.save_restore_list_gpm_size_bytes && - adev->gfx.rlc.save_restore_list_srm_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlc_iram_ucode_size_bytes && - adev->gfx.rlc.rlc_dram_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlcp_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_P; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlcv_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_V; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE); - } } out: @@ -5260,6 +5117,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 reg, data; + amdgpu_gfx_off_ctrl(adev, false); + reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); if (amdgpu_sriov_is_pp_one_vf(adev)) data = RREG32_NO_KIQ(reg); @@ -5273,6 +5132,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data); else WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data); + + amdgpu_gfx_off_ctrl(adev, true); } static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fc9c1043244c..037af8352677 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -5597,7 +5597,7 @@ static void gfx_v9_0_ring_emit_patch_cond_exec(struct amdgpu_ring *ring, unsigne BUG_ON(offset > ring->buf_mask); BUG_ON(ring->ring[offset] != 0x55aa55aa); - cur = (ring->wptr & ring->buf_mask) - 1; + cur = (ring->wptr - 1) & ring->buf_mask; if (likely(cur > offset)) ring->ring[offset] = cur - offset; else diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 4603653916f5..67ca16a8027c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1103,10 +1103,13 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level, *flags |= AMDGPU_PDE_BFS(0x9); } else if (level == AMDGPU_VM_PDB0) { - if (*flags & AMDGPU_PDE_PTE) + if (*flags & AMDGPU_PDE_PTE) { *flags &= ~AMDGPU_PDE_PTE; - else + if (!(*flags & AMDGPU_PTE_VALID)) + *addr |= 1 << PAGE_SHIFT; + } else { *flags |= AMDGPU_PTE_TF; + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 120ea294abef..f92744b8d79d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -183,6 +183,11 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; + mes_add_queue_pkt.trap_en = 1; + + /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ + mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; + mes_add_queue_pkt.gds_size = input->queue_size; return mes_v11_0_submit_pkt_and_poll_completion(mes, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index b465baa26762..aa761ff3a5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -380,6 +380,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, WREG32_PCIE(smnPCIE_LC_CNTL, data); } +#ifdef CONFIG_PCIEASPM static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -401,9 +402,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -459,7 +462,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v2_3_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v2_3_program_ltr(adev); def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -483,6 +489,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index f7f6ddebd3e4..37615a77287b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -282,6 +282,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } +#ifdef CONFIG_PCIEASPM static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -303,9 +304,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; def = data = RREG32_PCIE(smnPCIE_LC_CNTL); @@ -361,7 +364,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v6_1_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v6_1_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -385,6 +391,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 11848d1e238b..19455a725939 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -673,6 +673,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = { }; +#ifdef CONFIG_PCIEASPM static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) { uint32_t def, data; @@ -694,9 +695,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); } +#endif static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) { +#ifdef CONFIG_PCIEASPM uint32_t def, data; if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4)) @@ -755,7 +758,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL6, data); - nbio_v7_4_program_ltr(adev); + /* Don't bother about LTR if LTR is not enabled + * in the path */ + if (adev->pdev->ltr_path) + nbio_v7_4_program_ltr(adev); def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; @@ -779,6 +785,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; if (def != data) WREG32_PCIE(smnPCIE_LC_CNTL3, data); +#endif } const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index 1dc95ef21da6..def89379b51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -28,6 +28,14 @@ #include "nbio/nbio_7_7_0_sh_mask.h" #include <uapi/linux/kfd_ioctl.h> +static void nbio_v7_7_remap_hdp_registers(struct amdgpu_device *adev) +{ + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL); + WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL, + adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL); +} + static u32 nbio_v7_7_get_rev_id(struct amdgpu_device *adev) { u32 tmp; @@ -68,12 +76,6 @@ static void nbio_v7_7_sdma_doorbell_range(struct amdgpu_device *adev, int instan doorbell_range = REG_SET_FIELD(doorbell_range, GDC0_BIF_CSDMA_DOORBELL_RANGE, SIZE, doorbell_size); - doorbell_range = REG_SET_FIELD(doorbell_range, - GDC0_BIF_SDMA0_DOORBELL_RANGE, - OFFSET, doorbell_index); - doorbell_range = REG_SET_FIELD(doorbell_range, - GDC0_BIF_SDMA0_DOORBELL_RANGE, - SIZE, doorbell_size); } else { doorbell_range = REG_SET_FIELD(doorbell_range, GDC0_BIF_SDMA0_DOORBELL_RANGE, @@ -342,4 +344,5 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = { .get_clockgating_state = nbio_v7_7_get_clockgating_state, .ih_control = nbio_v7_7_ih_control, .init_registers = nbio_v7_7_init_registers, + .remap_hdp_registers = nbio_v7_7_remap_hdp_registers, }; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 65181efba50e..56424f75dd2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1504,6 +1504,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev) WREG32_SDMA(i, mmSDMA0_CNTL, temp); if (!amdgpu_sriov_vf(adev)) { + ring = &adev->sdma.instance[i].ring; + adev->nbio.funcs->sdma_doorbell_range(adev, i, + ring->use_doorbell, ring->doorbell_index, + adev->doorbell_index.sdma_doorbell_range); + /* unhalt engine */ temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL); temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index fde6154f2009..183024d7c184 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1211,25 +1211,6 @@ static int soc15_common_sw_fini(void *handle) return 0; } -static void soc15_doorbell_range_init(struct amdgpu_device *adev) -{ - int i; - struct amdgpu_ring *ring; - - /* sdma/ih doorbell range are programed by hypervisor */ - if (!amdgpu_sriov_vf(adev)) { - for (i = 0; i < adev->sdma.num_instances; i++) { - ring = &adev->sdma.instance[i].ring; - adev->nbio.funcs->sdma_doorbell_range(adev, i, - ring->use_doorbell, ring->doorbell_index, - adev->doorbell_index.sdma_doorbell_range); - } - - adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, - adev->irq.ih.doorbell_index); - } -} - static int soc15_common_hw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1249,12 +1230,6 @@ static int soc15_common_hw_init(void *handle) /* enable the doorbell aperture */ soc15_enable_doorbell_aperture(adev, true); - /* HW doorbell routing policy: doorbell writing not - * in SDMA/IH/MM/ACV range will be routed to CP. So - * we need to init SDMA/IH/MM/ACV doorbell range prior - * to CP ip block init and ring test. - */ - soc15_doorbell_range_init(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 55284b24f113..6e564b549b9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -421,6 +421,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): + return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): return false; default: @@ -624,6 +625,7 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; adev->external_rev_id = adev->rev_id + 0x1; break; diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 03b7066471f9..1e83db0c5438 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index 2022ffbb8dba..59dfca093155 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev) } } + if (!amdgpu_sriov_vf(adev)) + adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, + adev->irq.ih.doorbell_index); + pci_set_master(adev->pdev); /* enable interrupts */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e83725a28106..007a3db69df1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -205,6 +205,8 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, } queue_input.is_kfd_process = 1; + queue_input.is_aql_queue = (q->properties.format == KFD_QUEUE_FORMAT_AQL); + queue_input.queue_size = q->properties.queue_size >> 2; queue_input.paging = false; queue_input.tba_addr = qpd->tba_addr; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index a6fcbeeb7428..0d53f6067422 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -350,11 +350,11 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev, print_sq_intr_info_inst(context_id0, context_id1); sq_int_priv = REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, PRIV); - if (sq_int_priv /*&& (kfd_set_dbg_ev_from_interrupt(dev, pasid, + /*if (sq_int_priv && (kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_CTXID0_TRAP_CODE(context_id0), - NULL, 0))*/) - return; + NULL, 0))) + return;*/ break; case SQ_INTERRUPT_WORD_ENCODING_ERROR: print_sq_intr_info_error(context_id0, context_id1); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index b8e14c2cc295..3ae350220d42 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -126,6 +126,10 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF; m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF; m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se4 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se5 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se6 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se7 = 0xFFFFFFFF; m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; 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 5140d9c2bf3b..1efe7fa5bc58 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4759,7 +4759,7 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, plane_info->visible = true; plane_info->stereo_format = PLANE_STEREO_FORMAT_NONE; - plane_info->layer_index = 0; + plane_info->layer_index = plane_state->normalized_zpos; ret = fill_plane_color_attributes(plane_state, plane_info->format, &plane_info->color_space); @@ -4827,7 +4827,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, dc_plane_state->global_alpha = plane_info.global_alpha; dc_plane_state->global_alpha_value = plane_info.global_alpha_value; dc_plane_state->dcc = plane_info.dcc; - dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0 + dc_plane_state->layer_index = plane_info.layer_index; dc_plane_state->flip_int_enabled = true; /* @@ -9485,6 +9485,14 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } + /* + * DC consults the zpos (layer_index in DC terminology) to determine the + * hw plane on which to enable the hw cursor (see + * `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in + * atomic state, so call drm helper to normalize zpos. + */ + drm_atomic_normalize_zpos(dev, state); + /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { ret = dm_update_plane_state(dc, state, plane, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 0e48824f55e3..ee242d9d8b06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -3288,6 +3288,7 @@ void crtc_debugfs_init(struct drm_crtc *crtc) &crc_win_y_end_fops); debugfs_create_file_unsafe("crc_win_update", 0644, dir, crtc, &crc_win_update_fops); + dput(dir); #endif debugfs_create_file("amdgpu_current_bpc", 0644, crtc->debugfs_entry, crtc, &amdgpu_current_bpc_fops); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index c8da18e45b0e..8ca10ab3dfc1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -170,7 +170,13 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) &stream, 1, ¶ms); - power_opt |= psr_power_opt_z10_static_screen; + /* + * Only enable static-screen optimizations for PSR1. For PSR SU, this + * causes vstartup interrupt issues, used by amdgpu_dm to send vblank + * events. + */ + if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1) + power_opt |= psr_power_opt_z10_static_screen; return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index c09be3f15fe6..23a299c929a1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -99,7 +99,7 @@ static int dcn31_get_active_display_cnt_wa( return display_count; } -static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -110,9 +110,10 @@ static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -211,11 +212,11 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn31_disable_otg_wa(clk_mgr_base, true); + dcn31_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn31_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn31_disable_otg_wa(clk_mgr_base, false); + dcn31_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index beb025cd3dc2..4a15aa7a375f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -119,7 +119,7 @@ static int dcn314_get_active_display_cnt_wa( return display_count; } -static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -129,12 +129,21 @@ static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { + struct stream_encoder *stream_enc = pipe->stream_res.stream_enc; + + if (disable) { + if (stream_enc && stream_enc->funcs->disable_fifo) + pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc); + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else { pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); + + if (stream_enc && stream_enc->funcs->enable_fifo) + pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc); + } } } } @@ -233,11 +242,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn314_disable_otg_wa(clk_mgr_base, true); + dcn314_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn314_disable_otg_wa(clk_mgr_base, false); + dcn314_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } @@ -670,6 +679,8 @@ static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *cl } ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz); bw_params->vram_type = bios_info->memory_type; + + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4; for (i = 0; i < WM_SET_COUNT; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index cc076621f5e6..98ad8e0fd2d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -46,6 +46,9 @@ #define TO_CLK_MGR_DCN315(clk_mgr)\ container_of(clk_mgr, struct clk_mgr_dcn315, base) +#define UNSUPPORTED_DCFCLK 10000000 +#define MIN_DPP_DISP_CLK 100000 + static int dcn315_get_active_display_cnt_wa( struct dc *dc, struct dc_state *context) @@ -79,7 +82,7 @@ static int dcn315_get_active_display_cnt_wa( return display_count; } -static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -91,9 +94,10 @@ static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) continue; if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -146,6 +150,9 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, } } + /* Lock pstate by requesting unsupported dcfclk if change is unsupported */ + if (!new_clocks->p_state_change_support) + new_clocks->dcfclk_khz = UNSUPPORTED_DCFCLK; if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) { clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz; dcn315_smu_set_hard_min_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_khz); @@ -159,10 +166,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, // workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow. if (!IS_DIAG_DC(dc->ctx->dce_environment)) { - if (new_clocks->dppclk_khz < 100000) - new_clocks->dppclk_khz = 100000; - if (new_clocks->dispclk_khz < 100000) - new_clocks->dispclk_khz = 100000; + if (new_clocks->dppclk_khz < MIN_DPP_DISP_CLK) + new_clocks->dppclk_khz = MIN_DPP_DISP_CLK; + if (new_clocks->dispclk_khz < MIN_DPP_DISP_CLK) + new_clocks->dispclk_khz = MIN_DPP_DISP_CLK; } if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { @@ -175,12 +182,12 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { /* No need to apply the w/a if we haven't taken over from bios yet */ if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, true); + dcn315_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn315_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, false); + dcn315_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } @@ -275,7 +282,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -283,7 +290,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -291,7 +298,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -299,7 +306,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -556,8 +563,7 @@ static void dcn315_clk_mgr_helper_populate_bw_params( ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz); bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; - if (!bw_params->num_channels) - bw_params->num_channels = 2; + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; for (i = 0; i < WM_SET_COUNT; i++) { bw_params->wm_table.entries[i].wm_inst = i; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 0cd3d2eb7ac7..187f5b27fdc8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -112,7 +112,7 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -124,9 +124,10 @@ static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) continue; if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -221,11 +222,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, true); + dcn316_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, false); + dcn316_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index c6785969eb1a..f0f3f66629cc 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -156,12 +156,14 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); unsigned int num_levels; + unsigned int num_dcfclk_levels, num_dtbclk_levels, num_dispclk_levels; memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks)); clk_mgr_base->clks.p_state_change_support = true; clk_mgr_base->clks.prev_p_state_change_support = true; clk_mgr_base->clks.fclk_prev_p_state_change_support = true; clk_mgr->smu_present = false; + clk_mgr->dpm_present = false; if (!clk_mgr_base->bw_params) return; @@ -179,6 +181,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) dcn32_init_single_clock(clk_mgr, PPCLK_DCFCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz, &num_levels); + num_dcfclk_levels = num_levels; /* SOCCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_SOCCLK, @@ -189,11 +192,16 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) dcn32_init_single_clock(clk_mgr, PPCLK_DTBCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz, &num_levels); + num_dtbclk_levels = num_levels; /* DISPCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DISPCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz, &num_levels); + num_dispclk_levels = num_levels; + + if (num_dcfclk_levels && num_dtbclk_levels && num_dispclk_levels) + clk_mgr->dpm_present = true; if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) { unsigned int i; @@ -658,6 +666,12 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) &num_levels); clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1; + if (clk_mgr->dpm_present && !num_levels) + clk_mgr->dpm_present = false; + + if (!clk_mgr->dpm_present) + dcn32_patch_dpm_table(clk_mgr_base->bw_params); + DC_FP_START(); /* Refresh bounding box */ clk_mgr_base->ctx->dc->res_pool->funcs->update_bw_bounding_box( diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index aeecca68dea7..fb22c3d70528 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1094,7 +1094,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) dc->current_state->stream_count != context->stream_count) should_disable = true; - if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe) { + if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe && + !dc->current_state->res_ctx.pipe_ctx[i].prev_odm_pipe) { struct pipe_ctx *old_pipe, *new_pipe; old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 48dad093ae8b..780f7f4c28b6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2758,8 +2758,14 @@ bool perform_link_training_with_retries( skip_video_pattern); /* Transmit idle pattern once training successful. */ - if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) + if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) { dp_set_hw_test_pattern(link, &pipe_ctx->link_res, DP_TEST_PATTERN_VIDEO_MODE, NULL, 0); + /* Update verified link settings to current one + * Because DPIA LT might fallback to lower link setting. + */ + link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; + link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + } } else { status = dc_link_dp_perform_link_training(link, &pipe_ctx->link_res, @@ -5121,6 +5127,14 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link) lttpr_dpcd_data[DP_PHY_REPEATER_128B132B_RATES - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + /* If this chip cap is set, at least one retimer must exist in the chain + * Override count to 1 if we receive a known bad count (0 or an invalid value) */ + if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN && + (dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) { + ASSERT(0); + link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80; + } + /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ is_lttpr_present = (link->dpcd_caps.lttpr_caps.max_lane_count > 0 && link->dpcd_caps.lttpr_caps.max_lane_count <= 4 && diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7dbab15bfa68..ccf7bd3d90fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -3584,6 +3584,23 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, } } +void reset_sync_context_for_pipe(const struct dc *dc, + struct dc_state *context, + uint8_t pipe_idx) +{ + int i; + struct pipe_ctx *pipe_ctx_reset; + + /* reset the otg sync context for the pipe and its slave pipes if any */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe_ctx_reset = &context->res_ctx.pipe_ctx[i]; + + if (((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx_reset) == pipe_idx) && + IS_PIPE_SYNCD_VALID(pipe_ctx_reset)) || (i == pipe_idx)) + SET_PIPE_SYNCD_TO_PIPE(pipe_ctx_reset, i); + } +} + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter) { /* TODO - get transmitter to phy idx mapping from DMUB */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index f62d50901d92..0c85ab5933b4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -329,7 +329,7 @@ bool dc_stream_set_cursor_attributes( dc = stream->ctx->dc; - if (attributes->height * attributes->width * 4 > 16384) + if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384) if (stream->mall_stream_config.type == SUBVP_MAIN) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5908b60db313..dbf8158b832e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -745,6 +745,7 @@ struct dc_debug_options { bool disable_fixed_vs_aux_timeout_wa; bool force_disable_subvp; bool force_subvp_mclk_switch; + bool allow_sw_cursor_fallback; bool force_usr_allow; /* uses value at boot and disables switch */ bool disable_dtb_ref_clk_switch; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 09b304507bad..52a61b3e5a8b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -417,44 +417,42 @@ static void populate_subvp_cmd_drr_info(struct dc *dc, struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing; struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing; struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing; - int16_t drr_frame_us = 0; - int16_t min_drr_supported_us = 0; - int16_t max_drr_supported_us = 0; - int16_t max_drr_vblank_us = 0; - int16_t max_drr_mallregion_us = 0; - int16_t mall_region_us = 0; - int16_t prefetch_us = 0; - int16_t subvp_active_us = 0; - int16_t drr_active_us = 0; - int16_t min_vtotal_supported = 0; - int16_t max_vtotal_supported = 0; + uint16_t drr_frame_us = 0; + uint16_t min_drr_supported_us = 0; + uint16_t max_drr_supported_us = 0; + uint16_t max_drr_vblank_us = 0; + uint16_t max_drr_mallregion_us = 0; + uint16_t mall_region_us = 0; + uint16_t prefetch_us = 0; + uint16_t subvp_active_us = 0; + uint16_t drr_active_us = 0; + uint16_t min_vtotal_supported = 0; + uint16_t max_vtotal_supported = 0; pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true; pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now - drr_frame_us = div64_s64(drr_timing->v_total * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); + drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); // P-State allow width and FW delays already included phantom_timing->v_addressable - mall_region_us = div64_s64(phantom_timing->v_addressable * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000); + mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100))); min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US; - min_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * - (div64_s64((int64_t)min_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); - - prefetch_us = div64_s64((phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total, - (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000 + - dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp_active_us = div64_s64(main_timing->v_addressable * main_timing->h_total, - (int64_t)(main_timing->pix_clk_100hz * 100) * 1000000); - drr_active_us = div64_s64(drr_timing->v_addressable * drr_timing->h_total, - (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000); - max_drr_vblank_us = div64_s64((int64_t)(subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; + min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); + + prefetch_us = div64_u64(((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000), + (((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000), + (((uint64_t)main_timing->pix_clk_100hz * 100))); + drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000), + (((uint64_t)drr_timing->pix_clk_100hz * 100))); + max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us; max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us; - max_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * (div64_s64((int64_t)max_drr_supported_us, 1000000)), - (int64_t)drr_timing->h_total); + max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us), + (((uint64_t)drr_timing->h_total * 1000000))); pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported; pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported; @@ -548,10 +546,12 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing; struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL; - subvp0_prefetch_us = div64_s64((phantom_timing0->v_total - phantom_timing0->v_front_porch) * phantom_timing0->h_total, - (int64_t)(phantom_timing0->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); - subvp1_prefetch_us = div64_s64((phantom_timing1->v_total - phantom_timing1->v_front_porch) * phantom_timing1->h_total, - (int64_t)(phantom_timing1->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us); + subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) * + (uint64_t)phantom_timing0->h_total * 1000000), + (((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); + subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) * + (uint64_t)phantom_timing1->h_total * 1000000), + (((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us)); // Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time) // should increase it's prefetch time to match the other @@ -559,16 +559,17 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc, pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1]; prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing1->pix_clk_100hz * 100) + phantom_timing1->h_total - 1), - (int64_t)phantom_timing1->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing1->h_total * 1000000)); + } else if (subvp1_prefetch_us > subvp0_prefetch_us) { pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0]; prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us; pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) * - (phantom_timing0->pix_clk_100hz * 100) + phantom_timing0->h_total - 1), - (int64_t)phantom_timing0->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) * + ((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)), + ((uint64_t)phantom_timing0->h_total * 1000000)); } } @@ -630,13 +631,11 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc, // Round up pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_prefetch_end_to_mall_start_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); pipe_data->pipe_config.subvp_data.processing_delay_lines = - div64_s64(((div64_s64((int64_t)dc->caps.subvp_fw_processing_delay_us, 1000000)) * - (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1), - (int64_t)phantom_timing->h_total); + div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) + + ((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000)); // Find phantom pipe index based on phantom stream for (j = 0; j < dc->res_pool->pipe_count; j++) { struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h index cd2671161ef1..7ce64a3c1b02 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h @@ -445,226 +445,6 @@ type DSCRM_DSC_FORWARD_EN; \ type DSCRM_DSC_OPP_PIPE_SOURCE -#define DSC_REG_LIST_DCN314(id) \ - SRI(DSC_TOP_CONTROL, DSC_TOP, id),\ - SRI(DSC_DEBUG_CONTROL, DSC_TOP, id),\ - SRI(DSCC_CONFIG0, DSCC, id),\ - SRI(DSCC_CONFIG1, DSCC, id),\ - SRI(DSCC_STATUS, DSCC, id),\ - SRI(DSCC_INTERRUPT_CONTROL_STATUS, DSCC, id),\ - SRI(DSCC_PPS_CONFIG0, DSCC, id),\ - SRI(DSCC_PPS_CONFIG1, DSCC, id),\ - SRI(DSCC_PPS_CONFIG2, DSCC, id),\ - SRI(DSCC_PPS_CONFIG3, DSCC, id),\ - SRI(DSCC_PPS_CONFIG4, DSCC, id),\ - SRI(DSCC_PPS_CONFIG5, DSCC, id),\ - SRI(DSCC_PPS_CONFIG6, DSCC, id),\ - SRI(DSCC_PPS_CONFIG7, DSCC, id),\ - SRI(DSCC_PPS_CONFIG8, DSCC, id),\ - SRI(DSCC_PPS_CONFIG9, DSCC, id),\ - SRI(DSCC_PPS_CONFIG10, DSCC, id),\ - SRI(DSCC_PPS_CONFIG11, DSCC, id),\ - SRI(DSCC_PPS_CONFIG12, DSCC, id),\ - SRI(DSCC_PPS_CONFIG13, DSCC, id),\ - SRI(DSCC_PPS_CONFIG14, DSCC, id),\ - SRI(DSCC_PPS_CONFIG15, DSCC, id),\ - SRI(DSCC_PPS_CONFIG16, DSCC, id),\ - SRI(DSCC_PPS_CONFIG17, DSCC, id),\ - SRI(DSCC_PPS_CONFIG18, DSCC, id),\ - SRI(DSCC_PPS_CONFIG19, DSCC, id),\ - SRI(DSCC_PPS_CONFIG20, DSCC, id),\ - SRI(DSCC_PPS_CONFIG21, DSCC, id),\ - SRI(DSCC_PPS_CONFIG22, DSCC, id),\ - SRI(DSCC_MEM_POWER_CONTROL, DSCC, id),\ - SRI(DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_MAX_ABS_ERROR0, DSCC, id),\ - SRI(DSCC_MAX_ABS_ERROR1, DSCC, id),\ - SRI(DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCCIF_CONFIG0, DSCCIF, id),\ - SRI(DSCCIF_CONFIG1, DSCCIF, id),\ - SRI(DSCRM_DSC_FORWARD_CONFIG, DSCRM, id) - -#define DSC_REG_LIST_SH_MASK_DCN314(mask_sh)\ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_CLOCK_EN, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DISPCLK_R_GATE_DIS, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DSCCLK_R_GATE_DIS, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_DBG_EN, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_TEST_CLOCK_MUX_SEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_PER_LINE, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, ALTERNATE_ICH_ENCODING_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_IN_VERTICAL_DIRECTION, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_RATE_CONTROL_BUFFER_MODEL_SIZE, mask_sh), \ - /*DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_DISABLE_ICH, mask_sh),*/ \ - DSC_SF(DSCC0_DSCC_STATUS, DSCC_DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MINOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MAJOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, PPS_IDENTIFIER, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, LINEBUF_DEPTH, mask_sh), \ - DSC2_SF(DSCC0, DSCC_PPS_CONFIG0__BITS_PER_COMPONENT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BITS_PER_PIXEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, VBR_ENABLE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, SIMPLE_422, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CONVERT_RGB, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BLOCK_PRED_ENABLE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_422, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_420, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CHUNK_SIZE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_WIDTH, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_HEIGHT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_WIDTH, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_HEIGHT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_XMIT_DELAY, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_DEC_DELAY, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG5, INITIAL_SCALE_VALUE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG5, SCALE_INCREMENT_INTERVAL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SCALE_DECREMENT_INTERVAL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, FIRST_LINE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SECOND_LINE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG7, NFL_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG7, SLICE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG8, NSL_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG8, SECOND_LINE_OFFSET_ADJ, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG9, INITIAL_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG9, FINAL_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MIN_QP, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MAX_QP, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, RC_MODEL_SIZE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_EDGE_FACTOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_LO, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_HI, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MIN_QP0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MAX_QP0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_BPG_OFFSET0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP14, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP14, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET14, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_DEFAULT_MEM_LOW_POWER_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_FORCE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_DIS, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_FORCE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_DIS, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC_R_Y_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC_R_Y_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC_G_CB_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC_G_CB_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC_B_CR_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC_B_CR_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_R_Y_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_G_CB_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR1, DSCC_B_CR_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_RECOVERY_EN, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_STATUS, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_PIXEL_FORMAT, mask_sh), \ - DSC2_SF(DSCCIF0, DSCCIF_CONFIG0__BITS_PER_COMPONENT, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_WIDTH, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_HEIGHT, mask_sh), \ - DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, mask_sh), \ - DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_OPP_PIPE_SOURCE, mask_sh) - - struct dcn20_dsc_registers { uint32_t DSC_TOP_CONTROL; uint32_t DSC_DEBUG_CONTROL; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 884fa060f375..598ce872a8d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1565,6 +1565,7 @@ static void dcn20_update_dchubp_dpp( /* Any updates are handled in dc interface, just need * to apply existing for plane enable / opp change */ if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed + || pipe_ctx->update_flags.bits.plane_changed || pipe_ctx->stream->update_flags.bits.gamut_remap || pipe_ctx->stream->update_flags.bits.out_csc) { /* dpp/cm gamut remap*/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c index a788d160953b..ab70ebd8f223 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c @@ -104,6 +104,9 @@ static bool has_query_dp_alt(struct link_encoder *enc) { struct dc_dmub_srv *dc_dmub_srv = enc->ctx->dmub_srv; + if (enc->ctx->dce_version >= DCN_VERSION_3_15) + return true; + /* Supports development firmware and firmware >= 4.0.11 */ return dc_dmub_srv && !(dc_dmub_srv->dmub->fw_version >= DMUB_FW_VERSION(4, 0, 0) && diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 232cc15979dd..fb729674953b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -45,6 +45,48 @@ #define DC_LOGGER \ dccg->ctx->logger +static void dccg314_get_pixel_rate_div( + struct dccg *dccg, + uint32_t otg_inst, + enum pixel_rate_div *k1, + enum pixel_rate_div *k2) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA; + + *k1 = PIXEL_RATE_DIV_NA; + *k2 = PIXEL_RATE_DIV_NA; + + switch (otg_inst) { + case 0: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG0_PIXEL_RATE_DIVK1, &val_k1, + OTG0_PIXEL_RATE_DIVK2, &val_k2); + break; + case 1: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG1_PIXEL_RATE_DIVK1, &val_k1, + OTG1_PIXEL_RATE_DIVK2, &val_k2); + break; + case 2: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG2_PIXEL_RATE_DIVK1, &val_k1, + OTG2_PIXEL_RATE_DIVK2, &val_k2); + break; + case 3: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG3_PIXEL_RATE_DIVK1, &val_k1, + OTG3_PIXEL_RATE_DIVK2, &val_k2); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } + + *k1 = (enum pixel_rate_div)val_k1; + *k2 = (enum pixel_rate_div)val_k2; +} + static void dccg314_set_pixel_rate_div( struct dccg *dccg, uint32_t otg_inst, @@ -52,6 +94,11 @@ static void dccg314_set_pixel_rate_div( enum pixel_rate_div k2) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + + dccg314_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA || (k1 == cur_k1 && k2 == cur_k2)) + return; switch (otg_inst) { case 0: diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index b384f30395d3..8c0ab013764e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -56,7 +56,8 @@ static void enc314_enable_fifo(struct stream_encoder *enc) /* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */ REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000); - REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000); @@ -67,8 +68,7 @@ static void enc314_disable_fifo(struct stream_encoder *enc) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0, - DIG_FIFO_READ_START_LEVEL, 0); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0); } static void enc314_dp_set_odm_combine( @@ -262,6 +262,16 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } +void enc314_stream_encoder_dp_blank( + struct dc_link *link, + struct stream_encoder *enc) +{ + /* New to DCN314 - disable the FIFO before VID stream disable. */ + enc314_disable_fifo(enc); + + enc1_stream_encoder_dp_blank(link, enc); +} + static void enc314_stream_encoder_dp_unblank( struct dc_link *link, struct stream_encoder *enc, @@ -322,9 +332,6 @@ static void enc314_stream_encoder_dp_unblank( REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0); - /* DIG Resync FIFO now needs to be explicitly enabled. */ - enc314_enable_fifo(enc); - /* wait 100us for DIG/DP logic to prime * (i.e. a few video lines) */ @@ -340,6 +347,12 @@ static void enc314_stream_encoder_dp_unblank( REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, true); + /* + * DIG Resync FIFO now needs to be explicitly enabled. + * This should come after DP_VID_STREAM_ENABLE per HW docs. + */ + enc314_enable_fifo(enc); + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_DP_VID_STREAM); } @@ -408,7 +421,7 @@ static const struct stream_encoder_funcs dcn314_str_enc_funcs = { .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, .dp_blank = - enc1_stream_encoder_dp_blank, + enc314_stream_encoder_dp_blank, .dp_unblank = enc314_stream_encoder_dp_unblank, .audio_mute_control = enc3_audio_mute_control, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 39931d48f385..f4d1b83979fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -343,7 +343,6 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig { struct dc_stream_state *stream = pipe_ctx->stream; unsigned int odm_combine_factor = 0; - struct dc *dc = pipe_ctx->stream->ctx->dc; bool two_pix_per_container = false; two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); @@ -364,7 +363,7 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig } else { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_4; - if ((odm_combine_factor == 2) || dc->debug.enable_dp_dig_pixel_rate_div_policy) + if (odm_combine_factor == 2) *k2_div = PIXEL_RATE_DIV_BY_2; } } @@ -384,21 +383,10 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx) return; odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1 - || dcn314_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) + if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1) pix_per_cycle = 2; if (pipe_ctx->stream_res.stream_enc->funcs->set_input_mode) pipe_ctx->stream_res.stream_enc->funcs->set_input_mode(pipe_ctx->stream_res.stream_enc, pix_per_cycle); } - -bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) -{ - struct dc *dc = pipe_ctx->stream->ctx->dc; - - if (dc_is_dp_signal(pipe_ctx->stream->signal) && !is_dp_128b_132b_signal(pipe_ctx) && - dc->debug.enable_dp_dig_pixel_rate_div_policy) - return true; - return false; -} diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h index d014580592ac..244280298212 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h @@ -41,6 +41,4 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx); -bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); - #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index fcf67eb3478f..72a563a4c3e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -146,7 +146,6 @@ static const struct hwseq_private_funcs dcn314_private_funcs = { .setup_hpo_hw_control = dcn31_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn314_calculate_dccg_k1_k2_values, .set_pixels_per_cycle = dcn314_set_pixels_per_cycle, - .is_dp_dig_pixel_rate_div_policy = dcn314_is_dp_dig_pixel_rate_div_policy, }; void dcn314_hw_sequencer_construct(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c index 0c7980266b85..38aa28ec6b13 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c @@ -98,7 +98,8 @@ static void optc314_set_odm_combine(struct timing_generator *optc, int *opp_id, REG_UPDATE(OPTC_WIDTH_CONTROL, OPTC_SEGMENT_WIDTH, mpcc_hactive); - REG_SET(OTG_H_TIMING_CNTL, 0, OTG_H_TIMING_DIV_MODE, opp_cnt - 1); + REG_UPDATE(OTG_H_TIMING_CNTL, + OTG_H_TIMING_DIV_MODE, opp_cnt - 1); optc1->opp_count = opp_cnt; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 3a9e3870b3a9..44ac1c2aabf5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -87,6 +87,9 @@ #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH__SHIFT 0x10 #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH_MASK 0x01FF0000L +#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE__SHIFT 0x0 +#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE_MASK 0x0000000FL + #include "reg_helper.h" #include "dce/dmub_abm.h" #include "dce/dmub_psr.h" @@ -454,6 +457,7 @@ static const struct dcn31_hpo_dp_stream_encoder_registers hpo_dp_stream_enc_regs hpo_dp_stream_encoder_reg_list(0), hpo_dp_stream_encoder_reg_list(1), hpo_dp_stream_encoder_reg_list(2), + hpo_dp_stream_encoder_reg_list(3) }; static const struct dcn31_hpo_dp_stream_encoder_shift hpo_dp_se_shift = { @@ -578,7 +582,7 @@ static const struct dcn30_mmhubbub_mask mcif_wb30_mask = { #define dsc_regsDCN314(id)\ [id] = {\ - DSC_REG_LIST_DCN314(id)\ + DSC_REG_LIST_DCN20(id)\ } static const struct dcn20_dsc_registers dsc_regs[] = { @@ -589,11 +593,11 @@ static const struct dcn20_dsc_registers dsc_regs[] = { }; static const struct dcn20_dsc_shift dsc_shift = { - DSC_REG_LIST_SH_MASK_DCN314(__SHIFT) + DSC_REG_LIST_SH_MASK_DCN20(__SHIFT) }; static const struct dcn20_dsc_mask dsc_mask = { - DSC_REG_LIST_SH_MASK_DCN314(_MASK) + DSC_REG_LIST_SH_MASK_DCN20(_MASK) }; static const struct dcn30_mpc_registers mpc_regs = { @@ -843,7 +847,7 @@ static const struct resource_caps res_cap_dcn314 = { .num_ddc = 5, .num_vmid = 16, .num_mpc_3dlut = 2, - .num_dsc = 4, + .num_dsc = 3, }; static const struct dc_plane_cap plane_cap = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index a31c64b50410..6640d0ac4304 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -42,6 +42,48 @@ #define DC_LOGGER \ dccg->ctx->logger +static void dccg32_get_pixel_rate_div( + struct dccg *dccg, + uint32_t otg_inst, + enum pixel_rate_div *k1, + enum pixel_rate_div *k2) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA; + + *k1 = PIXEL_RATE_DIV_NA; + *k2 = PIXEL_RATE_DIV_NA; + + switch (otg_inst) { + case 0: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG0_PIXEL_RATE_DIVK1, &val_k1, + OTG0_PIXEL_RATE_DIVK2, &val_k2); + break; + case 1: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG1_PIXEL_RATE_DIVK1, &val_k1, + OTG1_PIXEL_RATE_DIVK2, &val_k2); + break; + case 2: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG2_PIXEL_RATE_DIVK1, &val_k1, + OTG2_PIXEL_RATE_DIVK2, &val_k2); + break; + case 3: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG3_PIXEL_RATE_DIVK1, &val_k1, + OTG3_PIXEL_RATE_DIVK2, &val_k2); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } + + *k1 = (enum pixel_rate_div)val_k1; + *k2 = (enum pixel_rate_div)val_k2; +} + static void dccg32_set_pixel_rate_div( struct dccg *dccg, uint32_t otg_inst, @@ -50,6 +92,17 @@ static void dccg32_set_pixel_rate_div( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + + // Don't program 0xF into the register field. Not valid since + // K1 / K2 field is only 1 / 2 bits wide + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) + return; + + dccg32_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); + if (k1 == cur_k1 && k2 == cur_k2) + return; + switch (otg_inst) { case 0: REG_UPDATE_2(OTG_PIXEL_RATE_DIV, @@ -225,19 +278,19 @@ void dccg32_set_dpstreamclk( case 0: REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK0_EN, - (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, 0); + (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, otg_inst); break; case 1: REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK1_EN, - (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, 1); + (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, otg_inst); break; case 2: REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK2_EN, - (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, 2); + (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, otg_inst); break; case 3: REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK3_EN, - (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, 3); + (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, otg_inst); break; default: BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c index 26648ce772da..38a48983f663 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c @@ -310,6 +310,11 @@ static void enc32_stream_encoder_dp_unblank( // TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000); + /* read start level = 0 will bring underflow / overflow and DIG_FIFO_ERROR = 1 + * so set it to 1/2 full = 7 before reset as suggested by hardware team. + */ + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c index 99eb239bbc7b..9aebc1be2f59 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c @@ -98,9 +98,13 @@ static void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigne default: break; } - /* Should never be hit, if it is we have an erroneous hw config*/ - ASSERT(hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size - + hubbub2->det3_size + hubbub2->compbuf_size_segments <= hubbub2->crb_size_segs); + if (hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size + + hubbub2->det3_size + hubbub2->compbuf_size_segments > hubbub2->crb_size_segs) { + /* This may happen during seamless transition from ODM 2:1 to ODM4:1 */ + DC_LOG_WARNING("CRB Config Warning: DET size (%d,%d,%d,%d) + Compbuf size (%d) > CRB segments (%d)\n", + hubbub2->det0_size, hubbub2->det1_size, hubbub2->det2_size, hubbub2->det3_size, + hubbub2->compbuf_size_segments, hubbub2->crb_size_segs); + } } static void dcn32_program_compbuf_size(struct hubbub *hubbub, unsigned int compbuf_size_kb, bool safe_to_increase) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index 6ec1c52535b9..2038cbda33f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes( enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk( attr->width, attr->color_format); + //Round cursor width up to next multiple of 64 + uint32_t cursor_width = ((attr->width + 63) / 64) * 64; + uint32_t cursor_height = attr->height; + uint32_t cursor_size = cursor_width * cursor_height; + hubp->curs_attr = *attr; REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH, @@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes( /* used to shift the cursor chunk request deadline */ CURSOR0_CHUNK_HDL_ADJUST, 3); - if (attr->width * attr->height * 4 > 16384) + switch (attr->color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true); else REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index ebd3945c71f1..344fe7535df5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -295,24 +295,38 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c } // Include cursor size for CAB allocation - if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) { - cursor_size = dc->caps.max_cursor_size * dc->caps.max_cursor_size; - switch (stream->cursor_attributes.color_format) { - case CURSOR_MODE_MONO: - cursor_size /= 2; - break; - case CURSOR_MODE_COLOR_1BIT_AND: - case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: - case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: - cursor_size *= 4; - break; + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe = &ctx->res_ctx.pipe_ctx[j]; + struct hubp *hubp = pipe->plane_res.hubp; - case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: - case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: - cursor_size *= 8; - break; - } - cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size, + if (pipe->stream && pipe->plane_state && hubp) + /* Find the cursor plane and use the exact size instead of + * using the max for calculation + */ + if (hubp->curs_attr.width > 0) { + cursor_size = hubp->curs_attr.width * hubp->curs_attr.height; + break; + } + } + + switch (stream->cursor_attributes.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + cursor_size *= 8; + break; + } + + if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) { + cache_lines_used += dcn32_cache_lines_for_surface(dc, cursor_size, plane->address.grph.cursor_cache_addr.quad_part); } } @@ -325,6 +339,26 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c if (cache_lines_used % lines_per_way > 0) num_ways++; + for (i = 0; i < ctx->stream_count; i++) { + stream = ctx->streams[i]; + for (j = 0; j < ctx->stream_status[i].plane_count; j++) { + plane = ctx->stream_status[i].plane_states[j]; + + if (stream->cursor_position.enable && plane && + !plane->address.grph.cursor_cache_addr.quad_part && + cursor_size > 16384) { + /* Cursor caching is not supported since it won't be on the same line. + * So we need an extra line to accommodate it. With large cursors and a single 4k monitor + * this case triggers corruption. If we're at the edge, then dont trigger display refresh + * from MALL. We only need to cache cursor if its greater that 64x64 at 4 bpp. + */ + num_ways++; + /* We only expect one cursor plane */ + break; + } + } + } + return num_ways; } @@ -707,7 +741,29 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) struct hubp *hubp = pipe->plane_res.hubp; if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) { - if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384) + //Round cursor width up to next multiple of 64 + int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64; + int cursor_height = hubp->curs_attr.height; + int cursor_size = cursor_width * cursor_height; + + switch (hubp->curs_attr.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + break; + case CURSOR_MODE_COLOR_1BIT_AND: + case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA: + case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA: + cursor_size *= 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + default: + cursor_size *= 8; + break; + } + + if (cursor_size > 16384) cache_cursor = true; if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 8b887b552f2c..c3b783cea8a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -871,6 +871,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -2039,7 +2040,8 @@ static bool dcn32_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max_cursor_size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 1e7e6201c880..cf15d0e5e9b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -30,6 +30,9 @@ #define DCN3_2_DET_SEG_SIZE 64 #define DCN3_2_MALL_MBLK_SIZE_BYTES 65536 // 64 * 1024 +#define DCN3_2_MBLK_WIDTH 128 +#define DCN3_2_MBLK_HEIGHT_4BPE 128 +#define DCN3_2_MBLK_HEIGHT_8BPE 64 #define TO_DCN32_RES_POOL(pool)\ container_of(pool, struct dcn32_resource_pool, base) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index 955f52e6064d..1f195c5b3377 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -46,7 +46,6 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_state *context) { uint32_t num_ways = 0; - uint32_t mall_region_pixels = 0; uint32_t bytes_per_pixel = 0; uint32_t cache_lines_used = 0; uint32_t lines_per_way = 0; @@ -54,20 +53,64 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat uint32_t bytes_in_mall = 0; uint32_t num_mblks = 0; uint32_t cache_lines_per_plane = 0; - uint32_t i = 0; + uint32_t i = 0, j = 0; + uint32_t mblk_width = 0; + uint32_t mblk_height = 0; + uint32_t full_vp_width_blk_aligned = 0; + uint32_t full_vp_height_blk_aligned = 0; + uint32_t mall_alloc_width_blk_aligned = 0; + uint32_t mall_alloc_height_blk_aligned = 0; + uint32_t full_vp_height = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; // Find the phantom pipes - if (pipe->stream && pipe->plane_state && !pipe->top_pipe && + if (pipe->stream && pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { - bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; - mall_region_pixels = pipe->plane_state->plane_size.surface_pitch * pipe->stream->timing.v_addressable; + struct pipe_ctx *main_pipe = NULL; - // For bytes required in MALL, calculate based on number of MBlks required - num_mblks = (mall_region_pixels * bytes_per_pixel + - DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES; + /* Get full viewport height from main pipe (required for MBLK calculation) */ + for (j = 0; j < dc->res_pool->pipe_count; j++) { + main_pipe = &context->res_ctx.pipe_ctx[j]; + if (main_pipe->stream == pipe->stream->mall_stream_config.paired_stream) { + full_vp_height = main_pipe->plane_res.scl_data.viewport.height; + break; + } + } + + bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4; + mblk_width = DCN3_2_MBLK_WIDTH; + mblk_height = bytes_per_pixel == 4 ? DCN3_2_MBLK_HEIGHT_4BPE : DCN3_2_MBLK_HEIGHT_8BPE; + + /* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) - + * FLOOR(vp_x_start, blk_width) + */ + full_vp_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x + + pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) + + (pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width); + + /* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) - + * FLOOR(vp_y_start, blk_height) + */ + full_vp_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + + full_vp_height + mblk_height - 1) / mblk_height * mblk_height) + + (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); + + /* mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c */ + mall_alloc_width_blk_aligned = full_vp_width_blk_aligned; + + /* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */ + mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) / + mblk_height * mblk_height + mblk_height; + + /* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c; + * full_mblk_height_ub_l/c = mall_alloc_height_blk_aligned_l/c; + * num_mblk_l/c = (full_mblk_width_ub_l/c / mblk_width_l/c) * (full_mblk_height_ub_l/c / mblk_height_l/c); + * (Should be divisible, but round up if not) + */ + num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * + ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; // cache lines used is total bytes / cache_line size. Add +2 for worst case alignment // (MALL is 64-byte aligned) @@ -144,7 +187,7 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc, struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->stream) - continue; + return false; if (!pipe->plane_state) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index c8b7d6ff38f4..7309eed33a61 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -872,6 +872,7 @@ static const struct dc_debug_options debug_defaults_drv = { .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, }; static const struct dc_debug_options debug_defaults_diags = { @@ -1651,7 +1652,8 @@ static bool dcn321_resource_construct( dc->caps.max_downscale_ratio = 600; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/ - dc->caps.max_cursor_size = 256; + /* TODO: Bring max cursor size back to 256 after subvp cursor corruption is fixed*/ + dc->caps.max_cursor_size = 64; dc->caps.min_horizontal_blanking_period = 80; dc->caps.dmdata_alloc_size = 2048; dc->caps.mall_size_per_mem_channel = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 86a3b5bfd699..cb81ed2fbd53 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -70,6 +70,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_ccflags) $(frame_warn_flag) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags) @@ -123,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o DML += dcn30/dcn30_fpu.o dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o +DML += dcn314/display_mode_vba_314.o dcn314/display_rq_dlg_calc_314.o DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o dcn32/display_mode_vba_util_32.o DML += dcn31/dcn31_fpu.o DML += dcn32/dcn32_fpu.o diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index 876b321b30ca..1cb858dd6ea0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -6610,8 +6610,7 @@ static double CalculateUrgentLatency( return ret; } - -static void UseMinimumDCFCLK( +static noinline_for_stack void UseMinimumDCFCLK( struct display_mode_lib *mode_lib, int MaxInterDCNTileRepeaters, int MaxPrefetchMode, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 149a1b17cdf3..fa7b0291ce4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .num_chans = 4, }; struct _vcs_dpi_ip_params_st dcn3_16_ip = { @@ -680,7 +681,11 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_15_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator; dcn3_15_ip.max_num_dpp = dc->res_pool->pipe_count; - dcn3_15_soc.num_chans = bw_params->num_channels; + + if (bw_params->num_channels > 0) + dcn3_15_soc.num_chans = bw_params->num_channels; + if (bw_params->dram_channel_width_bytes > 0) + dcn3_15_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes; ASSERT(clk_table->num_entries); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index d63b4209b14c..8ca66f1644dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -251,33 +251,13 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe); + double DPTEBytesPerRow); static double CalculateWriteBackDelay( enum source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -311,64 +291,28 @@ static void CalculateVupdateAndDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + double *Z8StutterEnterPlusExitWatermark); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, @@ -2904,33 +2848,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < v->NumberOfActivePlanes; ++k) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->UrgentExtraLatency, v->UrgentLatency, - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], - v->PixelPTEBytesPerRow[k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->PixelPTEBytesPerRow[k]); } v->total_dcn_read_bw_with_flip = 0.0; @@ -3017,64 +2941,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->DCFCLKDeepSleep, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, &v->StutterExitWatermark, &v->StutterEnterPlusExitWatermark, &v->Z8StutterExitWatermark, - &v->Z8StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->Z8StutterEnterPlusExitWatermark); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -3598,61 +3486,43 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe) + double DPTEBytesPerRow) { + struct vba_vars_st *v = &mode_lib->vba; double min_row_time = 0.0; unsigned int HostVMDynamicLevelsTrips; double TimeForFetchingMetaPTEImmediateFlip; double TimeForFetchingRowInVBlankImmediateFlip; double ImmediateFlipBW; + double LineTime = v->HTotal[k] / v->PixelClock[k]; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMDynamicLevelsTrips = 0; } - if (GPUVMEnable == true || DCCEnable == true) { - ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes; + if (v->GPUVMEnable == true || v->DCCEnable[k] == true) { + ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes; } - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { TimeForFetchingMetaPTEImmediateFlip = dml_max3( - Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, - UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), + v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, + UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), LineTime / 4.0); } else { TimeForFetchingMetaPTEImmediateFlip = 0; } - *DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; - if ((GPUVMEnable == true || DCCEnable == true)) { + v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; + if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { TimeForFetchingRowInVBlankImmediateFlip = dml_max3( (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW, UrgentLatency * (HostVMDynamicLevelsTrips + 1), @@ -3661,54 +3531,54 @@ static void CalculateFlipSchedule( TimeForFetchingRowInVBlankImmediateFlip = 0; } - *DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; + v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; - if (GPUVMEnable == true) { - *final_flip_bw = dml_max( - PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime), - (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime)); - } else if ((GPUVMEnable == true || DCCEnable == true)) { - *final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime); + if (v->GPUVMEnable == true) { + v->final_flip_bw[k] = dml_max( + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime), + (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime)); + } else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { + v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime); } else { - *final_flip_bw = 0; + v->final_flip_bw[k] = 0; } - if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma); - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma); + if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) { + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } else { min_row_time = dml_min4( - dpte_row_height * LineTime / VRatio, - meta_row_height * LineTime / VRatio, - dpte_row_height_chroma * LineTime / VRatioChroma, - meta_row_height_chroma * LineTime / VRatioChroma); + v->dpte_row_height[k] * LineTime / v->VRatio[k], + v->meta_row_height[k] * LineTime / v->VRatio[k], + v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k], + v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } } else { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dpte_row_height * LineTime / VRatio; - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = meta_row_height * LineTime / VRatio; + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k]; + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k]; } else { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio); + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]); } } - if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16 + if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16 || TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) { - *ImmediateFlipSupportedForPipe = false; + v->ImmediateFlipSupportedForPipe[k] = false; } else { - *ImmediateFlipSupportedForPipe = true; + v->ImmediateFlipSupportedForPipe[k] = true; } #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip); - dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip); + dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]); + dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]); dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip); dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip); dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time); - dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe); + dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]); #endif } @@ -5300,33 +5170,13 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k < v->NumberOfActivePlanes; k++) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->ExtraLatency, v->UrgLatency[i], - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesPerFrame[i][j][k], v->MetaRowBytes[i][j][k], - v->DPTEBytesPerRow[i][j][k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->DPTEBytesPerRow[i][j][k]); } v->total_dcn_read_bw_with_flip = 0.0; for (k = 0; k < v->NumberOfActivePlanes; k++) { @@ -5384,64 +5234,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->ProjectedDCFCLKDeepSleep[i][j], v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->NoOfDPPThisState, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, UnboundedRequestEnabledThisState, CompressedBufferSizeInkByteThisState, &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &dummy, &dummy, &dummy, &dummy, - &v->MinActiveDRAMClockChangeLatencySupported); + &dummy); } } @@ -5566,64 +5380,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, int unsigned CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + double *Z8StutterEnterPlusExitWatermark) { struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY; @@ -5643,103 +5421,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double TotalPixelBW = 0.0; int k, j; - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark); #endif - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark); + dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark); #endif v->TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } if (v->TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } if (v->TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { TotalPixelBW = TotalPixelBW - + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) - / (HTotal[k] / PixelClock[k]); + + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) + / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { double EffectiveDETBufferSizeY = DETBufferSizeY[k]; v->LBLatencyHidingSourceLinesY = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); v->LBLatencyHidingSourceLinesC = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY - + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + if (v->WritebackEnable[k] == true) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; @@ -5749,14 +5527,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5764,11 +5542,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } @@ -5776,25 +5554,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 + } else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); - *Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; - *Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); + *Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 34a5d0f87b5f..4bb3b31ea7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -194,6 +194,9 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator; dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count; + if (bw_params->dram_channel_width_bytes > 0) + dcn3_14_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes; + if (bw_params->num_channels > 0) dcn3_14_soc.num_chans = bw_params->num_channels; @@ -262,7 +265,7 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) - dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31); + dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314); else dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index fc4d7474c111..ee821c4fb5dd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -61,7 +61,7 @@ // fudge factor for min dcfclk calclation #define __DML_MIN_DCFCLK_FACTOR__ 1.15 -struct { +typedef struct { double DPPCLK; double DISPCLK; double PixelClock; @@ -265,33 +265,13 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe); + double DPTEBytesPerRow); static double CalculateWriteBackDelay( enum source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -325,64 +305,28 @@ static void CalculateVupdateAndDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + double *Z8StutterEnterPlusExitWatermark); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, @@ -1599,7 +1543,7 @@ static void CalculateDCCConfiguration( int segment_order_vert_contiguous_luma; int segment_order_vert_contiguous_chroma; - enum { + typedef enum { REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA } RequestType; RequestType RequestLuma; @@ -2928,33 +2872,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < v->NumberOfActivePlanes; ++k) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->UrgentExtraLatency, v->UrgentLatency, - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], - v->PixelPTEBytesPerRow[k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->PixelPTEBytesPerRow[k]); } v->total_dcn_read_bw_with_flip = 0.0; @@ -3041,64 +2965,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->DCFCLKDeepSleep, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, &v->StutterExitWatermark, &v->StutterEnterPlusExitWatermark, &v->Z8StutterExitWatermark, - &v->Z8StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->Z8StutterEnterPlusExitWatermark); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -3710,61 +3598,43 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe) + double DPTEBytesPerRow) { + struct vba_vars_st *v = &mode_lib->vba; double min_row_time = 0.0; unsigned int HostVMDynamicLevelsTrips; double TimeForFetchingMetaPTEImmediateFlip; double TimeForFetchingRowInVBlankImmediateFlip; double ImmediateFlipBW; + double LineTime = v->HTotal[k] / v->PixelClock[k]; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMDynamicLevelsTrips = 0; } - if (GPUVMEnable == true || DCCEnable == true) { - ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes; + if (v->GPUVMEnable == true || v->DCCEnable[k] == true) { + ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes; } - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { TimeForFetchingMetaPTEImmediateFlip = dml_max3( - Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, - UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), + v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, + UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), LineTime / 4.0); } else { TimeForFetchingMetaPTEImmediateFlip = 0; } - *DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; - if ((GPUVMEnable == true || DCCEnable == true)) { + v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; + if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { TimeForFetchingRowInVBlankImmediateFlip = dml_max3( (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW, UrgentLatency * (HostVMDynamicLevelsTrips + 1), @@ -3773,54 +3643,54 @@ static void CalculateFlipSchedule( TimeForFetchingRowInVBlankImmediateFlip = 0; } - *DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; + v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; - if (GPUVMEnable == true) { - *final_flip_bw = dml_max( - PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime), - (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime)); - } else if ((GPUVMEnable == true || DCCEnable == true)) { - *final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime); + if (v->GPUVMEnable == true) { + v->final_flip_bw[k] = dml_max( + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime), + (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime)); + } else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { + v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime); } else { - *final_flip_bw = 0; + v->final_flip_bw[k] = 0; } - if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma); - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma); + if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) { + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } else { min_row_time = dml_min4( - dpte_row_height * LineTime / VRatio, - meta_row_height * LineTime / VRatio, - dpte_row_height_chroma * LineTime / VRatioChroma, - meta_row_height_chroma * LineTime / VRatioChroma); + v->dpte_row_height[k] * LineTime / v->VRatio[k], + v->meta_row_height[k] * LineTime / v->VRatio[k], + v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k], + v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } } else { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dpte_row_height * LineTime / VRatio; - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = meta_row_height * LineTime / VRatio; + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k]; + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k]; } else { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio); + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]); } } - if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16 + if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16 || TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) { - *ImmediateFlipSupportedForPipe = false; + v->ImmediateFlipSupportedForPipe[k] = false; } else { - *ImmediateFlipSupportedForPipe = true; + v->ImmediateFlipSupportedForPipe[k] = true; } #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip); - dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip); + dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]); + dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]); dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip); dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip); dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time); - dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe); + dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]); #endif } @@ -4071,9 +3941,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ v->SourceFormatPixelAndScanSupport = true; for (k = 0; k < v->NumberOfActivePlanes; k++) { - if ((v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) - || ((v->SurfaceTiling[k] == dm_sw_64kb_d || v->SurfaceTiling[k] == dm_sw_64kb_d_t - || v->SurfaceTiling[k] == dm_sw_64kb_d_x) && !(v->SourcePixelFormat[k] == dm_444_64))) { + if (v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) { v->SourceFormatPixelAndScanSupport = false; } } @@ -5414,33 +5282,13 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ for (k = 0; k < v->NumberOfActivePlanes; k++) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->ExtraLatency, v->UrgLatency[i], - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesPerFrame[i][j][k], v->MetaRowBytes[i][j][k], - v->DPTEBytesPerRow[i][j][k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->DPTEBytesPerRow[i][j][k]); } v->total_dcn_read_bw_with_flip = 0.0; for (k = 0; k < v->NumberOfActivePlanes; k++) { @@ -5498,64 +5346,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->ProjectedDCFCLKDeepSleep[i][j], v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->NoOfDPPThisState, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, UnboundedRequestEnabledThisState, CompressedBufferSizeInkByteThisState, &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &dummy, &dummy, &dummy, &dummy, - &v->MinActiveDRAMClockChangeLatencySupported); + &dummy); } } @@ -5681,64 +5493,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + double *Z8StutterEnterPlusExitWatermark) { struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY; @@ -5758,103 +5534,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double TotalPixelBW = 0.0; int k, j; - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark); #endif - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark); + dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark); #endif v->TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } if (v->TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } if (v->TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { TotalPixelBW = TotalPixelBW - + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) - / (HTotal[k] / PixelClock[k]); + + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) + / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { double EffectiveDETBufferSizeY = DETBufferSizeY[k]; v->LBLatencyHidingSourceLinesY = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); v->LBLatencyHidingSourceLinesC = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY - + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + if (v->WritebackEnable[k] == true) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; @@ -5864,14 +5640,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5879,11 +5655,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } @@ -5891,25 +5667,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 + } else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); - *Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; - *Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); + *Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark); @@ -7157,12 +6933,13 @@ static double CalculateExtraLatencyBytes( HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 1); else HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 2); - else + } else { HostVMDynamicLevels = 0; + } ret = ReorderingBytes + (TotalNumberOfActiveDPP * PixelChunkSizeInKByte + TotalNumberOfDCCActiveDPP * MetaChunkSize) * 1024.0; - if (GPUVMEnable == true) + if (GPUVMEnable == true) { for (k = 0; k < NumberOfActivePlanes; ++k) ret = ret + NumberOfDPP[k] * dpte_group_bytes[k] * (1 + 8 * HostVMDynamicLevels) * HostVMInefficiencyFactor; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 8118cfc5b405..e573e706430d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -121,8 +121,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { }, }, .num_states = 1, - .sr_exit_time_us = 20.16, - .sr_enter_plus_exit_time_us = 27.13, + .sr_exit_time_us = 42.97, + .sr_enter_plus_exit_time_us = 49.94, .sr_exit_z8_time_us = 285.0, .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, @@ -244,6 +244,50 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) } /** + * Finds dummy_latency_index when MCLK switching using firmware based + * vblank stretch is enabled. This function will iterate through the + * table of dummy pstate latencies until the lowest value that allows + * dm_allow_self_refresh_and_mclk_switch to happen is found + */ +int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel) +{ + const int max_latency_table_entries = 4; + const struct vba_vars_st *vba = &context->bw_ctx.dml.vba; + int dummy_latency_index = 0; + + dc_assert_fp_enabled(); + + while (dummy_latency_index < max_latency_table_entries) { + context->bw_ctx.dml.soc.dram_clock_change_latency_us = + dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; + dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); + + if (vlevel < context->bw_ctx.dml.vba.soc.num_states && + vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported) + break; + + dummy_latency_index++; + } + + if (dummy_latency_index == max_latency_table_entries) { + ASSERT(dummy_latency_index != max_latency_table_entries); + /* If the execution gets here, it means dummy p_states are + * not possible. This should never happen and would mean + * something is severely wrong. + * Here we reset dummy_latency_index to 3, because it is + * better to have underflows than system crashes. + */ + dummy_latency_index = max_latency_table_entries - 1; + } + + return dummy_latency_index; +} + +/** * dcn32_helper_populate_phantom_dlg_params - Get DLG params for phantom pipes * and populate pipe_ctx with those params. * @@ -1014,6 +1058,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, dc->debug.force_subvp_mclk_switch)) { dcn32_merge_pipes_for_subvp(dc, context); + // to re-initialize viewport after the pipe merge + for (int i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (!pipe_ctx->plane_state || !pipe_ctx->stream) + continue; + + resource_build_scaling_params(pipe_ctx); + } while (!found_supported_config && dcn32_enough_pipes_for_subvp(dc, context) && dcn32_assign_subvp_pipe(dc, context, &dc_pipe_idx)) { @@ -1637,7 +1690,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dcn30_can_support_mclk_switch_using_fw_based_vblank_stretch(dc, context); if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dummy_latency_index = dcn30_find_dummy_latency_index_for_fw_based_mclk_switch(dc, + dummy_latency_index = dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(dc, context, pipes, pipe_cnt, vlevel); /* After calling dcn30_find_dummy_latency_index_for_fw_based_mclk_switch @@ -1873,6 +1926,45 @@ static void remove_entry_from_table_at_index(struct _vcs_dpi_voltage_scaling_st memset(&table[--(*num_entries)], 0, sizeof(struct _vcs_dpi_voltage_scaling_st)); } +void dcn32_patch_dpm_table(struct clk_bw_params *bw_params) +{ + int i; + unsigned int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, + max_phyclk_mhz = 0, max_dtbclk_mhz = 0, max_fclk_mhz = 0, max_uclk_mhz = 0; + + for (i = 0; i < MAX_NUM_DPM_LVL; i++) { + if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz) + max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; + if (bw_params->clk_table.entries[i].fclk_mhz > max_fclk_mhz) + max_fclk_mhz = bw_params->clk_table.entries[i].fclk_mhz; + if (bw_params->clk_table.entries[i].memclk_mhz > max_uclk_mhz) + max_uclk_mhz = bw_params->clk_table.entries[i].memclk_mhz; + if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz) + max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz; + if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz) + max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz; + if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz) + max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz; + if (bw_params->clk_table.entries[i].dtbclk_mhz > max_dtbclk_mhz) + max_dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; + } + + /* Scan through clock values we currently have and if they are 0, + * then populate it with dcn3_2_soc.clock_limits[] value. + * + * Do it for DCFCLK, DISPCLK, DTBCLK and UCLK as any of those being + * 0, will cause it to skip building the clock table. + */ + if (max_dcfclk_mhz == 0) + bw_params->clk_table.entries[0].dcfclk_mhz = dcn3_2_soc.clock_limits[0].dcfclk_mhz; + if (max_dispclk_mhz == 0) + bw_params->clk_table.entries[0].dispclk_mhz = dcn3_2_soc.clock_limits[0].dispclk_mhz; + if (max_dtbclk_mhz == 0) + bw_params->clk_table.entries[0].dtbclk_mhz = dcn3_2_soc.clock_limits[0].dtbclk_mhz; + if (max_uclk_mhz == 0) + bw_params->clk_table.entries[0].memclk_mhz = dcn3_2_soc.clock_limits[0].dram_speed_mts / 16; +} + static int build_synthetic_soc_states(struct clk_bw_params *bw_params, struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h index 3ed06ab855be..e1b79e2aab8c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h @@ -71,4 +71,12 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params); +int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel); + +void dcn32_patch_dpm_table(struct clk_bw_params *bw_params); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index cb2025771646..6980f698eb23 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -755,30 +755,18 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelY = v->BytePerPixelY[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelC = v->BytePerPixelC[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.ProgressiveToInterlaceUnitInOPP = mode_lib->vba.ProgressiveToInterlaceUnitInOPP; - v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, - &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, v->DSCDelay[k], - mode_lib->vba.DPPCLKDelaySubtotal + mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - (unsigned int) (v->SwathWidthY[k] / mode_lib->vba.HRatio[k]), - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, + v->ErrorResult[k] = dml32_CalculatePrefetchSchedule( + v, + k, + v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor, + &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, + v->DSCDelay[k], + (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, - mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, - mode_lib->vba.TCalc, + v->TCalc, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], v->PixelPTEBytesPerRow[k], @@ -792,8 +780,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathC[k], v->swath_width_luma_ub[k], v->swath_width_chroma_ub[k], - mode_lib->vba.SwathHeightY[k], - mode_lib->vba.SwathHeightC[k], + v->SwathHeightY[k], + v->SwathHeightC[k], TWait, /* Output */ &v->DSTXAfterScaler[k], @@ -1163,58 +1151,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters.SMNLatency = mode_lib->vba.SMNLatency; dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLK, - mode_lib->vba.ReturnBW, - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - v->dpte_group_bytes, - v->meta_row_height, - v->meta_row_height_chroma, + v, + v->PrefetchModePerState[v->VoltageLevel][v->maxMpcComb], + v->DCFCLK, + v->ReturnBW, v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLK, + v->SOCCLK, v->DCFCLKDeepSleep, - mode_lib->vba.DETBufferSizeY, - mode_lib->vba.DETBufferSizeC, - mode_lib->vba.SwathHeightY, - mode_lib->vba.SwathHeightC, - mode_lib->vba.LBBitPerPixel, + v->DETBufferSizeY, + v->DETBufferSizeC, + v->SwathHeightY, + v->SwathHeightC, v->SwathWidthY, v->SwathWidthC, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.DPPPerPlane, + v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, v->DSTXAfterScaler, v->DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, /* Output */ - &v->Watermark, &v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.dummy_dramchange_support, v->MaxActiveDRAMClockChangeLatencySupported, v->SubViewportLinesNeededInMALL, @@ -1806,10 +1764,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.Read256BlockHeightC[k], &mode_lib->vba.Read256BlockWidthY[k], &mode_lib->vba.Read256BlockWidthC[k], - &mode_lib->vba.MicroTileHeightY[k], - &mode_lib->vba.MicroTileHeightC[k], - &mode_lib->vba.MicroTileWidthY[k], - &mode_lib->vba.MicroTileWidthC[k]); + &mode_lib->vba.MacroTileHeightY[k], + &mode_lib->vba.MacroTileHeightC[k], + &mode_lib->vba.MacroTileWidthY[k], + &mode_lib->vba.MacroTileWidthC[k]); } /*Bandwidth Support Check*/ @@ -2034,6 +1992,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l dml32_CalculateODMMode( mode_lib->vba.MaximumPixelsPerLinePerDSCUnit, mode_lib->vba.HActive[k], + mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], mode_lib->vba.ODMUse[k], mode_lib->vba.MaxDispclk[i], @@ -2055,6 +2014,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l dml32_CalculateODMMode( mode_lib->vba.MaximumPixelsPerLinePerDSCUnit, mode_lib->vba.HActive[k], + mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], mode_lib->vba.ODMUse[k], mode_lib->vba.MaxDispclk[i], @@ -2659,10 +2619,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.Read256BlockWidthC, mode_lib->vba.Read256BlockHeightY, mode_lib->vba.Read256BlockHeightC, - mode_lib->vba.MicroTileWidthY, - mode_lib->vba.MicroTileWidthC, - mode_lib->vba.MicroTileHeightY, - mode_lib->vba.MicroTileHeightC, + mode_lib->vba.MacroTileWidthY, + mode_lib->vba.MacroTileWidthC, + mode_lib->vba.MacroTileHeightY, + mode_lib->vba.MacroTileHeightC, /* Output */ mode_lib->vba.SurfaceSizeInMALL, @@ -2709,10 +2669,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesY = mode_lib->vba.Read256BlockHeightY[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidth256BytesC = mode_lib->vba.Read256BlockWidthC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesC = mode_lib->vba.Read256BlockHeightC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MicroTileWidthY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MicroTileHeightY[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MicroTileWidthC[k]; - v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MicroTileHeightC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MacroTileWidthY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MacroTileHeightY[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MacroTileWidthC[k]; + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MacroTileHeightC[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].InterlaceEnable = mode_lib->vba.Interlace[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].HTotal = mode_lib->vba.HTotal[k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].DCCEnable = mode_lib->vba.DCCEnable[k]; @@ -3258,63 +3218,47 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.NoTimeForPrefetch[i][j][k] = dml32_CalculatePrefetchSchedule( + v, + k, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.HostVMInefficiencyFactor, &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe, - mode_lib->vba.DSCDelayPerState[i][k], - mode_lib->vba.DPPCLKDelaySubtotal + - mode_lib->vba.DPPCLKDelayCNVCFormater, - mode_lib->vba.DPPCLKDelaySCL, - mode_lib->vba.DPPCLKDelaySCLLBOnly, - mode_lib->vba.DPPCLKDelayCNVCCursor, - mode_lib->vba.DISPCLKDelaySubtotal, - mode_lib->vba.SwathWidthYThisState[k] / - mode_lib->vba.HRatio[k], - mode_lib->vba.OutputFormat[k], - mode_lib->vba.MaxInterDCNTileRepeaters, - dml_min(mode_lib->vba.MaxVStartup, - mode_lib->vba.MaximumVStartup[i][j][k]), - mode_lib->vba.MaximumVStartup[i][j][k], - mode_lib->vba.GPUVMMaxPageTableLevels, - mode_lib->vba.GPUVMEnable, mode_lib->vba.HostVMEnable, - mode_lib->vba.HostVMMaxNonCachedPageTableLevels, - mode_lib->vba.HostVMMinPageSize, - mode_lib->vba.DynamicMetadataEnable[k], - mode_lib->vba.DynamicMetadataVMEnabled, - mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k], - mode_lib->vba.DynamicMetadataTransmittedBytes[k], - mode_lib->vba.UrgLatency[i], - mode_lib->vba.ExtraLatency, - mode_lib->vba.TimeCalc, - mode_lib->vba.PDEAndMetaPTEBytesPerFrame[i][j][k], - mode_lib->vba.MetaRowBytes[i][j][k], - mode_lib->vba.DPTEBytesPerRow[i][j][k], - mode_lib->vba.PrefetchLinesY[i][j][k], - mode_lib->vba.SwathWidthYThisState[k], - mode_lib->vba.PrefillY[k], - mode_lib->vba.MaxNumSwY[k], - mode_lib->vba.PrefetchLinesC[i][j][k], - mode_lib->vba.SwathWidthCThisState[k], - mode_lib->vba.PrefillC[k], - mode_lib->vba.MaxNumSwC[k], - mode_lib->vba.swath_width_luma_ub_this_state[k], - mode_lib->vba.swath_width_chroma_ub_this_state[k], - mode_lib->vba.SwathHeightYThisState[k], - mode_lib->vba.SwathHeightCThisState[k], mode_lib->vba.TWait, + v->DSCDelayPerState[i][k], + v->SwathWidthYThisState[k] / v->HRatio[k], + dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), + v->MaximumVStartup[i][j][k], + v->UrgLatency[i], + v->ExtraLatency, + v->TimeCalc, + v->PDEAndMetaPTEBytesPerFrame[i][j][k], + v->MetaRowBytes[i][j][k], + v->DPTEBytesPerRow[i][j][k], + v->PrefetchLinesY[i][j][k], + v->SwathWidthYThisState[k], + v->PrefillY[k], + v->MaxNumSwY[k], + v->PrefetchLinesC[i][j][k], + v->SwathWidthCThisState[k], + v->PrefillC[k], + v->MaxNumSwC[k], + v->swath_width_luma_ub_this_state[k], + v->swath_width_chroma_ub_this_state[k], + v->SwathHeightYThisState[k], + v->SwathHeightCThisState[k], v->TWait, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler[k], - &mode_lib->vba.LineTimesForPrefetch[k], - &mode_lib->vba.PrefetchBW[k], - &mode_lib->vba.LinesForMetaPTE[k], - &mode_lib->vba.LinesForMetaAndDPTERow[k], - &mode_lib->vba.VRatioPreY[i][j][k], - &mode_lib->vba.VRatioPreC[i][j][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWLuma[0][0][k], - &mode_lib->vba.RequiredPrefetchPixelDataBWChroma[0][0][k], - &mode_lib->vba.NoTimeForDynamicMetadata[i][j][k], - &mode_lib->vba.Tno_bw[k], - &mode_lib->vba.prefetch_vmrow_bw[k], + &v->LineTimesForPrefetch[k], + &v->PrefetchBW[k], + &v->LinesForMetaPTE[k], + &v->LinesForMetaAndDPTERow[k], + &v->VRatioPreY[i][j][k], + &v->VRatioPreC[i][j][k], + &v->RequiredPrefetchPixelDataBWLuma[0][0][k], + &v->RequiredPrefetchPixelDataBWChroma[0][0][k], + &v->NoTimeForDynamicMetadata[i][j][k], + &v->Tno_bw[k], + &v->prefetch_vmrow_bw[k], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[0], // double *Tdmdl_vm &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[1], // double *Tdmdl &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[2], // double *TSetup @@ -3557,62 +3501,32 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l { dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - mode_lib->vba.USRRetrainingRequiredFinal, - mode_lib->vba.UsesMALLForPStateChange, - mode_lib->vba.PrefetchModePerState[i][j], - mode_lib->vba.NumberOfActiveSurfaces, - mode_lib->vba.MaxLineBufferLines, - mode_lib->vba.LineBufferSizeFinal, - mode_lib->vba.WritebackInterfaceBufferSize, - mode_lib->vba.DCFCLKState[i][j], - mode_lib->vba.ReturnBWPerState[i][j], - mode_lib->vba.SynchronizeTimingsFinal, - mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - mode_lib->vba.DRRDisplay, - mode_lib->vba.dpte_group_bytes, - mode_lib->vba.meta_row_height, - mode_lib->vba.meta_row_height_chroma, + v, + v->PrefetchModePerState[i][j], + v->DCFCLKState[i][j], + v->ReturnBWPerState[i][j], v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.mSOCParameters, - mode_lib->vba.WritebackChunkSize, - mode_lib->vba.SOCCLKPerState[i], - mode_lib->vba.ProjectedDCFCLKDeepSleep[i][j], - mode_lib->vba.DETBufferSizeYThisState, - mode_lib->vba.DETBufferSizeCThisState, - mode_lib->vba.SwathHeightYThisState, - mode_lib->vba.SwathHeightCThisState, - mode_lib->vba.LBBitPerPixel, - mode_lib->vba.SwathWidthYThisState, // 24 - mode_lib->vba.SwathWidthCThisState, - mode_lib->vba.HRatio, - mode_lib->vba.HRatioChroma, - mode_lib->vba.vtaps, - mode_lib->vba.VTAPsChroma, - mode_lib->vba.VRatio, - mode_lib->vba.VRatioChroma, - mode_lib->vba.HTotal, - mode_lib->vba.VTotal, - mode_lib->vba.VActive, - mode_lib->vba.PixelClock, - mode_lib->vba.BlendingAndTiming, - mode_lib->vba.NoOfDPPThisState, - mode_lib->vba.BytePerPixelInDETY, - mode_lib->vba.BytePerPixelInDETC, + v->SOCCLKPerState[i], + v->ProjectedDCFCLKDeepSleep[i][j], + v->DETBufferSizeYThisState, + v->DETBufferSizeCThisState, + v->SwathHeightYThisState, + v->SwathHeightCThisState, + v->SwathWidthYThisState, // 24 + v->SwathWidthCThisState, + v->NoOfDPPThisState, + v->BytePerPixelInDETY, + v->BytePerPixelInDETC, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler, v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler, - mode_lib->vba.WritebackEnable, - mode_lib->vba.WritebackPixelFormat, - mode_lib->vba.WritebackDestinationWidth, - mode_lib->vba.WritebackDestinationHeight, - mode_lib->vba.WritebackSourceHeight, - mode_lib->vba.UnboundedRequestEnabledThisState, - mode_lib->vba.CompressedBufferSizeInkByteThisState, + v->UnboundedRequestEnabledThisState, + v->CompressedBufferSizeInkByteThisState, /* Output */ - &mode_lib->vba.Watermark, // Store the values in vba - &mode_lib->vba.DRAMClockChangeSupport[i][j], + &v->DRAMClockChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[0], // double *MaxActiveDRAMClockChangeLatencySupported &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_integer[0], // Long SubViewportLinesNeededInMALL[] - &mode_lib->vba.FCLKChangeSupport[i][j], + &v->FCLKChangeSupport[i][j], &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[1], // double *MinActiveFCLKChangeLatencySupported &mode_lib->vba.USRRetrainingSupport[i][j], mode_lib->vba.ActiveDRAMClockChangeLatencyMargin); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 05fc14a47fba..365d290bba99 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -27,6 +27,8 @@ #include "display_mode_vba_32.h" #include "../display_mode_lib.h" +#define DCN32_MAX_FMT_420_BUFFER_WIDTH 4096 + unsigned int dml32_dscceComputeDelay( unsigned int bpc, double BPP, @@ -1182,6 +1184,7 @@ void dml32_CalculateDETBufferSize( void dml32_CalculateODMMode( unsigned int MaximumPixelsPerLinePerDSCUnit, unsigned int HActive, + enum output_format_class OutFormat, enum output_encoder_class Output, enum odm_combine_policy ODMUse, double StateDispclk, @@ -1253,6 +1256,29 @@ void dml32_CalculateODMMode( else *TotalAvailablePipesSupport = false; } + if (OutFormat == dm_420 && HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH && + ODMUse != dm_odm_combine_policy_4to1) { + if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 4) { + *ODMMode = dm_odm_combine_mode_disabled; + *NumberOfDPP = 0; + *TotalAvailablePipesSupport = false; + } else if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 2 || + *ODMMode == dm_odm_combine_mode_4to1) { + *ODMMode = dm_odm_combine_mode_4to1; + *RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineFourToOne; + *NumberOfDPP = 4; + } else { + *ODMMode = dm_odm_combine_mode_2to1; + *RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineTwoToOne; + *NumberOfDPP = 2; + } + } + if (Output == dm_hdmi && OutFormat == dm_420 && + HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH) { + *ODMMode = dm_odm_combine_mode_disabled; + *NumberOfDPP = 0; + *TotalAvailablePipesSupport = false; + } } double dml32_CalculateRequiredDispclk( @@ -3363,28 +3389,14 @@ double dml32_CalculateExtraLatency( } // CalculateExtraLatency bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -3425,6 +3437,7 @@ bool dml32_CalculatePrefetchSchedule( double *VUpdateWidthPix, double *VReadyOffsetPix) { + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles, DISPCLKCycles; double DSTTotalPixelsAfterScaler; @@ -3461,27 +3474,27 @@ bool dml32_CalculatePrefetchSchedule( double Tsw_est1 = 0; double Tsw_est3 = 0; - if (GPUVMEnable == true && HostVMEnable == true) - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; else HostVMDynamicLevelsTrips = 0; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: GPUVMEnable = %d\n", __func__, GPUVMEnable); - dml_print("DML::%s: GPUVMPageTableLevels = %d\n", __func__, GPUVMPageTableLevels); + dml_print("DML::%s: v->GPUVMEnable = %d\n", __func__, v->GPUVMEnable); + dml_print("DML::%s: v->GPUVMMaxPageTableLevels = %d\n", __func__, v->GPUVMMaxPageTableLevels); dml_print("DML::%s: DCCEnable = %d\n", __func__, myPipe->DCCEnable); - dml_print("DML::%s: HostVMEnable=%d HostVMInefficiencyFactor=%f\n", - __func__, HostVMEnable, HostVMInefficiencyFactor); + dml_print("DML::%s: v->HostVMEnable=%d HostVMInefficiencyFactor=%f\n", + __func__, v->HostVMEnable, HostVMInefficiencyFactor); #endif dml32_CalculateVUpdateAndDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->Dppclk, myPipe->Dispclk, myPipe->DCFClkDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, myPipe->ProgressiveToInterlaceUnitInOPP, TSetup, @@ -3496,19 +3509,19 @@ bool dml32_CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true) + if (v->DynamicMetadataVMEnabled == true) *Tdmdl = TWait + Tvm_trips + trip_to_mem; else *Tdmdl = TWait + UrgentExtraLatency; #ifdef __DML_VBA_ALLOW_DELTA__ - if (DynamicMetadataEnable == false) + if (v->DynamicMetadataEnable[k] == false) *Tdmdl = 0.0; #endif - if (DynamicMetadataEnable == true) { + if (v->DynamicMetadataEnable[k] == true) { if (VStartup * LineTime < *TSetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; #ifdef __DML_VBA_DEBUG__ @@ -3528,17 +3541,17 @@ bool dml32_CalculatePrefetchSchedule( *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && - GPUVMEnable == true ? TWait + Tvm_trips : 0); + *Tdmdl_vm = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && + v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->Dppclk == 0.0 || myPipe->Dispclk == 0.0) return true; @@ -3564,7 +3577,7 @@ bool dml32_CalculatePrefetchSchedule( dml_print("DML::%s: DSTXAfterScaler: %d\n", __func__, *DSTXAfterScaler); #endif - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP)) *DSTYAfterScaler = 1; else *DSTYAfterScaler = 0; @@ -3581,13 +3594,13 @@ bool dml32_CalculatePrefetchSchedule( Tr0_trips = trip_to_mem * (HostVMDynamicLevelsTrips + 1); - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1.0) / 4.0 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime; - if (GPUVMPageTableLevels >= 3) { + if (v->GPUVMMaxPageTableLevels >= 3) { *Tno_bw = UrgentExtraLatency + trip_to_mem * - (double) ((GPUVMPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); - } else if (GPUVMPageTableLevels == 1 && myPipe->DCCEnable != true) { + (double) ((v->GPUVMMaxPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1); + } else if (v->GPUVMMaxPageTableLevels == 1 && myPipe->DCCEnable != true) { Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / LineTime, 1.0) / 4.0 * LineTime; // VBA_ERROR *Tno_bw = UrgentExtraLatency; @@ -3622,7 +3635,7 @@ bool dml32_CalculatePrefetchSchedule( min_Lsw = dml_max(min_Lsw, 1.0); Lsw_oto = dml_ceil(4.0 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1.0) / 4.0; - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_oto = dml_max3( Tvm_trips, *Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, @@ -3630,7 +3643,7 @@ bool dml32_CalculatePrefetchSchedule( } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max4( Tr0_trips, (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, @@ -3833,7 +3846,7 @@ bool dml32_CalculatePrefetchSchedule( #endif if (prefetch_bw_equ > 0) { - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); @@ -3841,7 +3854,7 @@ bool dml32_CalculatePrefetchSchedule( Tvm_equ = LineTime / 4; } - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, (LineTime - Tvm_equ) / 2, LineTime / 4); @@ -4206,58 +4219,28 @@ void dml32_CalculateFlipSchedule( } // CalculateFlipSchedule void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], @@ -4299,136 +4282,136 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX]; unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX]; - Watermark->UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; - Watermark->USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + v->Watermark.UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency; + v->Watermark.USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency + mmSOCParameters.USRRetrainingLatency + mmSOCParameters.SMNLatency; - Watermark->DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + Watermark->UrgentWatermark; - Watermark->FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + Watermark->UrgentWatermark; - Watermark->StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + v->Watermark.DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.UrgentWatermark; + v->Watermark.StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + v->Watermark.StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + v->Watermark.Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; - Watermark->Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + v->Watermark.Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time + mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, mmSOCParameters.UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, mmSOCParameters.ExtraLatency); dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, mmSOCParameters.DRAMClockChangeLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, Watermark->UrgentWatermark); - dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, Watermark->USRRetrainingWatermark); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, Watermark->DRAMClockChangeWatermark); - dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, Watermark->FCLKChangeWatermark); - dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, Watermark->StutterExitWatermark); - dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, Watermark->StutterEnterPlusExitWatermark); - dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, Watermark->Z8StutterExitWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->Watermark.UrgentWatermark); + dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, v->Watermark.USRRetrainingWatermark); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->Watermark.DRAMClockChangeWatermark); + dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, v->Watermark.FCLKChangeWatermark); + dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, v->Watermark.StutterExitWatermark); + dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, v->Watermark.StutterEnterPlusExitWatermark); + dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, v->Watermark.Z8StutterExitWatermark); dml_print("DML::%s: Z8StutterEnterPlusExitWatermark = %f\n", - __func__, Watermark->Z8StutterEnterPlusExitWatermark); + __func__, v->Watermark.Z8StutterEnterPlusExitWatermark); #endif TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (WritebackEnable[k] == true) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->WritebackEnable[k] == true) TotalActiveWriteback = TotalActiveWriteback + 1; } if (TotalActiveWriteback <= 1) { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency - + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency + + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackUrgentWatermark = Watermark->WritebackUrgentWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackUrgentWatermark = v->Watermark.WritebackUrgentWatermark + mmSOCParameters.USRRetrainingLatency; if (TotalActiveWriteback <= 1) { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.WritebackLatency; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + mmSOCParameters.WritebackLatency; } else { - Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; - Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency - + mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024 / 32 / SOCCLK; + v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + + mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024 / 32 / SOCCLK; } - if (USRRetrainingRequiredFinal) - Watermark->WritebackDRAMClockChangeWatermark = Watermark->WritebackDRAMClockChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackDRAMClockChangeWatermark = v->Watermark.WritebackDRAMClockChangeWatermark + mmSOCParameters.USRRetrainingLatency; - if (USRRetrainingRequiredFinal) - Watermark->WritebackFCLKChangeWatermark = Watermark->WritebackFCLKChangeWatermark + if (v->USRRetrainingRequiredFinal) + v->Watermark.WritebackFCLKChangeWatermark = v->Watermark.WritebackFCLKChangeWatermark + mmSOCParameters.USRRetrainingLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: WritebackDRAMClockChangeWatermark = %f\n", - __func__, Watermark->WritebackDRAMClockChangeWatermark); - dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, Watermark->WritebackFCLKChangeWatermark); - dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, Watermark->WritebackUrgentWatermark); - dml_print("DML::%s: USRRetrainingRequiredFinal = %d\n", __func__, USRRetrainingRequiredFinal); + __func__, v->Watermark.WritebackDRAMClockChangeWatermark); + dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, v->Watermark.WritebackFCLKChangeWatermark); + dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, v->Watermark.WritebackUrgentWatermark); + dml_print("DML::%s: v->USRRetrainingRequiredFinal = %d\n", __func__, v->USRRetrainingRequiredFinal); dml_print("DML::%s: USRRetrainingLatency = %f\n", __func__, mmSOCParameters.USRRetrainingLatency); #endif - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + - SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) / (HTotal[k] / PixelClock[k]); + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { - LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1); - LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1); + LBLatencyHidingSourceLinesY[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); + LBLatencyHidingSourceLinesC[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: k=%d, MaxLineBufferLines = %d\n", __func__, k, MaxLineBufferLines); - dml_print("DML::%s: k=%d, LineBufferSize = %d\n", __func__, k, LineBufferSize); - dml_print("DML::%s: k=%d, LBBitPerPixel = %d\n", __func__, k, LBBitPerPixel[k]); - dml_print("DML::%s: k=%d, HRatio = %f\n", __func__, k, HRatio[k]); - dml_print("DML::%s: k=%d, VTaps = %d\n", __func__, k, VTaps[k]); + dml_print("DML::%s: k=%d, v->MaxLineBufferLines = %d\n", __func__, k, v->MaxLineBufferLines); + dml_print("DML::%s: k=%d, v->LineBufferSizeFinal = %d\n", __func__, k, v->LineBufferSizeFinal); + dml_print("DML::%s: k=%d, v->LBBitPerPixel = %d\n", __func__, k, v->LBBitPerPixel[k]); + dml_print("DML::%s: k=%d, v->HRatio = %f\n", __func__, k, v->HRatio[k]); + dml_print("DML::%s: k=%d, v->vtaps = %d\n", __func__, k, v->vtaps[k]); #endif - EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]); - EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); + EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); EffectiveDETBufferSizeY = DETBufferSizeY[k]; if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY + CompressedBufferSizeInkByte * 1024 - * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k]) - / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k]) + / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; ActiveClockChangeLatencyHidingY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k]; + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightY[k] * HTotal[k] - / PixelClock[k] / VRatio[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath[k] = dml_floor(LinesInDETC[k], SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) - / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) + / v->VRatioChroma[k]; ActiveClockChangeLatencyHidingC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] - / PixelClock[k]; - if (NumberOfActiveSurfaces > 1) { + - (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] + / v->PixelClock[k]; + if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingC = ActiveClockChangeLatencyHidingC - - (1 - 1 / NumberOfActiveSurfaces) * SwathHeightC[k] * HTotal[k] - / PixelClock[k] / VRatioChroma[k]; + - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightC[k] * v->HTotal[k] + / v->PixelClock[k] / v->VRatioChroma[k]; } ActiveClockChangeLatencyHiding = dml_min(ActiveClockChangeLatencyHidingY, ActiveClockChangeLatencyHidingC); @@ -4436,24 +4419,24 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( ActiveClockChangeLatencyHiding = ActiveClockChangeLatencyHidingY; } - ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->DRAMClockChangeWatermark; - ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark - - Watermark->FCLKChangeWatermark; - USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark; - - if (WritebackEnable[k]) { - WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] - / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) + ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.DRAMClockChangeWatermark; + ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark + - v->Watermark.FCLKChangeWatermark; + USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.USRRetrainingWatermark; + + if (v->WritebackEnable[k]) { + WritebackLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] + / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) WritebackLatencyHiding = WritebackLatencyHiding / 2; WritebackDRAMClockChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackDRAMClockChangeWatermark; + - v->Watermark.WritebackDRAMClockChangeWatermark; WritebackFCLKChangeLatencyMargin = WritebackLatencyHiding - - Watermark->WritebackFCLKChangeWatermark; + - v->Watermark.WritebackFCLKChangeWatermark; ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMargin[k], WritebackFCLKChangeLatencyMargin); @@ -4461,22 +4444,22 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( WritebackDRAMClockChangeLatencyMargin); } MaxActiveDRAMClockChangeLatencySupported[k] = - (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? + (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ? 0 : (ActiveDRAMClockChangeLatencyMargin[k] + mmSOCParameters.DRAMClockChangeLatency); } - for (i = 0; i < NumberOfActiveSurfaces; ++i) { - for (j = 0; j < NumberOfActiveSurfaces; ++j) { + for (i = 0; i < v->NumberOfActiveSurfaces; ++i) { + for (j = 0; j < v->NumberOfActiveSurfaces; ++j) { if (i == j || - (BlendingAndTiming[i] == i && BlendingAndTiming[j] == i) || - (BlendingAndTiming[j] == j && BlendingAndTiming[i] == j) || - (BlendingAndTiming[i] == BlendingAndTiming[j] && BlendingAndTiming[i] != i) || - (SynchronizeTimingsFinal && PixelClock[i] == PixelClock[j] && - HTotal[i] == HTotal[j] && VTotal[i] == VTotal[j] && - VActive[i] == VActive[j]) || (SynchronizeDRRDisplaysForUCLKPStateChangeFinal && - (DRRDisplay[i] || DRRDisplay[j]))) { + (v->BlendingAndTiming[i] == i && v->BlendingAndTiming[j] == i) || + (v->BlendingAndTiming[j] == j && v->BlendingAndTiming[i] == j) || + (v->BlendingAndTiming[i] == v->BlendingAndTiming[j] && v->BlendingAndTiming[i] != i) || + (v->SynchronizeTimingsFinal && v->PixelClock[i] == v->PixelClock[j] && + v->HTotal[i] == v->HTotal[j] && v->VTotal[i] == v->VTotal[j] && + v->VActive[i] == v->VActive[j]) || (v->SynchronizeDRRDisplaysForUCLKPStateChangeFinal && + (v->DRRDisplay[i] || v->DRRDisplay[j]))) { SynchronizedSurfaces[i][j] = true; } else { SynchronizedSurfaces[i][j] = false; @@ -4484,8 +4467,8 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (!FoundFirstSurfaceWithMinActiveFCLKChangeMargin || ActiveFCLKChangeLatencyMargin[k] < MinActiveFCLKChangeMargin)) { FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true; @@ -4497,9 +4480,9 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *MinActiveFCLKChangeLatencySupported = MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency; SameTimingForFCLKChange = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { if (!SynchronizedSurfaces[k][SurfaceWithMinActiveFCLKChangeMargin]) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (SameTimingForFCLKChange || ActiveFCLKChangeLatencyMargin[k] < SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) { @@ -4519,17 +4502,17 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } *USRRetrainingSupport = true; - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) && (USRRetrainingLatencyMargin[k] < 0)) { *USRRetrainingSupport = false; } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && - UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport && + v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe && ActiveDRAMClockChangeLatencyMargin[k] < 0) { if (PrefetchMode > 0) { DRAMClockChangeSupportNumber = 2; @@ -4543,10 +4526,10 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( } } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { - if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { + if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame) DRAMClockChangeMethod = 1; - else if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) + else if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport) DRAMClockChangeMethod = 2; } @@ -4573,16 +4556,16 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - for (k = 0; k < NumberOfActiveSurfaces; ++k) { + for (k = 0; k < v->NumberOfActiveSurfaces; ++k) { unsigned int dst_y_pstate; unsigned int src_y_pstate_l; unsigned int src_y_pstate_c; unsigned int src_y_ahead_l, src_y_ahead_c, sub_vp_lines_l, sub_vp_lines_c; - dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (HTotal[k] / PixelClock[k]), 1); - src_y_pstate_l = dml_ceil(dst_y_pstate * VRatio[k], SwathHeightY[k]); + dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (v->HTotal[k] / v->PixelClock[k]), 1); + src_y_pstate_l = dml_ceil(dst_y_pstate * v->VRatio[k], SwathHeightY[k]); src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + LBLatencyHidingSourceLinesY[k]; - sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + meta_row_height[k]; + sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + v->meta_row_height[k]; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, DETBufferSizeY = %d\n", __func__, k, DETBufferSizeY[k]); @@ -4593,21 +4576,21 @@ dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY = %d\n", __func__, k, LBL dml_print("DML::%s: k=%d, dst_y_pstate = %d\n", __func__, k, dst_y_pstate); dml_print("DML::%s: k=%d, src_y_pstate_l = %d\n", __func__, k, src_y_pstate_l); dml_print("DML::%s: k=%d, src_y_ahead_l = %d\n", __func__, k, src_y_ahead_l); -dml_print("DML::%s: k=%d, meta_row_height = %d\n", __func__, k, meta_row_height[k]); +dml_print("DML::%s: k=%d, v->meta_row_height = %d\n", __func__, k, v->meta_row_height[k]); dml_print("DML::%s: k=%d, sub_vp_lines_l = %d\n", __func__, k, sub_vp_lines_l); #endif SubViewportLinesNeededInMALL[k] = sub_vp_lines_l; if (BytePerPixelDETC[k] > 0) { - src_y_pstate_c = dml_ceil(dst_y_pstate * VRatioChroma[k], SwathHeightC[k]); + src_y_pstate_c = dml_ceil(dst_y_pstate * v->VRatioChroma[k], SwathHeightC[k]); src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + LBLatencyHidingSourceLinesC[k]; - sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + meta_row_height_chroma[k]; + sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + v->meta_row_height_chroma[k]; SubViewportLinesNeededInMALL[k] = dml_max(sub_vp_lines_l, sub_vp_lines_c); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d, src_y_pstate_c = %d\n", __func__, k, src_y_pstate_c); dml_print("DML::%s: k=%d, src_y_ahead_c = %d\n", __func__, k, src_y_ahead_c); -dml_print("DML::%s: k=%d, meta_row_height_chroma = %d\n", __func__, k, meta_row_height_chroma[k]); +dml_print("DML::%s: k=%d, v->meta_row_height_chroma = %d\n", __func__, k, v->meta_row_height_chroma[k]); dml_print("DML::%s: k=%d, sub_vp_lines_c = %d\n", __func__, k, sub_vp_lines_c); #endif } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index d293856ba906..0b427d89b3c5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,6 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" +#include "dml/display_mode_vba.h" unsigned int dml32_dscceComputeDelay( unsigned int bpc, @@ -215,6 +216,7 @@ void dml32_CalculateDETBufferSize( void dml32_CalculateODMMode( unsigned int MaximumPixelsPerLinePerDSCUnit, unsigned int HActive, + enum output_format_class OutFormat, enum output_encoder_class Output, enum odm_combine_policy ODMUse, double StateDispclk, @@ -712,28 +714,14 @@ double dml32_CalculateExtraLatency( unsigned int HostVMMaxNonCachedPageTableLevels); bool dml32_CalculatePrefetchSchedule( + struct vba_vars_st *v, + unsigned int k, double HostVMInefficiencyFactor, DmlPipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -807,58 +795,28 @@ void dml32_CalculateFlipSchedule( bool *ImmediateFlipSupportedForPipe); void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( - bool USRRetrainingRequiredFinal, - enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[], + struct vba_vars_st *v, unsigned int PrefetchMode, - unsigned int NumberOfActiveSurfaces, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizeTimingsFinal, - bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal, - bool DRRDisplay[], - unsigned int dpte_group_bytes[], - unsigned int meta_row_height[], - unsigned int meta_row_height_chroma[], SOCParametersList mmSOCParameters, - unsigned int WritebackChunkSize, double SOCCLK, double DCFClkDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int VTaps[], - unsigned int VTapsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - unsigned int VTotal[], - unsigned int VActive[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerSurface[], double BytePerPixelDETY[], double BytePerPixelDETC[], double DSTXAfterScaler[], double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, /* Output */ - Watermarks *Watermark, enum clock_change_support *DRAMClockChangeSupport, double MaxActiveDRAMClockChangeLatencySupported[], unsigned int SubViewportLinesNeededInMALL[], diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c index 5d27ff0ebb5f..f5400eda07a5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c @@ -35,6 +35,8 @@ #include "dcn30/display_rq_dlg_calc_30.h" #include "dcn31/display_mode_vba_31.h" #include "dcn31/display_rq_dlg_calc_31.h" +#include "dcn314/display_mode_vba_314.h" +#include "dcn314/display_rq_dlg_calc_314.h" #include "dcn32/display_mode_vba_32.h" #include "dcn32/display_rq_dlg_calc_32.h" #include "dml_logger.h" @@ -74,6 +76,13 @@ const struct dml_funcs dml31_funcs = { .rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg }; +const struct dml_funcs dml314_funcs = { + .validate = dml314_ModeSupportAndSystemConfigurationFull, + .recalculate = dml314_recalculate, + .rq_dlg_get_dlg_reg = dml314_rq_dlg_get_dlg_reg, + .rq_dlg_get_rq_reg = dml314_rq_dlg_get_rq_reg +}; + const struct dml_funcs dml32_funcs = { .validate = dml32_ModeSupportAndSystemConfigurationFull, .recalculate = dml32_recalculate, @@ -107,6 +116,9 @@ void dml_init_instance(struct display_mode_lib *lib, case DML_PROJECT_DCN31_FPGA: lib->funcs = dml31_funcs; break; + case DML_PROJECT_DCN314: + lib->funcs = dml314_funcs; + break; case DML_PROJECT_DCN32: lib->funcs = dml32_funcs; break; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h index 2bdd6ed22611..b1878a1440e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h @@ -41,6 +41,7 @@ enum dml_project { DML_PROJECT_DCN30, DML_PROJECT_DCN31, DML_PROJECT_DCN31_FPGA, + DML_PROJECT_DCN314, DML_PROJECT_DCN32, }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 492aec634b68..2051ddaa641a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -651,10 +651,10 @@ struct vba_vars_st { unsigned int OutputTypeAndRatePerState[DC__VOLTAGE_STATES][DC__NUM_DPP__MAX]; double RequiredDISPCLKPerSurface[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightY[DC__NUM_DPP__MAX]; - unsigned int MicroTileHeightC[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MicroTileWidthC[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightY[DC__NUM_DPP__MAX]; + unsigned int MacroTileHeightC[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; + unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; bool ImmediateFlipRequiredFinal; bool DCCProgrammingAssumesScanDirectionUnknownFinal; bool EnoughWritebackUnits; @@ -800,8 +800,6 @@ struct vba_vars_st { double PSCL_FACTOR[DC__NUM_DPP__MAX]; double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX]; double MaximumVStartup[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthY[DC__NUM_DPP__MAX]; - unsigned int MacroTileWidthC[DC__NUM_DPP__MAX]; double AlignedDCCMetaPitch[DC__NUM_DPP__MAX]; double AlignedYPitch[DC__NUM_DPP__MAX]; double AlignedCPitch[DC__NUM_DPP__MAX]; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5d2b028e5dad..d9f1b0a4fbd4 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -214,6 +214,7 @@ struct dummy_pstate_entry { struct clk_bw_params { unsigned int vram_type; unsigned int num_channels; + unsigned int dram_channel_width_bytes; unsigned int dispclk_vco_khz; unsigned int dc_mode_softmax_memclk; struct clk_limit_table clk_table; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h index 68c2ed434d2c..cff5fd55a0ad 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h @@ -340,6 +340,8 @@ struct clk_mgr_internal { bool smu_present; void *wm_range_table; long long wm_range_table_addr; + + bool dpm_present; }; struct clk_mgr_internal_funcs { diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 58158764adc0..7614125c92c7 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -219,6 +219,10 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, struct dc_state *context, uint8_t disabled_master_pipe_idx); +void reset_sync_context_for_pipe(const struct dc *dc, + struct dc_state *context, + uint8_t pipe_idx); + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter); const struct link_hwss *get_link_hwss(const struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c index db7b0b155374..226af06278ce 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c @@ -116,7 +116,7 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx) dto_params.timing = &pipe_ctx->stream->timing; dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr); - dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, link_enc->inst); + dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, stream_enc->inst); dccg->funcs->enable_symclk32_se(dccg, stream_enc->inst, phyd32clk); dccg->funcs->set_dtbclk_dto(dccg, &dto_params); stream_enc->funcs->enable_stream(stream_enc); @@ -137,7 +137,7 @@ static void reset_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx) stream_enc->funcs->disable(stream_enc); dccg->funcs->set_dtbclk_dto(dccg, &dto_params); dccg->funcs->disable_symclk32_se(dccg, stream_enc->inst); - dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, pipe_ctx->link_res.hpo_dp_link_enc->inst); + dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, stream_enc->inst); } static void setup_hpo_dp_stream_attribute(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 859ffd8725c5..04f7656906ca 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -1600,6 +1600,7 @@ static void interpolate_user_regamma(uint32_t hw_points_num, struct fixed31_32 lut2; struct fixed31_32 delta_lut; struct fixed31_32 delta_index; + const struct fixed31_32 one = dc_fixpt_from_int(1); i = 0; /* fixed_pt library has problems handling too small values */ @@ -1628,6 +1629,9 @@ static void interpolate_user_regamma(uint32_t hw_points_num, } else hw_x = coordinates_x[i].x; + if (dc_fixpt_le(one, hw_x)) + hw_x = one; + norm_x = dc_fixpt_mul(norm_factor, hw_x); index = dc_fixpt_floor(norm_x); if (index < 0 || index > 255) diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h index 80dab1146439..7e85cdc5bd34 100644 --- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h @@ -268,7 +268,9 @@ union MESAPI__ADD_QUEUE { uint32_t is_tmz_queue : 1; uint32_t map_kiq_utility_queue : 1; uint32_t is_kfd_process : 1; - uint32_t reserved : 22; + uint32_t trap_en : 1; + uint32_t is_aql_queue : 1; + uint32_t reserved : 20; }; struct MES_API_STATUS api_status; uint64_t tma_addr; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h index f745cd8f1ab7..063f4a737605 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h @@ -25,7 +25,7 @@ #define SMU13_DRIVER_IF_V13_0_0_H //Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x22 +#define PPTABLE_VERSION 0x24 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index ac308e72241a..f442bf085a31 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -30,7 +30,7 @@ #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2E +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms @@ -291,5 +291,11 @@ int smu_v13_0_set_default_dpm_tables(struct smu_context *smu); void smu_v13_0_set_smu_mailbox_registers(struct smu_context *smu); int smu_v13_0_mode1_reset(struct smu_context *smu); + +int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, + void **table, + uint32_t *size, + uint32_t pptable_id); + #endif #endif 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 6db67f082d91..644ea150e075 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 @@ -368,6 +368,17 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) smu_baco->platform_support = (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; + + /* + * Disable BACO entry/exit completely on below SKUs to + * avoid hardware intermittent failures. + */ + if (((adev->pdev->device == 0x73A1) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73BF) && + (adev->pdev->revision == 0xCF))) + smu_baco->platform_support = false; + } } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 18ee3b5e64c5..93f9b8377539 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -84,9 +84,6 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin"); static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; static const int link_speed[] = {25, 50, 80, 160}; -static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size, - uint32_t pptable_id); - int smu_v13_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -212,7 +209,8 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu) if (!adev->scpm_enabled) return 0; - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) || + (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0))) return 0; /* override pptable_id from driver parameter */ @@ -221,31 +219,6 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu) dev_info(adev->dev, "override pptable id %d\n", pptable_id); } else { pptable_id = smu->smu_table.boot_values.pp_table_id; - - /* - * Temporary solution for SMU V13.0.0 with SCPM enabled: - * - use 36831 signed pptable when pp_table_id is 3683 - * - use 37151 signed pptable when pp_table_id is 3715 - * - use 36641 signed pptable when pp_table_id is 3664 or 0 - * TODO: drop these when the pptable carried in vbios is ready. - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 0: - case 3664: - pptable_id = 36641; - break; - case 3683: - pptable_id = 36831; - break; - case 3715: - pptable_id = 37151; - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } } /* "pptable_id == 0" means vbios carries the pptable. */ @@ -425,8 +398,10 @@ static int smu_v13_0_get_pptable_from_vbios(struct smu_context *smu, void **tabl return 0; } -static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size, - uint32_t pptable_id) +int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, + void **table, + uint32_t *size, + uint32_t pptable_id) { const struct smc_firmware_header_v1_0 *hdr; struct amdgpu_device *adev = smu->adev; @@ -476,26 +451,6 @@ int smu_v13_0_setup_pptable(struct smu_context *smu) } else { pptable_id = smu->smu_table.boot_values.pp_table_id; - /* - * Temporary solution for SMU V13.0.0 with SCPM disabled: - * - use 3664, 3683 or 3715 on request - * - use 3664 when pptable_id is 0 - * TODO: drop these when the pptable carried in vbios is ready. - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 0: - pptable_id = 3664; - break; - case 3664: - case 3683: - case 3715: - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } } /* force using vbios pptable in sriov mode */ 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 df4a47acd724..1d454485e0d9 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 @@ -239,82 +239,47 @@ smu_v13_0_0_get_allowed_feature_mask(struct smu_context *smu, uint32_t *feature_mask, uint32_t num) { struct amdgpu_device *adev = smu->adev; + u32 smu_version; if (num > 2) return -EINVAL; - memset(feature_mask, 0, sizeof(uint32_t) * num); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DATA_READ_BIT); + memset(feature_mask, 0xff, sizeof(uint32_t) * num); - if (adev->pm.pp_feature & PP_SCLK_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_IMU_BIT); + if (!(adev->pm.pp_feature & PP_SCLK_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_IMU_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MM_DPM_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_VCN_BIT); - - if ((adev->pg_flags & AMD_PG_SUPPORT_ATHUB) && - (adev->pg_flags & AMD_PG_SUPPORT_MMHUB)) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT); - - if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); - -#if 0 - if (adev->pm.pp_feature & PP_GFXOFF_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFXOFF_BIT); -#endif + if (!(adev->pg_flags & AMD_PG_SUPPORT_ATHUB) || + !(adev->pg_flags & AMD_PG_SUPPORT_MMHUB)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_THROTTLERS_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FAN_CONTROL_BIT); + if (!(adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DF_CSTATE_BIT); - - if (adev->pm.pp_feature & PP_MCLK_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT); + /* PMFW 78.58 contains a critical fix for gfxoff feature */ + smu_cmn_get_smc_version(smu, NULL, &smu_version); + if ((smu_version < 0x004e3a00) || + !(adev->pm.pp_feature & PP_GFXOFF_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFXOFF_BIT); + + if (!(adev->pm.pp_feature & PP_MCLK_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_UCLK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MEM_TEMP_READ_BIT); - - if (adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_SOCCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_MPCLK_DS_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_MPCLK_DS_BIT); + if (!(adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_FCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCN_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_DCFCLK_BIT); - - if (adev->pm.pp_feature & PP_PCIE_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_LINK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_LCLK_BIT); + if (!(adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_LINK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_LCLK_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DSTATE_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_CG_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_FCLK_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_CTF_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_UCLK_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VR0HOT_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT); - - if (adev->pm.pp_feature & PP_ULV_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT); + if (!(adev->pm.pp_feature & PP_ULV_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_ULV_BIT); return 0; } @@ -388,30 +353,35 @@ static int smu_v13_0_0_append_powerplay_table(struct smu_context *smu) return 0; } -static int smu_v13_0_0_setup_pptable(struct smu_context *smu) +static int smu_v13_0_0_get_pptable_from_pmfw(struct smu_context *smu, + void **table, + uint32_t *size) { struct smu_table_context *smu_table = &smu->smu_table; void *combo_pptable = smu_table->combo_pptable; - struct amdgpu_device *adev = smu->adev; int ret = 0; - /* - * With SCPM enabled, the pptable used will be signed. It cannot - * be used directly by driver. To get the raw pptable, we need to - * rely on the combo pptable(and its revelant SMU message). - */ - if (adev->scpm_enabled) { - ret = smu_cmn_get_combo_pptable(smu); - if (ret) - return ret; + ret = smu_cmn_get_combo_pptable(smu); + if (ret) + return ret; - smu->smu_table.power_play_table = combo_pptable; - smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_0_powerplay_table); - } else { - ret = smu_v13_0_setup_pptable(smu); - if (ret) - return ret; - } + *table = combo_pptable; + *size = sizeof(struct smu_13_0_0_powerplay_table); + + return 0; +} + +static int smu_v13_0_0_setup_pptable(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + ret = smu_v13_0_0_get_pptable_from_pmfw(smu, + &smu_table->power_play_table, + &smu_table->power_play_table_size); + if (ret) + return ret; ret = smu_v13_0_0_store_powerplay_table(smu); if (ret) 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 1016d1c216d8..c422bf8a09b1 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 @@ -120,6 +120,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(DisallowGfxOff, PPSMC_MSG_DisallowGfxOff, 0), MSG_MAP(Mode1Reset, PPSMC_MSG_Mode1Reset, 0), MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 0), + MSG_MAP(SetMGpuFanBoostLimitRpm, PPSMC_MSG_SetMGpuFanBoostLimitRpm, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { @@ -400,11 +401,27 @@ static int smu_v13_0_7_append_powerplay_table(struct smu_context *smu) return 0; } +static int smu_v13_0_7_get_pptable_from_pmfw(struct smu_context *smu, + void **table, + uint32_t *size) +{ + struct smu_table_context *smu_table = &smu->smu_table; + void *combo_pptable = smu_table->combo_pptable; + int ret = 0; + + ret = smu_cmn_get_combo_pptable(smu); + if (ret) + return ret; + + *table = combo_pptable; + *size = sizeof(struct smu_13_0_7_powerplay_table); + + return 0; +} static int smu_v13_0_7_setup_pptable(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; - void *combo_pptable = smu_table->combo_pptable; struct amdgpu_device *adev = smu->adev; int ret = 0; @@ -413,18 +430,11 @@ static int smu_v13_0_7_setup_pptable(struct smu_context *smu) * be used directly by driver. To get the raw pptable, we need to * rely on the combo pptable(and its revelant SMU message). */ - if (adev->scpm_enabled) { - ret = smu_cmn_get_combo_pptable(smu); - if (ret) - return ret; - - smu->smu_table.power_play_table = combo_pptable; - smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_7_powerplay_table); - } else { - ret = smu_v13_0_setup_pptable(smu); - if (ret) - return ret; - } + ret = smu_v13_0_7_get_pptable_from_pmfw(smu, + &smu_table->power_play_table, + &smu_table->power_play_table_size); + if (ret) + return ret; ret = smu_v13_0_7_store_powerplay_table(smu); if (ret) |