diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
260 files changed, 9013 insertions, 5991 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 79bb6fd83094..ae9371b172e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -885,6 +885,7 @@ struct amdgpu_device { u64 fence_context; unsigned num_rings; struct amdgpu_ring *rings[AMDGPU_MAX_RINGS]; + struct dma_fence __rcu *gang_submit; bool ib_pool_ready; struct amdgpu_sa_manager ib_pools[AMDGPU_IB_POOL_MAX]; struct amdgpu_sched gpu_sched[AMDGPU_HW_IP_NUM][AMDGPU_RING_PRIO_MAX]; @@ -1294,6 +1295,8 @@ u32 amdgpu_device_pcie_port_rreg(struct amdgpu_device *adev, u32 reg); void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev, u32 reg, u32 v); +struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev, + struct dma_fence *gang); /* atpx handler */ #if defined(CONFIG_VGA_SWITCHEROO) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 55402d238919..b14800ac179e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT /* * Copyright 2012 Advanced Micro Devices, Inc. * @@ -849,6 +850,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev) if (amdgpu_device_has_dc_support(adev)) { #if defined(CONFIG_DRM_AMD_DC) struct amdgpu_display_manager *dm = &adev->dm; + if (dm->backlight_dev[0]) atif->bd = dm->backlight_dev[0]; #endif @@ -863,6 +865,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev) if ((enc->devices & (ATOM_DEVICE_LCD_SUPPORT)) && enc->enc_priv) { struct amdgpu_encoder_atom_dig *dig = enc->enc_priv; + if (dig->bl_dev) { atif->bd = dig->bl_dev; break; @@ -919,9 +922,9 @@ static bool amdgpu_atif_pci_probe_handle(struct pci_dev *pdev) return false; status = acpi_get_handle(dhandle, "ATIF", &atif_handle); - if (ACPI_FAILURE(status)) { + if (ACPI_FAILURE(status)) return false; - } + amdgpu_acpi_priv.atif.handle = atif_handle; acpi_get_name(amdgpu_acpi_priv.atif.handle, ACPI_FULL_PATHNAME, &buffer); DRM_DEBUG_DRIVER("Found ATIF handle %s\n", acpi_method_name); @@ -954,9 +957,9 @@ static bool amdgpu_atcs_pci_probe_handle(struct pci_dev *pdev) return false; status = acpi_get_handle(dhandle, "ATCS", &atcs_handle); - if (ACPI_FAILURE(status)) { + if (ACPI_FAILURE(status)) return false; - } + amdgpu_acpi_priv.atcs.handle = atcs_handle; acpi_get_name(amdgpu_acpi_priv.atcs.handle, ACPI_FULL_PATHNAME, &buffer); DRM_DEBUG_DRIVER("Found ATCS handle %s\n", acpi_method_name); @@ -1050,6 +1053,10 @@ 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.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 091415a4abf0..03bbfaa51cbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT /* * Copyright 2014 Advanced Micro Devices, Inc. * @@ -74,9 +75,6 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev) return; adev->kfd.dev = kgd2kfd_probe(adev, vf); - - if (adev->kfd.dev) - amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size; } /** @@ -130,6 +128,7 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work) kfd.reset_work); struct amdgpu_reset_context reset_context; + memset(&reset_context, 0, sizeof(reset_context)); reset_context.method = AMD_RESET_METHOD_NONE; @@ -199,6 +198,8 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev, adev_to_drm(adev), &gpu_resources); + amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size; + INIT_WORK(&adev->kfd.reset_work, amdgpu_amdkfd_reset_work); } } @@ -208,6 +209,7 @@ void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev) if (adev->kfd.dev) { kgd2kfd_device_exit(adev->kfd.dev); adev->kfd.dev = NULL; + amdgpu_amdkfd_total_mem_size -= adev->gmc.real_vram_size; } } @@ -684,6 +686,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev, ib->length_dw = ib_len; /* This works for NO_HWS. TODO: need to handle without knowing VMID */ job->vmid = vmid; + job->num_ibs = 1; ret = amdgpu_ib_schedule(ring, 1, ib, job, &f); @@ -753,11 +756,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, bo { struct ras_err_data err_data = {0, 0, 0, NULL}; - /* CPU MCA will handle page retirement if connected_to_cpu is 1 */ - if (!adev->gmc.xgmi.connected_to_cpu) - amdgpu_umc_poison_handler(adev, &err_data, reset); - else if (reset) - amdgpu_amdkfd_gpu_reset(adev); + amdgpu_umc_poison_handler(adev, &err_data, reset); } bool amdgpu_amdkfd_ras_query_utcl2_poison_status(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 2170db83e41d..978d3970b5cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT /* * Copyright 2014-2018 Advanced Micro Devices, Inc. * @@ -297,7 +298,7 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, */ replacement = dma_fence_get_stub(); dma_resv_replace_fences(bo->tbo.base.resv, ef->base.context, - replacement, DMA_RESV_USAGE_READ); + replacement, DMA_RESV_USAGE_BOOKKEEP); dma_fence_put(replacement); return 0; } @@ -1390,8 +1391,9 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, ret = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; - amdgpu_bo_fence(vm->root.bo, - &vm->process_info->eviction_fence->base, true); + dma_resv_add_fence(vm->root.bo->tbo.base.resv, + &vm->process_info->eviction_fence->base, + DMA_RESV_USAGE_BOOKKEEP); amdgpu_bo_unreserve(vm->root.bo); /* Update process info */ @@ -1612,6 +1614,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev) uint64_t reserved_for_pt = ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size); size_t available; + spin_lock(&kfd_mem_limit.mem_limit_lock); available = adev->gmc.real_vram_size - adev->kfd.vram_used_aligned @@ -1987,9 +1990,9 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( } if (!amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && !bo->tbo.pin_count) - amdgpu_bo_fence(bo, - &avm->process_info->eviction_fence->base, - true); + dma_resv_add_fence(bo->tbo.base.resv, + &avm->process_info->eviction_fence->base, + DMA_RESV_USAGE_BOOKKEEP); ret = unreserve_bo_and_vms(&ctx, false, false); goto out; @@ -2216,7 +2219,7 @@ int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev, { if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) { *mem = *adev->gmc.vm_fault_info; - mb(); + mb(); /* make sure read happened */ atomic_set(&adev->gmc.vm_fault_info_updated, 0); } return 0; @@ -2758,15 +2761,18 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) if (mem->bo->tbo.pin_count) continue; - amdgpu_bo_fence(mem->bo, - &process_info->eviction_fence->base, true); + dma_resv_add_fence(mem->bo->tbo.base.resv, + &process_info->eviction_fence->base, + DMA_RESV_USAGE_BOOKKEEP); } /* Attach eviction fence to PD / PT BOs */ list_for_each_entry(peer_vm, &process_info->vm_list_head, vm_list_node) { struct amdgpu_bo *bo = peer_vm->root.bo; - amdgpu_bo_fence(bo, &process_info->eviction_fence->base, true); + dma_resv_add_fence(bo->tbo.base.resv, + &process_info->eviction_fence->base, + DMA_RESV_USAGE_BOOKKEEP); } validate_map_fail: @@ -2820,7 +2826,9 @@ int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem ret = dma_resv_reserve_fences(gws_bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; - amdgpu_bo_fence(gws_bo, &process_info->eviction_fence->base, true); + dma_resv_add_fence(gws_bo->tbo.base.resv, + &process_info->eviction_fence->base, + DMA_RESV_USAGE_BOOKKEEP); amdgpu_bo_unreserve(gws_bo); mutex_unlock(&(*mem)->process_info->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index b7933c2ce765..491d4846fc02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -1674,10 +1674,12 @@ amdgpu_connector_add(struct amdgpu_device *adev, adev->mode_info.dither_property, AMDGPU_FMT_DITHER_DISABLE); - if (amdgpu_audio != 0) + if (amdgpu_audio != 0) { drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; + } subpixel_order = SubPixelHorizontalRGB; connector->interlace_allowed = true; @@ -1799,6 +1801,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, @@ -1852,6 +1855,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, @@ -1902,6 +1906,7 @@ amdgpu_connector_add(struct amdgpu_device *adev, drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.audio_property, AMDGPU_AUDIO_AUTO); + amdgpu_connector->audio = AMDGPU_AUDIO_AUTO; } drm_object_attach_property(&amdgpu_connector->base.base, adev->mode_info.dither_property, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b7bae833c804..1bbd39b3b0fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -39,9 +39,82 @@ #include "amdgpu_gem.h" #include "amdgpu_ras.h" -static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, - struct drm_amdgpu_cs_chunk_fence *data, - uint32_t *offset) +static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, + struct amdgpu_device *adev, + struct drm_file *filp, + union drm_amdgpu_cs *cs) +{ + struct amdgpu_fpriv *fpriv = filp->driver_priv; + + if (cs->in.num_chunks == 0) + return -EINVAL; + + memset(p, 0, sizeof(*p)); + p->adev = adev; + p->filp = filp; + + p->ctx = amdgpu_ctx_get(fpriv, cs->in.ctx_id); + if (!p->ctx) + return -EINVAL; + + if (atomic_read(&p->ctx->guilty)) { + amdgpu_ctx_put(p->ctx); + return -ECANCELED; + } + return 0; +} + +static int amdgpu_cs_job_idx(struct amdgpu_cs_parser *p, + struct drm_amdgpu_cs_chunk_ib *chunk_ib) +{ + struct drm_sched_entity *entity; + unsigned int i; + int r; + + r = amdgpu_ctx_get_entity(p->ctx, chunk_ib->ip_type, + chunk_ib->ip_instance, + chunk_ib->ring, &entity); + if (r) + return r; + + /* + * Abort if there is no run queue associated with this entity. + * Possibly because of disabled HW IP. + */ + if (entity->rq == NULL) + return -EINVAL; + + /* Check if we can add this IB to some existing job */ + for (i = 0; i < p->gang_size; ++i) + if (p->entities[i] == entity) + return i; + + /* If not increase the gang size if possible */ + if (i == AMDGPU_CS_GANG_SIZE) + return -EINVAL; + + p->entities[i] = entity; + p->gang_size = i + 1; + return i; +} + +static int amdgpu_cs_p1_ib(struct amdgpu_cs_parser *p, + struct drm_amdgpu_cs_chunk_ib *chunk_ib, + unsigned int *num_ibs) +{ + int r; + + r = amdgpu_cs_job_idx(p, chunk_ib); + if (r < 0) + return r; + + ++(num_ibs[r]); + return 0; +} + +static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, + struct drm_amdgpu_cs_chunk_fence *data, + uint32_t *offset) { struct drm_gem_object *gobj; struct amdgpu_bo *bo; @@ -80,11 +153,11 @@ error_unref: return r; } -static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p, - struct drm_amdgpu_bo_list_in *data) +static int amdgpu_cs_p1_bo_handles(struct amdgpu_cs_parser *p, + struct drm_amdgpu_bo_list_in *data) { + struct drm_amdgpu_bo_list_entry *info; int r; - struct drm_amdgpu_bo_list_entry *info = NULL; r = amdgpu_bo_create_list_entry_array(data, &info); if (r) @@ -104,38 +177,25 @@ error_free: return r; } -static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs) +/* Copy the data from userspace and go over it the first time */ +static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, + union drm_amdgpu_cs *cs) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + unsigned int num_ibs[AMDGPU_CS_GANG_SIZE] = { }; struct amdgpu_vm *vm = &fpriv->vm; uint64_t *chunk_array_user; uint64_t *chunk_array; - unsigned size, num_ibs = 0; uint32_t uf_offset = 0; - int i; + unsigned int size; int ret; + int i; - if (cs->in.num_chunks == 0) - return -EINVAL; - - chunk_array = kvmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL); + chunk_array = kvmalloc_array(cs->in.num_chunks, sizeof(uint64_t), + GFP_KERNEL); if (!chunk_array) return -ENOMEM; - p->ctx = amdgpu_ctx_get(fpriv, cs->in.ctx_id); - if (!p->ctx) { - ret = -EINVAL; - goto free_chunk; - } - - mutex_lock(&p->ctx->lock); - - /* skip guilty context job */ - if (atomic_read(&p->ctx->guilty) == 1) { - ret = -ECANCELED; - goto free_chunk; - } - /* get chunks */ chunk_array_user = u64_to_user_ptr(cs->in.chunks); if (copy_from_user(chunk_array, chunk_array_user, @@ -170,7 +230,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs size = p->chunks[i].length_dw; cdata = u64_to_user_ptr(user_chunk.chunk_data); - p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), GFP_KERNEL); + p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), + GFP_KERNEL); if (p->chunks[i].kdata == NULL) { ret = -ENOMEM; i--; @@ -182,36 +243,35 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_partial_kdata; } + /* Assume the worst on the following checks */ + ret = -EINVAL; switch (p->chunks[i].chunk_id) { case AMDGPU_CHUNK_ID_IB: - ++num_ibs; + if (size < sizeof(struct drm_amdgpu_cs_chunk_ib)) + goto free_partial_kdata; + + ret = amdgpu_cs_p1_ib(p, p->chunks[i].kdata, num_ibs); + if (ret) + goto free_partial_kdata; break; case AMDGPU_CHUNK_ID_FENCE: - size = sizeof(struct drm_amdgpu_cs_chunk_fence); - if (p->chunks[i].length_dw * sizeof(uint32_t) < size) { - ret = -EINVAL; + if (size < sizeof(struct drm_amdgpu_cs_chunk_fence)) goto free_partial_kdata; - } - ret = amdgpu_cs_user_fence_chunk(p, p->chunks[i].kdata, - &uf_offset); + ret = amdgpu_cs_p1_user_fence(p, p->chunks[i].kdata, + &uf_offset); if (ret) goto free_partial_kdata; - break; case AMDGPU_CHUNK_ID_BO_HANDLES: - size = sizeof(struct drm_amdgpu_bo_list_in); - if (p->chunks[i].length_dw * sizeof(uint32_t) < size) { - ret = -EINVAL; + if (size < sizeof(struct drm_amdgpu_bo_list_in)) goto free_partial_kdata; - } - ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata); + ret = amdgpu_cs_p1_bo_handles(p, p->chunks[i].kdata); if (ret) goto free_partial_kdata; - break; case AMDGPU_CHUNK_ID_DEPENDENCIES: @@ -223,22 +283,32 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs break; default: - ret = -EINVAL; goto free_partial_kdata; } } - ret = amdgpu_job_alloc(p->adev, num_ibs, &p->job, vm); - if (ret) - goto free_all_kdata; + if (!p->gang_size) + return -EINVAL; + + for (i = 0; i < p->gang_size; ++i) { + ret = amdgpu_job_alloc(p->adev, num_ibs[i], &p->jobs[i], vm); + if (ret) + goto free_all_kdata; + + ret = drm_sched_job_init(&p->jobs[i]->base, p->entities[i], + &fpriv->vm); + if (ret) + goto free_all_kdata; + } + p->gang_leader = p->jobs[p->gang_size - 1]; - if (p->ctx->vram_lost_counter != p->job->vram_lost_counter) { + if (p->ctx->vram_lost_counter != p->gang_leader->vram_lost_counter) { ret = -ECANCELED; goto free_all_kdata; } if (p->uf_entry.tv.bo) - p->job->uf_addr = uf_offset; + p->gang_leader->uf_addr = uf_offset; kvfree(chunk_array); /* Use this opportunity to fill in task info for the vm */ @@ -260,6 +330,297 @@ free_chunk: return ret; } +static int amdgpu_cs_p2_ib(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk, + unsigned int *ce_preempt, + unsigned int *de_preempt) +{ + struct drm_amdgpu_cs_chunk_ib *chunk_ib = chunk->kdata; + struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_ring *ring; + struct amdgpu_job *job; + struct amdgpu_ib *ib; + int r; + + r = amdgpu_cs_job_idx(p, chunk_ib); + if (r < 0) + return r; + + job = p->jobs[r]; + ring = amdgpu_job_ring(job); + ib = &job->ibs[job->num_ibs++]; + + /* MM engine doesn't support user fences */ + if (p->uf_entry.tv.bo && ring->funcs->no_user_fence) + return -EINVAL; + + if (chunk_ib->ip_type == AMDGPU_HW_IP_GFX && + chunk_ib->flags & AMDGPU_IB_FLAG_PREEMPT) { + if (chunk_ib->flags & AMDGPU_IB_FLAG_CE) + (*ce_preempt)++; + else + (*de_preempt)++; + + /* Each GFX command submit allows only 1 IB max + * preemptible for CE & DE */ + if (*ce_preempt > 1 || *de_preempt > 1) + return -EINVAL; + } + + if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE) + job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT; + + r = amdgpu_ib_get(p->adev, vm, ring->funcs->parse_cs ? + chunk_ib->ib_bytes : 0, + AMDGPU_IB_POOL_DELAYED, ib); + if (r) { + DRM_ERROR("Failed to get ib !\n"); + return r; + } + + ib->gpu_addr = chunk_ib->va_start; + ib->length_dw = chunk_ib->ib_bytes / 4; + ib->flags = chunk_ib->flags; + return 0; +} + +static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_dep *deps = chunk->kdata; + struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + unsigned num_deps; + int i, r; + + num_deps = chunk->length_dw * 4 / + sizeof(struct drm_amdgpu_cs_chunk_dep); + + for (i = 0; i < num_deps; ++i) { + struct amdgpu_ctx *ctx; + struct drm_sched_entity *entity; + struct dma_fence *fence; + + ctx = amdgpu_ctx_get(fpriv, deps[i].ctx_id); + if (ctx == NULL) + return -EINVAL; + + r = amdgpu_ctx_get_entity(ctx, deps[i].ip_type, + deps[i].ip_instance, + deps[i].ring, &entity); + if (r) { + amdgpu_ctx_put(ctx); + return r; + } + + fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle); + amdgpu_ctx_put(ctx); + + if (IS_ERR(fence)) + return PTR_ERR(fence); + else if (!fence) + continue; + + if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) { + struct drm_sched_fence *s_fence; + struct dma_fence *old = fence; + + s_fence = to_drm_sched_fence(fence); + fence = dma_fence_get(&s_fence->scheduled); + dma_fence_put(old); + } + + r = amdgpu_sync_fence(&p->gang_leader->sync, fence); + dma_fence_put(fence); + if (r) + return r; + } + return 0; +} + +static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p, + uint32_t handle, u64 point, + u64 flags) +{ + struct dma_fence *fence; + int r; + + r = drm_syncobj_find_fence(p->filp, handle, point, flags, &fence); + if (r) { + DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n", + handle, point, r); + return r; + } + + r = amdgpu_sync_fence(&p->gang_leader->sync, fence); + dma_fence_put(fence); + + return r; +} + +static int amdgpu_cs_p2_syncobj_in(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata; + unsigned num_deps; + int i, r; + + num_deps = chunk->length_dw * 4 / + sizeof(struct drm_amdgpu_cs_chunk_sem); + for (i = 0; i < num_deps; ++i) { + r = amdgpu_syncobj_lookup_and_add(p, deps[i].handle, 0, 0); + if (r) + return r; + } + + return 0; +} + +static int amdgpu_cs_p2_syncobj_timeline_wait(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata; + unsigned num_deps; + int i, r; + + num_deps = chunk->length_dw * 4 / + sizeof(struct drm_amdgpu_cs_chunk_syncobj); + for (i = 0; i < num_deps; ++i) { + r = amdgpu_syncobj_lookup_and_add(p, syncobj_deps[i].handle, + syncobj_deps[i].point, + syncobj_deps[i].flags); + if (r) + return r; + } + + return 0; +} + +static int amdgpu_cs_p2_syncobj_out(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata; + unsigned num_deps; + int i; + + num_deps = chunk->length_dw * 4 / + sizeof(struct drm_amdgpu_cs_chunk_sem); + + if (p->post_deps) + return -EINVAL; + + p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps), + GFP_KERNEL); + p->num_post_deps = 0; + + if (!p->post_deps) + return -ENOMEM; + + + for (i = 0; i < num_deps; ++i) { + p->post_deps[i].syncobj = + drm_syncobj_find(p->filp, deps[i].handle); + if (!p->post_deps[i].syncobj) + return -EINVAL; + p->post_deps[i].chain = NULL; + p->post_deps[i].point = 0; + p->num_post_deps++; + } + + return 0; +} + +static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p, + struct amdgpu_cs_chunk *chunk) +{ + struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata; + unsigned num_deps; + int i; + + num_deps = chunk->length_dw * 4 / + sizeof(struct drm_amdgpu_cs_chunk_syncobj); + + if (p->post_deps) + return -EINVAL; + + p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps), + GFP_KERNEL); + p->num_post_deps = 0; + + if (!p->post_deps) + return -ENOMEM; + + for (i = 0; i < num_deps; ++i) { + struct amdgpu_cs_post_dep *dep = &p->post_deps[i]; + + dep->chain = NULL; + if (syncobj_deps[i].point) { + dep->chain = dma_fence_chain_alloc(); + if (!dep->chain) + return -ENOMEM; + } + + dep->syncobj = drm_syncobj_find(p->filp, + syncobj_deps[i].handle); + if (!dep->syncobj) { + dma_fence_chain_free(dep->chain); + return -EINVAL; + } + dep->point = syncobj_deps[i].point; + p->num_post_deps++; + } + + return 0; +} + +static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p) +{ + unsigned int ce_preempt = 0, de_preempt = 0; + int i, r; + + for (i = 0; i < p->nchunks; ++i) { + struct amdgpu_cs_chunk *chunk; + + chunk = &p->chunks[i]; + + switch (chunk->chunk_id) { + case AMDGPU_CHUNK_ID_IB: + r = amdgpu_cs_p2_ib(p, chunk, &ce_preempt, &de_preempt); + if (r) + return r; + break; + case AMDGPU_CHUNK_ID_DEPENDENCIES: + case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: + r = amdgpu_cs_p2_dependencies(p, chunk); + if (r) + return r; + break; + case AMDGPU_CHUNK_ID_SYNCOBJ_IN: + r = amdgpu_cs_p2_syncobj_in(p, chunk); + if (r) + return r; + break; + case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: + r = amdgpu_cs_p2_syncobj_out(p, chunk); + if (r) + return r; + break; + case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: + r = amdgpu_cs_p2_syncobj_timeline_wait(p, chunk); + if (r) + return r; + break; + case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: + r = amdgpu_cs_p2_syncobj_timeline_signal(p, chunk); + if (r) + return r; + break; + } + } + + return 0; +} + /* Convert microseconds to bytes. */ static u64 us_to_bytes(struct amdgpu_device *adev, s64 us) { @@ -495,9 +856,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct list_head duplicates; - struct amdgpu_bo *gds; - struct amdgpu_bo *gws; - struct amdgpu_bo *oa; + unsigned int i; int r; INIT_LIST_HEAD(&p->validated); @@ -581,16 +940,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, e->bo_va = amdgpu_vm_bo_find(vm, bo); } - /* Move fence waiting after getting reservation lock of - * PD root. Then there is no need on a ctx mutex lock. - */ - r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entity); - if (unlikely(r != 0)) { - if (r != -ERESTARTSYS) - DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); - goto error_validate; - } - amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold, &p->bytes_moved_vis_threshold); p->bytes_moved = 0; @@ -611,197 +960,139 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, if (r) goto error_validate; - amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved, - p->bytes_moved_vis); + if (p->uf_entry.tv.bo) { + struct amdgpu_bo *uf = ttm_to_amdgpu_bo(p->uf_entry.tv.bo); - gds = p->bo_list->gds_obj; - gws = p->bo_list->gws_obj; - oa = p->bo_list->oa_obj; + r = amdgpu_ttm_alloc_gart(&uf->tbo); + if (r) + goto error_validate; - if (gds) { - p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; - p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; - } - if (gws) { - p->job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT; - p->job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT; - } - if (oa) { - p->job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT; - p->job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT; + p->gang_leader->uf_addr += amdgpu_bo_gpu_offset(uf); } - if (!r && p->uf_entry.tv.bo) { - struct amdgpu_bo *uf = ttm_to_amdgpu_bo(p->uf_entry.tv.bo); + amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved, + p->bytes_moved_vis); - r = amdgpu_ttm_alloc_gart(&uf->tbo); - p->job->uf_addr += amdgpu_bo_gpu_offset(uf); - } + for (i = 0; i < p->gang_size; ++i) + amdgpu_job_set_resources(p->jobs[i], p->bo_list->gds_obj, + p->bo_list->gws_obj, + p->bo_list->oa_obj); + return 0; error_validate: - if (r) - ttm_eu_backoff_reservation(&p->ticket, &p->validated); + ttm_eu_backoff_reservation(&p->ticket, &p->validated); out_free_user_pages: - if (r) { - amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - if (!e->user_pages) - continue; - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); - kvfree(e->user_pages); - e->user_pages = NULL; - } - mutex_unlock(&p->bo_list->bo_list_mutex); + if (!e->user_pages) + continue; + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + kvfree(e->user_pages); + e->user_pages = NULL; } return r; } -static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) +static void trace_amdgpu_cs_ibs(struct amdgpu_cs_parser *p) { - struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - struct amdgpu_bo_list_entry *e; - int r; + int i, j; - list_for_each_entry(e, &p->validated, tv.head) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - struct dma_resv *resv = bo->tbo.base.resv; - enum amdgpu_sync_mode sync_mode; + if (!trace_amdgpu_cs_enabled()) + return; - sync_mode = amdgpu_bo_explicit_sync(bo) ? - AMDGPU_SYNC_EXPLICIT : AMDGPU_SYNC_NE_OWNER; - r = amdgpu_sync_resv(p->adev, &p->job->sync, resv, sync_mode, - &fpriv->vm); - if (r) - return r; + for (i = 0; i < p->gang_size; ++i) { + struct amdgpu_job *job = p->jobs[i]; + + for (j = 0; j < job->num_ibs; ++j) + trace_amdgpu_cs(p, job, &job->ibs[j]); } - return 0; } -/** - * amdgpu_cs_parser_fini() - clean parser states - * @parser: parser structure holding parsing context. - * @error: error number - * @backoff: indicator to backoff the reservation - * - * If error is set then unvalidate buffer, otherwise just free memory - * used by parsing context. - **/ -static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, - bool backoff) +static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p, + struct amdgpu_job *job) { - unsigned i; + struct amdgpu_ring *ring = amdgpu_job_ring(job); + unsigned int i; + int r; - if (error && backoff) { - ttm_eu_backoff_reservation(&parser->ticket, - &parser->validated); - mutex_unlock(&parser->bo_list->bo_list_mutex); - } + /* Only for UVD/VCE VM emulation */ + if (!ring->funcs->parse_cs && !ring->funcs->patch_cs_in_place) + return 0; - for (i = 0; i < parser->num_post_deps; i++) { - drm_syncobj_put(parser->post_deps[i].syncobj); - kfree(parser->post_deps[i].chain); - } - kfree(parser->post_deps); + for (i = 0; i < job->num_ibs; ++i) { + struct amdgpu_ib *ib = &job->ibs[i]; + struct amdgpu_bo_va_mapping *m; + struct amdgpu_bo *aobj; + uint64_t va_start; + uint8_t *kptr; - dma_fence_put(parser->fence); + va_start = ib->gpu_addr & AMDGPU_GMC_HOLE_MASK; + r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m); + if (r) { + DRM_ERROR("IB va_start is invalid\n"); + return r; + } - if (parser->ctx) { - mutex_unlock(&parser->ctx->lock); - amdgpu_ctx_put(parser->ctx); + if ((va_start + ib->length_dw * 4) > + (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) { + DRM_ERROR("IB va_start+ib_bytes is invalid\n"); + return -EINVAL; + } + + /* the IB should be reserved at this point */ + r = amdgpu_bo_kmap(aobj, (void **)&kptr); + if (r) { + return r; + } + + kptr += va_start - (m->start * AMDGPU_GPU_PAGE_SIZE); + + if (ring->funcs->parse_cs) { + memcpy(ib->ptr, kptr, ib->length_dw * 4); + amdgpu_bo_kunmap(aobj); + + r = amdgpu_ring_parse_cs(ring, p, job, ib); + if (r) + return r; + } else { + ib->ptr = (uint32_t *)kptr; + r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib); + amdgpu_bo_kunmap(aobj); + if (r) + return r; + } } - if (parser->bo_list) - amdgpu_bo_list_put(parser->bo_list); - for (i = 0; i < parser->nchunks; i++) - kvfree(parser->chunks[i].kdata); - kvfree(parser->chunks); - if (parser->job) - amdgpu_job_free(parser->job); - if (parser->uf_entry.tv.bo) { - struct amdgpu_bo *uf = ttm_to_amdgpu_bo(parser->uf_entry.tv.bo); + return 0; +} - amdgpu_bo_unref(&uf); +static int amdgpu_cs_patch_jobs(struct amdgpu_cs_parser *p) +{ + unsigned int i; + int r; + + for (i = 0; i < p->gang_size; ++i) { + r = amdgpu_cs_patch_ibs(p, p->jobs[i]); + if (r) + return r; } + return 0; } static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) { - struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + struct amdgpu_job *job = p->gang_leader; struct amdgpu_device *adev = p->adev; struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct amdgpu_bo_va *bo_va; struct amdgpu_bo *bo; + unsigned int i; int r; - /* Only for UVD/VCE VM emulation */ - if (ring->funcs->parse_cs || ring->funcs->patch_cs_in_place) { - unsigned i, j; - - for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) { - struct drm_amdgpu_cs_chunk_ib *chunk_ib; - struct amdgpu_bo_va_mapping *m; - struct amdgpu_bo *aobj = NULL; - struct amdgpu_cs_chunk *chunk; - uint64_t offset, va_start; - struct amdgpu_ib *ib; - uint8_t *kptr; - - chunk = &p->chunks[i]; - ib = &p->job->ibs[j]; - chunk_ib = chunk->kdata; - - if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB) - continue; - - va_start = chunk_ib->va_start & AMDGPU_GMC_HOLE_MASK; - r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m); - if (r) { - DRM_ERROR("IB va_start is invalid\n"); - return r; - } - - if ((va_start + chunk_ib->ib_bytes) > - (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) { - DRM_ERROR("IB va_start+ib_bytes is invalid\n"); - return -EINVAL; - } - - /* the IB should be reserved at this point */ - r = amdgpu_bo_kmap(aobj, (void **)&kptr); - if (r) { - return r; - } - - offset = m->start * AMDGPU_GPU_PAGE_SIZE; - kptr += va_start - offset; - - if (ring->funcs->parse_cs) { - memcpy(ib->ptr, kptr, chunk_ib->ib_bytes); - amdgpu_bo_kunmap(aobj); - - r = amdgpu_ring_parse_cs(ring, p, p->job, ib); - if (r) - return r; - } else { - ib->ptr = (uint32_t *)kptr; - r = amdgpu_ring_patch_cs_in_place(ring, p, p->job, ib); - amdgpu_bo_kunmap(aobj); - if (r) - return r; - } - - j++; - } - } - - if (!p->job->vm) - return amdgpu_cs_sync_rings(p); - - r = amdgpu_vm_clear_freed(adev, vm, NULL); if (r) return r; @@ -810,18 +1101,18 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&p->job->sync, fpriv->prt_va->last_pt_update); + r = amdgpu_sync_fence(&job->sync, fpriv->prt_va->last_pt_update); if (r) return r; - if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) { + if (fpriv->csa_va) { bo_va = fpriv->csa_va; BUG_ON(!bo_va); r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; - r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update); + r = amdgpu_sync_fence(&job->sync, bo_va->last_pt_update); if (r) return r; } @@ -840,7 +1131,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update); + r = amdgpu_sync_fence(&job->sync, bo_va->last_pt_update); if (r) return r; } @@ -853,11 +1144,18 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&p->job->sync, vm->last_update); + r = amdgpu_sync_fence(&job->sync, vm->last_update); if (r) return r; - p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); + for (i = 0; i < p->gang_size; ++i) { + job = p->jobs[i]; + + if (!job->vm) + continue; + + job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); + } if (amdgpu_vm_debug) { /* Invalidate all BOs to test for userspace bugs */ @@ -872,331 +1170,40 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) } } - return amdgpu_cs_sync_rings(p); -} - -static int amdgpu_cs_ib_fill(struct amdgpu_device *adev, - struct amdgpu_cs_parser *parser) -{ - struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; - struct amdgpu_vm *vm = &fpriv->vm; - int r, ce_preempt = 0, de_preempt = 0; - struct amdgpu_ring *ring; - int i, j; - - for (i = 0, j = 0; i < parser->nchunks && j < parser->job->num_ibs; i++) { - struct amdgpu_cs_chunk *chunk; - struct amdgpu_ib *ib; - struct drm_amdgpu_cs_chunk_ib *chunk_ib; - struct drm_sched_entity *entity; - - chunk = &parser->chunks[i]; - ib = &parser->job->ibs[j]; - chunk_ib = (struct drm_amdgpu_cs_chunk_ib *)chunk->kdata; - - if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB) - continue; - - if (chunk_ib->ip_type == AMDGPU_HW_IP_GFX && - (amdgpu_mcbp || amdgpu_sriov_vf(adev))) { - if (chunk_ib->flags & AMDGPU_IB_FLAG_PREEMPT) { - if (chunk_ib->flags & AMDGPU_IB_FLAG_CE) - ce_preempt++; - else - de_preempt++; - } - - /* each GFX command submit allows 0 or 1 IB preemptible for CE & DE */ - if (ce_preempt > 1 || de_preempt > 1) - return -EINVAL; - } - - r = amdgpu_ctx_get_entity(parser->ctx, chunk_ib->ip_type, - chunk_ib->ip_instance, chunk_ib->ring, - &entity); - if (r) - return r; - - if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE) - parser->job->preamble_status |= - AMDGPU_PREAMBLE_IB_PRESENT; - - if (parser->entity && parser->entity != entity) - return -EINVAL; - - /* Return if there is no run queue associated with this entity. - * Possibly because of disabled HW IP*/ - if (entity->rq == NULL) - return -EINVAL; - - parser->entity = entity; - - ring = to_amdgpu_ring(entity->rq->sched); - r = amdgpu_ib_get(adev, vm, ring->funcs->parse_cs ? - chunk_ib->ib_bytes : 0, - AMDGPU_IB_POOL_DELAYED, ib); - if (r) { - DRM_ERROR("Failed to get ib !\n"); - return r; - } - - ib->gpu_addr = chunk_ib->va_start; - ib->length_dw = chunk_ib->ib_bytes / 4; - ib->flags = chunk_ib->flags; - - j++; - } - - /* MM engine doesn't support user fences */ - ring = to_amdgpu_ring(parser->entity->rq->sched); - if (parser->job->uf_addr && ring->funcs->no_user_fence) - return -EINVAL; - return 0; } -static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p, - struct amdgpu_cs_chunk *chunk) +static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - unsigned num_deps; - int i, r; - struct drm_amdgpu_cs_chunk_dep *deps; - - deps = (struct drm_amdgpu_cs_chunk_dep *)chunk->kdata; - num_deps = chunk->length_dw * 4 / - sizeof(struct drm_amdgpu_cs_chunk_dep); - - for (i = 0; i < num_deps; ++i) { - struct amdgpu_ctx *ctx; - struct drm_sched_entity *entity; - struct dma_fence *fence; - - ctx = amdgpu_ctx_get(fpriv, deps[i].ctx_id); - if (ctx == NULL) - return -EINVAL; - - r = amdgpu_ctx_get_entity(ctx, deps[i].ip_type, - deps[i].ip_instance, - deps[i].ring, &entity); - if (r) { - amdgpu_ctx_put(ctx); - return r; - } - - fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle); - amdgpu_ctx_put(ctx); - - if (IS_ERR(fence)) - return PTR_ERR(fence); - else if (!fence) - continue; - - if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) { - struct drm_sched_fence *s_fence; - struct dma_fence *old = fence; - - s_fence = to_drm_sched_fence(fence); - fence = dma_fence_get(&s_fence->scheduled); - dma_fence_put(old); - } - - r = amdgpu_sync_fence(&p->job->sync, fence); - dma_fence_put(fence); - if (r) - return r; - } - return 0; -} - -static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p, - uint32_t handle, u64 point, - u64 flags) -{ - struct dma_fence *fence; + struct amdgpu_job *leader = p->gang_leader; + struct amdgpu_bo_list_entry *e; + unsigned int i; int r; - r = drm_syncobj_find_fence(p->filp, handle, point, flags, &fence); - if (r) { - DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n", - handle, point, r); - return r; - } - - r = amdgpu_sync_fence(&p->job->sync, fence); - dma_fence_put(fence); - - return r; -} - -static int amdgpu_cs_process_syncobj_in_dep(struct amdgpu_cs_parser *p, - struct amdgpu_cs_chunk *chunk) -{ - struct drm_amdgpu_cs_chunk_sem *deps; - unsigned num_deps; - int i, r; + list_for_each_entry(e, &p->validated, tv.head) { + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + struct dma_resv *resv = bo->tbo.base.resv; + enum amdgpu_sync_mode sync_mode; - deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata; - num_deps = chunk->length_dw * 4 / - sizeof(struct drm_amdgpu_cs_chunk_sem); - for (i = 0; i < num_deps; ++i) { - r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle, - 0, 0); + sync_mode = amdgpu_bo_explicit_sync(bo) ? + AMDGPU_SYNC_EXPLICIT : AMDGPU_SYNC_NE_OWNER; + r = amdgpu_sync_resv(p->adev, &leader->sync, resv, sync_mode, + &fpriv->vm); if (r) return r; } - return 0; -} - - -static int amdgpu_cs_process_syncobj_timeline_in_dep(struct amdgpu_cs_parser *p, - struct amdgpu_cs_chunk *chunk) -{ - struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps; - unsigned num_deps; - int i, r; - - syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata; - num_deps = chunk->length_dw * 4 / - sizeof(struct drm_amdgpu_cs_chunk_syncobj); - for (i = 0; i < num_deps; ++i) { - r = amdgpu_syncobj_lookup_and_add_to_sync(p, - syncobj_deps[i].handle, - syncobj_deps[i].point, - syncobj_deps[i].flags); + for (i = 0; i < p->gang_size - 1; ++i) { + r = amdgpu_sync_clone(&leader->sync, &p->jobs[i]->sync); if (r) return r; } - return 0; -} - -static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p, - struct amdgpu_cs_chunk *chunk) -{ - struct drm_amdgpu_cs_chunk_sem *deps; - unsigned num_deps; - int i; - - deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata; - num_deps = chunk->length_dw * 4 / - sizeof(struct drm_amdgpu_cs_chunk_sem); - - if (p->post_deps) - return -EINVAL; - - p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps), - GFP_KERNEL); - p->num_post_deps = 0; - - if (!p->post_deps) - return -ENOMEM; - - - for (i = 0; i < num_deps; ++i) { - p->post_deps[i].syncobj = - drm_syncobj_find(p->filp, deps[i].handle); - if (!p->post_deps[i].syncobj) - return -EINVAL; - p->post_deps[i].chain = NULL; - p->post_deps[i].point = 0; - p->num_post_deps++; - } - - return 0; -} - - -static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p, - struct amdgpu_cs_chunk *chunk) -{ - struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps; - unsigned num_deps; - int i; - - syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata; - num_deps = chunk->length_dw * 4 / - sizeof(struct drm_amdgpu_cs_chunk_syncobj); - - if (p->post_deps) - return -EINVAL; - - p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps), - GFP_KERNEL); - p->num_post_deps = 0; - - if (!p->post_deps) - return -ENOMEM; - - for (i = 0; i < num_deps; ++i) { - struct amdgpu_cs_post_dep *dep = &p->post_deps[i]; - - dep->chain = NULL; - if (syncobj_deps[i].point) { - dep->chain = dma_fence_chain_alloc(); - if (!dep->chain) - return -ENOMEM; - } - - dep->syncobj = drm_syncobj_find(p->filp, - syncobj_deps[i].handle); - if (!dep->syncobj) { - dma_fence_chain_free(dep->chain); - return -EINVAL; - } - dep->point = syncobj_deps[i].point; - p->num_post_deps++; - } - - return 0; -} - -static int amdgpu_cs_dependencies(struct amdgpu_device *adev, - struct amdgpu_cs_parser *p) -{ - int i, r; - - /* TODO: Investigate why we still need the context lock */ - mutex_unlock(&p->ctx->lock); - - for (i = 0; i < p->nchunks; ++i) { - struct amdgpu_cs_chunk *chunk; - - chunk = &p->chunks[i]; + r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_size - 1]); + if (r && r != -ERESTARTSYS) + DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); - switch (chunk->chunk_id) { - case AMDGPU_CHUNK_ID_DEPENDENCIES: - case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: - r = amdgpu_cs_process_fence_dep(p, chunk); - if (r) - goto out; - break; - case AMDGPU_CHUNK_ID_SYNCOBJ_IN: - r = amdgpu_cs_process_syncobj_in_dep(p, chunk); - if (r) - goto out; - break; - case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: - r = amdgpu_cs_process_syncobj_out_dep(p, chunk); - if (r) - goto out; - break; - case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: - r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk); - if (r) - goto out; - break; - case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: - r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk); - if (r) - goto out; - break; - } - } - -out: - mutex_lock(&p->ctx->lock); return r; } @@ -1221,20 +1228,28 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - struct drm_sched_entity *entity = p->entity; + struct amdgpu_job *leader = p->gang_leader; struct amdgpu_bo_list_entry *e; - struct amdgpu_job *job; + unsigned int i; uint64_t seq; int r; - job = p->job; - p->job = NULL; + for (i = 0; i < p->gang_size; ++i) + drm_sched_job_arm(&p->jobs[i]->base); - r = drm_sched_job_init(&job->base, entity, &fpriv->vm); - if (r) - goto error_unlock; + for (i = 0; i < (p->gang_size - 1); ++i) { + struct dma_fence *fence; - drm_sched_job_arm(&job->base); + fence = &p->jobs[i]->base.s_fence->scheduled; + r = amdgpu_sync_fence(&leader->sync, fence); + if (r) + goto error_cleanup; + } + + if (p->gang_size > 1) { + for (i = 0; i < p->gang_size; ++i) + amdgpu_job_set_gang_leader(p->jobs[i], leader); + } /* No memory allocation is allowed while holding the notifier lock. * The lock is held until amdgpu_cs_submit is finished and fence is @@ -1245,6 +1260,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, /* If userptr are invalidated after amdgpu_cs_parser_bos(), return * -EAGAIN, drmIoctl in libdrm will restart the amdgpu_cs_ioctl. */ + r = 0; amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); @@ -1252,67 +1268,96 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, } if (r) { r = -EAGAIN; - goto error_abort; + goto error_unlock; } - p->fence = dma_fence_get(&job->base.s_fence->finished); + p->fence = dma_fence_get(&leader->base.s_fence->finished); + list_for_each_entry(e, &p->validated, tv.head) { + + /* Everybody except for the gang leader uses READ */ + for (i = 0; i < (p->gang_size - 1); ++i) { + dma_resv_add_fence(e->tv.bo->base.resv, + &p->jobs[i]->base.s_fence->finished, + DMA_RESV_USAGE_READ); + } - seq = amdgpu_ctx_add_fence(p->ctx, entity, p->fence); + /* The gang leader is remembered as writer */ + e->tv.num_shared = 0; + } + + seq = amdgpu_ctx_add_fence(p->ctx, p->entities[p->gang_size - 1], + p->fence); amdgpu_cs_post_dependencies(p); - if ((job->preamble_status & AMDGPU_PREAMBLE_IB_PRESENT) && + if ((leader->preamble_status & AMDGPU_PREAMBLE_IB_PRESENT) && !p->ctx->preamble_presented) { - job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT_FIRST; + leader->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT_FIRST; p->ctx->preamble_presented = true; } cs->out.handle = seq; - job->uf_sequence = seq; - - amdgpu_job_free_resources(job); + leader->uf_sequence = seq; - trace_amdgpu_cs_ioctl(job); amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket); - drm_sched_entity_push_job(&job->base); + for (i = 0; i < p->gang_size; ++i) { + amdgpu_job_free_resources(p->jobs[i]); + trace_amdgpu_cs_ioctl(p->jobs[i]); + drm_sched_entity_push_job(&p->jobs[i]->base); + p->jobs[i] = NULL; + } amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm); - - /* Make sure all BOs are remembered as writers */ - amdgpu_bo_list_for_each_entry(e, p->bo_list) - e->tv.num_shared = 0; - ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); + mutex_unlock(&p->adev->notifier_lock); mutex_unlock(&p->bo_list->bo_list_mutex); - return 0; -error_abort: - drm_sched_job_cleanup(&job->base); +error_unlock: mutex_unlock(&p->adev->notifier_lock); -error_unlock: - amdgpu_job_free(job); +error_cleanup: + for (i = 0; i < p->gang_size; ++i) + drm_sched_job_cleanup(&p->jobs[i]->base); return r; } -static void trace_amdgpu_cs_ibs(struct amdgpu_cs_parser *parser) +/* Cleanup the parser structure */ +static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) { - int i; + unsigned i; - if (!trace_amdgpu_cs_enabled()) - return; + for (i = 0; i < parser->num_post_deps; i++) { + drm_syncobj_put(parser->post_deps[i].syncobj); + kfree(parser->post_deps[i].chain); + } + kfree(parser->post_deps); + + dma_fence_put(parser->fence); + + if (parser->ctx) + amdgpu_ctx_put(parser->ctx); + if (parser->bo_list) + amdgpu_bo_list_put(parser->bo_list); + + for (i = 0; i < parser->nchunks; i++) + kvfree(parser->chunks[i].kdata); + kvfree(parser->chunks); + for (i = 0; i < parser->gang_size; ++i) { + if (parser->jobs[i]) + amdgpu_job_free(parser->jobs[i]); + } + if (parser->uf_entry.tv.bo) { + struct amdgpu_bo *uf = ttm_to_amdgpu_bo(parser->uf_entry.tv.bo); - for (i = 0; i < parser->job->num_ibs; i++) - trace_amdgpu_cs(parser, i); + amdgpu_bo_unref(&uf); + } } int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { struct amdgpu_device *adev = drm_to_adev(dev); - union drm_amdgpu_cs *cs = data; - struct amdgpu_cs_parser parser = {}; - bool reserved_buffers = false; + struct amdgpu_cs_parser parser; int r; if (amdgpu_ras_intr_triggered()) @@ -1321,25 +1366,20 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (!adev->accel_working) return -EBUSY; - parser.adev = adev; - parser.filp = filp; - - r = amdgpu_cs_parser_init(&parser, data); + r = amdgpu_cs_parser_init(&parser, adev, filp, data); if (r) { if (printk_ratelimit()) DRM_ERROR("Failed to initialize parser %d!\n", r); - goto out; + return r; } - r = amdgpu_cs_ib_fill(adev, &parser); + r = amdgpu_cs_pass1(&parser, data); if (r) - goto out; + goto error_fini; - r = amdgpu_cs_dependencies(adev, &parser); - if (r) { - DRM_ERROR("Failed in the dependencies handling %d!\n", r); - goto out; - } + r = amdgpu_cs_pass2(&parser); + if (r) + goto error_fini; r = amdgpu_cs_parser_bos(&parser, data); if (r) { @@ -1347,22 +1387,36 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) DRM_ERROR("Not enough memory for command submission!\n"); else if (r != -ERESTARTSYS && r != -EAGAIN) DRM_ERROR("Failed to process the buffer list %d!\n", r); - goto out; + goto error_fini; } - reserved_buffers = true; + r = amdgpu_cs_patch_jobs(&parser); + if (r) + goto error_backoff; + + r = amdgpu_cs_vm_handling(&parser); + if (r) + goto error_backoff; + + r = amdgpu_cs_sync_rings(&parser); + if (r) + goto error_backoff; trace_amdgpu_cs_ibs(&parser); - r = amdgpu_cs_vm_handling(&parser); + r = amdgpu_cs_submit(&parser, data); if (r) - goto out; + goto error_backoff; - r = amdgpu_cs_submit(&parser, cs); + amdgpu_cs_parser_fini(&parser); + return 0; -out: - amdgpu_cs_parser_fini(&parser, r, reserved_buffers); +error_backoff: + ttm_eu_backoff_reservation(&parser.ticket, &parser.validated); + mutex_unlock(&parser.bo_list->bo_list_mutex); +error_fini: + amdgpu_cs_parser_fini(&parser); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h index 30ecc4917f81..cbaa19b2b8a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h @@ -27,6 +27,8 @@ #include "amdgpu_bo_list.h" #include "amdgpu_ring.h" +#define AMDGPU_CS_GANG_SIZE 4 + struct amdgpu_bo_va_mapping; struct amdgpu_cs_chunk { @@ -50,9 +52,11 @@ struct amdgpu_cs_parser { unsigned nchunks; struct amdgpu_cs_chunk *chunks; - /* scheduler job object */ - struct amdgpu_job *job; - struct drm_sched_entity *entity; + /* scheduler job objects */ + unsigned int gang_size; + struct drm_sched_entity *entities[AMDGPU_CS_GANG_SIZE]; + struct amdgpu_job *jobs[AMDGPU_CS_GANG_SIZE]; + struct amdgpu_job *gang_leader; /* buffer objects */ struct ww_acquire_ctx ticket; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 3ea48385fab3..f6d9d5da53cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -315,7 +315,6 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, kref_init(&ctx->refcount); ctx->mgr = mgr; spin_lock_init(&ctx->ring_lock); - mutex_init(&ctx->lock); ctx->reset_counter = atomic_read(&mgr->adev->gpu_reset_counter); ctx->reset_counter_query = ctx->reset_counter; @@ -407,7 +406,6 @@ static void amdgpu_ctx_fini(struct kref *ref) drm_dev_exit(idx); } - mutex_destroy(&ctx->lock); kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h index cc7c8afff414..0fa0e56daf67 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h @@ -53,7 +53,6 @@ struct amdgpu_ctx { bool preamble_presented; int32_t init_priority; int32_t override_priority; - struct mutex lock; atomic_t guilty; unsigned long ras_counter_ce; unsigned long ras_counter_ue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 62b26f0e37b0..ab8f970b2849 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); @@ -2451,19 +2459,21 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) */ if (adev->gmc.xgmi.num_physical_nodes > 1) { if (amdgpu_xgmi_add_device(adev) == 0) { - struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + if (!amdgpu_sriov_vf(adev)) { + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); - if (!hive->reset_domain || - !amdgpu_reset_get_reset_domain(hive->reset_domain)) { - r = -ENOENT; + if (!hive->reset_domain || + !amdgpu_reset_get_reset_domain(hive->reset_domain)) { + r = -ENOENT; + amdgpu_put_xgmi_hive(hive); + goto init_failed; + } + + /* Drop the early temporary reset domain we created for device */ + amdgpu_reset_put_reset_domain(adev->reset_domain); + adev->reset_domain = hive->reset_domain; amdgpu_put_xgmi_hive(hive); - goto init_failed; } - - /* Drop the early temporary reset domain we created for device */ - amdgpu_reset_put_reset_domain(adev->reset_domain); - adev->reset_domain = hive->reset_domain; - amdgpu_put_xgmi_hive(hive); } } @@ -3052,8 +3062,8 @@ 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 +3154,8 @@ 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) { @@ -3501,6 +3512,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->gmc.gart_size = 512 * 1024 * 1024; adev->accel_working = false; adev->num_rings = 0; + RCU_INIT_POINTER(adev->gang_submit, dma_fence_get_stub()); adev->mman.buffer_funcs = NULL; adev->mman.buffer_funcs_ring = NULL; adev->vm_manager.vm_pte_funcs = NULL; @@ -3982,6 +3994,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) release_firmware(adev->firmware.gpu_info_fw); adev->firmware.gpu_info_fw = NULL; adev->accel_working = false; + dma_fence_put(rcu_dereference_protected(adev->gang_submit, true)); amdgpu_reset_fini(adev); @@ -4057,12 +4070,20 @@ 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"); @@ -4086,6 +4107,9 @@ 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; } @@ -4104,6 +4128,12 @@ 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; @@ -4118,6 +4148,13 @@ 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; @@ -4739,6 +4776,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, struct amdgpu_device *tmp_adev = NULL; bool need_full_reset, skip_hw_reset, vram_lost = false; int r = 0; + bool gpu_reset_for_dev_remove = 0; /* Try reset handler method first */ tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, @@ -4758,6 +4796,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags); + gpu_reset_for_dev_remove = + test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + /* * ASIC reset has to be done on all XGMI hive nodes ASAP * to allow proper links negotiation in FW (within 1 sec) @@ -4802,6 +4844,18 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, amdgpu_ras_intr_cleared(); } + /* Since the mode1 reset affects base ip blocks, the + * phase1 ip blocks need to be resumed. Otherwise there + * will be a BIOS signature error and the psp bootloader + * can't load kdb on the next amdgpu install. + */ + if (gpu_reset_for_dev_remove) { + list_for_each_entry(tmp_adev, device_list_handle, reset_list) + amdgpu_device_ip_resume_phase1(tmp_adev); + + goto end; + } + list_for_each_entry(tmp_adev, device_list_handle, reset_list) { if (need_full_reset) { /* post card */ @@ -5124,6 +5178,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, bool need_emergency_restart = false; bool audio_suspended = false; int tmp_vram_lost_counter; + bool gpu_reset_for_dev_remove = false; + + gpu_reset_for_dev_remove = + test_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context->flags) && + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); /* * Special case: RAS triggered and full reset isn't supported @@ -5159,8 +5218,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, */ INIT_LIST_HEAD(&device_list); if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) { - list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) + list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { list_add_tail(&tmp_adev->reset_list, &device_list); + if (gpu_reset_for_dev_remove && adev->shutdown) + tmp_adev->shutdown = true; + } if (!list_is_first(&adev->reset_list, &device_list)) list_rotate_to_front(&adev->reset_list, &device_list); device_list_handle = &device_list; @@ -5243,6 +5305,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { + if (gpu_reset_for_dev_remove) { + /* Workaroud for ASICs need to disable SMC first */ + amdgpu_device_smu_fini_early(tmp_adev); + } r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context); /*TODO Should we stop ?*/ if (r) { @@ -5276,6 +5342,9 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ adev->asic_reset_res = 0; goto retry; } + + if (!r && gpu_reset_for_dev_remove) + goto recover_end; } skip_hw_reset: @@ -5349,6 +5418,7 @@ skip_sched_resume: amdgpu_device_unset_mp1_state(tmp_adev); } +recover_end: tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, reset_list); amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain); @@ -5531,9 +5601,9 @@ 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 = !adev->gmc.xgmi.connected_to_cpu && - !(pci_p2pdma_distance_many(adev->pdev, - &peer_adev->dev, 1, true) < 0); + bool p2p_access = + !adev->gmc.xgmi.connected_to_cpu && + !(pci_p2pdma_distance(adev->pdev, peer_adev->dev, false) < 0); return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size && adev->gmc.real_vram_size == adev->gmc.visible_vram_size && @@ -5917,3 +5987,36 @@ void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev, (void)RREG32(data); spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); } + +/** + * amdgpu_device_switch_gang - switch to a new gang + * @adev: amdgpu_device pointer + * @gang: the gang to switch to + * + * Try to switch to a new gang. + * Returns: NULL if we switched to the new gang or a reference to the current + * gang leader. + */ +struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev, + struct dma_fence *gang) +{ + struct dma_fence *old = NULL; + + do { + dma_fence_put(old); + rcu_read_lock(); + old = dma_fence_get_rcu_safe(&adev->gang_submit); + rcu_read_unlock(); + + if (old == gang) + break; + + if (!dma_fence_is_signaled(old)) + return old; + + } while (cmpxchg((struct dma_fence __force **)&adev->gang_submit, + old, gang) != old); + + dma_fence_put(old); + return NULL; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 9fa2a5ceb77d..3993e6134914 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -229,7 +229,7 @@ static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, ui return r; } - memcpy((u8 *)binary, (u8 *)fw->data, adev->mman.discovery_tmr_size); + memcpy((u8 *)binary, (u8 *)fw->data, fw->size); release_firmware(fw); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index c20922a5af9f..1a06b8d724f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1101,6 +1101,7 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, goto err; ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (ret) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 782cbca37538..7bd8e33b14be 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -58,7 +58,7 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r; - if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0) + if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 728a0933ea6f..3c9fecdd6b2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -38,6 +38,8 @@ #include <linux/mmu_notifier.h> #include <linux/suspend.h> #include <linux/cc_platform.h> +#include <linux/fb.h> +#include <linux/dynamic_debug.h> #include "amdgpu.h" #include "amdgpu_irq.h" @@ -102,9 +104,10 @@ * - 3.46.0 - To enable hot plug amdgpu tests in libdrm * - 3.47.0 - Add AMDGPU_GEM_CREATE_DISCARDABLE and AMDGPU_VM_NOALLOC flags * - 3.48.0 - Add IP discovery version info to HW INFO + * 3.49.0 - Add gang submit into CS IOCTL */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 48 +#define KMS_DRIVER_MINOR 49 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit; @@ -185,6 +188,18 @@ int amdgpu_vcnfw_log; static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); +DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, + "DRM_UT_CORE", + "DRM_UT_DRIVER", + "DRM_UT_KMS", + "DRM_UT_PRIME", + "DRM_UT_ATOMIC", + "DRM_UT_VBL", + "DRM_UT_STATE", + "DRM_UT_LEASE", + "DRM_UT_DP", + "DRM_UT_DRMRES"); + struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), .delayed_reset_work = __DELAYED_WORK_INITIALIZER( @@ -2186,6 +2201,37 @@ amdgpu_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(dev->dev); } + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2)) { + bool need_to_reset_gpu = false; + + if (adev->gmc.xgmi.num_physical_nodes > 1) { + struct amdgpu_hive_info *hive; + + hive = amdgpu_get_xgmi_hive(adev); + if (hive->device_remove_count == 0) + need_to_reset_gpu = true; + hive->device_remove_count++; + amdgpu_put_xgmi_hive(hive); + } else { + need_to_reset_gpu = true; + } + + /* Workaround for ASICs need to reset SMU. + * Called only when the first device is removed. + */ + if (need_to_reset_gpu) { + struct amdgpu_reset_context reset_context; + + adev->shutdown = true; + memset(&reset_context, 0, sizeof(reset_context)); + reset_context.method = AMD_RESET_METHOD_NONE; + reset_context.reset_req_dev = adev; + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags); + amdgpu_device_gpu_recover(adev, NULL, &reset_context); + } + } + amdgpu_driver_unload_kms(dev); drm_dev_unplug(dev); 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_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index ceb91469958a..9546adc8a76f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -23,6 +23,7 @@ * */ +#include <linux/firmware.h> #include "amdgpu.h" #include "amdgpu_gfx.h" #include "amdgpu_rlc.h" @@ -865,3 +866,142 @@ int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev) } return amdgpu_num_kcq; } + +void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, + uint32_t ucode_id) +{ + const struct gfx_firmware_header_v1_0 *cp_hdr; + const struct gfx_firmware_header_v2_0 *cp_hdr_v2_0; + struct amdgpu_firmware_info *info = NULL; + const struct firmware *ucode_fw; + unsigned int fw_size; + + switch (ucode_id) { + case AMDGPU_UCODE_ID_CP_PFP: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.pfp_fw->data; + adev->gfx.pfp_fw_version = + le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.pfp_feature_version = + le32_to_cpu(cp_hdr->ucode_feature_version); + ucode_fw = adev->gfx.pfp_fw; + fw_size = le32_to_cpu(cp_hdr->header.ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_RS64_PFP: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.pfp_fw->data; + adev->gfx.pfp_fw_version = + le32_to_cpu(cp_hdr_v2_0->header.ucode_version); + adev->gfx.pfp_feature_version = + le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); + ucode_fw = adev->gfx.pfp_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_RS64_PFP_P0_STACK: + case AMDGPU_UCODE_ID_CP_RS64_PFP_P1_STACK: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.pfp_fw->data; + ucode_fw = adev->gfx.pfp_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->data_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_ME: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.me_fw->data; + adev->gfx.me_fw_version = + le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.me_feature_version = + le32_to_cpu(cp_hdr->ucode_feature_version); + ucode_fw = adev->gfx.me_fw; + fw_size = le32_to_cpu(cp_hdr->header.ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_RS64_ME: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.me_fw->data; + adev->gfx.me_fw_version = + le32_to_cpu(cp_hdr_v2_0->header.ucode_version); + adev->gfx.me_feature_version = + le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); + ucode_fw = adev->gfx.me_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_RS64_ME_P0_STACK: + case AMDGPU_UCODE_ID_CP_RS64_ME_P1_STACK: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.me_fw->data; + ucode_fw = adev->gfx.me_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->data_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_CE: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.ce_fw->data; + adev->gfx.ce_fw_version = + le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.ce_feature_version = + le32_to_cpu(cp_hdr->ucode_feature_version); + ucode_fw = adev->gfx.ce_fw; + fw_size = le32_to_cpu(cp_hdr->header.ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_MEC1: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.mec_fw->data; + adev->gfx.mec_fw_version = + le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.mec_feature_version = + le32_to_cpu(cp_hdr->ucode_feature_version); + ucode_fw = adev->gfx.mec_fw; + fw_size = le32_to_cpu(cp_hdr->header.ucode_size_bytes) - + le32_to_cpu(cp_hdr->jt_size) * 4; + break; + case AMDGPU_UCODE_ID_CP_MEC1_JT: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.mec_fw->data; + ucode_fw = adev->gfx.mec_fw; + fw_size = le32_to_cpu(cp_hdr->jt_size) * 4; + break; + case AMDGPU_UCODE_ID_CP_MEC2: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.mec2_fw->data; + adev->gfx.mec2_fw_version = + le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.mec2_feature_version = + le32_to_cpu(cp_hdr->ucode_feature_version); + ucode_fw = adev->gfx.mec2_fw; + fw_size = le32_to_cpu(cp_hdr->header.ucode_size_bytes) - + le32_to_cpu(cp_hdr->jt_size) * 4; + break; + case AMDGPU_UCODE_ID_CP_MEC2_JT: + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.mec2_fw->data; + ucode_fw = adev->gfx.mec2_fw; + fw_size = le32_to_cpu(cp_hdr->jt_size) * 4; + break; + case AMDGPU_UCODE_ID_CP_RS64_MEC: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.mec_fw->data; + adev->gfx.mec_fw_version = + le32_to_cpu(cp_hdr_v2_0->header.ucode_version); + adev->gfx.mec_feature_version = + le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); + ucode_fw = adev->gfx.mec_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes); + break; + case AMDGPU_UCODE_ID_CP_RS64_MEC_P0_STACK: + case AMDGPU_UCODE_ID_CP_RS64_MEC_P1_STACK: + case AMDGPU_UCODE_ID_CP_RS64_MEC_P2_STACK: + case AMDGPU_UCODE_ID_CP_RS64_MEC_P3_STACK: + cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *) + adev->gfx.mec_fw->data; + ucode_fw = adev->gfx.mec_fw; + fw_size = le32_to_cpu(cp_hdr_v2_0->data_size_bytes); + break; + default: + break; + } + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + info = &adev->firmware.ucode[ucode_id]; + info->ucode_id = ucode_id; + info->fw = ucode_fw; + adev->firmware.fw_size += ALIGN(fw_size, PAGE_SIZE); + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 8abdf41d0f83..832b3807f1d6 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; @@ -422,4 +426,6 @@ int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev, uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg); void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v); int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev); +void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, uint32_t ucode_id); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index aebc384531ac..34233a74248c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -572,45 +572,15 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) { struct amdgpu_gmc *gmc = &adev->gmc; - - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(9, 0, 1): - case IP_VERSION(9, 3, 0): - case IP_VERSION(9, 4, 0): - case IP_VERSION(9, 4, 1): - case IP_VERSION(9, 4, 2): - case IP_VERSION(10, 3, 3): - case IP_VERSION(10, 3, 4): - case IP_VERSION(10, 3, 5): - case IP_VERSION(10, 3, 6): - case IP_VERSION(10, 3, 7): - /* - * noretry = 0 will cause kfd page fault tests fail - * for some ASICs, so set default to 1 for these ASICs. - */ - if (amdgpu_noretry == -1) - gmc->noretry = 1; - else - gmc->noretry = amdgpu_noretry; - break; - default: - /* Raven currently has issues with noretry - * regardless of what we decide for other - * asics, we should leave raven with - * noretry = 0 until we root cause the - * issues. - * - * default this to 0 for now, but we may want - * to change this in the future for certain - * GPUs as it can increase performance in - * certain cases. - */ - if (amdgpu_noretry == -1) - gmc->noretry = 0; - else - gmc->noretry = amdgpu_noretry; - break; - } + uint32_t gc_ver = adev->ip_versions[GC_HWIP][0]; + bool noretry_default = (gc_ver == IP_VERSION(9, 0, 1) || + gc_ver == IP_VERSION(9, 3, 0) || + gc_ver == IP_VERSION(9, 4, 0) || + gc_ver == IP_VERSION(9, 4, 1) || + gc_ver == IP_VERSION(9, 4, 2) || + gc_ver >= IP_VERSION(10, 3, 0)); + + gmc->noretry = (amdgpu_noretry == -1) ? noretry_default : amdgpu_noretry; } void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 1062b7ed74ec..46c99331d7f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -105,7 +105,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, */ (*job)->base.sched = &adev->rings[0]->sched; (*job)->vm = vm; - (*job)->num_ibs = num_ibs; amdgpu_sync_create(&(*job)->sync); amdgpu_sync_create(&(*job)->sched_sync); @@ -125,6 +124,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, if (r) return r; + (*job)->num_ibs = 1; r = amdgpu_ib_get(adev, NULL, size, pool_type, &(*job)->ibs[0]); if (r) kfree(*job); @@ -132,6 +132,23 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, return r; } +void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, + struct amdgpu_bo *gws, struct amdgpu_bo *oa) +{ + if (gds) { + job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; + job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; + } + if (gws) { + job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT; + job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT; + } + if (oa) { + job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT; + job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT; + } +} + void amdgpu_job_free_resources(struct amdgpu_job *job) { struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); @@ -156,11 +173,29 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job) dma_fence_put(&job->hw_fence); } +void amdgpu_job_set_gang_leader(struct amdgpu_job *job, + struct amdgpu_job *leader) +{ + struct dma_fence *fence = &leader->base.s_fence->scheduled; + + WARN_ON(job->gang_submit); + + /* + * Don't add a reference when we are the gang leader to avoid circle + * dependency. + */ + if (job != leader) + dma_fence_get(fence); + job->gang_submit = fence; +} + void amdgpu_job_free(struct amdgpu_job *job) { amdgpu_job_free_resources(job); amdgpu_sync_free(&job->sync); amdgpu_sync_free(&job->sched_sync); + if (job->gang_submit != &job->base.s_fence->scheduled) + dma_fence_put(job->gang_submit); if (!job->hw_fence.ops) kfree(job); @@ -230,12 +265,16 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job, fence = amdgpu_sync_get_fence(&job->sync); } + if (!fence && job->gang_submit) + fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); + return fence; } static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) { struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched); + struct amdgpu_device *adev = ring->adev; struct dma_fence *fence = NULL, *finished; struct amdgpu_job *job; int r = 0; @@ -247,8 +286,10 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) trace_amdgpu_sched_run_job(job); - if (job->vram_lost_counter != atomic_read(&ring->adev->vram_lost_counter)) - dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */ + /* Skip job if VRAM is lost and never resubmit gangs */ + if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter) || + (job->job_run_counter && job->gang_submit)) + dma_fence_set_error(finished, -ECANCELED); if (finished->error < 0) { DRM_INFO("Skip scheduling IBs!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index babc0af751c2..ab7b150e5d50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -50,6 +50,7 @@ struct amdgpu_job { struct amdgpu_sync sync; struct amdgpu_sync sched_sync; struct dma_fence hw_fence; + struct dma_fence *gang_submit; uint32_t preamble_status; uint32_t preemption_status; bool vm_needs_flush; @@ -72,11 +73,20 @@ struct amdgpu_job { struct amdgpu_ib ibs[]; }; +static inline struct amdgpu_ring *amdgpu_job_ring(struct amdgpu_job *job) +{ + return to_amdgpu_ring(job->base.entity->rq->sched); +} + int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, struct amdgpu_job **job, struct amdgpu_vm *vm); int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, enum amdgpu_ib_pool_type pool, struct amdgpu_job **job); +void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, + struct amdgpu_bo *gws, struct amdgpu_bo *oa); void amdgpu_job_free_resources(struct amdgpu_job *job); +void amdgpu_job_set_gang_leader(struct amdgpu_job *job, + struct amdgpu_job *leader); void amdgpu_job_free(struct amdgpu_job *job); int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, void *owner, struct dma_fence **f); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 77668c3dae5b..fe23e09eec98 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -247,6 +247,14 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, fw_info->ver = adev->gfx.rlc_srls_fw_version; fw_info->feature = adev->gfx.rlc_srls_feature_version; break; + case AMDGPU_INFO_FW_GFX_RLCP: + fw_info->ver = adev->gfx.rlcp_ucode_version; + fw_info->feature = adev->gfx.rlcp_ucode_feature_version; + break; + case AMDGPU_INFO_FW_GFX_RLCV: + fw_info->ver = adev->gfx.rlcv_ucode_version; + fw_info->feature = adev->gfx.rlcv_ucode_feature_version; + break; case AMDGPU_INFO_FW_GFX_MEC: if (query_fw->index == 0) { fw_info->ver = adev->gfx.mec_fw_version; @@ -328,6 +336,14 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, fw_info->ver = adev->psp.cap_fw_version; fw_info->feature = adev->psp.cap_feature_version; break; + case AMDGPU_INFO_FW_MES_KIQ: + fw_info->ver = adev->mes.ucode_fw_version[0]; + fw_info->feature = 0; + break; + case AMDGPU_INFO_FW_MES: + fw_info->ver = adev->mes.ucode_fw_version[1]; + fw_info->feature = 0; + break; default: return -EINVAL; } @@ -1469,6 +1485,22 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused) seq_printf(m, "RLC SRLS feature version: %u, firmware version: 0x%08x\n", fw_info.feature, fw_info.ver); + /* RLCP */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLCP; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "RLCP feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* RLCV */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLCV; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "RLCV feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + /* MEC */ query_fw.fw_type = AMDGPU_INFO_FW_GFX_MEC; query_fw.index = 0; @@ -1581,6 +1613,22 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused) fw_info.feature, fw_info.ver); } + /* MES_KIQ */ + query_fw.fw_type = AMDGPU_INFO_FW_MES_KIQ; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "MES_KIQ feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* MES */ + query_fw.fw_type = AMDGPU_INFO_FW_MES; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "MES feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + seq_printf(m, "VBIOS version: %s\n", ctx->vbios_version); return 0; 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_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e6a9b9fc9e0b..2e8f6cd7a729 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -688,13 +688,16 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, * num of amdgpu_vm_pt entries. */ BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo_vm)); - bp->destroy = &amdgpu_bo_vm_destroy; r = amdgpu_bo_create(adev, bp, &bo_ptr); if (r) return r; *vmbo_ptr = to_amdgpu_bo_vm(bo_ptr); INIT_LIST_HEAD(&(*vmbo_ptr)->shadow_list); + /* Set destroy callback to amdgpu_bo_vm_destroy after vmbo->shadow_list + * is initialized. + */ + bo_ptr->tbo.destroy = &amdgpu_bo_vm_destroy; return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index cfcaf890a6a1..effa7df3ddbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -511,6 +511,11 @@ static int psp_sw_fini(void *handle) kfree(cmd); cmd = NULL; + if (psp->km_ring.ring_mem) + amdgpu_bo_free_kernel(&adev->firmware.rbuf, + &psp->km_ring.ring_mem_mc_addr, + (void **)&psp->km_ring.ring_mem); + amdgpu_bo_free_kernel(&psp->fw_pri_bo, &psp->fw_pri_mc_addr, &psp->fw_pri_buf); amdgpu_bo_free_kernel(&psp->fence_buf_bo, @@ -766,7 +771,7 @@ 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); @@ -2055,6 +2060,15 @@ static int psp_hw_start(struct psp_context *psp) } } + if ((is_psp_fw_valid(psp->ras_drv)) && + (psp->funcs->bootloader_load_ras_drv != NULL)) { + ret = psp_bootloader_load_ras_drv(psp); + if (ret) { + DRM_ERROR("PSP load ras_drv failed!\n"); + return ret; + } + } + if ((is_psp_fw_valid(psp->sos)) && (psp->funcs->bootloader_load_sos != NULL)) { ret = psp_bootloader_load_sos(psp); @@ -3040,6 +3054,12 @@ static int parse_sos_bin_descriptor(struct psp_context *psp, psp->dbg_drv.size_bytes = le32_to_cpu(desc->size_bytes); psp->dbg_drv.start_addr = ucode_start_addr; break; + case PSP_FW_TYPE_PSP_RAS_DRV: + psp->ras_drv.fw_version = le32_to_cpu(desc->fw_version); + psp->ras_drv.feature_version = le32_to_cpu(desc->fw_version); + psp->ras_drv.size_bytes = le32_to_cpu(desc->size_bytes); + psp->ras_drv.start_addr = ucode_start_addr; + break; default: dev_warn(psp->adev->dev, "Unsupported PSP FW type: %d\n", desc->fw_type); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index c32b74bd970f..58ce3ebb446c 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 { @@ -71,6 +72,7 @@ enum psp_bootloader_cmd { PSP_BL__LOAD_SOCDRV = 0xB0000, PSP_BL__LOAD_DBGDRV = 0xC0000, PSP_BL__LOAD_INTFDRV = 0xD0000, + PSP_BL__LOAD_RASDRV = 0xE0000, PSP_BL__DRAM_LONG_TRAIN = 0x100000, PSP_BL__DRAM_SHORT_TRAIN = 0x200000, PSP_BL__LOAD_TOS_SPL_TABLE = 0x10000000, @@ -114,6 +116,7 @@ struct psp_funcs int (*bootloader_load_soc_drv)(struct psp_context *psp); int (*bootloader_load_intf_drv)(struct psp_context *psp); int (*bootloader_load_dbg_drv)(struct psp_context *psp); + int (*bootloader_load_ras_drv)(struct psp_context *psp); int (*bootloader_load_sos)(struct psp_context *psp); int (*ring_init)(struct psp_context *psp, enum psp_ring_type ring_type); int (*ring_create)(struct psp_context *psp, @@ -323,6 +326,7 @@ struct psp_context struct psp_bin_desc soc_drv; struct psp_bin_desc intf_drv; struct psp_bin_desc dbg_drv; + struct psp_bin_desc ras_drv; /* tmr buffer */ struct amdgpu_bo *tmr_bo; @@ -403,6 +407,9 @@ struct amdgpu_psp_funcs { ((psp)->funcs->bootloader_load_intf_drv ? (psp)->funcs->bootloader_load_intf_drv((psp)) : 0) #define psp_bootloader_load_dbg_drv(psp) \ ((psp)->funcs->bootloader_load_dbg_drv ? (psp)->funcs->bootloader_load_dbg_drv((psp)) : 0) +#define psp_bootloader_load_ras_drv(psp) \ + ((psp)->funcs->bootloader_load_ras_drv ? \ + (psp)->funcs->bootloader_load_ras_drv((psp)) : 0) #define psp_bootloader_load_sos(psp) \ ((psp)->funcs->bootloader_load_sos ? (psp)->funcs->bootloader_load_sos((psp)) : 0) #define psp_smu_reload_quirk(psp) \ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ab9ba5a9c33d..2dad7aa9a03b 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"); } @@ -2719,7 +2720,8 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev) /* Need disable ras on all IPs here before ip [hw/sw]fini */ - amdgpu_ras_disable_all_features(adev, 0); + if (con->features) + amdgpu_ras_disable_all_features(adev, 0); amdgpu_ras_recovery_fini(adev); return 0; } @@ -2832,11 +2834,8 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, struct mce *m = (struct mce *)data; struct amdgpu_device *adev = NULL; uint32_t gpu_id = 0; - uint32_t umc_inst = 0; - uint32_t ch_inst, channel_index = 0; + uint32_t umc_inst = 0, ch_inst = 0; struct ras_err_data err_data = {0, 0, 0, NULL}; - struct eeprom_table_record err_rec; - uint64_t retired_page; /* * If the error was generated in UMC_V2, which belongs to GPU UMCs, @@ -2875,21 +2874,22 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d, chan_idx: %d", umc_inst, ch_inst); + err_data.err_addr = + kcalloc(adev->umc.max_ras_err_cnt_per_query, + sizeof(struct eeprom_table_record), GFP_KERNEL); + if (!err_data.err_addr) { + dev_warn(adev->dev, + "Failed to alloc memory for umc error record in mca notifier!\n"); + return NOTIFY_DONE; + } + /* * Translate UMC channel address to Physical address */ - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num - + ch_inst]; - - retired_page = ADDR_OF_8KB_BLOCK(m->addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(m->addr); - - memset(&err_rec, 0x0, sizeof(struct eeprom_table_record)); - err_data.err_addr = &err_rec; - amdgpu_umc_fill_error_record(&err_data, m->addr, - retired_page, channel_index, umc_inst); + if (adev->umc.ras && + adev->umc.ras->convert_ras_error_address) + adev->umc.ras->convert_ras_error_address(adev, + &err_data, m->addr, ch_inst, umc_inst); if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, @@ -2897,6 +2897,7 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, amdgpu_ras_save_bad_pages(adev); } + kfree(err_data.err_addr); return NOTIFY_OK; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index c4283987bb1e..84c241b9a2a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -38,6 +38,7 @@ #define EEPROM_I2C_MADDR_ARCTURUS_D342 0x0 #define EEPROM_I2C_MADDR_SIENNA_CICHLID 0x0 #define EEPROM_I2C_MADDR_ALDEBARAN 0x0 +#define EEPROM_I2C_MADDR_SMU_13_0_0 (0x54UL << 16) /* * The 2 macros bellow represent the actual size in bytes that @@ -156,6 +157,15 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, return false; } + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 0): + control->i2c_address = EEPROM_I2C_MADDR_SMU_13_0_0; + break; + + default: + break; + } + return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h index f71b83c42590..f5318fedf2f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h @@ -31,6 +31,7 @@ enum AMDGPU_RESET_FLAGS { AMDGPU_NEED_FULL_RESET = 0, AMDGPU_SKIP_HW_RESET = 1, AMDGPU_SKIP_MODE2_RESET = 2, + AMDGPU_RESET_FOR_DEVICE_REMOVE = 3, }; struct amdgpu_reset_context { @@ -112,7 +113,8 @@ static inline bool amdgpu_reset_get_reset_domain(struct amdgpu_reset_domain *dom static inline void amdgpu_reset_put_reset_domain(struct amdgpu_reset_domain *domain) { - kref_put(&domain->refcount, amdgpu_reset_destroy_reset_domain); + if (domain) + kref_put(&domain->refcount, amdgpu_reset_destroy_reset_domain); } static inline bool amdgpu_reset_domain_schedule(struct amdgpu_reset_domain *domain, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index 6373bfb47d55..012b72d00e04 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -272,3 +272,275 @@ 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_cntl_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.save_restore_list_cntl_size_bytes, PAGE_SIZE); + } + + 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_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 42c1f050542f..ea5278f094c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -21,6 +21,7 @@ * */ +#include <linux/firmware.h> #include "amdgpu.h" #include "amdgpu_sdma.h" #include "amdgpu_ras.h" @@ -150,3 +151,158 @@ int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev, amdgpu_ras_interrupt_dispatch(adev, &ih_data); return 0; } + +static int amdgpu_sdma_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst) +{ + int err = 0; + uint16_t version_major; + const struct common_firmware_header *header = NULL; + const struct sdma_firmware_header_v1_0 *hdr; + const struct sdma_firmware_header_v2_0 *hdr_v2; + + err = amdgpu_ucode_validate(sdma_inst->fw); + if (err) + return err; + + header = (const struct common_firmware_header *) + sdma_inst->fw->data; + version_major = le16_to_cpu(header->header_version_major); + + switch (version_major) { + case 1: + hdr = (const struct sdma_firmware_header_v1_0 *)sdma_inst->fw->data; + sdma_inst->fw_version = le32_to_cpu(hdr->header.ucode_version); + sdma_inst->feature_version = le32_to_cpu(hdr->ucode_feature_version); + break; + case 2: + hdr_v2 = (const struct sdma_firmware_header_v2_0 *)sdma_inst->fw->data; + sdma_inst->fw_version = le32_to_cpu(hdr_v2->header.ucode_version); + sdma_inst->feature_version = le32_to_cpu(hdr_v2->ucode_feature_version); + break; + default: + return -EINVAL; + } + + if (sdma_inst->feature_version >= 20) + sdma_inst->burst_nop = true; + + return 0; +} + +void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, + bool duplicate) +{ + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + if (duplicate) + break; + } + + memset((void *)adev->sdma.instance, 0, + sizeof(struct amdgpu_sdma_instance) * AMDGPU_MAX_SDMA_INSTANCES); +} + +int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, + char *fw_name, u32 instance, + bool duplicate) +{ + struct amdgpu_firmware_info *info = NULL; + const struct common_firmware_header *header = NULL; + int err = 0, i; + const struct sdma_firmware_header_v2_0 *sdma_hdr; + uint16_t version_major; + + err = request_firmware(&adev->sdma.instance[instance].fw, fw_name, adev->dev); + if (err) + goto out; + + header = (const struct common_firmware_header *) + adev->sdma.instance[instance].fw->data; + version_major = le16_to_cpu(header->header_version_major); + + if ((duplicate && instance) || (!duplicate && version_major > 1)) { + err = -EINVAL; + goto out; + } + + err = amdgpu_sdma_init_inst_ctx(&adev->sdma.instance[instance]); + if (err) + goto out; + + if (duplicate) { + for (i = 1; i < adev->sdma.num_instances; i++) + memcpy((void *)&adev->sdma.instance[i], + (void *)&adev->sdma.instance[0], + sizeof(struct amdgpu_sdma_instance)); + } + + if (amdgpu_sriov_vf(adev)) + return 0; + + DRM_DEBUG("psp_load == '%s'\n", + adev->firmware.load_type == AMDGPU_FW_LOAD_PSP ? "true" : "false"); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + switch (version_major) { + case 1: + for (i = 0; i < adev->sdma.num_instances; i++) { + if (!duplicate && (instance != i)) + continue; + else { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; + info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; + info->fw = adev->sdma.instance[i].fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); + } + } + break; + case 2: + sdma_hdr = (const struct sdma_firmware_header_v2_0 *) + adev->sdma.instance[0].fw->data; + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA_UCODE_TH0]; + info->ucode_id = AMDGPU_UCODE_ID_SDMA_UCODE_TH0; + info->fw = adev->sdma.instance[0].fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(sdma_hdr->ctx_ucode_size_bytes), PAGE_SIZE); + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA_UCODE_TH1]; + info->ucode_id = AMDGPU_UCODE_ID_SDMA_UCODE_TH1; + info->fw = adev->sdma.instance[0].fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(sdma_hdr->ctl_ucode_size_bytes), PAGE_SIZE); + break; + default: + err = -EINVAL; + } + } + +out: + if (err) { + DRM_ERROR("SDMA: Failed to init firmware \"%s\"\n", fw_name); + amdgpu_sdma_destroy_inst_ctx(adev, duplicate); + } + return err; +} + +void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev) +{ + struct amdgpu_ring *sdma; + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) { + if (adev->sdma.has_page_queue) { + sdma = &adev->sdma.instance[i].page; + if (adev->mman.buffer_funcs_ring == sdma) { + amdgpu_ttm_set_buffer_funcs_status(adev, false); + break; + } + } + sdma = &adev->sdma.instance[i].ring; + if (adev->mman.buffer_funcs_ring == sdma) { + amdgpu_ttm_set_buffer_funcs_status(adev, false); + break; + } + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 53ac3ebae8d6..7d99205c2e01 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -124,4 +124,10 @@ int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev, int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, + char *fw_name, u32 instance, bool duplicate); +void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, + bool duplicate); +void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 504af1b93bfa..090e66a1b284 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT /* * Copyright 2014 Advanced Micro Devices, Inc. * All Rights Reserved. @@ -315,6 +316,7 @@ struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync) struct hlist_node *tmp; struct dma_fence *f; int i; + hash_for_each_safe(sync->fences, i, tmp, e, node) { f = e->fence; @@ -392,7 +394,7 @@ void amdgpu_sync_free(struct amdgpu_sync *sync) { struct amdgpu_sync_entry *e; struct hlist_node *tmp; - unsigned i; + unsigned int i; hash_for_each_safe(sync->fences, i, tmp, e, node) { hash_del(&e->node); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 06dfcf297a8d..5e6ddc7e101c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -140,8 +140,10 @@ TRACE_EVENT(amdgpu_bo_create, ); TRACE_EVENT(amdgpu_cs, - TP_PROTO(struct amdgpu_cs_parser *p, int i), - TP_ARGS(p, i), + TP_PROTO(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib), + TP_ARGS(p, job, ib), TP_STRUCT__entry( __field(struct amdgpu_bo_list *, bo_list) __field(u32, ring) @@ -151,10 +153,10 @@ TRACE_EVENT(amdgpu_cs, TP_fast_assign( __entry->bo_list = p->bo_list; - __entry->ring = to_amdgpu_ring(p->entity->rq->sched)->idx; - __entry->dw = p->job->ibs[i].length_dw; + __entry->ring = to_amdgpu_ring(job->base.sched)->idx; + __entry->dw = ib->length_dw; __entry->fences = amdgpu_fence_count_emitted( - to_amdgpu_ring(p->entity->rq->sched)); + to_amdgpu_ring(job->base.sched)); ), TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u", __entry->bo_list, __entry->ring, __entry->dw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b1c455329023..dc262d2c2925 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -424,8 +424,9 @@ error: static bool amdgpu_mem_visible(struct amdgpu_device *adev, struct ttm_resource *mem) { - uint64_t mem_size = (u64)mem->num_pages << PAGE_SHIFT; + u64 mem_size = (u64)mem->num_pages << PAGE_SHIFT; struct amdgpu_res_cursor cursor; + u64 end; if (mem->mem_type == TTM_PL_SYSTEM || mem->mem_type == TTM_PL_TT) @@ -434,12 +435,18 @@ static bool amdgpu_mem_visible(struct amdgpu_device *adev, return false; amdgpu_res_first(mem, 0, mem_size, &cursor); + end = cursor.start + cursor.size; + while (cursor.remaining) { + amdgpu_res_next(&cursor, cursor.size); - /* ttm_resource_ioremap only supports contiguous memory */ - if (cursor.size != mem_size) - return false; + /* ttm_resource_ioremap only supports contiguous memory */ + if (end != cursor.start) + return false; + + end = cursor.start + cursor.size; + } - return cursor.start + cursor.size <= adev->gmc.visible_vram_size; + return end <= adev->gmc.visible_vram_size; } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 939c8614f0e3..dd0bc649a57d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -164,70 +164,138 @@ void amdgpu_ucode_print_rlc_hdr(const struct common_firmware_header *hdr) } else if (version_major == 2) { const struct rlc_firmware_header_v2_0 *rlc_hdr = container_of(hdr, struct rlc_firmware_header_v2_0, header); + const struct rlc_firmware_header_v2_1 *rlc_hdr_v2_1 = + container_of(rlc_hdr, struct rlc_firmware_header_v2_1, v2_0); + const struct rlc_firmware_header_v2_2 *rlc_hdr_v2_2 = + container_of(rlc_hdr_v2_1, struct rlc_firmware_header_v2_2, v2_1); + const struct rlc_firmware_header_v2_3 *rlc_hdr_v2_3 = + container_of(rlc_hdr_v2_2, struct rlc_firmware_header_v2_3, v2_2); + const struct rlc_firmware_header_v2_4 *rlc_hdr_v2_4 = + container_of(rlc_hdr_v2_3, struct rlc_firmware_header_v2_4, v2_3); - DRM_DEBUG("ucode_feature_version: %u\n", - le32_to_cpu(rlc_hdr->ucode_feature_version)); - DRM_DEBUG("jt_offset: %u\n", le32_to_cpu(rlc_hdr->jt_offset)); - DRM_DEBUG("jt_size: %u\n", le32_to_cpu(rlc_hdr->jt_size)); - DRM_DEBUG("save_and_restore_offset: %u\n", - le32_to_cpu(rlc_hdr->save_and_restore_offset)); - DRM_DEBUG("clear_state_descriptor_offset: %u\n", - le32_to_cpu(rlc_hdr->clear_state_descriptor_offset)); - DRM_DEBUG("avail_scratch_ram_locations: %u\n", - le32_to_cpu(rlc_hdr->avail_scratch_ram_locations)); - DRM_DEBUG("reg_restore_list_size: %u\n", - le32_to_cpu(rlc_hdr->reg_restore_list_size)); - DRM_DEBUG("reg_list_format_start: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_start)); - DRM_DEBUG("reg_list_format_separate_start: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_separate_start)); - DRM_DEBUG("starting_offsets_start: %u\n", - le32_to_cpu(rlc_hdr->starting_offsets_start)); - DRM_DEBUG("reg_list_format_size_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_size_bytes)); - DRM_DEBUG("reg_list_format_array_offset_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); - DRM_DEBUG("reg_list_size_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_size_bytes)); - DRM_DEBUG("reg_list_array_offset_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); - DRM_DEBUG("reg_list_format_separate_size_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_separate_size_bytes)); - DRM_DEBUG("reg_list_format_separate_array_offset_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_format_separate_array_offset_bytes)); - DRM_DEBUG("reg_list_separate_size_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_separate_size_bytes)); - DRM_DEBUG("reg_list_separate_array_offset_bytes: %u\n", - le32_to_cpu(rlc_hdr->reg_list_separate_array_offset_bytes)); - if (version_minor == 1) { - const struct rlc_firmware_header_v2_1 *v2_1 = - container_of(rlc_hdr, struct rlc_firmware_header_v2_1, v2_0); + switch (version_minor) { + case 0: + /* rlc_hdr v2_0 */ + DRM_DEBUG("ucode_feature_version: %u\n", + le32_to_cpu(rlc_hdr->ucode_feature_version)); + DRM_DEBUG("jt_offset: %u\n", le32_to_cpu(rlc_hdr->jt_offset)); + DRM_DEBUG("jt_size: %u\n", le32_to_cpu(rlc_hdr->jt_size)); + DRM_DEBUG("save_and_restore_offset: %u\n", + le32_to_cpu(rlc_hdr->save_and_restore_offset)); + DRM_DEBUG("clear_state_descriptor_offset: %u\n", + le32_to_cpu(rlc_hdr->clear_state_descriptor_offset)); + DRM_DEBUG("avail_scratch_ram_locations: %u\n", + le32_to_cpu(rlc_hdr->avail_scratch_ram_locations)); + DRM_DEBUG("reg_restore_list_size: %u\n", + le32_to_cpu(rlc_hdr->reg_restore_list_size)); + DRM_DEBUG("reg_list_format_start: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_start)); + DRM_DEBUG("reg_list_format_separate_start: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_separate_start)); + DRM_DEBUG("starting_offsets_start: %u\n", + le32_to_cpu(rlc_hdr->starting_offsets_start)); + DRM_DEBUG("reg_list_format_size_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_size_bytes)); + DRM_DEBUG("reg_list_format_array_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); + DRM_DEBUG("reg_list_size_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_size_bytes)); + DRM_DEBUG("reg_list_array_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); + DRM_DEBUG("reg_list_format_separate_size_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_separate_size_bytes)); + DRM_DEBUG("reg_list_format_separate_array_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_format_separate_array_offset_bytes)); + DRM_DEBUG("reg_list_separate_size_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_separate_size_bytes)); + DRM_DEBUG("reg_list_separate_array_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr->reg_list_separate_array_offset_bytes)); + break; + case 1: + /* rlc_hdr v2_1 */ DRM_DEBUG("reg_list_format_direct_reg_list_length: %u\n", - le32_to_cpu(v2_1->reg_list_format_direct_reg_list_length)); + le32_to_cpu(rlc_hdr_v2_1->reg_list_format_direct_reg_list_length)); DRM_DEBUG("save_restore_list_cntl_ucode_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_cntl_ucode_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_cntl_ucode_ver)); DRM_DEBUG("save_restore_list_cntl_feature_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_cntl_feature_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_cntl_feature_ver)); DRM_DEBUG("save_restore_list_cntl_size_bytes %u\n", - le32_to_cpu(v2_1->save_restore_list_cntl_size_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_cntl_size_bytes)); DRM_DEBUG("save_restore_list_cntl_offset_bytes: %u\n", - le32_to_cpu(v2_1->save_restore_list_cntl_offset_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_cntl_offset_bytes)); DRM_DEBUG("save_restore_list_gpm_ucode_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_gpm_ucode_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_gpm_ucode_ver)); DRM_DEBUG("save_restore_list_gpm_feature_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_gpm_feature_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_gpm_feature_ver)); DRM_DEBUG("save_restore_list_gpm_size_bytes %u\n", - le32_to_cpu(v2_1->save_restore_list_gpm_size_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_gpm_size_bytes)); DRM_DEBUG("save_restore_list_gpm_offset_bytes: %u\n", - le32_to_cpu(v2_1->save_restore_list_gpm_offset_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_gpm_offset_bytes)); DRM_DEBUG("save_restore_list_srm_ucode_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_srm_ucode_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_srm_ucode_ver)); DRM_DEBUG("save_restore_list_srm_feature_ver: %u\n", - le32_to_cpu(v2_1->save_restore_list_srm_feature_ver)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_srm_feature_ver)); DRM_DEBUG("save_restore_list_srm_size_bytes %u\n", - le32_to_cpu(v2_1->save_restore_list_srm_size_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_srm_size_bytes)); DRM_DEBUG("save_restore_list_srm_offset_bytes: %u\n", - le32_to_cpu(v2_1->save_restore_list_srm_offset_bytes)); + le32_to_cpu(rlc_hdr_v2_1->save_restore_list_srm_offset_bytes)); + break; + case 2: + /* rlc_hdr v2_2 */ + DRM_DEBUG("rlc_iram_ucode_size_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_2->rlc_iram_ucode_size_bytes)); + DRM_DEBUG("rlc_iram_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_2->rlc_iram_ucode_offset_bytes)); + DRM_DEBUG("rlc_dram_ucode_size_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_2->rlc_dram_ucode_size_bytes)); + DRM_DEBUG("rlc_dram_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_2->rlc_dram_ucode_offset_bytes)); + break; + case 3: + /* rlc_hdr v2_3 */ + DRM_DEBUG("rlcp_ucode_version: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcp_ucode_version)); + DRM_DEBUG("rlcp_ucode_feature_version: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcp_ucode_feature_version)); + DRM_DEBUG("rlcp_ucode_size_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcp_ucode_size_bytes)); + DRM_DEBUG("rlcp_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcp_ucode_offset_bytes)); + DRM_DEBUG("rlcv_ucode_version: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcv_ucode_version)); + DRM_DEBUG("rlcv_ucode_feature_version: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcv_ucode_feature_version)); + DRM_DEBUG("rlcv_ucode_size_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcv_ucode_size_bytes)); + DRM_DEBUG("rlcv_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_3->rlcv_ucode_offset_bytes)); + break; + case 4: + /* rlc_hdr v2_4 */ + DRM_DEBUG("global_tap_delays_ucode_size_bytes :%u\n", + le32_to_cpu(rlc_hdr_v2_4->global_tap_delays_ucode_size_bytes)); + DRM_DEBUG("global_tap_delays_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_4->global_tap_delays_ucode_offset_bytes)); + DRM_DEBUG("se0_tap_delays_ucode_size_bytes :%u\n", + le32_to_cpu(rlc_hdr_v2_4->se0_tap_delays_ucode_size_bytes)); + DRM_DEBUG("se0_tap_delays_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_4->se0_tap_delays_ucode_offset_bytes)); + DRM_DEBUG("se1_tap_delays_ucode_size_bytes :%u\n", + le32_to_cpu(rlc_hdr_v2_4->se1_tap_delays_ucode_size_bytes)); + DRM_DEBUG("se1_tap_delays_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_4->se1_tap_delays_ucode_offset_bytes)); + DRM_DEBUG("se2_tap_delays_ucode_size_bytes :%u\n", + le32_to_cpu(rlc_hdr_v2_4->se2_tap_delays_ucode_size_bytes)); + DRM_DEBUG("se2_tap_delays_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_4->se2_tap_delays_ucode_offset_bytes)); + DRM_DEBUG("se3_tap_delays_ucode_size_bytes :%u\n", + le32_to_cpu(rlc_hdr_v2_4->se3_tap_delays_ucode_size_bytes)); + DRM_DEBUG("se3_tap_delays_ucode_offset_bytes: %u\n", + le32_to_cpu(rlc_hdr_v2_4->se3_tap_delays_ucode_offset_bytes)); + break; + default: + DRM_ERROR("Unknown RLC v2 ucode: v2.%u\n", version_minor); + break; } } else { DRM_ERROR("Unknown RLC ucode version: %u.%u\n", version_major, version_minor); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 96b6cf4c4d54..1c36235b4539 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -124,6 +124,7 @@ enum psp_fw_type { PSP_FW_TYPE_PSP_SOC_DRV, PSP_FW_TYPE_PSP_INTF_DRV, PSP_FW_TYPE_PSP_DBG_DRV, + PSP_FW_TYPE_PSP_RAS_DRV, }; /* version_major=2, version_minor=0 */ @@ -260,8 +261,12 @@ 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; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index 3629d8f292ef..e46439274f3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -51,6 +51,9 @@ struct amdgpu_umc_ras { struct amdgpu_ras_block_object ras_block; void (*err_cnt_init)(struct amdgpu_device *adev); bool (*query_ras_poison_mode)(struct amdgpu_device *adev); + void (*convert_ras_error_address)(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst); void (*ecc_info_query_ras_error_count)(struct amdgpu_device *adev, void *ras_error_status); void (*ecc_info_query_ras_error_address)(struct amdgpu_device *adev, 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_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 80b7a6cfd026..253ea6b159df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -161,7 +161,8 @@ #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) #define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) -#define AMDGPU_VCN_VF_RB_SETUP_FLAG (1 << 12) +#define AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG (1 << 11) +#define AMDGPU_VCN_VF_RB_SETUP_FLAG (1 << 14) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -171,6 +172,9 @@ #define VCN_CODEC_DISABLE_MASK_HEVC (1 << 2) #define VCN_CODEC_DISABLE_MASK_H264 (1 << 3) +#define AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU (0) +#define AMDGPU_VCN_SMU_DPM_INTERFACE_APU (1) + enum fw_queue_mode { FW_QUEUE_RING_RESET = 1, FW_QUEUE_DPG_HOLD_OFF = 2, @@ -335,7 +339,9 @@ struct amdgpu_vcn4_fw_shared { struct amdgpu_fw_shared_unified_queue_struct sq; uint8_t pad1[8]; struct amdgpu_fw_shared_fw_logging fw_log; + uint8_t pad2[20]; struct amdgpu_fw_shared_rb_setup rb_setup; + struct amdgpu_fw_shared_smu_interface_info smu_dpm_interface; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 59cac347baa3..83b0c5d86e48 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -183,10 +183,12 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) struct amdgpu_bo *bo = vm_bo->bo; vm_bo->moved = true; + spin_lock(&vm_bo->vm->status_lock); if (bo->tbo.type == ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm->evicted); else list_move_tail(&vm_bo->vm_status, &vm->evicted); + spin_unlock(&vm_bo->vm->status_lock); } /** * amdgpu_vm_bo_moved - vm_bo is moved @@ -198,7 +200,9 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) { + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->moved); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -211,7 +215,9 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) { + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->idle); + spin_unlock(&vm_bo->vm->status_lock); vm_bo->moved = false; } @@ -225,9 +231,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->invalidated_lock); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated); - spin_unlock(&vm_bo->vm->invalidated_lock); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -240,10 +246,13 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) { - if (vm_bo->bo->parent) + if (vm_bo->bo->parent) { + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->relocated); - else + spin_unlock(&vm_bo->vm->status_lock); + } else { amdgpu_vm_bo_idle(vm_bo); + } } /** @@ -256,9 +265,9 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->invalidated_lock); + spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->done); - spin_unlock(&vm_bo->vm->invalidated_lock); + spin_unlock(&vm_bo->vm->status_lock); } /** @@ -363,12 +372,20 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, int (*validate)(void *p, struct amdgpu_bo *bo), void *param) { - struct amdgpu_vm_bo_base *bo_base, *tmp; + struct amdgpu_vm_bo_base *bo_base; + struct amdgpu_bo *shadow; + struct amdgpu_bo *bo; int r; - list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) { - struct amdgpu_bo *bo = bo_base->bo; - struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo); + spin_lock(&vm->status_lock); + while (!list_empty(&vm->evicted)) { + bo_base = list_first_entry(&vm->evicted, + struct amdgpu_vm_bo_base, + vm_status); + spin_unlock(&vm->status_lock); + + bo = bo_base->bo; + shadow = amdgpu_bo_shadowed(bo); r = validate(param, bo); if (r) @@ -385,7 +402,9 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, vm->update_funcs->map_table(to_amdgpu_bo_vm(bo)); amdgpu_vm_bo_relocated(bo_base); } + spin_lock(&vm->status_lock); } + spin_unlock(&vm->status_lock); amdgpu_vm_eviction_lock(vm); vm->evicting = false; @@ -406,13 +425,18 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, */ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { + bool empty; bool ret; amdgpu_vm_eviction_lock(vm); ret = !vm->evicting; amdgpu_vm_eviction_unlock(vm); - return ret && list_empty(&vm->evicted); + spin_lock(&vm->status_lock); + empty = list_empty(&vm->evicted); + spin_unlock(&vm->status_lock); + + return ret && empty; } /** @@ -680,9 +704,14 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, struct amdgpu_vm_update_params params; struct amdgpu_vm_bo_base *entry; bool flush_tlb_needed = false; + LIST_HEAD(relocated); int r, idx; - if (list_empty(&vm->relocated)) + spin_lock(&vm->status_lock); + list_splice_init(&vm->relocated, &relocated); + spin_unlock(&vm->status_lock); + + if (list_empty(&relocated)) return 0; if (!drm_dev_enter(adev_to_drm(adev), &idx)) @@ -697,7 +726,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, if (r) goto error; - list_for_each_entry(entry, &vm->relocated, vm_status) { + list_for_each_entry(entry, &relocated, vm_status) { /* vm_flush_needed after updating moved PDEs */ flush_tlb_needed |= entry->moved; @@ -713,9 +742,8 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, if (flush_tlb_needed) atomic64_inc(&vm->tlb_seq); - while (!list_empty(&vm->relocated)) { - entry = list_first_entry(&vm->relocated, - struct amdgpu_vm_bo_base, + while (!list_empty(&relocated)) { + entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base, vm_status); amdgpu_vm_bo_idle(entry); } @@ -912,6 +940,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, { struct amdgpu_bo_va *bo_va, *tmp; + spin_lock(&vm->status_lock); list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) { if (!bo_va->base.bo) continue; @@ -936,7 +965,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, amdgpu_bo_get_memory(bo_va->base.bo, vram_mem, gtt_mem, cpu_mem); } - spin_lock(&vm->invalidated_lock); list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) { if (!bo_va->base.bo) continue; @@ -949,7 +977,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, amdgpu_bo_get_memory(bo_va->base.bo, vram_mem, gtt_mem, cpu_mem); } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); } /** * amdgpu_vm_bo_update - update all BO mappings in the vm page table @@ -1278,24 +1306,29 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, int amdgpu_vm_handle_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm) { - struct amdgpu_bo_va *bo_va, *tmp; + struct amdgpu_bo_va *bo_va; struct dma_resv *resv; bool clear; int r; - list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { + spin_lock(&vm->status_lock); + while (!list_empty(&vm->moved)) { + bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va, + base.vm_status); + spin_unlock(&vm->status_lock); + /* Per VM BOs never need to bo cleared in the page tables */ r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; + spin_lock(&vm->status_lock); } - spin_lock(&vm->invalidated_lock); while (!list_empty(&vm->invalidated)) { bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va, base.vm_status); resv = bo_va->base.bo->tbo.base.resv; - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); /* Try to reserve the BO to avoid clearing its ptes */ if (!amdgpu_vm_debug && dma_resv_trylock(resv)) @@ -1310,9 +1343,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, if (!clear) dma_resv_unlock(resv); - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); return 0; } @@ -1387,7 +1420,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv && !bo_va->base.moved) { - list_move(&bo_va->base.vm_status, &vm->moved); + amdgpu_vm_bo_moved(&bo_va->base); } trace_amdgpu_vm_bo_map(bo_va, mapping); } @@ -1763,9 +1796,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, } } - spin_lock(&vm->invalidated_lock); + spin_lock(&vm->status_lock); list_del(&bo_va->base.vm_status); - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); list_for_each_entry_safe(mapping, next, &bo_va->valids, list) { list_del(&mapping->list); @@ -2019,9 +2052,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) INIT_LIST_HEAD(&vm->moved); INIT_LIST_HEAD(&vm->idle); INIT_LIST_HEAD(&vm->invalidated); - spin_lock_init(&vm->invalidated_lock); + spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->freed); INIT_LIST_HEAD(&vm->done); + INIT_LIST_HEAD(&vm->pt_freed); + INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work); /* create scheduler entities for page table updates */ r = drm_sched_entity_init(&vm->immediate, DRM_SCHED_PRIORITY_NORMAL, @@ -2223,6 +2258,8 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm); + flush_work(&vm->pt_free_work); + root = amdgpu_bo_ref(vm->root.bo); amdgpu_bo_reserve(root, true); amdgpu_vm_set_pasid(adev, vm, 0); @@ -2484,8 +2521,7 @@ 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 */ @@ -2548,6 +2584,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) unsigned int total_done_objs = 0; unsigned int id = 0; + spin_lock(&vm->status_lock); seq_puts(m, "\tIdle BOs:\n"); list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) { if (!bo_va->base.bo) @@ -2585,7 +2622,6 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) id = 0; seq_puts(m, "\tInvalidated BOs:\n"); - spin_lock(&vm->invalidated_lock); list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) { if (!bo_va->base.bo) continue; @@ -2600,7 +2636,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) continue; total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m); } - spin_unlock(&vm->invalidated_lock); + spin_unlock(&vm->status_lock); total_done_objs = id; seq_printf(m, "\tTotal idle size: %12lld\tobjs:\t%d\n", total_idle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 9ecb7f663e19..83acb7bd80fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -254,6 +254,9 @@ struct amdgpu_vm { bool evicting; unsigned int saved_flags; + /* Lock to protect vm_bo add/del/move on all lists of vm */ + spinlock_t status_lock; + /* BOs who needs a validation */ struct list_head evicted; @@ -268,7 +271,6 @@ struct amdgpu_vm { /* regular invalidated BOs, but not yet updated in the PT */ struct list_head invalidated; - spinlock_t invalidated_lock; /* BO mappings freed, but not yet updated in the PT */ struct list_head freed; @@ -276,6 +278,10 @@ struct amdgpu_vm { /* BOs which are invalidated, has been updated in the PTs */ struct list_head done; + /* PT BOs scheduled to free and fill with zero if vm_resv is not hold */ + struct list_head pt_freed; + struct work_struct pt_free_work; + /* contains the page directory */ struct amdgpu_vm_bo_base root; struct dma_fence *last_update; @@ -471,6 +477,7 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params, int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, uint64_t start, uint64_t end, uint64_t dst, uint64_t flags); +void amdgpu_vm_pt_free_work(struct work_struct *work); #if defined(CONFIG_DEBUG_FS) void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 88de9f0d4728..358b91243e37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -637,10 +637,34 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); entry->bo->vm_bo = NULL; + + spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); + spin_unlock(&entry->vm->status_lock); amdgpu_bo_unref(&entry->bo); } +void amdgpu_vm_pt_free_work(struct work_struct *work) +{ + struct amdgpu_vm_bo_base *entry, *next; + struct amdgpu_vm *vm; + LIST_HEAD(pt_freed); + + vm = container_of(work, struct amdgpu_vm, pt_free_work); + + spin_lock(&vm->status_lock); + list_splice_init(&vm->pt_freed, &pt_freed); + spin_unlock(&vm->status_lock); + + /* flush_work in amdgpu_vm_fini ensure vm->root.bo is valid. */ + amdgpu_bo_reserve(vm->root.bo, true); + + list_for_each_entry_safe(entry, next, &pt_freed, vm_status) + amdgpu_vm_pt_free(entry); + + amdgpu_bo_unreserve(vm->root.bo); +} + /** * amdgpu_vm_pt_free_dfs - free PD/PT levels * @@ -652,11 +676,24 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) */ static void amdgpu_vm_pt_free_dfs(struct amdgpu_device *adev, struct amdgpu_vm *vm, - struct amdgpu_vm_pt_cursor *start) + struct amdgpu_vm_pt_cursor *start, + bool unlocked) { struct amdgpu_vm_pt_cursor cursor; struct amdgpu_vm_bo_base *entry; + if (unlocked) { + spin_lock(&vm->status_lock); + for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry) + list_move(&entry->vm_status, &vm->pt_freed); + + if (start) + list_move(&start->entry->vm_status, &vm->pt_freed); + spin_unlock(&vm->status_lock); + schedule_work(&vm->pt_free_work); + return; + } + for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry) amdgpu_vm_pt_free(entry); @@ -673,7 +710,7 @@ static void amdgpu_vm_pt_free_dfs(struct amdgpu_device *adev, */ void amdgpu_vm_pt_free_root(struct amdgpu_device *adev, struct amdgpu_vm *vm) { - amdgpu_vm_pt_free_dfs(adev, vm, NULL); + amdgpu_vm_pt_free_dfs(adev, vm, NULL, false); } /** @@ -966,7 +1003,8 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, if (cursor.entry->bo) { params->table_freed = true; amdgpu_vm_pt_free_dfs(adev, params->vm, - &cursor); + &cursor, + params->unlocked); } amdgpu_vm_pt_next(adev, &cursor); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 1fd3cbca20a2..2b0669c464f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -112,7 +112,8 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, swap(p->vm->last_unlocked, tmp); dma_fence_put(tmp); } else { - amdgpu_bo_fence(p->vm->root.bo, f, true); + dma_resv_add_fence(p->vm->root.bo->tbo.base.resv, f, + DMA_RESV_USAGE_BOOKKEEP); } if (fence && !p->immediate) @@ -211,12 +212,15 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, int r; /* Wait for PD/PT moves to be completed */ - dma_resv_for_each_fence(&cursor, bo->tbo.base.resv, - DMA_RESV_USAGE_KERNEL, fence) { + dma_resv_iter_begin(&cursor, bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL); + dma_resv_for_each_fence_unlocked(&cursor, fence) { r = amdgpu_sync_fence(&p->job->sync, fence); - if (r) + if (r) { + dma_resv_iter_end(&cursor); return r; + } } + dma_resv_iter_end(&cursor); do { ndw = p->num_dw_left; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index d3b483aa81f8..47159e9a0884 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -392,12 +392,20 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev) } /** + * Only init hive->reset_domain for none SRIOV configuration. For SRIOV, + * Host driver decide how to reset the GPU either through FLR or chain reset. + * Guest side will get individual notifications from the host for the FLR + * if necessary. + */ + if (!amdgpu_sriov_vf(adev)) { + /** * Avoid recreating reset domain when hive is reconstructed for the case - * of reset the devices in the XGMI hive during probe for SRIOV + * of reset the devices in the XGMI hive during probe for passthrough GPU * See https://www.spinics.net/lists/amd-gfx/msg58836.html */ - if (adev->reset_domain->type != XGMI_HIVE) { - hive->reset_domain = amdgpu_reset_create_reset_domain(XGMI_HIVE, "amdgpu-reset-hive"); + if (adev->reset_domain->type != XGMI_HIVE) { + hive->reset_domain = + amdgpu_reset_create_reset_domain(XGMI_HIVE, "amdgpu-reset-hive"); if (!hive->reset_domain) { dev_err(adev->dev, "XGMI: failed initializing reset domain for xgmi hive\n"); ret = -ENOMEM; @@ -406,9 +414,10 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev) hive = NULL; goto pro_end; } - } else { - amdgpu_reset_get_reset_domain(adev->reset_domain); - hive->reset_domain = adev->reset_domain; + } else { + amdgpu_reset_get_reset_domain(adev->reset_domain); + hive->reset_domain = adev->reset_domain; + } } hive->hive_id = adev->gmc.xgmi.hive_id; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index 552e6fb55aa8..30dcc1681b4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -43,6 +43,7 @@ struct amdgpu_hive_info { } pstate; struct amdgpu_reset_domain *reset_domain; + uint32_t device_remove_count; }; struct amdgpu_pcs_ras_field { diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 5647f13b98d4..cbca9866645c 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -309,14 +309,10 @@ static void cik_sdma_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq */ static void cik_sdma_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index e4dde41f2f68..af94ac580d3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3943,56 +3943,6 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev) DRM_WARN_ONCE("CP firmware version too old, please update!"); } - -static void gfx_v10_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_v10_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_v10_0_init_tap_delays_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_4 *rlc_hdr; - - 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); -} - static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev) { bool ret = false; @@ -4028,12 +3978,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) char fw_name[40]; char *wks = ""; int err; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; - const struct gfx_firmware_header_v1_0 *cp_hdr; 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; @@ -4091,9 +4036,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.pfp_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; - adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); @@ -4102,9 +4045,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.me_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; - adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); @@ -4113,69 +4054,27 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.ce_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; - adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE); if (!amdgpu_sriov_vf(adev)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); if (err) goto out; + /* don't check this. There are apparently firmwares in the wild with + * incorrect size in the header + */ err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + if (err) + dev_dbg(adev->dev, + "gfx10: amdgpu_ucode_validate() failed \"%s\"\n", + fw_name); 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_v10_0_init_rlc_ext_microcode(adev); - if (version_minor >= 2) - gfx_v10_0_init_rlc_iram_dram_microcode(adev); - if (version_minor == 4) { - gfx_v10_0_init_tap_delays_microcode(adev); - } - } } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks); @@ -4185,9 +4084,8 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.mec_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; - adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); @@ -4195,164 +4093,18 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.mec2_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *) - adev->gfx.mec2_fw->data; - adev->gfx.mec2_fw_version = - le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.mec2_feature_version = - le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); } else { err = 0; adev->gfx.mec2_fw = NULL; } - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_PFP]; - info->ucode_id = AMDGPU_UCODE_ID_CP_PFP; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_ME]; - info->ucode_id = AMDGPU_UCODE_ID_CP_ME; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_CE]; - info->ucode_id = AMDGPU_UCODE_ID_CP_CE; - info->fw = adev->gfx.ce_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), 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_cntl_size_bytes && - 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_CNTL]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_cntl_size_bytes, PAGE_SIZE); - - 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.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); - } - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes) - - le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1_JT]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1_JT; - info->fw = adev->gfx.mec_fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - if (adev->gfx.mec2_fw) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - info->fw = adev->gfx.mec2_fw; - header = (const struct common_firmware_header *)info->fw->data; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes) - - le32_to_cpu(cp_hdr->jt_size) * 4, - PAGE_SIZE); - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2_JT]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2_JT; - info->fw = adev->gfx.mec2_fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, - PAGE_SIZE); - } - } - gfx_v10_0_check_fw_write_wait(adev); out: if (err) { dev_err(adev->dev, - "gfx10: Failed to load firmware \"%s\"\n", + "gfx10: Failed to init firmware \"%s\"\n", fw_name); release_firmware(adev->gfx.pfp_fw); adev->gfx.pfp_fw = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index fa718318568e..251109723ab6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -438,61 +438,12 @@ 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]; char ucode_prefix[30]; int err; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; - 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; @@ -513,14 +464,11 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) adev->gfx.pfp_fw->data, 2, 0); if (adev->gfx.rs64_enable) { dev_info(adev->dev, "CP RS64 enable\n"); - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.pfp_fw->data; - adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr_v2_0->header.ucode_version); - adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); - + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_PFP); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_PFP_P0_STACK); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_PFP_P1_STACK); } else { - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; - adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP); } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", ucode_prefix); @@ -531,14 +479,11 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) if (err) goto out; if (adev->gfx.rs64_enable) { - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.me_fw->data; - adev->gfx.me_fw_version = le32_to_cpu(cp_hdr_v2_0->header.ucode_version); - adev->gfx.me_feature_version = le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); - + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_ME); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_ME_P0_STACK); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_ME_P1_STACK); } else { - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; - adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME); } if (!amdgpu_sriov_vf(adev)) { @@ -547,58 +492,14 @@ 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); @@ -609,190 +510,23 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) if (err) goto out; if (adev->gfx.rs64_enable) { - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.mec_fw->data; - adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr_v2_0->header.ucode_version); - adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr_v2_0->ucode_feature_version); - + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_MEC); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_MEC_P0_STACK); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_MEC_P1_STACK); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_MEC_P2_STACK); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_RS64_MEC_P3_STACK); } else { - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; - adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT); } /* only one MEC for gfx 11.0.0. */ adev->gfx.mec2_fw = NULL; - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - if (adev->gfx.rs64_enable) { - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.pfp_fw->data; - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_PFP]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_PFP; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_PFP_P0_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_PFP_P0_STACK; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_PFP_P1_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_PFP_P1_STACK; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.me_fw->data; - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_ME]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_ME; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_ME_P0_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_ME_P0_STACK; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_ME_P1_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_ME_P1_STACK; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - cp_hdr_v2_0 = (const struct gfx_firmware_header_v2_0 *)adev->gfx.mec_fw->data; - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_MEC]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_MEC; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_MEC_P0_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_MEC_P0_STACK; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_MEC_P1_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_MEC_P1_STACK; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_MEC_P2_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_MEC_P2_STACK; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_RS64_MEC_P3_STACK]; - info->ucode_id = AMDGPU_UCODE_ID_CP_RS64_MEC_P3_STACK; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr_v2_0->data_size_bytes), PAGE_SIZE); - } else { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_PFP]; - info->ucode_id = AMDGPU_UCODE_ID_CP_PFP; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_ME]; - info->ucode_id = AMDGPU_UCODE_ID_CP_ME; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes) - - le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1_JT]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1_JT; - info->fw = adev->gfx.mec_fw; - 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: if (err) { dev_err(adev->dev, - "gfx11: Failed to load firmware \"%s\"\n", + "gfx11: Failed to init firmware \"%s\"\n", fw_name); release_firmware(adev->gfx.pfp_fw); adev->gfx.pfp_fw = NULL; @@ -5240,6 +4974,8 @@ 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); @@ -5253,6 +4989,8 @@ 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 1d6d3a852a0b..0320be4a5fc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1091,27 +1091,6 @@ static void gfx_v9_0_free_microcode(struct amdgpu_device *adev) kfree(adev->gfx.rlc.register_list_format); } -static void gfx_v9_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_v9_0_check_fw_write_wait(struct amdgpu_device *adev) { adev->gfx.me_fw_write_wait = false; @@ -1273,9 +1252,6 @@ static int gfx_v9_0_init_cp_gfx_microcode(struct amdgpu_device *adev, { char fw_name[30]; int err; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; - const struct gfx_firmware_header_v1_0 *cp_hdr; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); @@ -1284,9 +1260,7 @@ static int gfx_v9_0_init_cp_gfx_microcode(struct amdgpu_device *adev, err = amdgpu_ucode_validate(adev->gfx.pfp_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; - adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); @@ -1295,9 +1269,7 @@ static int gfx_v9_0_init_cp_gfx_microcode(struct amdgpu_device *adev, err = amdgpu_ucode_validate(adev->gfx.me_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; - adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); @@ -1306,37 +1278,12 @@ static int gfx_v9_0_init_cp_gfx_microcode(struct amdgpu_device *adev, err = amdgpu_ucode_validate(adev->gfx.ce_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; - adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_PFP]; - info->ucode_id = AMDGPU_UCODE_ID_CP_PFP; - info->fw = adev->gfx.pfp_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_ME]; - info->ucode_id = AMDGPU_UCODE_ID_CP_ME; - info->fw = adev->gfx.me_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_CE]; - info->ucode_id = AMDGPU_UCODE_ID_CP_CE; - info->fw = adev->gfx.ce_fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - } + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE); out: if (err) { dev_err(adev->dev, - "gfx9: Failed to load firmware \"%s\"\n", + "gfx9: Failed to init firmware \"%s\"\n", fw_name); release_firmware(adev->gfx.pfp_fw); adev->gfx.pfp_fw = NULL; @@ -1353,11 +1300,7 @@ static int gfx_v9_0_init_rlc_microcode(struct amdgpu_device *adev, { char fw_name[30]; int err; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; 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; uint32_t smu_version; @@ -1386,92 +1329,17 @@ static int gfx_v9_0_init_rlc_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); - if (version_major == 2 && version_minor == 1) - adev->gfx.rlc.is_rlc_v2_1 = true; - - 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; - goto out; - } - - tmp = (unsigned int *)((uintptr_t)rlc_hdr + - le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); - for (i = 0 ; i < (adev->gfx.rlc.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 < (adev->gfx.rlc.reg_list_size_bytes >> 2); i++) - adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); - - if (adev->gfx.rlc.is_rlc_v2_1) - gfx_v9_0_init_rlc_ext_microcode(adev); - - 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; - 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.is_rlc_v2_1 && - adev->gfx.rlc.save_restore_list_cntl_size_bytes && - 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_CNTL]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_cntl_size_bytes, PAGE_SIZE); - - 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); - } - } - + err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor); out: if (err) { dev_err(adev->dev, - "gfx9: Failed to load firmware \"%s\"\n", + "gfx9: Failed to init firmware \"%s\"\n", fw_name); release_firmware(adev->gfx.rlc_fw); adev->gfx.rlc_fw = NULL; @@ -1494,9 +1362,6 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, { char fw_name[30]; int err; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; - const struct gfx_firmware_header_v1_0 *cp_hdr; if (amdgpu_sriov_vf(adev) && (adev->asic_type == CHIP_ALDEBARAN)) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sjt_mec.bin", chip_name); @@ -1509,10 +1374,8 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, err = amdgpu_ucode_validate(adev->gfx.mec_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; - adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT); if (gfx_v9_0_load_mec2_fw_bin_support(adev)) { if (amdgpu_sriov_vf(adev) && (adev->asic_type == CHIP_ALDEBARAN)) @@ -1525,12 +1388,8 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, err = amdgpu_ucode_validate(adev->gfx.mec2_fw); if (err) goto out; - cp_hdr = (const struct gfx_firmware_header_v1_0 *) - adev->gfx.mec2_fw->data; - adev->gfx.mec2_fw_version = - le32_to_cpu(cp_hdr->header.ucode_version); - adev->gfx.mec2_feature_version = - le32_to_cpu(cp_hdr->ucode_feature_version); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); } else { err = 0; adev->gfx.mec2_fw = NULL; @@ -1540,49 +1399,12 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version; } - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1; - info->fw = adev->gfx.mec_fw; - header = (const struct common_firmware_header *)info->fw->data; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes) - le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1_JT]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1_JT; - info->fw = adev->gfx.mec_fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - if (adev->gfx.mec2_fw) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - info->fw = adev->gfx.mec2_fw; - header = (const struct common_firmware_header *)info->fw->data; - cp_hdr = (const struct gfx_firmware_header_v1_0 *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes) - le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); - - /* TODO: Determine if MEC2 JT FW loading can be removed - for all GFX V9 asic and above */ - if (gfx_v9_0_load_mec2_fw_bin_support(adev)) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2_JT]; - info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2_JT; - info->fw = adev->gfx.mec2_fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, - PAGE_SIZE); - } - } - } - out: gfx_v9_0_check_if_need_gfxoff(adev); gfx_v9_0_check_fw_write_wait(adev); if (err) { dev_err(adev->dev, - "gfx9: Failed to load firmware \"%s\"\n", + "gfx9: Failed to init firmware \"%s\"\n", fw_name); release_firmware(adev->gfx.mec_fw); adev->gfx.mec_fw = NULL; @@ -5607,7 +5429,7 @@ 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/imu_v11_0_3.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0_3.c index 536dafb57ee0..fc69c1a29e23 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0_3.c @@ -22,6 +22,7 @@ */ #include "amdgpu.h" #include "amdgpu_imu.h" +#include "imu_v11_0_3.h" #include "gc/gc_11_0_3_offset.h" #include "gc/gc_11_0_3_sh_mask.h" diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index b64cd46a159a..5cec6b259b7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -187,6 +187,19 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, 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; + + if (!(((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 4) && + (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) && + (adev->ip_versions[GC_HWIP][0] <= IP_VERSION(11, 0, 3)))) + mes_add_queue_pkt.trap_en = 1; + + /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ + mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; + mes_add_queue_pkt.gds_size = input->queue_size; + return mes_v11_0_submit_pkt_and_poll_completion(mes, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); 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 f30bc826a878..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; @@ -336,4 +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/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 5b5b1ef0c2b1..21d822b1d589 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -224,6 +224,12 @@ static int psp_v13_0_bootloader_load_dbg_drv(struct psp_context *psp) return psp_v13_0_bootloader_load_component(psp, &psp->dbg_drv, PSP_BL__LOAD_DBGDRV); } +static int psp_v13_0_bootloader_load_ras_drv(struct psp_context *psp) +{ + return psp_v13_0_bootloader_load_component(psp, &psp->ras_drv, PSP_BL__LOAD_RASDRV); +} + + static int psp_v13_0_bootloader_load_sos(struct psp_context *psp) { int ret; @@ -720,6 +726,7 @@ static const struct psp_funcs psp_v13_0_funcs = { .bootloader_load_soc_drv = psp_v13_0_bootloader_load_soc_drv, .bootloader_load_intf_drv = psp_v13_0_bootloader_load_intf_drv, .bootloader_load_dbg_drv = psp_v13_0_bootloader_load_dbg_drv, + .bootloader_load_ras_drv = psp_v13_0_bootloader_load_ras_drv, .bootloader_load_sos = psp_v13_0_bootloader_load_sos, .ring_init = psp_v13_0_ring_init, .ring_create = psp_v13_0_ring_create, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 6bdffdc1c0b9..c52d246a1d96 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -342,14 +342,10 @@ static void sdma_v2_4_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 2584fa3cb13e..486d9b5c1b9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -516,14 +516,10 @@ static void sdma_v3_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 0cf9d3b486b2..298fa11702e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -561,44 +561,6 @@ static void sdma_v4_0_setup_ulv(struct amdgpu_device *adev) } } -static int sdma_v4_0_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst) -{ - int err = 0; - const struct sdma_firmware_header_v1_0 *hdr; - - err = amdgpu_ucode_validate(sdma_inst->fw); - if (err) - return err; - - hdr = (const struct sdma_firmware_header_v1_0 *)sdma_inst->fw->data; - sdma_inst->fw_version = le32_to_cpu(hdr->header.ucode_version); - sdma_inst->feature_version = le32_to_cpu(hdr->ucode_feature_version); - - if (sdma_inst->feature_version >= 20) - sdma_inst->burst_nop = true; - - return 0; -} - -static void sdma_v4_0_destroy_inst_ctx(struct amdgpu_device *adev) -{ - int i; - - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - - /* arcturus shares the same FW memory across - all SDMA isntances */ - if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) || - adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0)) - break; - } - - memset((void *)adev->sdma.instance, 0, - sizeof(struct amdgpu_sdma_instance) * AMDGPU_MAX_SDMA_INSTANCES); -} - /** * sdma_v4_0_init_microcode - load ucode images from disk * @@ -615,9 +577,7 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[30]; - int err = 0, i; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; + int ret, i; DRM_DEBUG("\n"); @@ -656,58 +616,25 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) BUG(); } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); - - err = request_firmware(&adev->sdma.instance[0].fw, fw_name, adev->dev); - if (err) - goto out; - - err = sdma_v4_0_init_inst_ctx(&adev->sdma.instance[0]); - if (err) - goto out; - - for (i = 1; i < adev->sdma.num_instances; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { + if (i == 0) + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); + else + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma%d.bin", chip_name, i); if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) || adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0)) { /* Acturus & Aldebaran will leverage the same FW memory for every SDMA instance */ - memcpy((void *)&adev->sdma.instance[i], - (void *)&adev->sdma.instance[0], - sizeof(struct amdgpu_sdma_instance)); - } - else { - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma%d.bin", chip_name, i); - - err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); - if (err) - goto out; - - err = sdma_v4_0_init_inst_ctx(&adev->sdma.instance[i]); - if (err) - goto out; - } - } - - DRM_DEBUG("psp_load == '%s'\n", - adev->firmware.load_type == AMDGPU_FW_LOAD_PSP ? "true" : "false"); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - for (i = 0; i < adev->sdma.num_instances; i++) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; - info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; - info->fw = adev->sdma.instance[i].fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); + ret = amdgpu_sdma_init_microcode(adev, fw_name, 0, true); + break; + } else { + ret = amdgpu_sdma_init_microcode(adev, fw_name, i, false); + if (ret) + return ret; } } -out: - if (err) { - DRM_ERROR("sdma_v4_0: Failed to load firmware \"%s\"\n", fw_name); - sdma_v4_0_destroy_inst_ctx(adev); - } - return err; + return ret; } /** @@ -988,18 +915,12 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 rb_cntl, ib_cntl; - int i, unset = 0; - - for (i = 0; i < adev->sdma.num_instances; i++) { - sdma[i] = &adev->sdma.instance[i].ring; + int i; - if ((adev->mman.buffer_funcs_ring == sdma[i]) && unset != 1) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = 1; - } + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl); @@ -1030,20 +951,12 @@ static void sdma_v4_0_rlc_stop(struct amdgpu_device *adev) */ static void sdma_v4_0_page_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 rb_cntl, ib_cntl; int i; - bool unset = false; - for (i = 0; i < adev->sdma.num_instances; i++) { - sdma[i] = &adev->sdma.instance[i].page; - - if ((adev->mman.buffer_funcs_ring == sdma[i]) && - (!unset)) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = true; - } + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_PAGE_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_PAGE_RB_CNTL, RB_ENABLE, 0); @@ -1504,6 +1417,11 @@ 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); @@ -1995,7 +1913,11 @@ static int sdma_v4_0_sw_fini(void *handle) amdgpu_ring_fini(&adev->sdma.instance[i].page); } - sdma_v4_0_destroy_inst_ctx(adev); + if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 0) || + adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0)) + amdgpu_sdma_destroy_inst_ctx(adev, true); + else + amdgpu_sdma_destroy_inst_ctx(adev, false); return 0; } @@ -2018,8 +1940,11 @@ static int sdma_v4_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } for (i = 0; i < adev->sdma.num_instances; i++) { amdgpu_irq_put(adev, &adev->sdma.ecc_irq, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index a019ac92edb7..d4d9f196db83 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -240,10 +240,7 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[40]; - int err = 0, i; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; - const struct sdma_firmware_header_v1_0 *hdr; + int ret, i; if (amdgpu_sriov_vf(adev) && (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(5, 0, 5))) return 0; @@ -272,38 +269,12 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); - if (err) - goto out; - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; - adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - if (adev->sdma.instance[i].feature_version >= 20) - adev->sdma.instance[i].burst_nop = true; - DRM_DEBUG("psp_load == '%s'\n", - adev->firmware.load_type == AMDGPU_FW_LOAD_PSP ? "true" : "false"); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; - info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; - info->fw = adev->sdma.instance[i].fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - } + ret = amdgpu_sdma_init_microcode(adev, fw_name, i, false); + if (ret) + return ret; } -out: - if (err) { - DRM_ERROR("sdma_v5_0: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } - } - return err; + + return ret; } static unsigned sdma_v5_0_ring_init_cond_exec(struct amdgpu_ring *ring) @@ -613,14 +584,10 @@ static void sdma_v5_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v5_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL)); @@ -1465,12 +1432,10 @@ static int sdma_v5_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - + for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); - } + + amdgpu_sdma_destroy_inst_ctx(adev, false); return 0; } @@ -1491,8 +1456,11 @@ static int sdma_v5_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } sdma_v5_0_ctx_switch_enable(adev, false); sdma_v5_0_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 95689ef4be10..809eca54fc61 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -89,33 +89,6 @@ static u32 sdma_v5_2_get_reg_offset(struct amdgpu_device *adev, u32 instance, u3 return base + internal_offset; } -static int sdma_v5_2_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst) -{ - int err = 0; - const struct sdma_firmware_header_v1_0 *hdr; - - err = amdgpu_ucode_validate(sdma_inst->fw); - if (err) - return err; - - hdr = (const struct sdma_firmware_header_v1_0 *)sdma_inst->fw->data; - sdma_inst->fw_version = le32_to_cpu(hdr->header.ucode_version); - sdma_inst->feature_version = le32_to_cpu(hdr->ucode_feature_version); - - if (sdma_inst->feature_version >= 20) - sdma_inst->burst_nop = true; - - return 0; -} - -static void sdma_v5_2_destroy_inst_ctx(struct amdgpu_device *adev) -{ - release_firmware(adev->sdma.instance[0].fw); - - memset((void *)adev->sdma.instance, 0, - sizeof(struct amdgpu_sdma_instance) * AMDGPU_MAX_SDMA_INSTANCES); -} - /** * sdma_v5_2_init_microcode - load ucode images from disk * @@ -132,9 +105,6 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[40]; - int err = 0, i; - struct amdgpu_firmware_info *info = NULL; - const struct common_firmware_header *header = NULL; DRM_DEBUG("\n"); @@ -169,42 +139,7 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", chip_name); - err = request_firmware(&adev->sdma.instance[0].fw, fw_name, adev->dev); - if (err) - goto out; - - err = sdma_v5_2_init_inst_ctx(&adev->sdma.instance[0]); - if (err) - goto out; - - for (i = 1; i < adev->sdma.num_instances; i++) - memcpy((void *)&adev->sdma.instance[i], - (void *)&adev->sdma.instance[0], - sizeof(struct amdgpu_sdma_instance)); - - if (amdgpu_sriov_vf(adev) && (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(5, 2, 0))) - return 0; - - DRM_DEBUG("psp_load == '%s'\n", - adev->firmware.load_type == AMDGPU_FW_LOAD_PSP ? "true" : "false"); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - for (i = 0; i < adev->sdma.num_instances; i++) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; - info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; - info->fw = adev->sdma.instance[i].fw; - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - } - } - -out: - if (err) { - DRM_ERROR("sdma_v5_2: Failed to load firmware \"%s\"\n", fw_name); - sdma_v5_2_destroy_inst_ctx(adev); - } - return err; + return amdgpu_sdma_init_microcode(adev, fw_name, 0, true); } static unsigned sdma_v5_2_ring_init_cond_exec(struct amdgpu_ring *ring) @@ -479,18 +414,10 @@ static void sdma_v5_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v5_2_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; - struct amdgpu_ring *sdma2 = &adev->sdma.instance[2].ring; - struct amdgpu_ring *sdma3 = &adev->sdma.instance[3].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1) || - (adev->mman.buffer_funcs_ring == sdma2) || - (adev->mman.buffer_funcs_ring == sdma3)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL)); @@ -1406,7 +1333,7 @@ static int sdma_v5_2_sw_fini(void *handle) for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); - sdma_v5_2_destroy_inst_ctx(adev); + amdgpu_sdma_destroy_inst_ctx(adev, true); return 0; } @@ -1422,8 +1349,11 @@ static int sdma_v5_2_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } sdma_v5_2_ctx_switch_enable(adev, false); sdma_v5_2_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 7ae572a08cb3..da3beb0bf2fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -78,33 +78,6 @@ static u32 sdma_v6_0_get_reg_offset(struct amdgpu_device *adev, u32 instance, u3 return base + internal_offset; } -static int sdma_v6_0_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst) -{ - int err = 0; - const struct sdma_firmware_header_v2_0 *hdr; - - err = amdgpu_ucode_validate(sdma_inst->fw); - if (err) - return err; - - hdr = (const struct sdma_firmware_header_v2_0 *)sdma_inst->fw->data; - sdma_inst->fw_version = le32_to_cpu(hdr->header.ucode_version); - sdma_inst->feature_version = le32_to_cpu(hdr->ucode_feature_version); - - if (sdma_inst->feature_version >= 20) - sdma_inst->burst_nop = true; - - return 0; -} - -static void sdma_v6_0_destroy_inst_ctx(struct amdgpu_device *adev) -{ - release_firmware(adev->sdma.instance[0].fw); - - memset((void*)adev->sdma.instance, 0, - sizeof(struct amdgpu_sdma_instance) * AMDGPU_MAX_SDMA_INSTANCES); -} - /** * sdma_v6_0_init_microcode - load ucode images from disk * @@ -114,16 +87,10 @@ static void sdma_v6_0_destroy_inst_ctx(struct amdgpu_device *adev) * the driver (not loaded into hw). * Returns 0 on success, error on failure. */ - -// emulation only, won't work on real chip -// sdma 6.0.0 real chip need to use PSP to load firmware static int sdma_v6_0_init_microcode(struct amdgpu_device *adev) { char fw_name[30]; char ucode_prefix[30]; - int err = 0, i; - struct amdgpu_firmware_info *info = NULL; - const struct sdma_firmware_header_v2_0 *sdma_hdr; DRM_DEBUG("\n"); @@ -131,43 +98,7 @@ static int sdma_v6_0_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix); - err = request_firmware(&adev->sdma.instance[0].fw, fw_name, adev->dev); - if (err) - goto out; - - err = sdma_v6_0_init_inst_ctx(&adev->sdma.instance[0]); - if (err) - goto out; - - for (i = 1; i < adev->sdma.num_instances; i++) { - memcpy((void*)&adev->sdma.instance[i], - (void*)&adev->sdma.instance[0], - sizeof(struct amdgpu_sdma_instance)); - } - - DRM_DEBUG("psp_load == '%s'\n", - adev->firmware.load_type == AMDGPU_FW_LOAD_PSP ? "true" : "false"); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - sdma_hdr = (const struct sdma_firmware_header_v2_0 *)adev->sdma.instance[0].fw->data; - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA_UCODE_TH0]; - info->ucode_id = AMDGPU_UCODE_ID_SDMA_UCODE_TH0; - info->fw = adev->sdma.instance[0].fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(sdma_hdr->ctx_ucode_size_bytes), PAGE_SIZE); - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA_UCODE_TH1]; - info->ucode_id = AMDGPU_UCODE_ID_SDMA_UCODE_TH1; - info->fw = adev->sdma.instance[0].fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(sdma_hdr->ctl_ucode_size_bytes), PAGE_SIZE); - } - -out: - if (err) { - DRM_ERROR("sdma_v6_0: Failed to load firmware \"%s\"\n", fw_name); - sdma_v6_0_destroy_inst_ctx(adev); - } - return err; + return amdgpu_sdma_init_microcode(adev, fw_name, 0, true); } static unsigned sdma_v6_0_ring_init_cond_exec(struct amdgpu_ring *ring) @@ -467,14 +398,10 @@ static void sdma_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v6_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_RB_CNTL)); @@ -484,9 +411,6 @@ static void sdma_v6_0_gfx_stop(struct amdgpu_device *adev) ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_QUEUE0_IB_CNTL, IB_ENABLE, 0); WREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_IB_CNTL), ib_cntl); } - - sdma0->sched.ready = false; - sdma1->sched.ready = false; } /** @@ -915,7 +839,8 @@ static int sdma_v6_0_mqd_init(struct amdgpu_device *adev, void *mqd, m->sdmax_rlcx_rb_cntl = order_base_2(prop->queue_size / 4) << SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT | 1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT | - 4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT; + 4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT | + 1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT; m->sdmax_rlcx_rb_base = lower_32_bits(prop->hqd_base_gpu_addr >> 8); m->sdmax_rlcx_rb_base_hi = upper_32_bits(prop->hqd_base_gpu_addr >> 8); @@ -1370,27 +1295,27 @@ static int sdma_v6_0_sw_fini(void *handle) for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); - sdma_v6_0_destroy_inst_ctx(adev); + amdgpu_sdma_destroy_inst_ctx(adev, true); return 0; } static int sdma_v6_0_hw_init(void *handle) { - int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = sdma_v6_0_start(adev); - - return r; + return sdma_v6_0_start(adev); } static int sdma_v6_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } sdma_v6_0_ctx_switch_enable(adev, false); sdma_v6_0_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c index f675111ace20..4d5e718540aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c @@ -116,15 +116,14 @@ static void si_dma_stop(struct amdgpu_device *adev) u32 rb_cntl; unsigned i; + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { ring = &adev->sdma.instance[i].ring; /* dma0 */ rb_cntl = RREG32(DMA_RB_CNTL + sdma_offsets[i]); rb_cntl &= ~DMA_RB_ENABLE; WREG32(DMA_RB_CNTL + sdma_offsets[i], rb_cntl); - - if (adev->mman.buffer_funcs_ring == ring) - amdgpu_ttm_set_buffer_funcs_status(adev, false); } } 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 a26c5723c46e..795706b3b092 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: @@ -628,6 +629,8 @@ 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 | + 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/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c index 939cb203f7ad..f17d297b594b 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c @@ -327,10 +327,9 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev, return; } - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); /* the lowest lsb bits should be ignored */ @@ -343,10 +342,7 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev, ADDR_OF_256B_BLOCK(channel_index) | OFFSET_IN_256B_BLOCK(err_addr); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, + amdgpu_umc_fill_error_record(err_data, err_addr, retired_page, channel_index, umc_inst); } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index bf7524f16b66..5d5d031c9e7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -187,20 +187,51 @@ static void umc_v6_7_ecc_info_query_ras_error_count(struct amdgpu_device *adev, } } +static void umc_v6_7_convert_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst) +{ + uint32_t channel_index; + uint64_t soc_pa, retired_page, column; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + /* translate umc channel address to soc pa, 3 parts are included */ + soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + /* The umc channel bits are not original values, they are hashed */ + SET_CHANNEL_HASH(channel_index, soc_pa); + + /* clear [C4 C3 C2] in soc physical address */ + soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); + + /* loop for all possibilities of [C4 C3 C2] */ + for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { + retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + + /* shift R14 bit */ + retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + } +} + static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t ch_inst, uint32_t umc_inst) { - uint64_t mc_umc_status, err_addr, soc_pa, retired_page, column; - uint32_t channel_index; + uint64_t mc_umc_status, err_addr; uint32_t eccinfo_table_idx; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); eccinfo_table_idx = umc_inst * adev->umc.channel_inst_num + ch_inst; - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; if (mc_umc_status == 0) @@ -209,42 +240,15 @@ static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, if (!err_data->err_addr) return; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* The umc channel bits are not original values, they are hashed */ - SET_CHANNEL_HASH(channel_index, soc_pa); - - /* clear [C4 C3 C2] in soc physical address */ - soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) { - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } - } + umc_v6_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } } @@ -452,14 +456,11 @@ static void umc_v6_7_query_ras_error_count(struct amdgpu_device *adev, static void umc_v6_7_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, - uint32_t umc_reg_offset, - uint32_t ch_inst, + uint32_t umc_reg_offset, uint32_t ch_inst, uint32_t umc_inst) { uint32_t mc_umc_status_addr; - uint32_t channel_index; - uint64_t mc_umc_status, mc_umc_addrt0; - uint64_t err_addr, soc_pa, retired_page, column; + uint64_t mc_umc_status = 0, mc_umc_addrt0, err_addr; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); @@ -477,45 +478,15 @@ static void umc_v6_7_query_error_address(struct amdgpu_device *adev, return; } - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { - + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); - err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); + err_addr = + REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* The umc channel bits are not original values, they are hashed */ - SET_CHANNEL_HASH(channel_index, soc_pa); - - /* clear [C4 C3 C2] in soc physical address */ - soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) { - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } - } + umc_v6_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } /* clear umc status */ @@ -540,8 +511,7 @@ static void umc_v6_7_query_ras_error_address(struct amdgpu_device *adev, ch_inst); umc_v6_7_query_error_address(adev, err_data, - umc_reg_offset, - ch_inst, + umc_reg_offset, ch_inst, umc_inst); } } @@ -583,4 +553,5 @@ struct amdgpu_umc_ras umc_v6_7_ras = { .query_ras_poison_mode = umc_v6_7_query_ras_poison_mode, .ecc_info_query_ras_error_count = umc_v6_7_ecc_info_query_ras_error_count, .ecc_info_query_ras_error_address = umc_v6_7_ecc_info_query_ras_error_address, + .convert_ras_error_address = umc_v6_7_convert_error_address, }; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c index 36a2053f2e8b..91235df54e22 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c @@ -101,22 +101,16 @@ static void umc_v8_10_query_correctable_error_count(struct amdgpu_device *adev, uint32_t umc_reg_offset, unsigned long *error_count) { - uint32_t ecc_err_cnt, ecc_err_cnt_addr; uint64_t mc_umc_status; uint32_t mc_umc_status_addr; /* UMC 8_10 registers */ - ecc_err_cnt_addr = - SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_GeccErrCnt); mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); - ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4); - *error_count += - (REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_GeccErrCnt, GeccErrCnt) - - UMC_V8_10_CE_CNT_INIT); - - /* Check for SRAM correctable error, MCUMC_STATUS is a 64 bit register */ + /* Rely on MCUMC_STATUS for correctable error counter + * MCUMC_STATUS is a 64 bit register + */ mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1) @@ -214,7 +208,10 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, { uint64_t mc_umc_status_addr; uint64_t mc_umc_status, err_addr; - uint32_t channel_index; + uint64_t mc_umc_addrt0, na_err_addr_base; + uint64_t na_err_addr, retired_page_addr; + uint32_t channel_index, addr_lsb, col = 0; + int ret = 0; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); @@ -235,13 +232,10 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, umc_inst * adev->umc.channel_inst_num + ch_inst]; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrV) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { - uint32_t addr_lsb; - uint64_t mc_umc_addrt0; + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { mc_umc_addrt0 = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); @@ -249,32 +243,24 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, /* the lowest lsb bits should be ignored */ addr_lsb = REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrLsb); - err_addr &= ~((0x1ULL << addr_lsb) - 1); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { - uint64_t na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); - uint64_t na_err_addr, retired_page_addr; - uint32_t col = 0; - int ret = 0; - - /* loop for all possibilities of [C6 C5] in normal address. */ - for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { - na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); - - /* Mapping normal error address to retired soc physical address. */ - ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, - na_err_addr, &retired_page_addr); - if (ret) { - dev_err(adev->dev, "Failed to map pa from umc na.\n"); - break; - } - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", - retired_page_addr); - amdgpu_umc_fill_error_record(err_data, na_err_addr, - retired_page_addr, channel_index, umc_inst); + na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); + + /* loop for all possibilities of [C6 C5] in normal address. */ + for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { + na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); + + /* Mapping normal error address to retired soc physical address. */ + ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, + na_err_addr, &retired_page_addr); + if (ret) { + dev_err(adev->dev, "Failed to map pa from umc na.\n"); + break; } + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", + retired_page_addr); + amdgpu_umc_fill_error_record(err_data, na_err_addr, + retired_page_addr, channel_index, umc_inst); } } @@ -344,6 +330,31 @@ static void umc_v8_10_err_cnt_init(struct amdgpu_device *adev) } } +static uint32_t umc_v8_10_query_ras_poison_mode_per_channel( + struct amdgpu_device *adev, + uint32_t umc_reg_offset) +{ + uint32_t ecc_ctrl_addr, ecc_ctrl; + + ecc_ctrl_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_GeccCtrl); + ecc_ctrl = RREG32_PCIE((ecc_ctrl_addr + + umc_reg_offset) * 4); + + return REG_GET_FIELD(ecc_ctrl, UMCCH0_0_GeccCtrl, UCFatalEn); +} + +static bool umc_v8_10_query_ras_poison_mode(struct amdgpu_device *adev) +{ + uint32_t umc_reg_offset = 0; + + /* Enabling fatal error in umc node0 instance0 channel0 will be + * considered as fatal error mode + */ + umc_reg_offset = get_umc_v8_10_reg_offset(adev, 0, 0, 0); + return !umc_v8_10_query_ras_poison_mode_per_channel(adev, umc_reg_offset); +} + const struct amdgpu_ras_block_hw_ops umc_v8_10_ras_hw_ops = { .query_ras_error_count = umc_v8_10_query_ras_error_count, .query_ras_error_address = umc_v8_10_query_ras_error_address, @@ -354,4 +365,5 @@ struct amdgpu_umc_ras umc_v8_10_ras = { .hw_ops = &umc_v8_10_ras_hw_ops, }, .err_cnt_init = umc_v8_10_err_cnt_init, + .query_ras_poison_mode = umc_v8_10_query_ras_poison_mode, }; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c index f35253e0eaa6..b717fdaa46e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c @@ -108,20 +108,35 @@ static void umc_v8_7_ecc_info_query_ras_error_count(struct amdgpu_device *adev, } } +static void umc_v8_7_convert_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst) +{ + uint64_t retired_page; + uint32_t channel_index; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + + /* translate umc channel address to soc pa, 3 parts are included */ + retired_page = ADDR_OF_4KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); +} + static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t ch_inst, uint32_t umc_inst) { - uint64_t mc_umc_status, err_addr, retired_page; - uint32_t channel_index; + uint64_t mc_umc_status, err_addr; uint32_t eccinfo_table_idx; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); eccinfo_table_idx = umc_inst * adev->umc.channel_inst_num + ch_inst; - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; if (mc_umc_status == 0) @@ -130,24 +145,15 @@ static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, if (!err_data->err_addr) return; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - retired_page = ADDR_OF_4KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); + umc_v8_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } } @@ -324,14 +330,12 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, uint32_t umc_inst) { uint32_t lsb, mc_umc_status_addr; - uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0; - uint32_t channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + uint64_t mc_umc_status, err_addr, mc_umc_addrt0; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0); mc_umc_addrt0 = SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0); - mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); if (mc_umc_status == 0) @@ -343,10 +347,9 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, return; } - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); /* the lowest lsb bits should be ignored */ @@ -354,16 +357,8 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); err_addr &= ~((0x1ULL << lsb) - 1); - /* translate umc channel address to soc pa, 3 parts are included */ - retired_page = ADDR_OF_4KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); + umc_v8_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } /* clear umc status */ diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 39405f0db824..9c8b5fd99037 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1761,21 +1761,23 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; -static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p) +static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, + struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; /* The create msg must be in the first IB submitted */ - if (atomic_read(&p->entity->fence_seq)) + if (atomic_read(&job->base.entity->fence_seq)) return -EINVAL; scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; - drm_sched_entity_modify_sched(p->entity, scheds, 1); + drm_sched_entity_modify_sched(job->base.entity, scheds, 1); return 0; } -static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) +static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, + uint64_t addr) { struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo_va_mapping *map; @@ -1846,7 +1848,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) continue; - r = vcn_v3_0_limit_sched(p); + r = vcn_v3_0_limit_sched(p, job); if (r) goto out; } @@ -1860,7 +1862,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_job *job, struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); + struct amdgpu_ring *ring = amdgpu_job_ring(job); uint32_t msg_lo = 0, msg_hi = 0; unsigned i; int r; @@ -1879,7 +1881,8 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, msg_hi = val; } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) && val == 0) { - r = vcn_v3_0_dec_msg(p, ((u64)msg_hi) << 32 | msg_lo); + r = vcn_v3_0_dec_msg(p, job, + ((u64)msg_hi) << 32 | msg_lo); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 09c89faa8c27..897a5ce9c9da 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -150,6 +150,10 @@ static int vcn_v4_0_sw_init(void *handle) fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); fw_shared->sq.is_enabled = 1; + fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG); + fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ? + AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU; + if (amdgpu_sriov_vf(adev)) fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_VF_RB_SETUP_FLAG); @@ -1591,21 +1595,23 @@ static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring) } } -static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p) +static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, + struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; /* The create msg must be in the first IB submitted */ - if (atomic_read(&p->entity->fence_seq)) + if (atomic_read(&job->base.entity->fence_seq)) return -EINVAL; scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; - drm_sched_entity_modify_sched(p->entity, scheds, 1); + drm_sched_entity_modify_sched(job->base.entity, scheds, 1); return 0; } -static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) +static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, + uint64_t addr) { struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo_va_mapping *map; @@ -1676,7 +1682,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) continue; - r = vcn_v4_0_limit_sched(p); + r = vcn_v4_0_limit_sched(p, job); if (r) goto out; } @@ -1689,32 +1695,34 @@ out: #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, - struct amdgpu_job *job, - struct amdgpu_ib *ib) + struct amdgpu_job *job, + struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); - struct amdgpu_vcn_decode_buffer *decode_buffer = NULL; + struct amdgpu_ring *ring = amdgpu_job_ring(job); + struct amdgpu_vcn_decode_buffer *decode_buffer; + uint64_t addr; uint32_t val; - int r = 0; /* The first instance can decode anything */ if (!ring->me) - return r; + return 0; /* unified queue ib header has 8 double words. */ if (ib->length_dw < 8) - return r; + return 0; val = amdgpu_ib_get_value(ib, 6); //RADEON_VCN_ENGINE_TYPE + if (val != RADEON_VCN_ENGINE_TYPE_DECODE) + return 0; - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[10]; + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[10]; - if (decode_buffer->valid_buf_flag & 0x1) - r = vcn_v4_0_dec_msg(p, ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo); - } - return r; + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); } static const struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { 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/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 60a81649cf12..c7118843db05 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -742,7 +742,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = { 0xbf88fffe, 0x877aff7f, 0x04000000, 0x8f7a857a, 0x886d7a6d, 0xb97b02dc, - 0x8f7b997b, 0xb97a2a05, + 0x8f7b997b, 0xb97a3a05, 0x807a817a, 0xbf0d997b, 0xbf850002, 0x8f7a897a, 0xbf820001, 0x8f7a8a7a, @@ -819,7 +819,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = { 0xbefe037c, 0xbefc0370, 0xf4611c7a, 0xf8000000, 0x80708470, 0xbefc037e, - 0xb9702a05, 0x80708170, + 0xb9703a05, 0x80708170, 0xbf0d9973, 0xbf850002, 0x8f708970, 0xbf820001, 0x8f708a70, 0xb97a1e06, @@ -1069,7 +1069,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = { 0xb9f9f816, 0x876f7bff, 0xfffff800, 0x906f8b6f, 0xb9efa2c3, 0xb9f3f801, - 0xb96e2a05, 0x806e816e, + 0xb96e3a05, 0x806e816e, 0xbf0d9972, 0xbf850002, 0x8f6e896e, 0xbf820001, 0x8f6e8a6e, 0xb96f1e06, @@ -2114,7 +2114,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x007a0000, 0x7e000280, 0xbefe037a, 0xbeff037b, 0xb97b02dc, 0x8f7b997b, - 0xb97a2a05, 0x807a817a, + 0xb97a3a05, 0x807a817a, 0xbf0d997b, 0xbf850002, 0x8f7a897a, 0xbf820001, 0x8f7a8a7a, 0xb97b1e06, @@ -2157,7 +2157,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x01000000, 0xe0704100, 0x705d0100, 0xe0704200, 0x705d0200, 0xe0704300, - 0x705d0300, 0xb9702a05, + 0x705d0300, 0xb9703a05, 0x80708170, 0xbf0d9973, 0xbf850002, 0x8f708970, 0xbf820001, 0x8f708a70, @@ -2189,7 +2189,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0xbefe03ff, 0x0000ffff, 0xbeff0380, 0xe0704000, 0x705d0200, 0xbefe03c1, - 0xb9702a05, 0x80708170, + 0xb9703a05, 0x80708170, 0xbf0d9973, 0xbf850002, 0x8f708970, 0xbf820001, 0x8f708a70, 0xb97a1e06, @@ -2475,7 +2475,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0xb9ef4803, 0x876f7bff, 0xfffff800, 0x906f8b6f, 0xb9efa2c3, 0xb9f3f801, - 0xb96e2a05, 0x806e816e, + 0xb96e3a05, 0x806e816e, 0xbf0d9972, 0xbf850002, 0x8f6e896e, 0xbf820001, 0x8f6e8a6e, 0xb96f1e06, @@ -2494,438 +2494,441 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0x00000000, }; - static const uint32_t cwsr_trap_gfx11_hex[] = { - 0xbfa00001, 0xbfa0021b, + 0xbfa00001, 0xbfa0021e, 0xb0804006, 0xb8f8f802, - 0x91788678, 0xb8fbf803, - 0x8b6eff78, 0x00002000, - 0xbfa10009, 0x8b6eff6d, - 0x00ff0000, 0xbfa2001e, - 0x8b6eff7b, 0x00000400, - 0xbfa20041, 0xbf830010, - 0xb8fbf803, 0xbfa0fffa, - 0x8b6eff7b, 0x00000900, - 0xbfa20015, 0x8b6eff7b, - 0x000071ff, 0xbfa10008, - 0x8b6fff7b, 0x00007080, - 0xbfa10001, 0xbeee1287, - 0xb8eff801, 0x846e8c6e, - 0x8b6e6f6e, 0xbfa2000a, + 0x9178ff78, 0x00020006, + 0xb8fbf803, 0xbf0d9f6d, + 0xbfa20006, 0x8b6eff78, + 0x00002000, 0xbfa10009, 0x8b6eff6d, 0x00ff0000, - 0xbfa20007, 0xb8eef801, - 0x8b6eff6e, 0x00000800, - 0xbfa20003, 0x8b6eff7b, - 0x00000400, 0xbfa20026, - 0xbefa4d82, 0xbf89fc07, - 0x84fa887a, 0xf4005bbd, - 0xf8000010, 0xbf89fc07, - 0x846e976e, 0x9177ff77, - 0x00800000, 0x8c776e77, - 0xf4045bbd, 0xf8000000, - 0xbf89fc07, 0xf4045ebd, - 0xf8000008, 0xbf89fc07, - 0x8bee6e6e, 0xbfa10001, - 0xbe80486e, 0x8b6eff6d, - 0x01ff0000, 0xbfa20005, - 0x8c78ff78, 0x00002000, - 0x80ec886c, 0x82ed806d, - 0xbfa00005, 0x8b6eff6d, - 0x01000000, 0xbfa20002, - 0x806c846c, 0x826d806d, - 0x8b6dff6d, 0x0000ffff, - 0x8bfe7e7e, 0x8bea6a6a, - 0xb978f802, 0xbe804a6c, - 0x8b6dff6d, 0x0000ffff, - 0xbefa0080, 0xb97a0283, - 0xbeee007e, 0xbeef007f, - 0xbefe0180, 0xbefe4d84, - 0xbf89fc07, 0x8b7aff7f, - 0x04000000, 0x847a857a, - 0x8c6d7a6d, 0xbefa007e, - 0x8b7bff7f, 0x0000ffff, - 0xbefe00c1, 0xbeff00c1, - 0xdca6c000, 0x007a0000, - 0x7e000280, 0xbefe007a, - 0xbeff007b, 0xb8fb02dc, - 0x847b997b, 0xb8fa3b05, - 0x807a817a, 0xbf0d997b, - 0xbfa20002, 0x847a897a, - 0xbfa00001, 0x847a8a7a, - 0xb8fb1e06, 0x847b8a7b, - 0x807a7b7a, 0x8b7bff7f, - 0x0000ffff, 0x807aff7a, - 0x00000200, 0x807a7e7a, - 0x827b807b, 0xd7610000, - 0x00010870, 0xd7610000, - 0x00010a71, 0xd7610000, - 0x00010c72, 0xd7610000, - 0x00010e73, 0xd7610000, - 0x00011074, 0xd7610000, - 0x00011275, 0xd7610000, - 0x00011476, 0xd7610000, - 0x00011677, 0xd7610000, - 0x00011a79, 0xd7610000, - 0x00011c7e, 0xd7610000, - 0x00011e7f, 0xbefe00ff, - 0x00003fff, 0xbeff0080, - 0xdca6c040, 0x007a0000, - 0xd760007a, 0x00011d00, - 0xd760007b, 0x00011f00, + 0xbfa2001e, 0x8b6eff7b, + 0x00000400, 0xbfa20041, + 0xbf830010, 0xb8fbf803, + 0xbfa0fffa, 0x8b6eff7b, + 0x00000900, 0xbfa20015, + 0x8b6eff7b, 0x000071ff, + 0xbfa10008, 0x8b6fff7b, + 0x00007080, 0xbfa10001, + 0xbeee1287, 0xb8eff801, + 0x846e8c6e, 0x8b6e6f6e, + 0xbfa2000a, 0x8b6eff6d, + 0x00ff0000, 0xbfa20007, + 0xb8eef801, 0x8b6eff6e, + 0x00000800, 0xbfa20003, + 0x8b6eff7b, 0x00000400, + 0xbfa20026, 0xbefa4d82, + 0xbf89fc07, 0x84fa887a, + 0xf4005bbd, 0xf8000010, + 0xbf89fc07, 0x846e976e, + 0x9177ff77, 0x00800000, + 0x8c776e77, 0xf4045bbd, + 0xf8000000, 0xbf89fc07, + 0xf4045ebd, 0xf8000008, + 0xbf89fc07, 0x8bee6e6e, + 0xbfa10001, 0xbe80486e, + 0x8b6eff6d, 0x01ff0000, + 0xbfa20005, 0x8c78ff78, + 0x00002000, 0x80ec886c, + 0x82ed806d, 0xbfa00005, + 0x8b6eff6d, 0x01000000, + 0xbfa20002, 0x806c846c, + 0x826d806d, 0x8b6dff6d, + 0x0000ffff, 0x8bfe7e7e, + 0x8bea6a6a, 0xb978f802, + 0xbe804a6c, 0x8b6dff6d, + 0x0000ffff, 0xbefa0080, + 0xb97a0283, 0xbeee007e, + 0xbeef007f, 0xbefe0180, + 0xbefe4d84, 0xbf89fc07, + 0x8b7aff7f, 0x04000000, + 0x847a857a, 0x8c6d7a6d, + 0xbefa007e, 0x8b7bff7f, + 0x0000ffff, 0xbefe00c1, + 0xbeff00c1, 0xdca6c000, + 0x007a0000, 0x7e000280, 0xbefe007a, 0xbeff007b, - 0xbef4007e, 0x8b75ff7f, - 0x0000ffff, 0x8c75ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x10807fac, - 0xbef1007d, 0xbef00080, - 0xb8f302dc, 0x84739973, - 0xbefe00c1, 0x857d9973, - 0x8b7d817d, 0xbf06817d, - 0xbfa20002, 0xbeff0080, - 0xbfa00002, 0xbeff00c1, - 0xbfa00009, 0xbef600ff, - 0x01000000, 0xe0685080, - 0x701d0100, 0xe0685100, - 0x701d0200, 0xe0685180, - 0x701d0300, 0xbfa00008, + 0xb8fb02dc, 0x847b997b, + 0xb8fa3b05, 0x807a817a, + 0xbf0d997b, 0xbfa20002, + 0x847a897a, 0xbfa00001, + 0x847a8a7a, 0xb8fb1e06, + 0x847b8a7b, 0x807a7b7a, + 0x8b7bff7f, 0x0000ffff, + 0x807aff7a, 0x00000200, + 0x807a7e7a, 0x827b807b, + 0xd7610000, 0x00010870, + 0xd7610000, 0x00010a71, + 0xd7610000, 0x00010c72, + 0xd7610000, 0x00010e73, + 0xd7610000, 0x00011074, + 0xd7610000, 0x00011275, + 0xd7610000, 0x00011476, + 0xd7610000, 0x00011677, + 0xd7610000, 0x00011a79, + 0xd7610000, 0x00011c7e, + 0xd7610000, 0x00011e7f, + 0xbefe00ff, 0x00003fff, + 0xbeff0080, 0xdca6c040, + 0x007a0000, 0xd760007a, + 0x00011d00, 0xd760007b, + 0x00011f00, 0xbefe007a, + 0xbeff007b, 0xbef4007e, + 0x8b75ff7f, 0x0000ffff, + 0x8c75ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x10807fac, 0xbef1007d, + 0xbef00080, 0xb8f302dc, + 0x84739973, 0xbefe00c1, + 0x857d9973, 0x8b7d817d, + 0xbf06817d, 0xbfa20002, + 0xbeff0080, 0xbfa00002, + 0xbeff00c1, 0xbfa00009, 0xbef600ff, 0x01000000, - 0xe0685100, 0x701d0100, - 0xe0685200, 0x701d0200, - 0xe0685300, 0x701d0300, + 0xe0685080, 0x701d0100, + 0xe0685100, 0x701d0200, + 0xe0685180, 0x701d0300, + 0xbfa00008, 0xbef600ff, + 0x01000000, 0xe0685100, + 0x701d0100, 0xe0685200, + 0x701d0200, 0xe0685300, + 0x701d0300, 0xb8f03b05, + 0x80708170, 0xbf0d9973, + 0xbfa20002, 0x84708970, + 0xbfa00001, 0x84708a70, + 0xb8fa1e06, 0x847a8a7a, + 0x80707a70, 0x8070ff70, + 0x00000200, 0xbef600ff, + 0x01000000, 0x7e000280, + 0x7e020280, 0x7e040280, + 0xbefd0080, 0xd7610002, + 0x0000fa71, 0x807d817d, + 0xd7610002, 0x0000fa6c, + 0x807d817d, 0x917aff6d, + 0x80000000, 0xd7610002, + 0x0000fa7a, 0x807d817d, + 0xd7610002, 0x0000fa6e, + 0x807d817d, 0xd7610002, + 0x0000fa6f, 0x807d817d, + 0xd7610002, 0x0000fa78, + 0x807d817d, 0xb8faf803, + 0xd7610002, 0x0000fa7a, + 0x807d817d, 0xd7610002, + 0x0000fa7b, 0x807d817d, + 0xb8f1f801, 0xd7610002, + 0x0000fa71, 0x807d817d, + 0xb8f1f814, 0xd7610002, + 0x0000fa71, 0x807d817d, + 0xb8f1f815, 0xd7610002, + 0x0000fa71, 0x807d817d, + 0xbefe00ff, 0x0000ffff, + 0xbeff0080, 0xe0685000, + 0x701d0200, 0xbefe00c1, 0xb8f03b05, 0x80708170, 0xbf0d9973, 0xbfa20002, 0x84708970, 0xbfa00001, 0x84708a70, 0xb8fa1e06, 0x847a8a7a, 0x80707a70, - 0x8070ff70, 0x00000200, 0xbef600ff, 0x01000000, - 0x7e000280, 0x7e020280, - 0x7e040280, 0xbefd0080, - 0xd7610002, 0x0000fa71, - 0x807d817d, 0xd7610002, - 0x0000fa6c, 0x807d817d, - 0x917aff6d, 0x80000000, - 0xd7610002, 0x0000fa7a, - 0x807d817d, 0xd7610002, - 0x0000fa6e, 0x807d817d, - 0xd7610002, 0x0000fa6f, - 0x807d817d, 0xd7610002, - 0x0000fa78, 0x807d817d, - 0xb8faf803, 0xd7610002, - 0x0000fa7a, 0x807d817d, - 0xd7610002, 0x0000fa7b, - 0x807d817d, 0xb8f1f801, - 0xd7610002, 0x0000fa71, - 0x807d817d, 0xb8f1f814, - 0xd7610002, 0x0000fa71, - 0x807d817d, 0xb8f1f815, - 0xd7610002, 0x0000fa71, - 0x807d817d, 0xbefe00ff, - 0x0000ffff, 0xbeff0080, - 0xe0685000, 0x701d0200, - 0xbefe00c1, 0xb8f03b05, - 0x80708170, 0xbf0d9973, - 0xbfa20002, 0x84708970, - 0xbfa00001, 0x84708a70, - 0xb8fa1e06, 0x847a8a7a, - 0x80707a70, 0xbef600ff, - 0x01000000, 0xbef90080, - 0xbefd0080, 0xbf800000, - 0xbe804100, 0xbe824102, - 0xbe844104, 0xbe864106, - 0xbe884108, 0xbe8a410a, - 0xbe8c410c, 0xbe8e410e, - 0xd7610002, 0x0000f200, - 0x80798179, 0xd7610002, - 0x0000f201, 0x80798179, - 0xd7610002, 0x0000f202, - 0x80798179, 0xd7610002, - 0x0000f203, 0x80798179, - 0xd7610002, 0x0000f204, + 0xbef90080, 0xbefd0080, + 0xbf800000, 0xbe804100, + 0xbe824102, 0xbe844104, + 0xbe864106, 0xbe884108, + 0xbe8a410a, 0xbe8c410c, + 0xbe8e410e, 0xd7610002, + 0x0000f200, 0x80798179, + 0xd7610002, 0x0000f201, 0x80798179, 0xd7610002, - 0x0000f205, 0x80798179, - 0xd7610002, 0x0000f206, + 0x0000f202, 0x80798179, + 0xd7610002, 0x0000f203, 0x80798179, 0xd7610002, - 0x0000f207, 0x80798179, - 0xd7610002, 0x0000f208, + 0x0000f204, 0x80798179, + 0xd7610002, 0x0000f205, 0x80798179, 0xd7610002, - 0x0000f209, 0x80798179, - 0xd7610002, 0x0000f20a, + 0x0000f206, 0x80798179, + 0xd7610002, 0x0000f207, 0x80798179, 0xd7610002, - 0x0000f20b, 0x80798179, - 0xd7610002, 0x0000f20c, + 0x0000f208, 0x80798179, + 0xd7610002, 0x0000f209, 0x80798179, 0xd7610002, - 0x0000f20d, 0x80798179, - 0xd7610002, 0x0000f20e, + 0x0000f20a, 0x80798179, + 0xd7610002, 0x0000f20b, 0x80798179, 0xd7610002, - 0x0000f20f, 0x80798179, - 0xbf06a079, 0xbfa10006, - 0xe0685000, 0x701d0200, - 0x8070ff70, 0x00000080, - 0xbef90080, 0x7e040280, - 0x807d907d, 0xbf0aff7d, - 0x00000060, 0xbfa2ffbc, - 0xbe804100, 0xbe824102, - 0xbe844104, 0xbe864106, - 0xbe884108, 0xbe8a410a, - 0xd7610002, 0x0000f200, + 0x0000f20c, 0x80798179, + 0xd7610002, 0x0000f20d, 0x80798179, 0xd7610002, - 0x0000f201, 0x80798179, - 0xd7610002, 0x0000f202, + 0x0000f20e, 0x80798179, + 0xd7610002, 0x0000f20f, + 0x80798179, 0xbf06a079, + 0xbfa10006, 0xe0685000, + 0x701d0200, 0x8070ff70, + 0x00000080, 0xbef90080, + 0x7e040280, 0x807d907d, + 0xbf0aff7d, 0x00000060, + 0xbfa2ffbc, 0xbe804100, + 0xbe824102, 0xbe844104, + 0xbe864106, 0xbe884108, + 0xbe8a410a, 0xd7610002, + 0x0000f200, 0x80798179, + 0xd7610002, 0x0000f201, 0x80798179, 0xd7610002, - 0x0000f203, 0x80798179, - 0xd7610002, 0x0000f204, + 0x0000f202, 0x80798179, + 0xd7610002, 0x0000f203, 0x80798179, 0xd7610002, - 0x0000f205, 0x80798179, - 0xd7610002, 0x0000f206, + 0x0000f204, 0x80798179, + 0xd7610002, 0x0000f205, 0x80798179, 0xd7610002, - 0x0000f207, 0x80798179, - 0xd7610002, 0x0000f208, + 0x0000f206, 0x80798179, + 0xd7610002, 0x0000f207, 0x80798179, 0xd7610002, - 0x0000f209, 0x80798179, - 0xd7610002, 0x0000f20a, + 0x0000f208, 0x80798179, + 0xd7610002, 0x0000f209, 0x80798179, 0xd7610002, - 0x0000f20b, 0x80798179, - 0xe0685000, 0x701d0200, + 0x0000f20a, 0x80798179, + 0xd7610002, 0x0000f20b, + 0x80798179, 0xe0685000, + 0x701d0200, 0xbefe00c1, + 0x857d9973, 0x8b7d817d, + 0xbf06817d, 0xbfa20002, + 0xbeff0080, 0xbfa00001, + 0xbeff00c1, 0xb8fb4306, + 0x8b7bc17b, 0xbfa10044, + 0xbfbd0000, 0x8b7aff6d, + 0x80000000, 0xbfa10040, + 0x847b867b, 0x847b827b, + 0xbef6007b, 0xb8f03b05, + 0x80708170, 0xbf0d9973, + 0xbfa20002, 0x84708970, + 0xbfa00001, 0x84708a70, + 0xb8fa1e06, 0x847a8a7a, + 0x80707a70, 0x8070ff70, + 0x00000200, 0x8070ff70, + 0x00000080, 0xbef600ff, + 0x01000000, 0xd71f0000, + 0x000100c1, 0xd7200000, + 0x000200c1, 0x16000084, + 0x857d9973, 0x8b7d817d, + 0xbf06817d, 0xbefd0080, + 0xbfa20012, 0xbe8300ff, + 0x00000080, 0xbf800000, + 0xbf800000, 0xbf800000, + 0xd8d80000, 0x01000000, + 0xbf890000, 0xe0685000, + 0x701d0100, 0x807d037d, + 0x80700370, 0xd5250000, + 0x0001ff00, 0x00000080, + 0xbf0a7b7d, 0xbfa2fff4, + 0xbfa00011, 0xbe8300ff, + 0x00000100, 0xbf800000, + 0xbf800000, 0xbf800000, + 0xd8d80000, 0x01000000, + 0xbf890000, 0xe0685000, + 0x701d0100, 0x807d037d, + 0x80700370, 0xd5250000, + 0x0001ff00, 0x00000100, + 0xbf0a7b7d, 0xbfa2fff4, 0xbefe00c1, 0x857d9973, 0x8b7d817d, 0xbf06817d, - 0xbfa20002, 0xbeff0080, - 0xbfa00001, 0xbeff00c1, - 0xb8fb4306, 0x8b7bc17b, - 0xbfa10044, 0xbfbd0000, - 0x8b7aff6d, 0x80000000, - 0xbfa10040, 0x847b867b, - 0x847b827b, 0xbef6007b, - 0xb8f03b05, 0x80708170, - 0xbf0d9973, 0xbfa20002, - 0x84708970, 0xbfa00001, - 0x84708a70, 0xb8fa1e06, - 0x847a8a7a, 0x80707a70, - 0x8070ff70, 0x00000200, - 0x8070ff70, 0x00000080, - 0xbef600ff, 0x01000000, - 0xd71f0000, 0x000100c1, - 0xd7200000, 0x000200c1, - 0x16000084, 0x857d9973, + 0xbfa20004, 0xbef000ff, + 0x00000200, 0xbeff0080, + 0xbfa00003, 0xbef000ff, + 0x00000400, 0xbeff00c1, + 0xb8fb3b05, 0x807b817b, + 0x847b827b, 0x857d9973, 0x8b7d817d, 0xbf06817d, - 0xbefd0080, 0xbfa20012, - 0xbe8300ff, 0x00000080, - 0xbf800000, 0xbf800000, - 0xbf800000, 0xd8d80000, - 0x01000000, 0xbf890000, - 0xe0685000, 0x701d0100, - 0x807d037d, 0x80700370, - 0xd5250000, 0x0001ff00, - 0x00000080, 0xbf0a7b7d, - 0xbfa2fff4, 0xbfa00011, - 0xbe8300ff, 0x00000100, - 0xbf800000, 0xbf800000, - 0xbf800000, 0xd8d80000, - 0x01000000, 0xbf890000, - 0xe0685000, 0x701d0100, - 0x807d037d, 0x80700370, - 0xd5250000, 0x0001ff00, - 0x00000100, 0xbf0a7b7d, - 0xbfa2fff4, 0xbefe00c1, - 0x857d9973, 0x8b7d817d, - 0xbf06817d, 0xbfa20004, - 0xbef000ff, 0x00000200, - 0xbeff0080, 0xbfa00003, - 0xbef000ff, 0x00000400, - 0xbeff00c1, 0xb8fb3b05, - 0x807b817b, 0x847b827b, - 0x857d9973, 0x8b7d817d, - 0xbf06817d, 0xbfa20017, + 0xbfa20017, 0xbef600ff, + 0x01000000, 0xbefd0084, + 0xbf0a7b7d, 0xbfa10037, + 0x7e008700, 0x7e028701, + 0x7e048702, 0x7e068703, + 0xe0685000, 0x701d0000, + 0xe0685080, 0x701d0100, + 0xe0685100, 0x701d0200, + 0xe0685180, 0x701d0300, + 0x807d847d, 0x8070ff70, + 0x00000200, 0xbf0a7b7d, + 0xbfa2ffef, 0xbfa00025, 0xbef600ff, 0x01000000, 0xbefd0084, 0xbf0a7b7d, - 0xbfa10037, 0x7e008700, + 0xbfa10011, 0x7e008700, 0x7e028701, 0x7e048702, 0x7e068703, 0xe0685000, - 0x701d0000, 0xe0685080, - 0x701d0100, 0xe0685100, - 0x701d0200, 0xe0685180, + 0x701d0000, 0xe0685100, + 0x701d0100, 0xe0685200, + 0x701d0200, 0xe0685300, 0x701d0300, 0x807d847d, - 0x8070ff70, 0x00000200, + 0x8070ff70, 0x00000400, 0xbf0a7b7d, 0xbfa2ffef, - 0xbfa00025, 0xbef600ff, - 0x01000000, 0xbefd0084, - 0xbf0a7b7d, 0xbfa10011, - 0x7e008700, 0x7e028701, - 0x7e048702, 0x7e068703, + 0xb8fb1e06, 0x8b7bc17b, + 0xbfa1000c, 0x847b837b, + 0x807b7d7b, 0xbefe00c1, + 0xbeff0080, 0x7e008700, 0xe0685000, 0x701d0000, - 0xe0685100, 0x701d0100, - 0xe0685200, 0x701d0200, - 0xe0685300, 0x701d0300, - 0x807d847d, 0x8070ff70, - 0x00000400, 0xbf0a7b7d, - 0xbfa2ffef, 0xb8fb1e06, - 0x8b7bc17b, 0xbfa1000c, - 0x847b837b, 0x807b7d7b, - 0xbefe00c1, 0xbeff0080, - 0x7e008700, 0xe0685000, - 0x701d0000, 0x807d817d, - 0x8070ff70, 0x00000080, - 0xbf0a7b7d, 0xbfa2fff8, - 0xbfa00141, 0xbef4007e, - 0x8b75ff7f, 0x0000ffff, - 0x8c75ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x10807fac, 0xb8f202dc, - 0x84729972, 0x8b6eff7f, - 0x04000000, 0xbfa1003a, + 0x807d817d, 0x8070ff70, + 0x00000080, 0xbf0a7b7d, + 0xbfa2fff8, 0xbfa00146, + 0xbef4007e, 0x8b75ff7f, + 0x0000ffff, 0x8c75ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x10807fac, + 0xb8f202dc, 0x84729972, + 0x8b6eff7f, 0x04000000, + 0xbfa1003a, 0xbefe00c1, + 0x857d9972, 0x8b7d817d, + 0xbf06817d, 0xbfa20002, + 0xbeff0080, 0xbfa00001, + 0xbeff00c1, 0xb8ef4306, + 0x8b6fc16f, 0xbfa1002f, + 0x846f866f, 0x846f826f, + 0xbef6006f, 0xb8f83b05, + 0x80788178, 0xbf0d9972, + 0xbfa20002, 0x84788978, + 0xbfa00001, 0x84788a78, + 0xb8ee1e06, 0x846e8a6e, + 0x80786e78, 0x8078ff78, + 0x00000200, 0x8078ff78, + 0x00000080, 0xbef600ff, + 0x01000000, 0x857d9972, + 0x8b7d817d, 0xbf06817d, + 0xbefd0080, 0xbfa2000c, + 0xe0500000, 0x781d0000, + 0xbf8903f7, 0xdac00000, + 0x00000000, 0x807dff7d, + 0x00000080, 0x8078ff78, + 0x00000080, 0xbf0a6f7d, + 0xbfa2fff5, 0xbfa0000b, + 0xe0500000, 0x781d0000, + 0xbf8903f7, 0xdac00000, + 0x00000000, 0x807dff7d, + 0x00000100, 0x8078ff78, + 0x00000100, 0xbf0a6f7d, + 0xbfa2fff5, 0xbef80080, 0xbefe00c1, 0x857d9972, 0x8b7d817d, 0xbf06817d, 0xbfa20002, 0xbeff0080, 0xbfa00001, 0xbeff00c1, - 0xb8ef4306, 0x8b6fc16f, - 0xbfa1002f, 0x846f866f, - 0x846f826f, 0xbef6006f, - 0xb8f83b05, 0x80788178, - 0xbf0d9972, 0xbfa20002, - 0x84788978, 0xbfa00001, - 0x84788a78, 0xb8ee1e06, - 0x846e8a6e, 0x80786e78, + 0xb8ef3b05, 0x806f816f, + 0x846f826f, 0x857d9972, + 0x8b7d817d, 0xbf06817d, + 0xbfa20024, 0xbef600ff, + 0x01000000, 0xbeee0078, 0x8078ff78, 0x00000200, - 0x8078ff78, 0x00000080, - 0xbef600ff, 0x01000000, - 0x857d9972, 0x8b7d817d, - 0xbf06817d, 0xbefd0080, - 0xbfa2000c, 0xe0500000, - 0x781d0000, 0xbf8903f7, - 0xdac00000, 0x00000000, - 0x807dff7d, 0x00000080, - 0x8078ff78, 0x00000080, - 0xbf0a6f7d, 0xbfa2fff5, - 0xbfa0000b, 0xe0500000, - 0x781d0000, 0xbf8903f7, - 0xdac00000, 0x00000000, - 0x807dff7d, 0x00000100, - 0x8078ff78, 0x00000100, - 0xbf0a6f7d, 0xbfa2fff5, - 0xbef80080, 0xbefe00c1, - 0x857d9972, 0x8b7d817d, - 0xbf06817d, 0xbfa20002, - 0xbeff0080, 0xbfa00001, - 0xbeff00c1, 0xb8ef3b05, - 0x806f816f, 0x846f826f, - 0x857d9972, 0x8b7d817d, - 0xbf06817d, 0xbfa20024, - 0xbef600ff, 0x01000000, - 0xbeee0078, 0x8078ff78, - 0x00000200, 0xbefd0084, - 0xbf0a6f7d, 0xbfa10050, + 0xbefd0084, 0xbf0a6f7d, + 0xbfa10050, 0xe0505000, + 0x781d0000, 0xe0505080, + 0x781d0100, 0xe0505100, + 0x781d0200, 0xe0505180, + 0x781d0300, 0xbf8903f7, + 0x7e008500, 0x7e028501, + 0x7e048502, 0x7e068503, + 0x807d847d, 0x8078ff78, + 0x00000200, 0xbf0a6f7d, + 0xbfa2ffee, 0xe0505000, + 0x6e1d0000, 0xe0505080, + 0x6e1d0100, 0xe0505100, + 0x6e1d0200, 0xe0505180, + 0x6e1d0300, 0xbf8903f7, + 0xbfa00034, 0xbef600ff, + 0x01000000, 0xbeee0078, + 0x8078ff78, 0x00000400, + 0xbefd0084, 0xbf0a6f7d, + 0xbfa10012, 0xe0505000, + 0x781d0000, 0xe0505100, + 0x781d0100, 0xe0505200, + 0x781d0200, 0xe0505300, + 0x781d0300, 0xbf8903f7, + 0x7e008500, 0x7e028501, + 0x7e048502, 0x7e068503, + 0x807d847d, 0x8078ff78, + 0x00000400, 0xbf0a6f7d, + 0xbfa2ffee, 0xb8ef1e06, + 0x8b6fc16f, 0xbfa1000e, + 0x846f836f, 0x806f7d6f, + 0xbefe00c1, 0xbeff0080, 0xe0505000, 0x781d0000, - 0xe0505080, 0x781d0100, - 0xe0505100, 0x781d0200, - 0xe0505180, 0x781d0300, 0xbf8903f7, 0x7e008500, - 0x7e028501, 0x7e048502, - 0x7e068503, 0x807d847d, - 0x8078ff78, 0x00000200, - 0xbf0a6f7d, 0xbfa2ffee, + 0x807d817d, 0x8078ff78, + 0x00000080, 0xbf0a6f7d, + 0xbfa2fff7, 0xbeff00c1, 0xe0505000, 0x6e1d0000, - 0xe0505080, 0x6e1d0100, - 0xe0505100, 0x6e1d0200, - 0xe0505180, 0x6e1d0300, - 0xbf8903f7, 0xbfa00034, - 0xbef600ff, 0x01000000, - 0xbeee0078, 0x8078ff78, - 0x00000400, 0xbefd0084, - 0xbf0a6f7d, 0xbfa10012, - 0xe0505000, 0x781d0000, - 0xe0505100, 0x781d0100, - 0xe0505200, 0x781d0200, - 0xe0505300, 0x781d0300, - 0xbf8903f7, 0x7e008500, - 0x7e028501, 0x7e048502, - 0x7e068503, 0x807d847d, - 0x8078ff78, 0x00000400, - 0xbf0a6f7d, 0xbfa2ffee, - 0xb8ef1e06, 0x8b6fc16f, - 0xbfa1000e, 0x846f836f, - 0x806f7d6f, 0xbefe00c1, - 0xbeff0080, 0xe0505000, - 0x781d0000, 0xbf8903f7, - 0x7e008500, 0x807d817d, - 0x8078ff78, 0x00000080, - 0xbf0a6f7d, 0xbfa2fff7, - 0xbeff00c1, 0xe0505000, - 0x6e1d0000, 0xe0505100, - 0x6e1d0100, 0xe0505200, - 0x6e1d0200, 0xe0505300, - 0x6e1d0300, 0xbf8903f7, + 0xe0505100, 0x6e1d0100, + 0xe0505200, 0x6e1d0200, + 0xe0505300, 0x6e1d0300, + 0xbf8903f7, 0xb8f83b05, + 0x80788178, 0xbf0d9972, + 0xbfa20002, 0x84788978, + 0xbfa00001, 0x84788a78, + 0xb8ee1e06, 0x846e8a6e, + 0x80786e78, 0x8078ff78, + 0x00000200, 0x80f8ff78, + 0x00000050, 0xbef600ff, + 0x01000000, 0xbefd00ff, + 0x0000006c, 0x80f89078, + 0xf428403a, 0xf0000000, + 0xbf89fc07, 0x80fd847d, + 0xbf800000, 0xbe804300, + 0xbe824302, 0x80f8a078, + 0xf42c403a, 0xf0000000, + 0xbf89fc07, 0x80fd887d, + 0xbf800000, 0xbe804300, + 0xbe824302, 0xbe844304, + 0xbe864306, 0x80f8c078, + 0xf430403a, 0xf0000000, + 0xbf89fc07, 0x80fd907d, + 0xbf800000, 0xbe804300, + 0xbe824302, 0xbe844304, + 0xbe864306, 0xbe884308, + 0xbe8a430a, 0xbe8c430c, + 0xbe8e430e, 0xbf06807d, + 0xbfa1fff0, 0xb980f801, + 0x00000000, 0xbfbd0000, 0xb8f83b05, 0x80788178, 0xbf0d9972, 0xbfa20002, 0x84788978, 0xbfa00001, 0x84788a78, 0xb8ee1e06, 0x846e8a6e, 0x80786e78, 0x8078ff78, 0x00000200, - 0x80f8ff78, 0x00000050, 0xbef600ff, 0x01000000, - 0xbefd00ff, 0x0000006c, - 0x80f89078, 0xf428403a, - 0xf0000000, 0xbf89fc07, - 0x80fd847d, 0xbf800000, - 0xbe804300, 0xbe824302, - 0x80f8a078, 0xf42c403a, - 0xf0000000, 0xbf89fc07, - 0x80fd887d, 0xbf800000, - 0xbe804300, 0xbe824302, - 0xbe844304, 0xbe864306, - 0x80f8c078, 0xf430403a, - 0xf0000000, 0xbf89fc07, - 0x80fd907d, 0xbf800000, - 0xbe804300, 0xbe824302, - 0xbe844304, 0xbe864306, - 0xbe884308, 0xbe8a430a, - 0xbe8c430c, 0xbe8e430e, - 0xbf06807d, 0xbfa1fff0, - 0xb980f801, 0x00000000, - 0xbfbd0000, 0xb8f83b05, - 0x80788178, 0xbf0d9972, - 0xbfa20002, 0x84788978, - 0xbfa00001, 0x84788a78, - 0xb8ee1e06, 0x846e8a6e, - 0x80786e78, 0x8078ff78, - 0x00000200, 0xbef600ff, - 0x01000000, 0xf4205bfa, + 0xf4205bfa, 0xf0000000, + 0x80788478, 0xf4205b3a, 0xf0000000, 0x80788478, - 0xf4205b3a, 0xf0000000, - 0x80788478, 0xf4205b7a, + 0xf4205b7a, 0xf0000000, + 0x80788478, 0xf4205c3a, 0xf0000000, 0x80788478, - 0xf4205c3a, 0xf0000000, - 0x80788478, 0xf4205c7a, + 0xf4205c7a, 0xf0000000, + 0x80788478, 0xf4205eba, 0xf0000000, 0x80788478, - 0xf4205eba, 0xf0000000, - 0x80788478, 0xf4205efa, + 0xf4205efa, 0xf0000000, + 0x80788478, 0xf4205e7a, 0xf0000000, 0x80788478, - 0xf4205e7a, 0xf0000000, - 0x80788478, 0xf4205cfa, + 0xf4205cfa, 0xf0000000, + 0x80788478, 0xf4205bba, 0xf0000000, 0x80788478, + 0xbf89fc07, 0xb96ef814, 0xf4205bba, 0xf0000000, 0x80788478, 0xbf89fc07, - 0xb96ef814, 0xf4205bba, - 0xf0000000, 0x80788478, - 0xbf89fc07, 0xb96ef815, - 0xbefd006f, 0xbefe0070, - 0xbeff0071, 0x8b6f7bff, - 0x000003ff, 0xb96f4803, - 0x8b6f7bff, 0xfffff800, - 0x856f8b6f, 0xb96fa2c3, - 0xb973f801, 0xb8ee3b05, - 0x806e816e, 0xbf0d9972, - 0xbfa20002, 0x846e896e, - 0xbfa00001, 0x846e8a6e, - 0xb8ef1e06, 0x846f8a6f, - 0x806e6f6e, 0x806eff6e, - 0x00000200, 0x806e746e, - 0x826f8075, 0x8b6fff6f, - 0x0000ffff, 0xf4085c37, - 0xf8000050, 0xf4085d37, - 0xf8000060, 0xf4005e77, - 0xf8000074, 0xbf89fc07, - 0x8b6dff6d, 0x0000ffff, - 0x8bfe7e7e, 0x8bea6a6a, + 0xb96ef815, 0xbefd006f, + 0xbefe0070, 0xbeff0071, + 0x8b6f7bff, 0x000003ff, + 0xb96f4803, 0x8b6f7bff, + 0xfffff800, 0x856f8b6f, + 0xb96fa2c3, 0xb973f801, + 0xb8ee3b05, 0x806e816e, + 0xbf0d9972, 0xbfa20002, + 0x846e896e, 0xbfa00001, + 0x846e8a6e, 0xb8ef1e06, + 0x846f8a6f, 0x806e6f6e, + 0x806eff6e, 0x00000200, + 0x806e746e, 0x826f8075, + 0x8b6fff6f, 0x0000ffff, + 0xf4085c37, 0xf8000050, + 0xf4085d37, 0xf8000060, + 0xf4005e77, 0xf8000074, + 0xbf89fc07, 0x8b6dff6d, + 0x0000ffff, 0x8bfe7e7e, + 0x8bea6a6a, 0xb8eef802, + 0xbf0d866e, 0xbfa20002, + 0xb97af802, 0xbe80486c, 0xb97af802, 0xbe804a6c, 0xbfb00000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index 250ab007399b..0f81670f6f9c 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -43,12 +43,14 @@ #define HAVE_XNACK (ASIC_FAMILY < CHIP_SIENNA_CICHLID) #define HAVE_SENDMSG_RTN (ASIC_FAMILY >= CHIP_PLUM_BONITO) #define HAVE_BUFFER_LDS_LOAD (ASIC_FAMILY < CHIP_PLUM_BONITO) +#define SW_SA_TRAP (ASIC_FAMILY >= CHIP_PLUM_BONITO) var SINGLE_STEP_MISSED_WORKAROUND = 1 //workaround for lost MODE.DEBUG_EN exception when SAVECTX raised var SQ_WAVE_STATUS_SPI_PRIO_MASK = 0x00000006 var SQ_WAVE_STATUS_HALT_MASK = 0x2000 var SQ_WAVE_STATUS_ECC_ERR_MASK = 0x20000 +var SQ_WAVE_STATUS_TRAP_EN_SHIFT = 6 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT = 12 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE = 9 @@ -183,6 +185,13 @@ L_SKIP_RESTORE: s_getreg_b32 s_save_trapsts, hwreg(HW_REG_TRAPSTS) +#if SW_SA_TRAP + // If ttmp1[31] is set then trap may occur early. + // Spin wait until SAVECTX exception is raised. + s_bitcmp1_b32 s_save_pc_hi, 31 + s_cbranch_scc1 L_CHECK_SAVE +#endif + s_and_b32 ttmp2, s_save_status, SQ_WAVE_STATUS_HALT_MASK s_cbranch_scc0 L_NOT_HALTED @@ -1061,8 +1070,20 @@ L_RESTORE_HWREG: s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff //pc[47:32] //Do it here in order not to affect STATUS s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 + +#if SW_SA_TRAP + // If traps are enabled then return to the shader with PRIV=0. + // Otherwise retain PRIV=1 for subsequent context save requests. + s_getreg_b32 s_restore_tmp, hwreg(HW_REG_STATUS) + s_bitcmp1_b32 s_restore_tmp, SQ_WAVE_STATUS_TRAP_EN_SHIFT + s_cbranch_scc1 L_RETURN_WITHOUT_PRIV + s_setreg_b32 hwreg(HW_REG_STATUS), s_restore_status // SCC is included, which is changed by previous salu + s_setpc_b64 [s_restore_pc_lo, s_restore_pc_hi] +L_RETURN_WITHOUT_PRIV: +#endif + s_setreg_b32 hwreg(HW_REG_STATUS), s_restore_status // SCC is included, which is changed by previous salu s_rfe_b64 s_restore_pc_lo //Return to the main shader program and resume execution L_END_PGM: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 84da1a9ce37c..5feaba6a77de 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1584,6 +1584,8 @@ static int kfd_ioctl_smi_events(struct file *filep, return kfd_smi_event_open(pdd->dev, &args->anon_fd); } +#if IS_ENABLED(CONFIG_HSA_AMD_SVM) + static int kfd_ioctl_set_xnack_mode(struct file *filep, struct kfd_process *p, void *data) { @@ -1594,22 +1596,29 @@ static int kfd_ioctl_set_xnack_mode(struct file *filep, if (args->xnack_enabled >= 0) { if (!list_empty(&p->pqm.queues)) { pr_debug("Process has user queues running\n"); - mutex_unlock(&p->mutex); - return -EBUSY; + r = -EBUSY; + goto out_unlock; } - if (args->xnack_enabled && !kfd_process_xnack_mode(p, true)) + + if (p->xnack_enabled == args->xnack_enabled) + goto out_unlock; + + if (args->xnack_enabled && !kfd_process_xnack_mode(p, true)) { r = -EPERM; - else - p->xnack_enabled = args->xnack_enabled; + goto out_unlock; + } + + r = svm_range_switch_xnack_reserve_mem(p, args->xnack_enabled); } else { args->xnack_enabled = p->xnack_enabled; } + +out_unlock: mutex_unlock(&p->mutex); return r; } -#if IS_ENABLED(CONFIG_HSA_AMD_SVM) static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data) { struct kfd_ioctl_svm_args *args = data; @@ -1629,6 +1638,11 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data) return r; } #else +static int kfd_ioctl_set_xnack_mode(struct file *filep, + struct kfd_process *p, void *data) +{ + return -EPERM; +} static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data) { return -EPERM; @@ -2153,6 +2167,12 @@ static int criu_restore_devices(struct kfd_process *p, ret = PTR_ERR(pdd); goto exit; } + + if (!pdd->doorbell_index && + kfd_alloc_process_doorbells(pdd->dev, &pdd->doorbell_index) < 0) { + ret = -ENOMEM; + goto exit; + } } /* diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 24b414cff3ec..cd5f8b219bf9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -2284,7 +2284,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image, /* Fill in Subtype: IO_LINKS * Only direct links are added here which is Link from GPU to - * to its NUMA node. Indirect links are added by userspace. + * its NUMA node. Indirect links are added by userspace. */ sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr + cache_mem_filled); 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..ecb4c3abc629 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; @@ -1240,6 +1242,24 @@ static void init_interrupts(struct device_queue_manager *dqm) dqm->dev->kfd2kgd->init_interrupts(dqm->dev->adev, i); } +static void init_sdma_bitmaps(struct device_queue_manager *dqm) +{ + unsigned int num_sdma_queues = + min_t(unsigned int, sizeof(dqm->sdma_bitmap)*8, + get_num_sdma_queues(dqm)); + unsigned int num_xgmi_sdma_queues = + min_t(unsigned int, sizeof(dqm->xgmi_sdma_bitmap)*8, + get_num_xgmi_sdma_queues(dqm)); + + if (num_sdma_queues) + dqm->sdma_bitmap = GENMASK_ULL(num_sdma_queues-1, 0); + if (num_xgmi_sdma_queues) + dqm->xgmi_sdma_bitmap = GENMASK_ULL(num_xgmi_sdma_queues-1, 0); + + dqm->sdma_bitmap &= ~get_reserved_sdma_queues_bitmap(dqm); + pr_info("sdma_bitmap: %llx\n", dqm->sdma_bitmap); +} + static int initialize_nocpsch(struct device_queue_manager *dqm) { int pipe, queue; @@ -1268,11 +1288,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm) memset(dqm->vmid_pasid, 0, sizeof(dqm->vmid_pasid)); - dqm->sdma_bitmap = ~0ULL >> (64 - get_num_sdma_queues(dqm)); - dqm->sdma_bitmap &= ~(get_reserved_sdma_queues_bitmap(dqm)); - pr_info("sdma_bitmap: %llx\n", dqm->sdma_bitmap); - - dqm->xgmi_sdma_bitmap = ~0ULL >> (64 - get_num_xgmi_sdma_queues(dqm)); + init_sdma_bitmaps(dqm); return 0; } @@ -1450,9 +1466,6 @@ static int set_sched_resources(struct device_queue_manager *dqm) static int initialize_cpsch(struct device_queue_manager *dqm) { - uint64_t num_sdma_queues; - uint64_t num_xgmi_sdma_queues; - pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm)); mutex_init(&dqm->lock_hidden); @@ -1461,24 +1474,10 @@ static int initialize_cpsch(struct device_queue_manager *dqm) dqm->active_cp_queue_count = 0; dqm->gws_queue_count = 0; dqm->active_runlist = false; - - num_sdma_queues = get_num_sdma_queues(dqm); - if (num_sdma_queues >= BITS_PER_TYPE(dqm->sdma_bitmap)) - dqm->sdma_bitmap = ULLONG_MAX; - else - dqm->sdma_bitmap = (BIT_ULL(num_sdma_queues) - 1); - - dqm->sdma_bitmap &= ~(get_reserved_sdma_queues_bitmap(dqm)); - pr_info("sdma_bitmap: %llx\n", dqm->sdma_bitmap); - - num_xgmi_sdma_queues = get_num_xgmi_sdma_queues(dqm); - if (num_xgmi_sdma_queues >= BITS_PER_TYPE(dqm->xgmi_sdma_bitmap)) - dqm->xgmi_sdma_bitmap = ULLONG_MAX; - else - dqm->xgmi_sdma_bitmap = (BIT_ULL(num_xgmi_sdma_queues) - 1); - INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception); + init_sdma_bitmaps(dqm); + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index b33798f89ef0..cd4e61bf0493 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -303,6 +303,9 @@ int kfd_alloc_process_doorbells(struct kfd_dev *kfd, unsigned int *doorbell_inde if (r > 0) *doorbell_index = r; + if (r < 0) + pr_err("Failed to allocate process doorbells\n"); + return r; } 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_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index b059a77b6081..2797029bd500 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - lock_page(page); + zone_device_page_init(page); } static void @@ -322,12 +322,13 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, for (i = j = 0; i < npages; i++) { struct page *spage; + dst[i] = cursor.start + (j << PAGE_SHIFT); + migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); + svm_migrate_get_vram_page(prange, migrate->dst[i]); + migrate->dst[i] = migrate_pfn(migrate->dst[i]); + spage = migrate_pfn_to_page(migrate->src[i]); if (spage && !is_zone_device_page(spage)) { - dst[i] = cursor.start + (j << PAGE_SHIFT); - migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); - svm_migrate_get_vram_page(prange, migrate->dst[i]); - migrate->dst[i] = migrate_pfn(migrate->dst[i]); src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, DMA_TO_DEVICE); r = dma_mapping_error(dev, src[i]); @@ -409,7 +410,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t npages = (end - start) >> PAGE_SHIFT; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; dma_addr_t *scratch; void *buf; @@ -522,9 +523,6 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("svms 0x%p [0x%lx 0x%lx] to gpu 0x%x\n", prange->svms, prange->start, prange->last, best_loc); - /* FIXME: workaround for page locking bug with invalid pages */ - svm_range_prefault(prange, mm, SVM_ADEV_PGMAP_OWNER(adev)); - start = prange->start << PAGE_SHIFT; end = (prange->last + 1) << PAGE_SHIFT; @@ -668,7 +666,7 @@ out_oom: static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; @@ -676,7 +674,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, unsigned long cpages = 0; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -699,6 +697,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.src = buf; migrate.dst = migrate.src + npages; + migrate.fault_page = fault_page; scratch = (dma_addr_t *)(migrate.dst + npages); kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid, @@ -766,7 +765,7 @@ out: * 0 - OK, otherwise error code */ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct amdgpu_device *adev; struct vm_area_struct *vma; @@ -807,7 +806,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, } next = min(vma->vm_end, end); - r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger); + r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger, + fault_page); if (r < 0) { pr_debug("failed %ld to migrate prange %p\n", r, prange); break; @@ -851,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc); do { - r = svm_migrate_vram_to_ram(prange, mm, trigger); + r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL); if (r) return r; } while (prange->actual_loc && --retries); @@ -886,7 +886,7 @@ svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc, static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) { unsigned long addr = vmf->address; - struct vm_area_struct *vma; + struct svm_range_bo *svm_bo; enum svm_work_list_ops op; struct svm_range *parent; struct svm_range *prange; @@ -894,29 +894,42 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) struct mm_struct *mm; int r = 0; - vma = vmf->vma; - mm = vma->vm_mm; + svm_bo = vmf->page->zone_device_data; + if (!svm_bo) { + pr_debug("failed get device page at addr 0x%lx\n", addr); + return VM_FAULT_SIGBUS; + } + if (!mmget_not_zero(svm_bo->eviction_fence->mm)) { + pr_debug("addr 0x%lx of process mm is destroyed\n", addr); + return VM_FAULT_SIGBUS; + } + + mm = svm_bo->eviction_fence->mm; + if (mm != vmf->vma->vm_mm) + pr_debug("addr 0x%lx is COW mapping in child process\n", addr); - p = kfd_lookup_process_by_mm(vma->vm_mm); + p = kfd_lookup_process_by_mm(mm); if (!p) { pr_debug("failed find process at fault address 0x%lx\n", addr); - return VM_FAULT_SIGBUS; + r = VM_FAULT_SIGBUS; + goto out_mmput; } if (READ_ONCE(p->svms.faulting_task) == current) { pr_debug("skipping ram migration\n"); - kfd_unref_process(p); - return 0; + r = 0; + goto out_unref_process; } - addr >>= PAGE_SHIFT; + pr_debug("CPU page fault svms 0x%p address 0x%lx\n", &p->svms, addr); + addr >>= PAGE_SHIFT; mutex_lock(&p->svms.lock); prange = svm_range_from_addr(&p->svms, addr, &parent); if (!prange) { - pr_debug("cannot find svm range at 0x%lx\n", addr); + pr_debug("failed get range svms 0x%p addr 0x%lx\n", &p->svms, addr); r = -EFAULT; - goto out; + goto out_unlock_svms; } mutex_lock(&parent->migrate_mutex); @@ -938,10 +951,12 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) goto out_unlock_prange; } - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU); + r = svm_migrate_vram_to_ram(prange, vmf->vma->vm_mm, + KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + vmf->page); if (r) - pr_debug("failed %d migrate 0x%p [0x%lx 0x%lx] to ram\n", r, - prange, prange->start, prange->last); + pr_debug("failed %d migrate svms 0x%p range 0x%p [0x%lx 0x%lx]\n", + r, prange->svms, prange, prange->start, prange->last); /* xnack on, update mapping on GPUs with ACCESS_IN_PLACE */ if (p->xnack_enabled && parent == prange) @@ -955,9 +970,12 @@ out_unlock_prange: if (prange != parent) mutex_unlock(&prange->migrate_mutex); mutex_unlock(&parent->migrate_mutex); -out: +out_unlock_svms: mutex_unlock(&p->svms.lock); +out_unref_process: kfd_unref_process(p); +out_mmput: + mmput(mm); pr_debug("CPU fault svms 0x%p address 0x%lx done\n", &p->svms, addr); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index b3f0754b32fa..a5d7e6d22264 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR { int svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc, struct mm_struct *mm, uint32_t trigger); int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger); + uint32_t trigger, struct page *fault_page); unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); 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..4f6390f3236e 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; @@ -177,14 +181,6 @@ static int load_mqd(struct mqd_manager *mm, void *mqd, return r; } -static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd, - uint32_t pipe_id, uint32_t queue_id, - struct queue_properties *p, struct mm_struct *mms) -{ - return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->adev, mqd, pipe_id, - queue_id, p->doorbell_off); -} - static void update_mqd(struct mqd_manager *mm, void *mqd, struct queue_properties *q, struct mqd_update_info *minfo) @@ -256,31 +252,6 @@ static uint32_t read_doorbell_id(void *mqd) return m->queue_doorbell_id0; } -static int destroy_mqd(struct mqd_manager *mm, void *mqd, - enum kfd_preempt_type type, - unsigned int timeout, uint32_t pipe_id, - uint32_t queue_id) -{ - return mm->dev->kfd2kgd->hqd_destroy - (mm->dev->adev, mqd, type, timeout, - pipe_id, queue_id); -} - -static void free_mqd(struct mqd_manager *mm, void *mqd, - struct kfd_mem_obj *mqd_mem_obj) -{ - kfd_gtt_sa_free(mm->dev, mqd_mem_obj); -} - -static bool is_occupied(struct mqd_manager *mm, void *mqd, - uint64_t queue_address, uint32_t pipe_id, - uint32_t queue_id) -{ - return mm->dev->kfd2kgd->hqd_is_occupied( - mm->dev->adev, queue_address, - pipe_id, queue_id); -} - static int get_wave_state(struct mqd_manager *mm, void *mqd, void __user *ctl_stack, u32 *ctl_stack_used_size, @@ -349,15 +320,6 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, mm->update_mqd(mm, m, q, NULL); } -static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, - uint32_t pipe_id, uint32_t queue_id, - struct queue_properties *p, struct mm_struct *mms) -{ - return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd, - (uint32_t __user *)p->write_ptr, - mms); -} - #define SDMA_RLC_DUMMY_DEFAULT 0xf static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, @@ -371,7 +333,8 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, << SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT | q->vmid << SDMA0_QUEUE0_RB_CNTL__RB_VMID__SHIFT | 1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT | - 6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT; + 6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT | + 1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT; m->sdmax_rlcx_rb_base = lower_32_bits(q->queue_address >> 8); m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8); @@ -389,25 +352,6 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, q->is_active = QUEUE_IS_ACTIVE(*q); } -/* - * * preempt type here is ignored because there is only one way - * * to preempt sdma queue - */ -static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd, - enum kfd_preempt_type type, - unsigned int timeout, uint32_t pipe_id, - uint32_t queue_id) -{ - return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout); -} - -static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd, - uint64_t queue_address, uint32_t pipe_id, - uint32_t queue_id) -{ - return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd); -} - #if defined(CONFIG_DEBUG_FS) static int debugfs_show_mqd(struct seq_file *m, void *data) @@ -445,11 +389,11 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, pr_debug("%s@%i\n", __func__, __LINE__); mqd->allocate_mqd = allocate_mqd; mqd->init_mqd = init_mqd; - mqd->free_mqd = free_mqd; + mqd->free_mqd = kfd_free_mqd_cp; mqd->load_mqd = load_mqd; mqd->update_mqd = update_mqd; - mqd->destroy_mqd = destroy_mqd; - mqd->is_occupied = is_occupied; + mqd->destroy_mqd = kfd_destroy_mqd_cp; + mqd->is_occupied = kfd_is_occupied_cp; mqd->mqd_size = sizeof(struct v11_compute_mqd); mqd->get_wave_state = get_wave_state; #if defined(CONFIG_DEBUG_FS) @@ -462,10 +406,10 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, mqd->allocate_mqd = allocate_hiq_mqd; mqd->init_mqd = init_mqd_hiq; mqd->free_mqd = free_mqd_hiq_sdma; - mqd->load_mqd = hiq_load_mqd_kiq; + mqd->load_mqd = kfd_hiq_load_mqd_kiq; mqd->update_mqd = update_mqd; - mqd->destroy_mqd = destroy_mqd; - mqd->is_occupied = is_occupied; + mqd->destroy_mqd = kfd_destroy_mqd_cp; + mqd->is_occupied = kfd_is_occupied_cp; mqd->mqd_size = sizeof(struct v11_compute_mqd); #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd; @@ -476,11 +420,11 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, case KFD_MQD_TYPE_DIQ: mqd->allocate_mqd = allocate_mqd; mqd->init_mqd = init_mqd_hiq; - mqd->free_mqd = free_mqd; + mqd->free_mqd = kfd_free_mqd_cp; mqd->load_mqd = load_mqd; mqd->update_mqd = update_mqd; - mqd->destroy_mqd = destroy_mqd; - mqd->is_occupied = is_occupied; + mqd->destroy_mqd = kfd_destroy_mqd_cp; + mqd->is_occupied = kfd_is_occupied_cp; mqd->mqd_size = sizeof(struct v11_compute_mqd); #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd; @@ -491,10 +435,10 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, mqd->allocate_mqd = allocate_sdma_mqd; mqd->init_mqd = init_mqd_sdma; mqd->free_mqd = free_mqd_hiq_sdma; - mqd->load_mqd = load_mqd_sdma; + mqd->load_mqd = kfd_load_mqd_sdma; mqd->update_mqd = update_mqd_sdma; - mqd->destroy_mqd = destroy_mqd_sdma; - mqd->is_occupied = is_occupied_sdma; + mqd->destroy_mqd = kfd_destroy_mqd_sdma; + mqd->is_occupied = kfd_is_occupied_sdma; mqd->mqd_size = sizeof(struct v11_sdma_mqd); #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd_sdma; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 6e3e7f54381b..5137476ec18e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -857,6 +857,13 @@ int kfd_criu_restore_queue(struct kfd_process *p, ret = -EINVAL; goto exit; } + + if (!pdd->doorbell_index && + kfd_alloc_process_doorbells(pdd->dev, &pdd->doorbell_index) < 0) { + ret = -ENOMEM; + goto exit; + } + /* data stored in this order: mqd, ctl_stack */ mqd = q_extra_data; ctl_stack = mqd + q_data->mqd_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 11074cc8c333..64fdf63093a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -278,7 +278,7 @@ static void svm_range_free(struct svm_range *prange, bool update_mem_usage) svm_range_free_dma_mappings(prange); if (update_mem_usage && !p->xnack_enabled) { - pr_debug("unreserve mem limit: %lld\n", size); + pr_debug("unreserve prange 0x%p size: 0x%llx\n", prange, size); amdgpu_amdkfd_unreserve_mem_limit(NULL, size, KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); } @@ -2913,13 +2913,15 @@ retry_write_locked: */ if (prange->actual_loc) r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); else r = 0; } } else { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); } if (r) { pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n", @@ -2956,6 +2958,64 @@ out: return r; } +int +svm_range_switch_xnack_reserve_mem(struct kfd_process *p, bool xnack_enabled) +{ + struct svm_range *prange, *pchild; + uint64_t reserved_size = 0; + uint64_t size; + int r = 0; + + pr_debug("switching xnack from %d to %d\n", p->xnack_enabled, xnack_enabled); + + mutex_lock(&p->svms.lock); + + list_for_each_entry(prange, &p->svms.list, list) { + svm_range_lock(prange); + list_for_each_entry(pchild, &prange->child_list, child_list) { + size = (pchild->last - pchild->start + 1) << PAGE_SHIFT; + if (xnack_enabled) { + amdgpu_amdkfd_unreserve_mem_limit(NULL, size, + KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); + } else { + r = amdgpu_amdkfd_reserve_mem_limit(NULL, size, + KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); + if (r) + goto out_unlock; + reserved_size += size; + } + } + + size = (prange->last - prange->start + 1) << PAGE_SHIFT; + if (xnack_enabled) { + amdgpu_amdkfd_unreserve_mem_limit(NULL, size, + KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); + } else { + r = amdgpu_amdkfd_reserve_mem_limit(NULL, size, + KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); + if (r) + goto out_unlock; + reserved_size += size; + } +out_unlock: + svm_range_unlock(prange); + if (r) + break; + } + + if (r) + amdgpu_amdkfd_unreserve_mem_limit(NULL, reserved_size, + KFD_IOC_ALLOC_MEM_FLAGS_USERPTR); + else + /* Change xnack mode must be inside svms lock, to avoid race with + * svm_range_deferred_list_work unreserve memory in parallel. + */ + p->xnack_enabled = xnack_enabled; + + mutex_unlock(&p->svms.lock); + return r; +} + void svm_range_list_fini(struct kfd_process *p) { struct svm_range *prange; @@ -3181,28 +3241,6 @@ out: return best_loc; } -/* FIXME: This is a workaround for page locking bug when some pages are - * invalid during migration to VRAM - */ -void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm, - void *owner) -{ - struct hmm_range *hmm_range; - int r; - - if (prange->validated_once) - return; - - r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, - prange->start << PAGE_SHIFT, - prange->npages, &hmm_range, - false, true, owner); - if (!r) { - amdgpu_hmm_range_get_pages_done(hmm_range); - prange->validated_once = true; - } -} - /* svm_range_trigger_migration - start page migration if prefetch loc changed * @mm: current process mm_struct * @prange: svm range structure @@ -3242,7 +3280,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, return 0; if (!best_loc) { - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); + r = svm_migrate_vram_to_ram(prange, mm, + KFD_MIGRATE_TRIGGER_PREFETCH, NULL); *migrated = !r; return r; } @@ -3303,7 +3342,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mutex_lock(&prange->migrate_mutex); do { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_TTM_EVICTION); + KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL); } while (!r && prange->actual_loc && --retries); if (!r && prange->actual_loc) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h index cfac13ad06ef..7a33b93f9df6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h @@ -181,8 +181,6 @@ void schedule_deferred_list_work(struct svm_range_list *svms); void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr, unsigned long offset, unsigned long npages); void svm_range_free_dma_mappings(struct svm_range *prange); -void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm, - void *owner); int svm_range_get_info(struct kfd_process *p, uint32_t *num_svm_ranges, uint64_t *svm_priv_data_size); int kfd_criu_checkpoint_svm(struct kfd_process *p, @@ -205,6 +203,7 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s void svm_range_bo_unref_async(struct svm_range_bo *svm_bo); void svm_range_set_max_pages(struct amdgpu_device *adev); +int svm_range_switch_xnack_reserve_mem(struct kfd_process *p, bool xnack_enabled); #else diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 413d8c6d592f..6925e0280dbe 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -28,7 +28,6 @@ config DRM_AMD_DC_SI bool "AMD DC support for Southern Islands ASICs" depends on DRM_AMDGPU_SI depends on DRM_AMD_DC - default n help Choose this option to enable new AMD DC support for SI asics by default. This includes Tahiti, Pitcairn, Cape Verde, Oland. @@ -43,7 +42,6 @@ config DEBUG_KERNEL_DC config DRM_AMD_SECURE_DISPLAY bool "Enable secure display support" - default n depends on DEBUG_FS depends on DRM_AMD_DC_DCN help 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 7b19f444624c..c053cb79cd06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -100,8 +100,6 @@ #include "soc15_common.h" #include "vega10_ip_offset.h" -#include "soc15_common.h" - #include "gc/gc_11_0_0_offset.h" #include "gc/gc_11_0_0_sh_mask.h" @@ -1112,7 +1110,8 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) hw_params.fb[i] = &fb_info->fb[i]; switch (adev->ip_versions[DCE_HWIP][0]) { - case IP_VERSION(3, 1, 3): /* Only for this asic hw internal rev B0 */ + case IP_VERSION(3, 1, 3): + case IP_VERSION(3, 1, 4): hw_params.dpia_supported = true; hw_params.disable_dpia = adev->dm.dc->debug.dpia_debug.bits.disable_dpia; break; @@ -1298,13 +1297,21 @@ static struct hpd_rx_irq_offload_work_queue *hpd_rx_irq_create_workqueue(struct if (hpd_rx_offload_wq[i].wq == NULL) { DRM_ERROR("create amdgpu_dm_hpd_rx_offload_wq fail!"); - return NULL; + goto out_err; } spin_lock_init(&hpd_rx_offload_wq[i].offload_lock); } return hpd_rx_offload_wq; + +out_err: + for (i = 0; i < max_caps; i++) { + if (hpd_rx_offload_wq[i].wq) + destroy_workqueue(hpd_rx_offload_wq[i].wq); + } + kfree(hpd_rx_offload_wq); + return NULL; } struct amdgpu_stutter_quirk { @@ -4742,7 +4749,7 @@ 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); @@ -4810,7 +4817,7 @@ 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; /* @@ -7379,11 +7386,6 @@ static void update_freesync_state_on_stream( &vrr_infopacket, pack_sdp_v1_3); - new_crtc_state->freesync_timing_changed |= - (memcmp(&acrtc->dm_irq_params.vrr_params.adjust, - &vrr_params.adjust, - sizeof(vrr_params.adjust)) != 0); - new_crtc_state->freesync_vrr_info_changed |= (memcmp(&new_crtc_state->vrr_infopacket, &vrr_infopacket, @@ -7392,7 +7394,6 @@ static void update_freesync_state_on_stream( acrtc->dm_irq_params.vrr_params = vrr_params; new_crtc_state->vrr_infopacket = vrr_infopacket; - new_stream->adjust = acrtc->dm_irq_params.vrr_params.adjust; new_stream->vrr_infopacket = vrr_infopacket; if (new_crtc_state->freesync_vrr_info_changed) @@ -7455,10 +7456,6 @@ static void update_stream_irq_parameters( new_stream, &config, &vrr_params); - new_crtc_state->freesync_timing_changed |= - (memcmp(&acrtc->dm_irq_params.vrr_params.adjust, - &vrr_params.adjust, sizeof(vrr_params.adjust)) != 0); - new_crtc_state->freesync_config = config; /* Copy state for access from DM IRQ handler */ acrtc->dm_irq_params.freesync_config = config; @@ -7482,15 +7479,15 @@ static void amdgpu_dm_handle_vrr_transition(struct dm_crtc_state *old_state, * We also need vupdate irq for the actual core vblank handling * at end of vblank. */ - dm_set_vupdate_irq(new_state->base.crtc, true); - drm_crtc_vblank_get(new_state->base.crtc); + WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, true) != 0); + WARN_ON(drm_crtc_vblank_get(new_state->base.crtc) != 0); DRM_DEBUG_DRIVER("%s: crtc=%u VRR off->on: Get vblank ref\n", __func__, new_state->base.crtc->base.id); } else if (old_vrr_active && !new_vrr_active) { /* Transition VRR active -> inactive: * Allow vblank irq disable again for fixed refresh rate. */ - dm_set_vupdate_irq(new_state->base.crtc, false); + WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, false) != 0); drm_crtc_vblank_put(new_state->base.crtc); DRM_DEBUG_DRIVER("%s: crtc=%u VRR on->off: Drop vblank ref\n", __func__, new_state->base.crtc->base.id); @@ -8246,23 +8243,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) mutex_unlock(&dm->dc_lock); } - /* Count number of newly disabled CRTCs for dropping PM refs later. */ - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { - if (old_crtc_state->active && !new_crtc_state->active) - crtc_disable_count++; - - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); - dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); - - /* For freesync config update on crtc state and params for irq */ - update_stream_irq_parameters(dm, dm_new_crtc_state); - - /* Handle vrr on->off / off->on transitions */ - amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, - dm_new_crtc_state); - } - /** * Enable interrupts for CRTCs that are newly enabled or went through * a modeset. It was intentionally deferred until after the front end @@ -8272,16 +8252,29 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); #ifdef CONFIG_DEBUG_FS - bool configure_crc = false; enum amdgpu_dm_pipe_crc_source cur_crc_src; #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - struct crc_rd_work *crc_rd_wrk = dm->crc_rd_wrk; + struct crc_rd_work *crc_rd_wrk; +#endif +#endif + /* Count number of newly disabled CRTCs for dropping PM refs later. */ + if (old_crtc_state->active && !new_crtc_state->active) + crtc_disable_count++; + + dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); + dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); + + /* For freesync config update on crtc state and params for irq */ + update_stream_irq_parameters(dm, dm_new_crtc_state); + +#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + crc_rd_wrk = dm->crc_rd_wrk; #endif spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); cur_crc_src = acrtc->dm_irq_params.crc_src; spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); #endif - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); if (new_crtc_state->active && (!old_crtc_state->active || @@ -8289,16 +8282,19 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dc_stream_retain(dm_new_crtc_state->stream); acrtc->dm_irq_params.stream = dm_new_crtc_state->stream; manage_dm_interrupts(adev, acrtc, true); + } + /* Handle vrr on->off / off->on transitions */ + amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, dm_new_crtc_state); #ifdef CONFIG_DEBUG_FS + if (new_crtc_state->active && + (!old_crtc_state->active || + drm_atomic_crtc_needs_modeset(new_crtc_state))) { /** * Frontend may have changed so reapply the CRC capture * settings for the stream. */ - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); - if (amdgpu_dm_is_valid_crc_source(cur_crc_src)) { - configure_crc = true; #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) if (amdgpu_dm_crc_window_is_activated(crtc)) { spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); @@ -8310,14 +8306,12 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } #endif - } - - if (configure_crc) if (amdgpu_dm_crtc_configure_crc_source( crtc, dm_new_crtc_state, cur_crc_src)) DRM_DEBUG_DRIVER("Failed to configure crc source"); -#endif + } } +#endif } for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) @@ -9396,10 +9390,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } } - if (!pre_validate_dsc(state, &dm_state, vars)) { - ret = -EINVAL; - goto fail; - } } #endif for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { @@ -9473,6 +9463,14 @@ 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, @@ -9525,6 +9523,15 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (dc_resource_is_dsc_encoding_supported(dc)) { + if (!pre_validate_dsc(state, &dm_state, vars)) { + ret = -EINVAL; + goto fail; + } + } +#endif + /* Run this here since we want to validate the streams we created */ ret = drm_atomic_helper_check_planes(dev, state); if (ret) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index b44faaad9b0b..b5ce15c43bcc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -681,7 +681,6 @@ struct dm_crtc_state { int crc_skip_count; - bool freesync_timing_changed; bool freesync_vrr_info_changed; bool dsc_force_changed; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index b8077fcd4651..f0b01c8dc4a6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -880,8 +880,17 @@ void dm_helpers_smu_timeout(struct dc_context *ctx, unsigned int msg_id, unsigne void dm_helpers_init_panel_settings( struct dc_context *ctx, - struct dc_panel_config *panel_config) -{ + struct dc_panel_config *panel_config, + struct dc_sink *sink) +{ + // Extra Panel Power Sequence + panel_config->pps.extra_t3_ms = sink->edid_caps.panel_patch.extra_t3_ms; + panel_config->pps.extra_t7_ms = sink->edid_caps.panel_patch.extra_t7_ms; + panel_config->pps.extra_delay_backlight_off = sink->edid_caps.panel_patch.extra_delay_backlight_off; + panel_config->pps.extra_post_t7_ms = 0; + panel_config->pps.extra_pre_t11_ms = 0; + panel_config->pps.extra_t12_ms = sink->edid_caps.panel_patch.extra_t12_ms; + panel_config->pps.extra_post_OUI_ms = 0; // Feature DSC panel_config->dsc.disable_dsc_edp = false; panel_config->dsc.force_dsc_edp_policy = 0; 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..26291db0a3cf 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 @@ -60,11 +60,15 @@ static bool link_supports_psrsu(struct dc_link *link) */ void amdgpu_dm_set_psr_caps(struct dc_link *link) { - if (!(link->connector_signal & SIGNAL_TYPE_EDP)) + if (!(link->connector_signal & SIGNAL_TYPE_EDP)) { + link->psr_settings.psr_feature_enabled = false; return; + } - if (link->type == dc_connection_none) + if (link->type == dc_connection_none) { + link->psr_settings.psr_feature_enabled = false; return; + } if (link->dpcd_caps.psr_info.psr_version == 0) { link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; @@ -170,7 +174,13 @@ 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/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index ead4da11a992..ee0456b5e14e 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -24,6 +24,7 @@ */ #include "dm_services.h" +#include "core_types.h" #include "ObjectID.h" #include "atomfirmware.h" @@ -50,13 +51,6 @@ #define LAST_RECORD_TYPE 0xff #define SMU9_SYSPLL0_ID 0 -struct i2c_id_config_access { - uint8_t bfI2C_LineMux:4; - uint8_t bfHW_EngineID:3; - uint8_t bfHW_Capable:1; - uint8_t ucAccess; -}; - static enum bp_result get_gpio_i2c_info(struct bios_parser *bp, struct atom_i2c_record *record, struct graphics_object_i2c_info *info); @@ -849,6 +843,8 @@ static enum bp_result get_ss_info_v4_1( disp_cntl_tbl->dvi_ss_rate_10hz * 10; if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_HDMI: ss_info->spread_spectrum_percentage = @@ -857,6 +853,8 @@ static enum bp_result get_ss_info_v4_1( disp_cntl_tbl->hdmi_ss_rate_10hz * 10; if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; /* TODO LVDS not support anymore? */ case AS_SIGNAL_TYPE_DISPLAY_PORT: @@ -866,6 +864,8 @@ static enum bp_result get_ss_info_v4_1( disp_cntl_tbl->dp_ss_rate_10hz * 10; if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: /* atom_firmware: DAL only get data from dce_info table. @@ -879,13 +879,15 @@ static enum bp_result get_ss_info_v4_1( DATA_TABLES(smu_info)); if (!smu_info) return BP_RESULT_BADBIOSTABLE; - + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info->gpuclk_ss_percentage); ss_info->spread_spectrum_percentage = smu_info->waflclk_ss_percentage; ss_info->spread_spectrum_range = smu_info->gpuclk_ss_rate_10hz * 10; if (smu_info->waflclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_XGMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; default: result = BP_RESULT_UNSUPPORTED; @@ -922,6 +924,7 @@ static enum bp_result get_ss_info_v4_2( if (!smu_info) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info->gpuclk_ss_percentage); ss_info->type.STEP_AND_DELAY_INFO = false; ss_info->spread_percentage_divider = 1000; /* BIOS no longer uses target clock. Always enable for now */ @@ -935,6 +938,8 @@ static enum bp_result get_ss_info_v4_2( disp_cntl_tbl->dvi_ss_rate_10hz * 10; if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_HDMI: ss_info->spread_spectrum_percentage = @@ -943,6 +948,8 @@ static enum bp_result get_ss_info_v4_2( disp_cntl_tbl->hdmi_ss_rate_10hz * 10; if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; /* TODO LVDS not support anymore? */ case AS_SIGNAL_TYPE_DISPLAY_PORT: @@ -952,6 +959,8 @@ static enum bp_result get_ss_info_v4_2( smu_info->gpuclk_ss_rate_10hz * 10; if (smu_info->gpuclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: /* atom_firmware: DAL only get data from dce_info table. @@ -1000,6 +1009,8 @@ static enum bp_result get_ss_info_v4_5( disp_cntl_tbl->dvi_ss_rate_10hz * 10; if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_HDMI: ss_info->spread_spectrum_percentage = @@ -1008,6 +1019,8 @@ static enum bp_result get_ss_info_v4_5( disp_cntl_tbl->hdmi_ss_rate_10hz * 10; if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_DISPLAY_PORT: ss_info->spread_spectrum_percentage = @@ -1016,6 +1029,8 @@ static enum bp_result get_ss_info_v4_5( disp_cntl_tbl->dp_ss_rate_10hz * 10; if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) ss_info->type.CENTER_MODE = true; + + DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: /* atom_smu_info_v4_0 does not have fields for SS for SMU Display PLL anymore. @@ -1353,7 +1368,7 @@ static enum bp_result bios_parser_get_lttpr_interop( default: break; } - + DC_LOG_BIOS("DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE: %d tbl_revision.major = %d tbl_revision.minor = %d\n", *dce_caps, tbl_revision.major, tbl_revision.minor); return result; } @@ -1369,6 +1384,7 @@ static enum bp_result bios_parser_get_lttpr_caps( if (!DATA_TABLES(dce_info)) return BP_RESULT_UNSUPPORTED; + *dce_caps = 0; header = GET_IMAGE(struct atom_common_table_header, DATA_TABLES(dce_info)); get_atom_data_table_revision(header, &tbl_revision); @@ -1402,7 +1418,11 @@ static enum bp_result bios_parser_get_lttpr_caps( default: break; } - + DC_LOG_BIOS("DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE: %d tbl_revision.major = %d tbl_revision.minor = %d\n", *dce_caps, tbl_revision.major, tbl_revision.minor); + if (dcb->ctx->dc->config.force_bios_enable_lttpr && *dce_caps == 0) { + *dce_caps = 1; + DC_LOG_BIOS("DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE: forced enabled"); + } return result; } @@ -1840,7 +1860,7 @@ static enum bp_result get_firmware_info_v3_2( /* Vega12 */ smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2, DATA_TABLES(smu_info)); - + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage); if (!smu_info_v3_2) return BP_RESULT_BADBIOSTABLE; @@ -1849,7 +1869,7 @@ static enum bp_result get_firmware_info_v3_2( /* Vega20 */ smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3, DATA_TABLES(smu_info)); - + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage); if (!smu_info_v3_3) return BP_RESULT_BADBIOSTABLE; @@ -1991,7 +2011,7 @@ static enum bp_result get_firmware_info_v3_4( if (!smu_info_v3_5) return BP_RESULT_BADBIOSTABLE; - + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_5->gpuclk_ss_percentage); info->default_engine_clk = smu_info_v3_5->bootup_dcefclk_10khz * 10; break; @@ -2397,6 +2417,7 @@ static enum bp_result get_integrated_info_v11( info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11, DATA_TABLES(integratedsysteminfo)); + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage); if (info_v11 == NULL) return BP_RESULT_BADBIOSTABLE; @@ -2611,6 +2632,7 @@ static enum bp_result get_integrated_info_v2_1( info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1, DATA_TABLES(integratedsysteminfo)); + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage); if (info_v2_1 == NULL) return BP_RESULT_BADBIOSTABLE; @@ -2772,6 +2794,8 @@ static enum bp_result get_integrated_info_v2_2( info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2, DATA_TABLES(integratedsysteminfo)); + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage); + if (info_v2_2 == NULL) return BP_RESULT_BADBIOSTABLE; @@ -2923,6 +2947,27 @@ static enum bp_result construct_integrated_info( default: return result; } + if (result == BP_RESULT_OK) { + + DC_LOG_BIOS("edp1:\n" + "\tedp_pwr_on_off_delay = %d\n" + "\tedp_pwr_on_vary_bl_to_blon = %d\n" + "\tedp_pwr_down_bloff_to_vary_bloff = %d\n" + "\tedp_bootup_bl_level = %d\n", + info->edp1_info.edp_pwr_on_off_delay, + info->edp1_info.edp_pwr_on_vary_bl_to_blon, + info->edp1_info.edp_pwr_down_bloff_to_vary_bloff, + info->edp1_info.edp_bootup_bl_level); + DC_LOG_BIOS("edp2:\n" + "\tedp_pwr_on_off_delayv = %d\n" + "\tedp_pwr_on_vary_bl_to_blon = %d\n" + "\tedp_pwr_down_bloff_to_vary_bloff = %d\n" + "\tedp_bootup_bl_level = %d\n", + info->edp2_info.edp_pwr_on_off_delay, + info->edp2_info.edp_pwr_on_vary_bl_to_blon, + info->edp2_info.edp_pwr_down_bloff_to_vary_bloff, + info->edp2_info.edp_bootup_bl_level); + } } if (result != BP_RESULT_OK) @@ -2948,13 +2993,22 @@ static enum bp_result construct_integrated_info( info->ext_disp_conn_info.path[i].ext_encoder_obj_id.id, info->ext_disp_conn_info.path[i].caps ); + if (info->ext_disp_conn_info.path[i].caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) + DC_LOG_BIOS("BIOS EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); + else if (bp->base.ctx->dc->config.force_bios_fixed_vs) { + info->ext_disp_conn_info.path[i].caps |= EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN; + DC_LOG_BIOS("driver forced EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN on path %d\n", i); + } } - // Log the Checksum and Voltage Swing DC_LOG_BIOS("Integrated info table CHECKSUM: %d\n" "Integrated info table FIX_DP_VOLTAGE_SWING: %d\n", info->ext_disp_conn_info.checksum, info->ext_disp_conn_info.fixdpvoltageswing); + if (bp->base.ctx->dc->config.force_bios_fixed_vs && info->ext_disp_conn_info.fixdpvoltageswing == 0) { + info->ext_disp_conn_info.fixdpvoltageswing = bp->base.ctx->dc->config.force_bios_fixed_vs & 0xF; + DC_LOG_BIOS("driver forced fixdpvoltageswing = %d\n", info->ext_disp_conn_info.fixdpvoltageswing); + } } /* Sort voltage table from low to high*/ for (i = 1; i < NUMBER_OF_DISP_CLK_VOLTAGE; ++i) { @@ -3300,6 +3354,7 @@ static enum bp_result bios_get_board_layout_info( struct bios_parser *bp; static enum bp_result record_result; + unsigned int max_slots; const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = { GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1, @@ -3316,8 +3371,14 @@ static enum bp_result bios_get_board_layout_info( } board_layout_info->num_of_slots = 0; + max_slots = MAX_BOARD_SLOTS; + + // Assume single slot on v1_5 + if (bp->object_info_tbl.revision.minor == 5) { + max_slots = 1; + } - for (i = 0; i < MAX_BOARD_SLOTS; ++i) { + for (i = 0; i < max_slots; ++i) { record_result = get_bracket_layout_record(dcb, slot_index_to_vbios_id[i], &board_layout_info->slots[i]); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 0d30d1d9d67e..650f3b4b562e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -179,7 +179,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct } else if (dispclk_wdivider == 127 && current_dispclk_wdivider != 127) { REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, 126); - REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 100); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 2000); for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; struct dccg *dccg = clk_mgr->base.ctx->dc->res_pool->dccg; @@ -206,7 +206,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider); - REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 2000); REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider); REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100); 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 d43258e3cd4f..c1eaf571407a 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 @@ -104,7 +104,7 @@ 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; @@ -115,9 +115,10 @@ 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); } } @@ -216,11 +217,11 @@ 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 171c38fac6a3..1131c6d73f6c 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 @@ -126,7 +126,7 @@ 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; @@ -136,12 +136,21 @@ 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); + } } } } @@ -240,11 +249,11 @@ 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; } @@ -677,6 +686,8 @@ 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/dcn314/dcn314_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c index 897105d1c111..ef0795b14a1f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c @@ -339,29 +339,24 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs if (!clk_mgr->smu_present) return; - if (!clk_mgr->base.ctx->dc->debug.enable_z9_disable_interface && - (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY)) - support = DCN_ZSTATE_SUPPORT_DISALLOW; - - // Arg[15:0] = 8/9/0 for Z8/Z9/disallow -> existing bits // Arg[16] = Disallow Z9 -> new bit switch (support) { case DCN_ZSTATE_SUPPORT_ALLOW: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 9; + param = (1 << 10) | (1 << 9) | (1 << 8); break; case DCN_ZSTATE_SUPPORT_DISALLOW: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 8; + param = 0; break; case DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 0x00010008; + param = (1 << 10); break; default: //DCN_ZSTATE_SUPPORT_UNKNOWN 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 14071aef5eab..893991a0eb97 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 @@ -51,6 +51,9 @@ #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) @@ -84,7 +87,7 @@ 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; @@ -96,9 +99,10 @@ 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); } } @@ -151,6 +155,9 @@ 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); @@ -164,10 +171,10 @@ 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)) { @@ -180,12 +187,12 @@ 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; } @@ -280,7 +287,7 @@ 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, @@ -288,7 +295,7 @@ 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, @@ -296,7 +303,7 @@ 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, @@ -304,7 +311,7 @@ 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, @@ -561,8 +568,7 @@ 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..1c612ccf1944 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; + struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk; 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; @@ -178,22 +180,29 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) /* DCFCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DCFCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz, - &num_levels); + &num_entries_per_clk->num_dcfclk_levels); /* SOCCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_SOCCLK, &clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz, - &num_levels); + &num_entries_per_clk->num_socclk_levels); + /* DTBCLK */ if (!clk_mgr->base.ctx->dc->debug.disable_dtb_ref_clk_switch) dcn32_init_single_clock(clk_mgr, PPCLK_DTBCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz, - &num_levels); + &num_entries_per_clk->num_dtbclk_levels); /* DISPCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DISPCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz, - &num_levels); + &num_entries_per_clk->num_dispclk_levels); + num_levels = num_entries_per_clk->num_dispclk_levels; + + if (num_entries_per_clk->num_dcfclk_levels && + num_entries_per_clk->num_dtbclk_levels && + num_entries_per_clk->num_dispclk_levels) + clk_mgr->dpm_present = true; if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) { unsigned int i; @@ -325,6 +334,21 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, if (enter_display_off == safe_to_lower) dcn30_smu_set_num_of_displays(clk_mgr, display_count); + clk_mgr_base->clks.fclk_prev_p_state_change_support = clk_mgr_base->clks.fclk_p_state_change_support; + + total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context); + fclk_p_state_change_support = new_clocks->fclk_p_state_change_support || (total_plane_count == 0); + + if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support)) { + clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; + + /* To enable FCLK P-state switching, send FCLK_PSTATE_SUPPORTED message to PMFW */ + if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support) { + /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ + dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_SUPPORTED); + } + } + if (dc->debug.force_min_dcfclk_mhz > 0) new_clocks->dcfclk_khz = (new_clocks->dcfclk_khz > (dc->debug.force_min_dcfclk_mhz * 1000)) ? new_clocks->dcfclk_khz : (dc->debug.force_min_dcfclk_mhz * 1000); @@ -344,7 +368,6 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz; clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support; - clk_mgr_base->clks.fclk_prev_p_state_change_support = clk_mgr_base->clks.fclk_p_state_change_support; clk_mgr_base->clks.prev_num_ways = clk_mgr_base->clks.num_ways; if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && @@ -353,27 +376,25 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, dcn32_smu_send_cab_for_uclk_message(clk_mgr, clk_mgr_base->clks.num_ways); } - total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context); + p_state_change_support = new_clocks->p_state_change_support || (total_plane_count == 0); - fclk_p_state_change_support = new_clocks->fclk_p_state_change_support || (total_plane_count == 0); if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { clk_mgr_base->clks.p_state_change_support = p_state_change_support; /* to disable P-State switching, set UCLK min = max */ if (!clk_mgr_base->clks.p_state_change_support) dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } - if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support) && - clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21) { - clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; + /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ + if (safe_to_lower && (clk_mgr_base->clks.fclk_p_state_change_support != clk_mgr_base->clks.fclk_prev_p_state_change_support)) { + update_fclk = true; + } - /* To disable FCLK P-state switching, send FCLK_PSTATE_NOTSUPPORTED message to PMFW */ - if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && !clk_mgr_base->clks.fclk_p_state_change_support) { - /* Handle code for sending a message to PMFW that FCLK P-state change is not supported */ - dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_NOTSUPPORTED); - } + if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && !clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { + /* Handle code for sending a message to PMFW that FCLK P-state change is not supported */ + dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_NOTSUPPORTED); } /* Always update saved value, even if new value not set due to P-State switching unsupported */ @@ -382,21 +403,11 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, update_uclk = true; } - /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ - if (safe_to_lower && (clk_mgr_base->clks.fclk_p_state_change_support != clk_mgr_base->clks.fclk_prev_p_state_change_support)) { - update_fclk = true; - } - /* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */ if (clk_mgr_base->clks.p_state_change_support && (update_uclk || !clk_mgr_base->clks.prev_p_state_change_support)) dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); - if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { - /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ - dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_SUPPORTED); - } - if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && clk_mgr_base->clks.num_ways > new_clocks->num_ways) { clk_mgr_base->clks.num_ways = new_clocks->num_ways; @@ -624,7 +635,7 @@ static void dcn32_set_hard_min_memclk(struct clk_mgr *clk_mgr_base, bool current khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); else dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } else { dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz); @@ -640,24 +651,42 @@ static void dcn32_set_hard_max_memclk(struct clk_mgr *clk_mgr_base) return; dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } /* Get current memclk states, update bounding box */ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk; unsigned int num_levels; if (!clk_mgr->smu_present) return; - /* Refresh memclk states */ + /* Refresh memclk and fclk states */ dcn32_init_single_clock(clk_mgr, PPCLK_UCLK, &clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz, - &num_levels); + &num_entries_per_clk->num_memclk_levels); + + dcn32_init_single_clock(clk_mgr, PPCLK_FCLK, + &clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz, + &num_entries_per_clk->num_fclk_levels); + + if (num_entries_per_clk->num_memclk_levels >= num_entries_per_clk->num_fclk_levels) { + num_levels = num_entries_per_clk->num_memclk_levels; + } else { + num_levels = num_entries_per_clk->num_fclk_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 9860bf38c547..997ab031f816 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -401,6 +401,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, { int i; + if (memcmp(adjust, &stream->adjust, sizeof(struct dc_crtc_timing_adjust)) == 0) + return true; + stream->adjust.v_total_max = adjust->v_total_max; stream->adjust.v_total_mid = adjust->v_total_mid; stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num; @@ -1181,11 +1184,7 @@ static void disable_vbios_mode_if_required( pipe->stream_res.pix_clk_params.requested_pix_clk_100hz; if (pix_clk_100hz != requested_pix_clk_100hz) { - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(dc->current_state, - pipe, TX_OFF_SYMCLK_OFF); - else - core_link_disable_stream(pipe); + core_link_disable_stream(pipe); pipe->stream->dpms_off = false; } } @@ -1202,7 +1201,7 @@ static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) int count = 0; struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - if (!pipe->plane_state) + if (!pipe->plane_state || pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) continue; /* Timeout 100 ms */ @@ -1735,10 +1734,20 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c int i, k, l; struct dc_stream_state *dc_streams[MAX_STREAMS] = {0}; struct dc_state *old_state; + bool subvp_prev_use = false; dc_z10_restore(dc); dc_allow_idle_optimizations(dc, false); + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + /* Check old context for SubVP */ + subvp_prev_use |= (old_pipe->stream && old_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM); + if (subvp_prev_use) + break; + } + for (i = 0; i < context->stream_count; i++) dc_streams[i] = context->streams[i]; @@ -1751,6 +1760,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c context->stream_count == 0) dc->hwss.prepare_bandwidth(dc, context); + if (dc->debug.enable_double_buffered_dsc_pg_support) + dc->hwss.update_dsc_pg(dc, context, false); + disable_dangling_plane(dc, context); /* re-program planes for existing stream, in case we need to * free up plane resource for later use @@ -1775,6 +1787,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe); } + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); + result = dc->hwss.apply_ctx_to_hw(dc, context); if (result != DC_OK) { @@ -1792,6 +1807,12 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.interdependent_update_lock(dc, context, false); dc->hwss.post_unlock_program_front_end(dc, context); } + + if (dc->hwss.commit_subvp_config) + dc->hwss.commit_subvp_config(dc, context); + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, true, NULL, subvp_prev_use); + for (i = 0; i < context->stream_count; i++) { const struct dc_link *link = context->streams[i]->link; @@ -1841,6 +1862,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.optimize_bandwidth(dc, context); } + if (dc->debug.enable_double_buffered_dsc_pg_support) + dc->hwss.update_dsc_pg(dc, context, true); + if (dc->ctx->dce_version >= DCE_VERSION_MAX) TRACE_DCN_CLOCK_STATE(&context->bw_ctx.bw.dcn.clk); else @@ -2004,6 +2028,9 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) dc->hwss.optimize_bandwidth(dc, context); + if (dc->debug.enable_double_buffered_dsc_pg_support) + dc->hwss.update_dsc_pg(dc, context, true); + dc->optimized_required = false; dc->wm_optimized_required = false; } @@ -2323,9 +2350,13 @@ static enum surface_update_type det_surface_update(const struct dc *dc, type = get_scaling_info_update_type(u); elevate_update_type(&overall_type, type); - if (u->flip_addr) + if (u->flip_addr) { update_flags->bits.addr_update = 1; - + if (u->flip_addr->address.tmz_surface != u->surface->address.tmz_surface) { + update_flags->bits.tmz_changed = 1; + elevate_update_type(&overall_type, UPDATE_TYPE_FULL); + } + } if (u->in_transfer_func) update_flags->bits.in_transfer_func_change = 1; @@ -2760,11 +2791,8 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->abm_level) stream->abm_level = *update->abm_level; - if (update->periodic_interrupt0) - stream->periodic_interrupt0 = *update->periodic_interrupt0; - - if (update->periodic_interrupt1) - stream->periodic_interrupt1 = *update->periodic_interrupt1; + if (update->periodic_interrupt) + stream->periodic_interrupt = *update->periodic_interrupt; if (update->gamut_remap) stream->gamut_remap_matrix = *update->gamut_remap; @@ -2849,16 +2877,6 @@ static void copy_stream_update_to_stream(struct dc *dc, } } -void dc_reset_state(struct dc *dc, struct dc_state *context) -{ - dc_resource_state_destruct(context); - - /* clear the structure, but don't reset the reference count */ - memset(context, 0, offsetof(struct dc_state, refcount)); - - init_state(dc, context); -} - static bool update_planes_and_stream_state(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, struct dc_stream_state *stream, @@ -2928,6 +2946,12 @@ static bool update_planes_and_stream_state(struct dc *dc, dc_resource_state_copy_construct( dc->current_state, context); + /* For each full update, remove all existing phantom pipes first. + * Ensures that we have enough pipes for newly added MPO planes + */ + if (dc->res_pool->funcs->remove_phantom_pipes) + dc->res_pool->funcs->remove_phantom_pipes(dc, context); + /*remove old surfaces from context */ if (!dc_rem_all_planes_for_stream(dc, stream, context)) { @@ -2994,13 +3018,8 @@ static void commit_planes_do_stream_update(struct dc *dc, if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->stream == stream) { - if (stream_update->periodic_interrupt0 && - dc->hwss.setup_periodic_interrupt) - dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE0); - - if (stream_update->periodic_interrupt1 && - dc->hwss.setup_periodic_interrupt) - dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE1); + if (stream_update->periodic_interrupt && dc->hwss.setup_periodic_interrupt) + dc->hwss.setup_periodic_interrupt(dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || stream_update->vrr_infopacket || @@ -3068,11 +3087,7 @@ static void commit_planes_do_stream_update(struct dc *dc, if (stream_update->dpms_off) { if (*stream_update->dpms_off) { - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(dc->current_state, - pipe_ctx, TX_OFF_SYMCLK_ON); - else - core_link_disable_stream(pipe_ctx); + core_link_disable_stream(pipe_ctx); /* for dpms, keep acquired resources*/ if (pipe_ctx->stream_res.audio && !dc->debug.az_endpoint_mute_only) pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio); @@ -3082,12 +3097,7 @@ static void commit_planes_do_stream_update(struct dc *dc, } else { if (get_seamless_boot_stream_count(context) == 0) dc->hwss.prepare_bandwidth(dc, dc->current_state); - - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(dc->current_state, - pipe_ctx, TX_ON_SYMCLK_ON); - else - core_link_enable_stream(dc->current_state, pipe_ctx); + core_link_enable_stream(dc->current_state, pipe_ctx); } } @@ -3218,6 +3228,9 @@ static void commit_planes_for_stream(struct dc *dc, if (get_seamless_boot_stream_count(context) == 0) dc->hwss.prepare_bandwidth(dc, context); + if (dc->debug.enable_double_buffered_dsc_pg_support) + dc->hwss.update_dsc_pg(dc, context, false); + context_clock_trace(dc, context); } @@ -3346,8 +3359,14 @@ static void commit_planes_for_stream(struct dc *dc, /* Since phantom pipe programming is moved to post_unlock_program_front_end, * move the SubVP lock to after the phantom pipes have been setup */ - if (dc->hwss.subvp_pipe_control_lock) - dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) { + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + } else { + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + } + return; } @@ -3507,6 +3526,9 @@ static void commit_planes_for_stream(struct dc *dc, if (update_type != UPDATE_TYPE_FAST) dc->hwss.post_unlock_program_front_end(dc, context); + if (update_type != UPDATE_TYPE_FAST) + if (dc->hwss.commit_subvp_config) + dc->hwss.commit_subvp_config(dc, context); if (update_type != UPDATE_TYPE_FAST) if (dc->hwss.commit_subvp_config) @@ -3541,11 +3563,91 @@ static void commit_planes_for_stream(struct dc *dc, } } +/* Determines if the incoming context requires a applying transition state with unnecessary + * pipe splitting and ODM disabled, due to hardware limitations. In a case where + * the OPP associated with an MPCC might change due to plane additions, this function + * returns true. + */ +static bool could_mpcc_tree_change_for_active_pipes(struct dc *dc, + struct dc_stream_state *stream, + int surface_count, + bool *is_plane_addition) +{ + + struct dc_stream_status *cur_stream_status = stream_get_status(dc->current_state, stream); + bool force_minimal_pipe_splitting = false; + uint32_t i; + + *is_plane_addition = false; + + if (cur_stream_status && + dc->current_state->stream_count > 0 && + dc->debug.pipe_split_policy != MPC_SPLIT_AVOID) { + /* determine if minimal transition is required due to MPC*/ + if (surface_count > 0) { + if (cur_stream_status->plane_count > surface_count) { + force_minimal_pipe_splitting = true; + } else if (cur_stream_status->plane_count < surface_count) { + force_minimal_pipe_splitting = true; + *is_plane_addition = true; + } + } + } + + if (cur_stream_status && + dc->current_state->stream_count == 1 && + dc->debug.enable_single_display_2to1_odm_policy) { + /* determine if minimal transition is required due to dynamic ODM*/ + if (surface_count > 0) { + if (cur_stream_status->plane_count > 2 && cur_stream_status->plane_count > surface_count) { + force_minimal_pipe_splitting = true; + } else if (surface_count > 2 && cur_stream_status->plane_count < surface_count) { + force_minimal_pipe_splitting = true; + *is_plane_addition = true; + } + } + } + + /* For SubVP pipe split case when adding MPO video + * we need to add a minimal transition. In this case + * there will be 2 streams (1 main stream, 1 phantom + * stream). + */ + if (cur_stream_status && + dc->current_state->stream_count == 2 && + stream->mall_stream_config.type == SUBVP_MAIN) { + bool is_pipe_split = false; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream && + (dc->current_state->res_ctx.pipe_ctx[i].bottom_pipe || + dc->current_state->res_ctx.pipe_ctx[i].next_odm_pipe)) { + is_pipe_split = true; + break; + } + } + + /* determine if minimal transition is required due to SubVP*/ + if (surface_count > 0 && is_pipe_split) { + if (cur_stream_status->plane_count > surface_count) { + force_minimal_pipe_splitting = true; + } else if (cur_stream_status->plane_count < surface_count) { + force_minimal_pipe_splitting = true; + *is_plane_addition = true; + } + } + } + + return force_minimal_pipe_splitting; +} + static bool commit_minimal_transition_state(struct dc *dc, struct dc_state *transition_base_context) { struct dc_state *transition_context = dc_create_state(dc); - enum pipe_split_policy tmp_policy; + enum pipe_split_policy tmp_mpc_policy; + bool temp_dynamic_odm_policy; + bool temp_subvp_policy; enum dc_status ret = DC_ERROR_UNEXPECTED; unsigned int i, j; @@ -3553,10 +3655,16 @@ static bool commit_minimal_transition_state(struct dc *dc, return false; if (!dc->config.is_vmin_only_asic) { - tmp_policy = dc->debug.pipe_split_policy; + tmp_mpc_policy = dc->debug.pipe_split_policy; dc->debug.pipe_split_policy = MPC_SPLIT_AVOID; } + temp_dynamic_odm_policy = dc->debug.enable_single_display_2to1_odm_policy; + dc->debug.enable_single_display_2to1_odm_policy = false; + + temp_subvp_policy = dc->debug.force_disable_subvp; + dc->debug.force_disable_subvp = true; + dc_resource_state_copy_construct(transition_base_context, transition_context); //commit minimal state @@ -3577,20 +3685,23 @@ static bool commit_minimal_transition_state(struct dc *dc, ret = dc_commit_state_no_check(dc, transition_context); } - //always release as dc_commit_state_no_check retains in good case + /*always release as dc_commit_state_no_check retains in good case*/ dc_release_state(transition_context); - //restore previous pipe split policy + /*restore previous pipe split and odm policy*/ if (!dc->config.is_vmin_only_asic) - dc->debug.pipe_split_policy = tmp_policy; + dc->debug.pipe_split_policy = tmp_mpc_policy; + + dc->debug.enable_single_display_2to1_odm_policy = temp_dynamic_odm_policy; + dc->debug.force_disable_subvp = temp_subvp_policy; if (ret != DC_OK) { - //this should never happen + /*this should never happen*/ BREAK_TO_DEBUGGER(); return false; } - //force full surface update + /*force full surface update*/ for (i = 0; i < dc->current_state->stream_count; i++) { for (j = 0; j < dc->current_state->stream_status[i].plane_count; j++) { dc->current_state->stream_status[i].plane_states[j]->update_flags.raw = 0xFFFFFFFF; @@ -3613,22 +3724,14 @@ bool dc_update_planes_and_stream(struct dc *dc, * cause underflow. Apply stream configuration with minimal pipe * split first to avoid unsupported transitions for active pipes. */ - bool force_minimal_pipe_splitting = false; - bool is_plane_addition = false; + bool force_minimal_pipe_splitting; + bool is_plane_addition; - struct dc_stream_status *cur_stream_status = stream_get_status(dc->current_state, stream); - - if (cur_stream_status && - dc->current_state->stream_count > 0 && - dc->debug.pipe_split_policy != MPC_SPLIT_AVOID) { - /* determine if minimal transition is required */ - if (cur_stream_status->plane_count > surface_count) { - force_minimal_pipe_splitting = true; - } else if (cur_stream_status->plane_count < surface_count) { - force_minimal_pipe_splitting = true; - is_plane_addition = true; - } - } + force_minimal_pipe_splitting = could_mpcc_tree_change_for_active_pipes( + dc, + stream, + surface_count, + &is_plane_addition); /* on plane addition, minimal state is the current one */ if (force_minimal_pipe_splitting && is_plane_addition && @@ -3645,7 +3748,7 @@ bool dc_update_planes_and_stream(struct dc *dc, &context)) return false; - /* on plane addition, minimal state is the new one */ + /* on plane removal, minimal state is the new one */ if (force_minimal_pipe_splitting && !is_plane_addition) { if (!commit_minimal_transition_state(dc, context)) { dc_release_state(context); @@ -4032,7 +4135,7 @@ struct dc_sink *dc_link_add_remote_sink( * Treat device as no EDID device if EDID * parsing fails */ - if (edid_status != EDID_OK) { + if (edid_status != EDID_OK && edid_status != EDID_PARTIAL_VALID) { dc_sink->dc_edid.length = 0; dm_error("Bad EDID, status%d!\n", edid_status); } @@ -4554,6 +4657,37 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, } /** + ***************************************************************************** + * Function: dc_process_dmub_dpia_hpd_int_enable + * + * @brief + * Submits dpia hpd int enable command to dmub via inbox message + * + * @param + * [in] dc: dc structure + * [in] hpd_int_enable: 1 for hpd int enable, 0 to disable + * + * @return + * None + ***************************************************************************** + */ +void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, + uint32_t hpd_int_enable) +{ + union dmub_rb_cmd cmd = {0}; + struct dc_dmub_srv *dmub_srv = dc->ctx->dmub_srv; + + cmd.dpia_hpd_int_enable.header.type = DMUB_CMD__DPIA_HPD_INT_ENABLE; + cmd.dpia_hpd_int_enable.enable = hpd_int_enable; + + dc_dmub_srv_cmd_queue(dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dmub_srv); + dc_dmub_srv_wait_idle(dmub_srv); + + DC_LOG_DEBUG("%s: hpd_int_enable(%d)\n", __func__, hpd_int_enable); +} + +/** * dc_disable_accelerated_mode - disable accelerated mode * @dc: dc structure */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 9dd705b985b9..7c2e3b8dc26a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -417,8 +417,8 @@ void get_subvp_visual_confirm_color( for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; - if (pipe->stream && pipe->stream->mall_stream_config.paired_stream && - pipe->stream->mall_stream_config.type == SUBVP_MAIN) { + if (pipe->stream && pipe->stream->mall_stream_config.paired_stream && + pipe->stream->mall_stream_config.type == SUBVP_MAIN) { /* SubVP enable - red */ color->color_r_cr = color_value; enable_subvp = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 4ab27e231337..d7b1ace6328a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -832,8 +832,9 @@ static bool discover_dp_mst_topology(struct dc_link *link, enum dc_detect_reason LINK_INFO("link=%d, mst branch is now Connected\n", link->link_index); - apply_dpia_mst_dsc_always_on_wa(link); link->type = dc_connection_mst_branch; + apply_dpia_mst_dsc_always_on_wa(link); + dm_helpers_dp_update_branch_info(link->ctx, link); if (dm_helpers_dp_mst_start_top_mgr(link->ctx, link, (reason == DETECT_REASON_BOOT || reason == DETECT_REASON_RESUMEFROMS3S4))) { @@ -847,20 +848,13 @@ static bool discover_dp_mst_topology(struct dc_link *link, enum dc_detect_reason bool reset_cur_dp_mst_topology(struct dc_link *link) { - bool result = false; DC_LOGGER_INIT(link->ctx->logger); LINK_INFO("link=%d, mst branch is now Disconnected\n", link->link_index); revert_dpia_mst_dsc_always_on_wa(link); - result = dm_helpers_dp_mst_stop_top_mgr(link->ctx, link); - - link->mst_stream_alloc_table.stream_count = 0; - memset(link->mst_stream_alloc_table.stream_allocations, - 0, - sizeof(link->mst_stream_alloc_table.stream_allocations)); - return result; + return dm_helpers_dp_mst_stop_top_mgr(link->ctx, link); } static bool should_prepare_phy_clocks_for_link_verification(const struct dc *dc, @@ -1313,8 +1307,11 @@ static bool detect_link_and_local_sink(struct dc_link *link, } if (link->connector_signal == SIGNAL_TYPE_EDP) { - // Init dc_panel_config - dm_helpers_init_panel_settings(dc_ctx, &link->panel_config); + /* Init dc_panel_config by HW config */ + if (dc_ctx->dc->res_pool->funcs->get_panel_config_defaults) + dc_ctx->dc->res_pool->funcs->get_panel_config_defaults(&link->panel_config); + /* Pickup base DM settings */ + dm_helpers_init_panel_settings(dc_ctx, &link->panel_config, sink); // Override dc_panel_config if system has specific settings dm_helpers_override_panel_settings(dc_ctx, &link->panel_config); } @@ -1983,7 +1980,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, int i; bool apply_seamless_boot_optimization = false; uint32_t bl_oled_enable_delay = 50; // in ms - const uint32_t post_oui_delay = 30; // 30ms + uint32_t post_oui_delay = 30; // 30ms /* Reduce link bandwidth between failed link training attempts. */ bool do_fallback = false; @@ -2030,8 +2027,10 @@ static enum dc_status enable_link_dp(struct dc_state *state, // during mode switch we do DP_SET_POWER off then on, and OUI is lost dpcd_set_source_specific_data(link); - if (link->dpcd_sink_ext_caps.raw != 0) + if (link->dpcd_sink_ext_caps.raw != 0) { + post_oui_delay += link->panel_config.pps.extra_post_OUI_ms; msleep(post_oui_delay); + } // similarly, mode switch can cause loss of cable ID dpcd_write_cable_id_to_dprx(link); @@ -2643,9 +2642,8 @@ static void disable_link(struct dc_link *link, const struct link_resource *link_ dp_set_fec_ready(link, link_res, false); } } - } else { - if (signal != SIGNAL_TYPE_VIRTUAL) - link->link_enc->funcs->disable_output(link->link_enc, signal); + } else if (signal != SIGNAL_TYPE_VIRTUAL) { + link->dc->hwss.disable_link_output(link, link_res, signal); } if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { @@ -2667,6 +2665,7 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) bool is_over_340mhz = false; bool is_vga_mode = (stream->timing.h_addressable == 640) && (stream->timing.v_addressable == 480); + struct dc *dc = pipe_ctx->stream->ctx->dc; if (stream->phy_pix_clk == 0) stream->phy_pix_clk = stream->timing.pix_clk_100hz / 10; @@ -2706,11 +2705,12 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR422) display_color_depth = COLOR_DEPTH_888; - link->link_enc->funcs->enable_tmds_output( - link->link_enc, + dc->hwss.enable_tmds_link_output( + link, + &pipe_ctx->link_res, + pipe_ctx->stream->signal, pipe_ctx->clock_source->id, display_color_depth, - pipe_ctx->stream->signal, stream->phy_pix_clk); if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) @@ -2721,15 +2721,16 @@ static void enable_link_lvds(struct pipe_ctx *pipe_ctx) { struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; + struct dc *dc = stream->ctx->dc; if (stream->phy_pix_clk == 0) stream->phy_pix_clk = stream->timing.pix_clk_100hz / 10; memset(&stream->link->cur_link_settings, 0, sizeof(struct dc_link_settings)); - - link->link_enc->funcs->enable_lvds_output( - link->link_enc, + dc->hwss.enable_lvds_link_output( + link, + &pipe_ctx->link_res, pipe_ctx->clock_source->id, stream->phy_pix_clk); @@ -3145,7 +3146,7 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, const bool *allow_active if (!dc_get_edp_link_panel_inst(dc, link, &panel_inst)) return false; - if (allow_active && link->type == dc_connection_none) { + if ((allow_active != NULL) && (*allow_active == true) && (link->type == dc_connection_none)) { // Don't enter PSR if panel is not connected return false; } @@ -3377,8 +3378,8 @@ bool dc_link_setup_psr(struct dc_link *link, case FAMILY_YELLOW_CARP: case AMDGPU_FAMILY_GC_10_3_6: case AMDGPU_FAMILY_GC_11_0_1: - if(!dc->debug.disable_z10) - psr_context->psr_level.bits.SKIP_CRTC_DISABLE = false; + if (dc->debug.disable_z10) + psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; break; default: psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; @@ -3567,6 +3568,35 @@ static void update_mst_stream_alloc_table( work_table[i]; } +static void remove_stream_from_alloc_table( + struct dc_link *link, + struct stream_encoder *dio_stream_enc, + struct hpo_dp_stream_encoder *hpo_dp_stream_enc) +{ + int i = 0; + struct link_mst_stream_allocation_table *table = + &link->mst_stream_alloc_table; + + if (hpo_dp_stream_enc) { + for (; i < table->stream_count; i++) + if (hpo_dp_stream_enc == table->stream_allocations[i].hpo_dp_stream_enc) + break; + } else { + for (; i < table->stream_count; i++) + if (dio_stream_enc == table->stream_allocations[i].stream_enc) + break; + } + + if (i < table->stream_count) { + i++; + for (; i < table->stream_count; i++) + table->stream_allocations[i-1] = table->stream_allocations[i]; + memset(&table->stream_allocations[table->stream_count-1], 0, + sizeof(struct link_mst_stream_allocation)); + table->stream_count--; + } +} + static void dc_log_vcp_x_y(const struct dc_link *link, struct fixed31_32 avg_time_slots_per_mtp) { const uint32_t VCP_Y_PRECISION = 1000; @@ -3984,26 +4014,32 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) &empty_link_settings, avg_time_slots_per_mtp); - /* TODO: which component is responsible for remove payload table? */ if (mst_mode) { + /* when link is in mst mode, reply on mst manager to remove + * payload + */ if (dm_helpers_dp_mst_write_payload_allocation_table( stream->ctx, stream, &proposed_table, - false)) { + false)) update_mst_stream_alloc_table( - link, - pipe_ctx->stream_res.stream_enc, - pipe_ctx->stream_res.hpo_dp_stream_enc, - &proposed_table); - } - else { - DC_LOG_WARNING("Failed to update" - "MST allocation table for" - "pipe idx:%d\n", - pipe_ctx->pipe_idx); - } + link, + pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc, + &proposed_table); + else + DC_LOG_WARNING("Failed to update" + "MST allocation table for" + "pipe idx:%d\n", + pipe_ctx->pipe_idx); + } else { + /* when link is no longer in mst mode (mst hub unplugged), + * remove payload with default dc logic + */ + remove_stream_from_alloc_table(link, pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc); } DC_LOG_MST("%s" @@ -4299,6 +4335,19 @@ void core_link_enable_stream( if (pipe_ctx->stream->dpms_off) return; + /* Have to setup DSC before DIG FE and BE are connected (which happens before the + * link training). This is to make sure the bandwidth sent to DIG BE won't be + * bigger than what the link and/or DIG BE can handle. VBID[6]/CompressedStream_flag + * will be automatically set at a later time when the video is enabled + * (DP_VID_STREAM_EN = 1). + */ + if (pipe_ctx->stream->timing.flags.DSC) { + if (dc_is_dp_signal(pipe_ctx->stream->signal) || + dc_is_virtual_signal(pipe_ctx->stream->signal)) + dp_set_dsc_enable(pipe_ctx, true); + + } + status = enable_link(state, pipe_ctx); if (status != DC_OK) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index d01d2eeed813..651231387043 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -35,6 +35,8 @@ #include "dc_link_ddc.h" #include "dce/dce_aux.h" #include "dmub/inc/dmub_cmd.h" +#include "link_dpcd.h" +#include "include/dal_asic_id.h" #define DC_LOGGER_INIT(logger) @@ -683,6 +685,21 @@ bool dc_link_aux_try_to_configure_timeout(struct ddc_service *ddc, bool result = false; struct ddc *ddc_pin = ddc->ddc_pin; + if ((ddc->link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && + !ddc->link->dc->debug.disable_fixed_vs_aux_timeout_wa && + ASICREV_IS_YELLOW_CARP(ddc->ctx->asic_id.hw_internal_rev)) { + /* Fixed VS workaround for AUX timeout */ + const uint32_t fixed_vs_address = 0xF004F; + const uint8_t fixed_vs_data[4] = {0x1, 0x22, 0x63, 0xc}; + + core_link_write_dpcd(ddc->link, + fixed_vs_address, + fixed_vs_data, + sizeof(fixed_vs_data)); + + timeout = 3072; + } + /* Do not try to access nonexistent DDC pin. */ if (ddc->link->ep_type != DISPLAY_ENDPOINT_PHY) return true; @@ -691,6 +708,7 @@ bool dc_link_aux_try_to_configure_timeout(struct ddc_service *ddc, ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout); result = true; } + return result; } 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 e2413d2908c9..1254d38f1778 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 @@ -526,9 +526,9 @@ uint8_t dc_dp_initialize_scrambling_data_symbols( return disable_scrabled_data_symbols; } -static inline bool is_repeater(struct dc_link *link, uint32_t offset) +static inline bool is_repeater(const struct link_training_settings *lt_settings, uint32_t offset) { - return (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (offset != 0); + return (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (offset != 0); } static void dpcd_set_lt_pattern_and_lane_settings( @@ -545,7 +545,7 @@ static void dpcd_set_lt_pattern_and_lane_settings( bool edp_workaround = false; /* TODO link_prop.INTERNAL */ dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET; - if (is_repeater(link, offset)) + if (is_repeater(lt_settings, offset)) dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET_PHY_REPEATER1 + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); @@ -561,7 +561,7 @@ static void dpcd_set_lt_pattern_and_lane_settings( dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET] = dpcd_pattern.raw; - if (is_repeater(link, offset)) { + if (is_repeater(lt_settings, offset)) { DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n 0x%X pattern = %x\n", __func__, offset, @@ -584,7 +584,7 @@ static void dpcd_set_lt_pattern_and_lane_settings( lt_settings->dpcd_lane_settings, size_in_bytes); - if (is_repeater(link, offset)) { + if (is_repeater(lt_settings, offset)) { if (dp_get_link_encoding_format(<_settings->link_settings) == DP_128b_132b_ENCODING) DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n" @@ -873,7 +873,7 @@ enum dc_status dp_get_lane_status_and_lane_adjust( uint32_t lane; enum dc_status status; - if (is_repeater(link, offset)) { + if (is_repeater(link_training_setting, offset)) { lane01_status_address = DP_LANE0_1_STATUS_PHY_REPEATER1 + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); @@ -906,7 +906,7 @@ enum dc_status dp_get_lane_status_and_lane_adjust( ln_align->raw = dpcd_buf[2]; - if (is_repeater(link, offset)) { + if (is_repeater(link_training_setting, offset)) { DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n" " 0x%X Lane01Status = %x\n 0x%X Lane23Status = %x\n ", __func__, @@ -944,6 +944,23 @@ enum dc_status dp_get_lane_status_and_lane_adjust( return status; } +static enum dc_status dpcd_128b_132b_set_lane_settings( + struct dc_link *link, + const struct link_training_settings *link_training_setting) +{ + enum dc_status status = core_link_write_dpcd(link, + DP_TRAINING_LANE0_SET, + (uint8_t *)(link_training_setting->dpcd_lane_settings), + sizeof(link_training_setting->dpcd_lane_settings)); + + DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", + __func__, + DP_TRAINING_LANE0_SET, + link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); + return status; +} + + enum dc_status dpcd_set_lane_settings( struct dc_link *link, const struct link_training_settings *link_training_setting, @@ -954,7 +971,7 @@ enum dc_status dpcd_set_lane_settings( lane0_set_address = DP_TRAINING_LANE0_SET; - if (is_repeater(link, offset)) + if (is_repeater(link_training_setting, offset)) lane0_set_address = DP_TRAINING_LANE0_SET_PHY_REPEATER1 + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); @@ -963,17 +980,7 @@ enum dc_status dpcd_set_lane_settings( (uint8_t *)(link_training_setting->dpcd_lane_settings), link_training_setting->link_settings.lane_count); - if (is_repeater(link, offset)) { - if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_128b_132b_ENCODING) - DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n" - " 0x%X TX_FFE_PRESET_VALUE = %x\n", - __func__, - offset, - lane0_set_address, - link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); - else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_8b_10b_ENCODING) + if (is_repeater(link_training_setting, offset)) { DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n" " 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, @@ -985,14 +992,6 @@ enum dc_status dpcd_set_lane_settings( link_training_setting->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } else { - if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_128b_132b_ENCODING) - DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", - __func__, - lane0_set_address, - link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); - else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_8b_10b_ENCODING) DC_LOG_HW_LINK_TRAINING("%s\n 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, lane0_set_address, @@ -1172,7 +1171,7 @@ static enum link_training_result perform_channel_equalization_sequence( /* Note: also check that TPS4 is a supported feature*/ tr_pattern = lt_settings->pattern_for_eq; - if (is_repeater(link, offset) && dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) + if (is_repeater(lt_settings, offset) && dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_4; dp_set_hw_training_pattern(link, link_res, tr_pattern, offset); @@ -1198,7 +1197,7 @@ static enum link_training_result perform_channel_equalization_sequence( /* 3. wait for receiver to lock-on*/ wait_time_microsec = lt_settings->eq_pattern_time; - if (is_repeater(link, offset)) + if (is_repeater(lt_settings, offset)) wait_time_microsec = dp_translate_training_aux_read_interval( link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]); @@ -1469,7 +1468,6 @@ static inline void decide_8b_10b_training_settings( */ lt_settings->link_settings.link_spread = link->dp_ss_off ? LINK_SPREAD_DISABLED : LINK_SPREAD_05_DOWNSPREAD_30KHZ; - lt_settings->lttpr_mode = link->lttpr_mode; lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting); lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting); lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting); @@ -1478,6 +1476,7 @@ static inline void decide_8b_10b_training_settings( lt_settings->should_set_fec_ready = true; lt_settings->disallow_per_lane_settings = true; lt_settings->always_match_dpcd_with_hw_lane_settings = true; + lt_settings->lttpr_mode = dp_decide_8b_10b_lttpr_mode(link); dp_hw_to_dpcd_lane_settings(lt_settings, lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } @@ -1501,9 +1500,8 @@ static inline void decide_128b_132b_training_settings(struct dc_link *link, lt_settings->cds_pattern_time = 2500; lt_settings->cds_wait_time_limit = (dp_convert_to_count( link->dpcd_caps.lttpr_caps.phy_repeater_cnt) + 1) * 20000; - lt_settings->lttpr_mode = dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) ? - LTTPR_MODE_NON_TRANSPARENT : LTTPR_MODE_TRANSPARENT; lt_settings->disallow_per_lane_settings = true; + lt_settings->lttpr_mode = dp_decide_128b_132b_lttpr_mode(link); dp_hw_to_dpcd_lane_settings(lt_settings, lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } @@ -1543,7 +1541,7 @@ static void override_training_settings( lt_settings->ffe_preset = overrides->ffe_preset; /* Override HW lane settings with BIOS forced values if present */ if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN && - link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { + lt_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) { lt_settings->voltage_swing = &link->bios_forced_drive_settings.VOLTAGE_SWING; lt_settings->pre_emphasis = &link->bios_forced_drive_settings.PRE_EMPHASIS; lt_settings->always_match_dpcd_with_hw_lane_settings = false; @@ -1584,6 +1582,15 @@ static void override_training_settings( if (link->preferred_training_settings.fec_enable != NULL) lt_settings->should_set_fec_ready = *link->preferred_training_settings.fec_enable; + + #if defined(CONFIG_DRM_AMD_DC_DCN) + /* Check DP tunnel LTTPR mode debug option. */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && link->dc->debug.dpia_debug.bits.force_non_lttpr) + lt_settings->lttpr_mode = LTTPR_MODE_NON_LTTPR; + +#endif + dp_get_lttpr_mode_override(link, <_settings->lttpr_mode); + } uint8_t dp_convert_to_count(uint8_t lttpr_repeater_count) @@ -1649,7 +1656,7 @@ static enum dc_status configure_lttpr_mode_non_transparent( link->dpcd_caps.lttpr_caps.mode = repeater_mode; } - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Non Transparent Mode\n", __func__); @@ -2015,7 +2022,7 @@ static enum link_training_result dp_perform_128b_132b_channel_eq_done_sequence( result = DP_128b_132b_LT_FAILED; } else { dp_set_hw_lane_settings(link, link_res, lt_settings, DPRX); - dpcd_set_lane_settings(link, lt_settings, DPRX); + dpcd_128b_132b_set_lane_settings(link, lt_settings); } loop_count++; } @@ -2099,7 +2106,7 @@ static enum link_training_result dp_perform_8b_10b_link_training( /* 1. set link rate, lane count and spread. */ dpcd_set_link_settings(link, lt_settings); - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { /* 2. perform link training (set link training done * to false is done as well) @@ -2216,7 +2223,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq link->vendor_specific_lttpr_link_rate_wa = target_rate; - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { /* 2. perform link training (set link training done * to false is done as well) @@ -2288,7 +2295,7 @@ static enum link_training_result dp_perform_fixed_vs_pe_training_sequence( ASSERT(dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING); - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { status = perform_fixed_vs_pe_nontransparent_training_sequence(link, link_res, lt_settings); return status; } @@ -2635,6 +2642,7 @@ enum link_training_result dc_link_dp_perform_link_training( link, link_settings, <_settings); + override_training_settings( link, &link->preferred_training_settings, @@ -2652,7 +2660,7 @@ enum link_training_result dc_link_dp_perform_link_training( * Per DP specs starting from here, DPTX device shall not issue * Non-LT AUX transactions inside training mode. */ - if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) + if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN && encoding == DP_8b_10b_ENCODING) status = dp_perform_fixed_vs_pe_training_sequence(link, link_res, <_settings); else if (encoding == DP_8b_10b_ENCODING) status = dp_perform_8b_10b_link_training(link, link_res, <_settings); @@ -2758,8 +2766,14 @@ 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, @@ -3080,7 +3094,7 @@ struct dc_link_settings dp_get_max_link_cap(struct dc_link *link) * account for lttpr repeaters cap * notes: repeaters do not snoop in the DPRX Capabilities addresses (3.6.3). */ - if (link->lttpr_mode != LTTPR_MODE_NON_LTTPR) { + if (dp_is_lttpr_present(link)) { if (link->dpcd_caps.lttpr_caps.max_lane_count < max_link_cap.lane_count) max_link_cap.lane_count = link->dpcd_caps.lttpr_caps.max_lane_count; lttpr_max_link_rate = get_lttpr_max_link_rate(link); @@ -3234,7 +3248,7 @@ static bool dp_verify_link_cap( cur_link_settings = max_link_settings; /* Grant extended timeout request */ - if ((link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (link->dpcd_caps.lttpr_caps.max_ext_timeout > 0)) { + if (dp_is_lttpr_present(link) && link->dpcd_caps.lttpr_caps.max_ext_timeout > 0) { uint8_t grant = link->dpcd_caps.lttpr_caps.max_ext_timeout & 0x80; core_link_write_dpcd(link, DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT, &grant, sizeof(grant)); @@ -4095,8 +4109,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) &dpcd_lane_adjustment[0].raw, sizeof(dpcd_lane_adjustment)); + /* prepare link training settings */ + link_training_settings.link_settings = link->cur_link_settings; + + link_training_settings.lttpr_mode = dp_decide_lttpr_mode(link, &link->cur_link_settings); + if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && - link->lttpr_mode == LTTPR_MODE_TRANSPARENT) + link_training_settings.lttpr_mode == LTTPR_MODE_TRANSPARENT) dp_fixed_vs_pe_read_lane_adjust( link, link_training_settings.dpcd_lane_settings); @@ -4203,9 +4222,6 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) test_pattern_size); } - /* prepare link training settings */ - link_training_settings.link_settings = link->cur_link_settings; - for (lane = 0; lane < (unsigned int)(link->cur_link_settings.lane_count); lane++) { @@ -4518,25 +4534,15 @@ void dc_link_dp_handle_link_loss(struct dc_link *link) for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) { - if (link->dc->hwss.update_phy_state) - link->dc->hwss.update_phy_state(link->dc->current_state, - pipe_ctx, TX_OFF_SYMCLK_OFF); - else - core_link_disable_stream(pipe_ctx); - } + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) + core_link_disable_stream(pipe_ctx); } for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) { - if (link->dc->hwss.update_phy_state) - link->dc->hwss.update_phy_state(link->dc->current_state, - pipe_ctx, TX_ON_SYMCLK_ON); - else - core_link_enable_stream(link->dc->current_state, pipe_ctx); - } + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) + core_link_enable_stream(link->dc->current_state, pipe_ctx); } } @@ -5025,125 +5031,151 @@ static bool dpcd_read_sink_ext_caps(struct dc_link *link) return true; } -/* Logic to determine LTTPR mode */ -static void determine_lttpr_mode(struct dc_link *link) +bool dp_retrieve_lttpr_cap(struct dc_link *link) { - bool allow_lttpr_non_transparent_mode = 0; - bool vbios_lttpr_enable = link->dc->caps.vbios_lttpr_enable; + uint8_t lttpr_dpcd_data[8]; + enum dc_status status = DC_ERROR_UNEXPECTED; + bool is_lttpr_present = false; + + /* Logic to determine LTTPR support*/ bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware; - if (link->ctx->dc->debug.lttpr_mode_override != 0) { - link->lttpr_mode = link->ctx->dc->debug.lttpr_mode_override; - return; - } + if (!vbios_lttpr_interop || !link->dc->caps.extended_aux_timeout_support) + return false; - if ((link->dc->config.allow_lttpr_non_transparent_mode.bits.DP2_0 && - link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED)) { - allow_lttpr_non_transparent_mode = 1; - } else if (link->dc->config.allow_lttpr_non_transparent_mode.bits.DP1_4A && - !link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) { - allow_lttpr_non_transparent_mode = 1; + /* By reading LTTPR capability, RX assumes that we will enable + * LTTPR extended aux timeout if LTTPR is present. + */ + status = core_link_read_dpcd(link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + lttpr_dpcd_data, + sizeof(lttpr_dpcd_data)); + + link->dpcd_caps.lttpr_caps.revision.raw = + lttpr_dpcd_data[DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.max_link_rate = + lttpr_dpcd_data[DP_MAX_LINK_RATE_PHY_REPEATER - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.phy_repeater_cnt = + lttpr_dpcd_data[DP_PHY_REPEATER_CNT - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.max_lane_count = + lttpr_dpcd_data[DP_MAX_LANE_COUNT_PHY_REPEATER - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.mode = + lttpr_dpcd_data[DP_PHY_REPEATER_MODE - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.max_ext_timeout = + lttpr_dpcd_data[DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + link->dpcd_caps.lttpr_caps.main_link_channel_coding.raw = + lttpr_dpcd_data[DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + + link->dpcd_caps.lttpr_caps.supported_128b_132b_rates.raw = + 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; + DC_LOG_DC("lttpr_caps forced phy_repeater_cnt = %d\n", link->dpcd_caps.lttpr_caps.phy_repeater_cnt); } - link->lttpr_mode = LTTPR_MODE_NON_LTTPR; - if (vbios_lttpr_enable && vbios_lttpr_interop) - link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; - else if (!vbios_lttpr_enable && vbios_lttpr_interop) { - if (allow_lttpr_non_transparent_mode) - link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; - else - link->lttpr_mode = LTTPR_MODE_TRANSPARENT; - } else if (!vbios_lttpr_enable && !vbios_lttpr_interop) { - if (!allow_lttpr_non_transparent_mode || !link->dc->caps.extended_aux_timeout_support) - link->lttpr_mode = LTTPR_MODE_NON_LTTPR; - else - link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; - } + /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ + is_lttpr_present = dp_is_lttpr_present(link); -#if defined(CONFIG_DRM_AMD_DC_DCN) - /* Check DP tunnel LTTPR mode debug option. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && - link->dc->debug.dpia_debug.bits.force_non_lttpr) - link->lttpr_mode = LTTPR_MODE_NON_LTTPR; -#endif + if (is_lttpr_present) + CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); + + DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); + return is_lttpr_present; } -bool dp_retrieve_lttpr_cap(struct dc_link *link) +bool dp_is_lttpr_present(struct dc_link *link) { - uint8_t lttpr_dpcd_data[8]; - enum dc_status status = DC_ERROR_UNEXPECTED; - bool is_lttpr_present = false; + return (dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) != 0 && + link->dpcd_caps.lttpr_caps.max_lane_count > 0 && + link->dpcd_caps.lttpr_caps.max_lane_count <= 4 && + link->dpcd_caps.lttpr_caps.revision.raw >= 0x14); +} - memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data)); +enum lttpr_mode dp_decide_lttpr_mode(struct dc_link *link, struct dc_link_settings *link_setting) +{ + enum dp_link_encoding encoding = dp_get_link_encoding_format(link_setting); - /* Logic to determine LTTPR mode*/ - determine_lttpr_mode(link); + if (encoding == DP_8b_10b_ENCODING) + return dp_decide_8b_10b_lttpr_mode(link); + else if (encoding == DP_128b_132b_ENCODING) + return dp_decide_128b_132b_lttpr_mode(link); - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT || link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { - if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && - !link->dc->debug.disable_fixed_vs_aux_timeout_wa) { - /* Fixed VS workaround for AUX timeout */ - const uint32_t fixed_vs_address = 0xF004F; - const uint8_t fixed_vs_data[4] = {0x1, 0x22, 0x63, 0xc}; + ASSERT(0); + return LTTPR_MODE_NON_LTTPR; +} - core_link_write_dpcd( - link, - fixed_vs_address, - fixed_vs_data, - sizeof(fixed_vs_data)); +void dp_get_lttpr_mode_override(struct dc_link *link, enum lttpr_mode *override) +{ + if (!dp_is_lttpr_present(link)) + return; + + if (link->dc->debug.lttpr_mode_override == LTTPR_MODE_TRANSPARENT) { + *override = LTTPR_MODE_TRANSPARENT; + } else if (link->dc->debug.lttpr_mode_override == LTTPR_MODE_NON_TRANSPARENT) { + *override = LTTPR_MODE_NON_TRANSPARENT; + } else if (link->dc->debug.lttpr_mode_override == LTTPR_MODE_NON_LTTPR) { + *override = LTTPR_MODE_NON_LTTPR; + } + DC_LOG_DC("lttpr_mode_override chose LTTPR_MODE = %d\n", (uint8_t)(*override)); +} + +enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link) +{ + bool is_lttpr_present = dp_is_lttpr_present(link); + bool vbios_lttpr_force_non_transparent = link->dc->caps.vbios_lttpr_enable; + bool vbios_lttpr_aware = link->dc->caps.vbios_lttpr_aware; + + if (!is_lttpr_present) + return LTTPR_MODE_NON_LTTPR; + + if (vbios_lttpr_aware) { + if (vbios_lttpr_force_non_transparent) { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT due to VBIOS DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE set to 1.\n"); + return LTTPR_MODE_NON_TRANSPARENT; + } else { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT by default due to VBIOS not set DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE set to 1.\n"); + return LTTPR_MODE_TRANSPARENT; } + } - /* By reading LTTPR capability, RX assumes that we will enable - * LTTPR extended aux timeout if LTTPR is present. - */ - status = core_link_read_dpcd( - link, - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, - lttpr_dpcd_data, - sizeof(lttpr_dpcd_data)); - - link->dpcd_caps.lttpr_caps.revision.raw = - lttpr_dpcd_data[DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.max_link_rate = - lttpr_dpcd_data[DP_MAX_LINK_RATE_PHY_REPEATER - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.phy_repeater_cnt = - lttpr_dpcd_data[DP_PHY_REPEATER_CNT - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.max_lane_count = - lttpr_dpcd_data[DP_MAX_LANE_COUNT_PHY_REPEATER - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.mode = - lttpr_dpcd_data[DP_PHY_REPEATER_MODE - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.max_ext_timeout = - lttpr_dpcd_data[DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - link->dpcd_caps.lttpr_caps.main_link_channel_coding.raw = - lttpr_dpcd_data[DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - link->dpcd_caps.lttpr_caps.supported_128b_132b_rates.raw = - lttpr_dpcd_data[DP_PHY_REPEATER_128B132B_RATES - - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; - - /* 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 && - link->dpcd_caps.lttpr_caps.revision.raw >= 0x14); - if (is_lttpr_present) { - CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); - configure_lttpr_mode_transparent(link); - } else - link->lttpr_mode = LTTPR_MODE_NON_LTTPR; + if (link->dc->config.allow_lttpr_non_transparent_mode.bits.DP1_4A && + link->dc->caps.extended_aux_timeout_support) { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT by default and dc->config.allow_lttpr_non_transparent_mode.bits.DP1_4A set to 1.\n"); + return LTTPR_MODE_NON_TRANSPARENT; } - return is_lttpr_present; + + DC_LOG_DC("chose LTTPR_MODE_NON_LTTPR.\n"); + return LTTPR_MODE_NON_LTTPR; +} + +enum lttpr_mode dp_decide_128b_132b_lttpr_mode(struct dc_link *link) +{ + enum lttpr_mode mode = LTTPR_MODE_NON_LTTPR; + + if (dp_is_lttpr_present(link)) + mode = LTTPR_MODE_NON_TRANSPARENT; + + DC_LOG_DC("128b_132b chose LTTPR_MODE %d.\n", mode); + return mode; } static bool get_usbc_cable_id(struct dc_link *link, union dp_cable_id *cable_id) @@ -5161,9 +5193,10 @@ static bool get_usbc_cable_id(struct dc_link *link, union dp_cable_id *cable_id) cmd.cable_id.data.input.phy_inst = resource_transmitter_to_phy_idx( link->dc, link->link_enc->transmitter); if (dc_dmub_srv_cmd_with_reply_data(link->ctx->dmub_srv, &cmd) && - cmd.cable_id.header.ret_status == 1) + cmd.cable_id.header.ret_status == 1) { cable_id->raw = cmd.cable_id.data.output_raw; - + DC_LOG_DC("usbc_cable_id = %d.\n", cable_id->raw); + } return cmd.cable_id.header.ret_status == 1; } @@ -5205,13 +5238,17 @@ static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout uint64_t current_ts = 0; uint64_t time_taken_ms = 0; enum dc_connection_type type = dc_connection_none; + bool lttpr_present; + bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware; - determine_lttpr_mode(link); + lttpr_present = dp_is_lttpr_present(link) || + (!vbios_lttpr_interop || !link->dc->caps.extended_aux_timeout_support); + DC_LOG_DC("lttpr_present = %d.\n", lttpr_present ? 1 : 0); /* Issue an AUX read to test DPRX responsiveness. If LTTPR is supported the first read is expected to * be to determine LTTPR capabilities. Otherwise trying to read power state should be an innocuous AUX read. */ - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT || link->lttpr_mode == LTTPR_MODE_TRANSPARENT) + if (lttpr_present) status = core_link_read_dpcd( link, DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, @@ -5341,6 +5378,10 @@ static bool retrieve_link_cap(struct dc_link *link) } is_lttpr_present = dp_retrieve_lttpr_cap(link); + + if (is_lttpr_present) + configure_lttpr_mode_transparent(link); + /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); @@ -5770,7 +5811,7 @@ void detect_edp_sink_caps(struct dc_link *link) * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13 && - (link->dc->debug.optimize_edp_link_rate || + (link->panel_config.ilr.optimize_edp_link_rate || link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)) { // Read DPCD 00010h - 0001Fh 16 bytes at one shot core_link_read_dpcd(link, DP_SUPPORTED_LINK_RATES, @@ -6092,7 +6133,7 @@ bool dc_link_dp_set_test_pattern( /* Set DPCD Lane Settings before running test pattern */ if (p_link_settings != NULL) { if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) && - link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { + p_link_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) { dp_fixed_vs_pe_set_retimer_lane_settings( link, p_link_settings->dpcd_lane_settings, @@ -6719,7 +6760,7 @@ bool is_edp_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timin ASSERT(link || crtc_timing); // invalid input if (link->dpcd_caps.edp_supported_link_rates_count == 0 || - !link->dc->debug.optimize_edp_link_rate) + !link->panel_config.ilr.optimize_edp_link_rate) return false; @@ -7069,68 +7110,16 @@ void dp_enable_link_phy( enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct dc *dc = link->ctx->dc; - struct dmcu *dmcu = dc->res_pool->dmcu; - struct pipe_ctx *pipes = - link->dc->current_state->res_ctx.pipe_ctx; - struct clock_source *dp_cs = - link->dc->res_pool->dp_clock_source; - const struct link_hwss *link_hwss = get_link_hwss(link, link_res); - unsigned int i; - - if (link->connector_signal == SIGNAL_TYPE_EDP) { - if (!link->dc->config.edp_no_power_sequencing) - link->dc->hwss.edp_power_control(link, true); - link->dc->hwss.edp_wait_for_hpd_ready(link, true); - } - - /* If the current pixel clock source is not DTO(happens after - * switching from HDMI passive dongle to DP on the same connector), - * switch the pixel clock source to DTO. - */ - for (i = 0; i < MAX_PIPES; i++) { - if (pipes[i].stream != NULL && - pipes[i].stream->link == link) { - if (pipes[i].clock_source != NULL && - pipes[i].clock_source->id != CLOCK_SOURCE_ID_DP_DTO) { - pipes[i].clock_source = dp_cs; - pipes[i].stream_res.pix_clk_params.requested_pix_clk_100hz = - pipes[i].stream->timing.pix_clk_100hz; - pipes[i].clock_source->funcs->program_pix_clk( - pipes[i].clock_source, - &pipes[i].stream_res.pix_clk_params, - dp_get_link_encoding_format(link_settings), - &pipes[i].pll_settings); - } - } - } - link->cur_link_settings = *link_settings; - - if (dp_get_link_encoding_format(link_settings) == DP_8b_10b_ENCODING) { - if (dc->clk_mgr->funcs->notify_link_rate_change) - dc->clk_mgr->funcs->notify_link_rate_change(dc->clk_mgr, link); - } - - if (dmcu != NULL && dmcu->funcs->lock_phy) - dmcu->funcs->lock_phy(dmcu); - - if (link_hwss->ext.enable_dp_link_output) - link_hwss->ext.enable_dp_link_output(link, link_res, signal, - clock_source, link_settings); - - if (dmcu != NULL && dmcu->funcs->unlock_phy) - dmcu->funcs->unlock_phy(dmcu); - - dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_LINK_PHY); + link->dc->hwss.enable_dp_link_output(link, link_res, signal, + clock_source, link_settings); dp_receiver_power_ctrl(link, true); } void edp_add_delay_for_T9(struct dc_link *link) { - if (link->local_sink && - link->local_sink->edid_caps.panel_patch.extra_delay_backlight_off > 0) - udelay(link->local_sink->edid_caps.panel_patch.extra_delay_backlight_off * 1000); + if (link && link->panel_config.pps.extra_delay_backlight_off > 0) + udelay(link->panel_config.pps.extra_delay_backlight_off * 1000); } bool edp_receiver_ready_T9(struct dc_link *link) @@ -7186,9 +7175,8 @@ bool edp_receiver_ready_T7(struct dc_link *link) } while (time_taken_in_ns < 50 * 1000000); //MAx T7 is 50ms } - if (link->local_sink && - link->local_sink->edid_caps.panel_patch.extra_t7_ms > 0) - udelay(link->local_sink->edid_caps.panel_patch.extra_t7_ms * 1000); + if (link && link->panel_config.pps.extra_t7_ms > 0) + udelay(link->panel_config.pps.extra_t7_ms * 1000); return result; } @@ -7197,29 +7185,11 @@ void dp_disable_link_phy(struct dc_link *link, const struct link_resource *link_ enum signal_type signal) { struct dc *dc = link->ctx->dc; - struct dmcu *dmcu = dc->res_pool->dmcu; - const struct link_hwss *link_hwss = get_link_hwss(link, link_res); if (!link->wa_flags.dp_keep_receiver_powered) dp_receiver_power_ctrl(link, false); - if (signal == SIGNAL_TYPE_EDP) { - if (link->dc->hwss.edp_backlight_control) - link->dc->hwss.edp_backlight_control(link, false); - if (link_hwss->ext.disable_dp_link_output) - link_hwss->ext.disable_dp_link_output(link, link_res, signal); - link->dc->hwss.edp_power_control(link, false); - } else { - if (dmcu != NULL && dmcu->funcs->lock_phy) - dmcu->funcs->lock_phy(dmcu); - if (link_hwss->ext.disable_dp_link_output) - link_hwss->ext.disable_dp_link_output(link, link_res, signal); - if (dmcu != NULL && dmcu->funcs->unlock_phy) - dmcu->funcs->unlock_phy(dmcu); - } - - dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); - + dc->hwss.disable_link_output(link, link_res, signal); /* Clear current link setting.*/ memset(&link->cur_link_settings, 0, sizeof(link->cur_link_settings)); @@ -7285,7 +7255,7 @@ void dp_set_hw_lane_settings( { const struct link_hwss *link_hwss = get_link_hwss(link, link_res); - if ((link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && !is_immediate_downstream(link, offset)) + if ((link_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && !is_immediate_downstream(link, offset)) return; if (link_hwss->ext.set_dp_lane_settings) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c index 468e39589ed8..74e36b34d3f7 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c @@ -115,12 +115,14 @@ static enum link_training_result dpia_configure_link( DC_LOG_HW_LINK_TRAINING("%s\n DPIA(%d) configuring\n - LTTPR mode(%d)\n", __func__, link->link_id.enum_id - ENUM_ID_1, - link->lttpr_mode); + lt_settings->lttpr_mode); dp_decide_training_settings(link, link_setting, lt_settings); + dp_get_lttpr_mode_override(link, <_settings->lttpr_mode); + status = dpcd_configure_channel_coding(link, lt_settings); if (status != DC_OK && link->is_hpd_pending) return LINK_TRAINING_ABORT; @@ -178,7 +180,7 @@ static uint8_t dpia_build_set_config_data(enum dpia_set_config_type type, switch (type) { case DPIA_SET_CFG_SET_LINK: - data.set_link.mode = link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT ? 1 : 0; + data.set_link.mode = lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT ? 1 : 0; break; case DPIA_SET_CFG_SET_PHY_TEST_MODE: break; @@ -553,7 +555,7 @@ static enum link_training_result dpia_training_cr_phase( { enum link_training_result result = LINK_TRAINING_CR_FAIL_LANE0; - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) result = dpia_training_cr_non_transparent(link, link_res, lt_settings, hop); else result = dpia_training_cr_transparent(link, link_res, lt_settings); @@ -830,7 +832,7 @@ static enum link_training_result dpia_training_eq_phase( { enum link_training_result result; - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) result = dpia_training_eq_non_transparent(link, link_res, lt_settings, hop); else result = dpia_training_eq_transparent(link, link_res, lt_settings); @@ -870,13 +872,14 @@ static enum dc_status dpcd_clear_lt_pattern(struct dc_link *link, uint32_t hop) * @param hop The Hop in display path. DPRX = 0. */ static enum link_training_result dpia_training_end(struct dc_link *link, + struct link_training_settings *lt_settings, uint32_t hop) { enum link_training_result result = LINK_TRAINING_SUCCESS; uint8_t repeater_cnt = 0; /* Number of hops/repeaters in display path. */ enum dc_status status; - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { + if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { repeater_cnt = dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); if (hop == repeater_cnt) { /* DPTX-to-DPIA */ @@ -916,7 +919,7 @@ static enum link_training_result dpia_training_end(struct dc_link *link, link->link_id.enum_id - ENUM_ID_1, hop, result, - link->lttpr_mode); + lt_settings->lttpr_mode); return result; } @@ -928,7 +931,9 @@ static enum link_training_result dpia_training_end(struct dc_link *link, * @param link DPIA link being trained. * @param hop The Hop in display path. DPRX = 0. */ -static void dpia_training_abort(struct dc_link *link, uint32_t hop) +static void dpia_training_abort(struct dc_link *link, + struct link_training_settings *lt_settings, + uint32_t hop) { uint8_t data = 0; uint32_t dpcd_tps_offset = DP_TRAINING_PATTERN_SET; @@ -936,7 +941,7 @@ static void dpia_training_abort(struct dc_link *link, uint32_t hop) DC_LOG_HW_LINK_TRAINING("%s\n DPIA(%d) aborting\n - LTTPR mode(%d)\n - HPD(%d)\n", __func__, link->link_id.enum_id - ENUM_ID_1, - link->lttpr_mode, + lt_settings->lttpr_mode, link->is_hpd_pending); /* Abandon clean-up if sink unplugged. */ @@ -964,12 +969,16 @@ enum link_training_result dc_link_dpia_perform_link_training( uint8_t repeater_cnt = 0; /* Number of hops/repeaters in display path. */ int8_t repeater_id; /* Current hop. */ + struct dc_link_settings link_settings = *link_setting; // non-const copy to pass in + + lt_settings.lttpr_mode = dp_decide_lttpr_mode(link, &link_settings); + /* Configure link as prescribed in link_setting and set LTTPR mode. */ result = dpia_configure_link(link, link_res, link_setting, <_settings); if (result != LINK_TRAINING_SUCCESS) return result; - if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + if (lt_settings.lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) repeater_cnt = dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); /* Train each hop in turn starting with the one closest to DPTX. @@ -987,7 +996,7 @@ enum link_training_result dc_link_dpia_perform_link_training( break; /* Stop training hop. */ - result = dpia_training_end(link, repeater_id); + result = dpia_training_end(link, <_settings, repeater_id); if (result != LINK_TRAINING_SUCCESS) break; } @@ -1001,9 +1010,9 @@ enum link_training_result dc_link_dpia_perform_link_training( msleep(5); result = dp_check_link_loss_status(link, <_settings); } else if (result == LINK_TRAINING_ABORT) { - dpia_training_abort(link, repeater_id); + dpia_training_abort(link, <_settings, repeater_id); } else { - dpia_training_end(link, repeater_id); + dpia_training_end(link, <_settings, repeater_id); } return result; } 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 29f27e3fe3ac..fd8db482e56f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1747,7 +1747,6 @@ bool dc_remove_plane_from_context( for (i = 0; i < stream_status->plane_count; i++) { if (stream_status->plane_states[i] == plane_state) { - dc_plane_state_release(stream_status->plane_states[i]); break; } @@ -3581,6 +3580,23 @@ 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 */ @@ -3645,3 +3661,77 @@ const struct link_hwss *get_link_hwss(const struct dc_link *link, else return get_virtual_link_hwss(); } + +bool is_h_timing_divisible_by_2(struct dc_stream_state *stream) +{ + bool divisible = false; + uint16_t h_blank_start = 0; + uint16_t h_blank_end = 0; + + if (stream) { + h_blank_start = stream->timing.h_total - stream->timing.h_front_porch; + h_blank_end = h_blank_start - stream->timing.h_addressable; + + /* HTOTAL, Hblank start/end, and Hsync start/end all must be + * divisible by 2 in order for the horizontal timing params + * to be considered divisible by 2. Hsync start is always 0. + */ + divisible = (stream->timing.h_total % 2 == 0) && + (h_blank_start % 2 == 0) && + (h_blank_end % 2 == 0) && + (stream->timing.h_sync_width % 2 == 0); + } + return divisible; +} + +bool dc_resource_acquire_secondary_pipe_for_mpc_odm( + const struct dc *dc, + struct dc_state *state, + struct pipe_ctx *pri_pipe, + struct pipe_ctx *sec_pipe, + bool odm) +{ + int pipe_idx = sec_pipe->pipe_idx; + struct pipe_ctx *sec_top, *sec_bottom, *sec_next, *sec_prev; + const struct resource_pool *pool = dc->res_pool; + + sec_top = sec_pipe->top_pipe; + sec_bottom = sec_pipe->bottom_pipe; + sec_next = sec_pipe->next_odm_pipe; + sec_prev = sec_pipe->prev_odm_pipe; + + *sec_pipe = *pri_pipe; + + sec_pipe->top_pipe = sec_top; + sec_pipe->bottom_pipe = sec_bottom; + sec_pipe->next_odm_pipe = sec_next; + sec_pipe->prev_odm_pipe = sec_prev; + + sec_pipe->pipe_idx = pipe_idx; + sec_pipe->plane_res.mi = pool->mis[pipe_idx]; + sec_pipe->plane_res.hubp = pool->hubps[pipe_idx]; + sec_pipe->plane_res.ipp = pool->ipps[pipe_idx]; + sec_pipe->plane_res.xfm = pool->transforms[pipe_idx]; + sec_pipe->plane_res.dpp = pool->dpps[pipe_idx]; + sec_pipe->plane_res.mpcc_inst = pool->dpps[pipe_idx]->inst; + sec_pipe->stream_res.dsc = NULL; + if (odm) { + if (!sec_pipe->top_pipe) + sec_pipe->stream_res.opp = pool->opps[pipe_idx]; + else + sec_pipe->stream_res.opp = sec_pipe->top_pipe->stream_res.opp; + if (sec_pipe->stream->timing.flags.DSC == 1) { +#if defined(CONFIG_DRM_AMD_DC_DCN) + dcn20_acquire_dsc(dc, &state->res_ctx, &sec_pipe->stream_res.dsc, pipe_idx); +#endif + ASSERT(sec_pipe->stream_res.dsc); + if (sec_pipe->stream_res.dsc == NULL) + return false; + } +#if defined(CONFIG_DRM_AMD_DC_DCN) + dcn20_build_mapped_resource(dc, state, sec_pipe->stream); +#endif + } + + return true; +}
\ No newline at end of file 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..38d71b5c1f2d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -30,6 +30,7 @@ #include "resource.h" #include "ipp.h" #include "timing_generator.h" +#include "dc_dmub_srv.h" #define DC_LOGGER dc->ctx->logger @@ -275,6 +276,8 @@ static void program_cursor_attributes( } dc->hwss.set_cursor_attribute(pipe_ctx); + + dc_send_update_cursor_info_to_dmu(pipe_ctx, i); if (dc->hwss.set_cursor_sdr_white_level) dc->hwss.set_cursor_sdr_white_level(pipe_ctx); } @@ -329,7 +332,7 @@ 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; @@ -381,6 +384,8 @@ static void program_cursor_position( } dc->hwss.set_cursor_position(pipe_ctx); + + dc_send_update_cursor_info_to_dmu(pipe_ctx, i); } if (pipe_to_program) @@ -521,7 +526,7 @@ bool dc_stream_remove_writeback(struct dc *dc, /* remove writeback info for disabled writeback pipes from stream */ for (i = 0, j = 0; i < stream->num_wb_info; i++) { if (stream->writeback_info[i].wb_enabled) { - if (i != j) + if (j < i) /* trim the array */ stream->writeback_info[j] = stream->writeback_info[i]; j++; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 75dbc665f435..bfc5474c0f4c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.201" +#define DC_VER "3.2.207" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -406,6 +406,9 @@ struct dc_config { bool ignore_dpref_ss; bool enable_mipi_converter_optimization; bool use_default_clock_table; + bool force_bios_enable_lttpr; + uint8_t force_bios_fixed_vs; + }; enum visual_confirm { @@ -818,7 +821,6 @@ struct dc_debug_options { /* Enable dmub aux for legacy ddc */ bool enable_dmub_aux_for_legacy_ddc; bool disable_fams; - bool optimize_edp_link_rate; /* eDP ILR */ /* FEC/PSR1 sequence enable delay in 100us */ uint8_t fec_enable_delay_in100us; bool enable_driver_sequence_debug; @@ -830,6 +832,10 @@ 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; + unsigned int force_subvp_num_ways; + unsigned int force_mall_ss_num_ways; + bool alloc_extra_way_for_cursor; bool force_usr_allow; /* uses value at boot and disables switch */ bool disable_dtb_ref_clk_switch; @@ -843,6 +849,7 @@ struct dc_debug_options { bool use_legacy_soc_bb_mechanism; bool exit_idle_opt_for_cursor_updates; bool enable_single_display_2to1_odm_policy; + bool enable_double_buffered_dsc_pg_support; bool enable_dp_dig_pixel_rate_div_policy; enum lttpr_mode lttpr_mode_override; }; @@ -1114,6 +1121,7 @@ union surface_update_flags { uint32_t clock_change:1; uint32_t stereo_format_change:1; uint32_t lut_3d:1; + uint32_t tmz_changed:1; uint32_t full_update:1; } bits; @@ -1183,6 +1191,8 @@ struct dc_plane_state { enum dc_irq_source irq_source; struct kref refcount; struct tg_color visual_confirm_color; + + bool is_statically_allocated; }; struct dc_plane_info { @@ -1602,6 +1612,9 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, uint8_t mst_alloc_slots, uint8_t *mst_slots_in_use); +void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, + uint32_t hpd_int_enable); + /******************************************************************************* * DSC Interfaces ******************************************************************************/ 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 7b765efe0825..0541e87e4f38 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -30,6 +30,7 @@ #include "dc_hw_types.h" #include "core_types.h" #include "../basics/conversion.h" +#include "cursor_reg_cache.h" #define CTX dc_dmub_srv->ctx #define DC_LOGGER CTX->logger @@ -450,44 +451,42 @@ 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; @@ -581,10 +580,12 @@ 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 @@ -592,16 +593,17 @@ 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)); } } @@ -668,19 +670,33 @@ 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)); + + if (subvp_pipe->bottom_pipe) { + pipe_data->pipe_config.subvp_data.main_split_pipe_index = subvp_pipe->bottom_pipe->pipe_idx; + } else if (subvp_pipe->next_odm_pipe) { + pipe_data->pipe_config.subvp_data.main_split_pipe_index = subvp_pipe->next_odm_pipe->pipe_idx; + } else { + pipe_data->pipe_config.subvp_data.main_split_pipe_index = 0; + } + // 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]; if (phantom_pipe->stream == subvp_pipe->stream->mall_stream_config.paired_stream) { pipe_data->pipe_config.subvp_data.phantom_pipe_index = phantom_pipe->pipe_idx; + if (phantom_pipe->bottom_pipe) { + pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = phantom_pipe->bottom_pipe->pipe_idx; + } else if (phantom_pipe->next_odm_pipe) { + pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = phantom_pipe->next_odm_pipe->pipe_idx; + } else { + pipe_data->pipe_config.subvp_data.phantom_split_pipe_index = 0; + } break; } } @@ -725,7 +741,9 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, if (!pipe->stream) continue; - if (pipe->plane_state && !pipe->top_pipe && + /* For SubVP pipe count, only count the top most (ODM / MPC) pipe + */ + if (pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && pipe->stream->mall_stream_config.type == SUBVP_MAIN) subvp_pipes[subvp_count++] = pipe; } @@ -738,7 +756,12 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, if (!pipe->stream) continue; + /* When populating subvp cmd info, only pass in the top most (ODM / MPC) pipe. + * Any ODM or MPC splits being used in SubVP will be handled internally in + * populate_subvp_cmd_pipe_info + */ if (pipe->plane_state && pipe->stream->mall_stream_config.paired_stream && + !pipe->top_pipe && !pipe->prev_odm_pipe && pipe->stream->mall_stream_config.type == SUBVP_MAIN) { populate_subvp_cmd_pipe_info(dc, context, &cmd, pipe, cmd_pipe_index++); } else if (pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_NONE) { @@ -758,7 +781,7 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, // Store the original watermark value for this SubVP config so we can lower it when the // MCLK switch starts wm_val_refclk = context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns * - dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 / 1000; + (dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000) / 1000; cmd.fw_assisted_mclk_switch_v2.config_data.watermark_a_cache = wm_val_refclk < 0xFFFF ? wm_val_refclk : 0xFFFF; } @@ -858,3 +881,147 @@ void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv) diag_data.is_cw0_enabled, diag_data.is_cw6_enabled); } + +static bool dc_dmub_should_update_cursor_data(struct pipe_ctx *pipe_ctx) +{ + if (pipe_ctx->plane_state != NULL) { + if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + return false; + } + + if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || + pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) && + pipe_ctx->stream->ctx->dce_version >= DCN_VERSION_3_1) + return true; + + return false; +} + +static void dc_build_cursor_update_payload0( + struct pipe_ctx *pipe_ctx, uint8_t p_idx, + struct dmub_cmd_update_cursor_payload0 *payload) +{ + struct hubp *hubp = pipe_ctx->plane_res.hubp; + unsigned int panel_inst = 0; + + if (!dc_get_edp_link_panel_inst(hubp->ctx->dc, + pipe_ctx->stream->link, &panel_inst)) + return; + + /* Payload: Cursor Rect is built from position & attribute + * x & y are obtained from postion + */ + payload->cursor_rect.x = hubp->cur_rect.x; + payload->cursor_rect.y = hubp->cur_rect.y; + /* w & h are obtained from attribute */ + payload->cursor_rect.width = hubp->cur_rect.w; + payload->cursor_rect.height = hubp->cur_rect.h; + + payload->enable = hubp->pos.cur_ctl.bits.cur_enable; + payload->pipe_idx = p_idx; + payload->cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1; + payload->panel_inst = panel_inst; +} + +static void dc_send_cmd_to_dmu(struct dc_dmub_srv *dmub_srv, + union dmub_rb_cmd *cmd) +{ + dc_dmub_srv_cmd_queue(dmub_srv, cmd); + dc_dmub_srv_cmd_execute(dmub_srv); + dc_dmub_srv_wait_idle(dmub_srv); +} + +static void dc_build_cursor_position_update_payload0( + struct dmub_cmd_update_cursor_payload0 *pl, const uint8_t p_idx, + const struct hubp *hubp, const struct dpp *dpp) +{ + /* Hubp */ + pl->position_cfg.pHubp.cur_ctl.raw = hubp->pos.cur_ctl.raw; + pl->position_cfg.pHubp.position.raw = hubp->pos.position.raw; + pl->position_cfg.pHubp.hot_spot.raw = hubp->pos.hot_spot.raw; + pl->position_cfg.pHubp.dst_offset.raw = hubp->pos.dst_offset.raw; + + /* dpp */ + pl->position_cfg.pDpp.cur0_ctl.raw = dpp->pos.cur0_ctl.raw; + pl->position_cfg.pipe_idx = p_idx; +} + +static void dc_build_cursor_attribute_update_payload1( + struct dmub_cursor_attributes_cfg *pl_A, const uint8_t p_idx, + const struct hubp *hubp, const struct dpp *dpp) +{ + /* Hubp */ + pl_A->aHubp.SURFACE_ADDR_HIGH = hubp->att.SURFACE_ADDR_HIGH; + pl_A->aHubp.SURFACE_ADDR = hubp->att.SURFACE_ADDR; + pl_A->aHubp.cur_ctl.raw = hubp->att.cur_ctl.raw; + pl_A->aHubp.size.raw = hubp->att.size.raw; + pl_A->aHubp.settings.raw = hubp->att.settings.raw; + + /* dpp */ + pl_A->aDpp.cur0_ctl.raw = dpp->att.cur0_ctl.raw; +} + +/** + * *************************************************************************************** + * dc_send_update_cursor_info_to_dmu: Populate the DMCUB Cursor update info command + * + * This function would store the cursor related information and pass it into dmub + * + * @param [in] pCtx: pipe context + * @param [in] pipe_idx: pipe index + * + * @return: void + * + * *************************************************************************************** + */ + +void dc_send_update_cursor_info_to_dmu( + struct pipe_ctx *pCtx, uint8_t pipe_idx) +{ + union dmub_rb_cmd cmd = { 0 }; + union dmub_cmd_update_cursor_info_data *update_cursor_info = + &cmd.update_cursor_info.update_cursor_info_data; + + if (!dc_dmub_should_update_cursor_data(pCtx)) + return; + /* + * Since we use multi_cmd_pending for dmub command, the 2nd command is + * only assigned to store cursor attributes info. + * 1st command can view as 2 parts, 1st is for PSR/Replay data, the other + * is to store cursor position info. + * + * Command heaer type must be the same type if using multi_cmd_pending. + * Besides, while process 2nd command in DMU, the sub type is useless. + * So it's meanless to pass the sub type header with different type. + */ + + { + /* Build Payload#0 Header */ + cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; + cmd.update_cursor_info.header.payload_bytes = + sizeof(cmd.update_cursor_info.update_cursor_info_data); + cmd.update_cursor_info.header.multi_cmd_pending = 1; /* To combine multi dmu cmd, 1st cmd */ + + /* Prepare Payload */ + dc_build_cursor_update_payload0(pCtx, pipe_idx, &update_cursor_info->payload0); + + dc_build_cursor_position_update_payload0(&update_cursor_info->payload0, pipe_idx, + pCtx->plane_res.hubp, pCtx->plane_res.dpp); + /* Send update_curosr_info to queue */ + dc_dmub_srv_cmd_queue(pCtx->stream->ctx->dmub_srv, &cmd); + } + { + /* Build Payload#1 Header */ + memset(update_cursor_info, 0, sizeof(union dmub_cmd_update_cursor_info_data)); + cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; + cmd.update_cursor_info.header.payload_bytes = sizeof(struct cursor_attributes_cfg); + cmd.update_cursor_info.header.multi_cmd_pending = 0; /* Indicate it's the last command. */ + + dc_build_cursor_attribute_update_payload1( + &cmd.update_cursor_info.update_cursor_info_data.payload1.attribute_cfg, + pipe_idx, pCtx->plane_res.hubp, pCtx->plane_res.dpp); + + /* Combine 2nd cmds update_curosr_info to DMU */ + dc_send_cmd_to_dmu(pCtx->stream->ctx->dmub_srv, &cmd); + } +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h index 9f5b47b9a83d..d34f5563df2e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -85,6 +85,8 @@ void dc_dmub_srv_send_inbox0_cmd(struct dc_dmub_srv *dmub_srv, union dmub_inbox0 bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmub_diagnostic_data *dmub_oca); +void dc_dmub_setup_subvp_dmub_command(struct dc *dc, struct dc_state *context, bool enable); void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv); +void dc_send_update_cursor_info_to_dmu(struct pipe_ctx *pCtx, uint8_t pipe_idx); #endif /* _DMUB_DC_SRV_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index 3f64b3092692..caf0c7af2d0b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -117,11 +117,31 @@ struct psr_settings { * Add a struct dc_panel_config under dc_link */ struct dc_panel_config { + // extra panel power sequence parameters + struct pps { + unsigned int extra_t3_ms; + unsigned int extra_t7_ms; + unsigned int extra_delay_backlight_off; + unsigned int extra_post_t7_ms; + unsigned int extra_pre_t11_ms; + unsigned int extra_t12_ms; + unsigned int extra_post_OUI_ms; + } pps; + // ABM + struct varib { + unsigned int varibright_feature_enable; + unsigned int def_varibright_level; + unsigned int abm_config_setting; + } varib; // edp DSC struct dsc { bool disable_dsc_edp; unsigned int force_dsc_edp_policy; } dsc; + /* eDP ILR */ + struct ilr { + bool optimize_edp_link_rate; /* eDP ILR */ + } ilr; }; /* * A link contains one or more sinks and their connected status. @@ -141,7 +161,6 @@ struct dc_link { bool link_state_valid; bool aux_access_disabled; bool sync_lt_in_progress; - enum lttpr_mode lttpr_mode; bool is_internal_display; /* TODO: Rename. Flag an endpoint as having a programmable mapping to a @@ -244,7 +263,7 @@ struct dc_link { struct gpio *hpd_gpio; enum dc_link_fec_state fec_state; struct dc_panel_config panel_config; - enum phy_state phy_state; + struct phy_state phy_state; }; const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link); diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 9fcf9dc5bce4..9e6025c98db9 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -212,8 +212,7 @@ struct dc_stream_state { /* DMCU info */ unsigned int abm_level; - struct periodic_interrupt_config periodic_interrupt0; - struct periodic_interrupt_config periodic_interrupt1; + struct periodic_interrupt_config periodic_interrupt; /* from core_stream struct */ struct dc_context *ctx; @@ -281,8 +280,7 @@ struct dc_stream_update { struct dc_info_packet *hdr_static_metadata; unsigned int *abm_level; - struct periodic_interrupt_config *periodic_interrupt0; - struct periodic_interrupt_config *periodic_interrupt1; + struct periodic_interrupt_config *periodic_interrupt; struct dc_info_packet *vrr_infopacket; struct dc_info_packet *vsc_infopacket; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c index bdb6bac8dd97..c94a966c6612 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c @@ -300,7 +300,7 @@ static void set_high_bit_rate_capable( AZ_REG_WRITE(AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_HBR, value); } -/* set video latency in in ms/2+1 */ +/* set video latency in ms/2+1 */ static void set_video_latency( struct audio *audio, int latency_in_ms) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 32782ef9ef77..140297c8ff55 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -942,10 +942,6 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, case AUX_RET_ERROR_ENGINE_ACQUIRE: case AUX_RET_ERROR_UNKNOWN: default: - DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION, - LOG_FLAG_I2cAux_DceAux, - "dce_aux_transfer_with_retries: Failure: operation_result=%d", - (int)operation_result); goto fail; } } @@ -953,14 +949,11 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, fail: DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR, LOG_FLAG_Error_I2cAux, - "dce_aux_transfer_with_retries: FAILURE"); + "%s: Failure: operation_result=%d", + __func__, + (int)operation_result); if (!payload_reply) payload->reply = NULL; - DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR, - WPP_BIT_FLAG_DC_ERROR, - "AUX transaction failed. Result: %d", - operation_result); - return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 0df06740ec39..bec5e9f787fc 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -393,17 +393,18 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, if (copy_settings_data->dsc_enable_status && link->dpcd_caps.sink_dev_id == DP_DEVICE_ID_38EC11 && !memcmp(link->dpcd_caps.sink_dev_id_str, DP_SINK_DEVICE_STR_ID_1, - sizeof(link->dpcd_caps.sink_dev_id_str))) + sizeof(DP_SINK_DEVICE_STR_ID_1))) link->psr_settings.force_ffu_mode = 1; else link->psr_settings.force_ffu_mode = 0; copy_settings_data->force_ffu_mode = link->psr_settings.force_ffu_mode; if (link->fec_state == dc_link_fec_enabled && + link->dpcd_caps.sink_dev_id == DP_DEVICE_ID_38EC11 && (!memcmp(link->dpcd_caps.sink_dev_id_str, DP_SINK_DEVICE_STR_ID_1, - sizeof(link->dpcd_caps.sink_dev_id_str)) || + sizeof(DP_SINK_DEVICE_STR_ID_1)) || !memcmp(link->dpcd_caps.sink_dev_id_str, DP_SINK_DEVICE_STR_ID_2, - sizeof(link->dpcd_caps.sink_dev_id_str)))) + sizeof(DP_SINK_DEVICE_STR_ID_2)))) copy_settings_data->debug.bitfields.force_wakeup_by_tps3 = 1; else copy_settings_data->debug.bitfields.force_wakeup_by_tps3 = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index fe346e96c2d1..d260eaa1509e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -722,7 +722,6 @@ void dce110_edp_wait_for_hpd_ready( struct dc_context *ctx = link->ctx; struct graphics_object_id connector = link->link_enc->connector; struct gpio *hpd; - struct dc_sink *sink = link->local_sink; bool edp_hpd_high = false; uint32_t time_elapsed = 0; uint32_t timeout = power_up ? @@ -755,9 +754,9 @@ void dce110_edp_wait_for_hpd_ready( return; } - if (sink != NULL) { - if (sink->edid_caps.panel_patch.extra_t3_ms > 0) { - int extra_t3_in_ms = sink->edid_caps.panel_patch.extra_t3_ms; + if (link != NULL) { + if (link->panel_config.pps.extra_t3_ms > 0) { + int extra_t3_in_ms = link->panel_config.pps.extra_t3_ms; msleep(extra_t3_in_ms); } @@ -842,7 +841,7 @@ void dce110_edp_power_control( /* add time defined by a patch, if any (usually patch extra_t12_ms is 0) */ if (link->local_sink != NULL) remaining_min_edp_poweroff_time_ms += - link->local_sink->edid_caps.panel_patch.extra_t12_ms; + link->panel_config.pps.extra_t12_ms; /* Adjust remaining_min_edp_poweroff_time_ms if this is not the first time. */ if (dp_trace_get_edp_poweroff_timestamp(link) != 0) { @@ -946,7 +945,7 @@ void dce110_edp_wait_for_T12( current_ts, dp_trace_get_edp_poweroff_timestamp(link)), 1000000); - t12_duration += link->local_sink->edid_caps.panel_patch.extra_t12_ms; // Add extra T12 + t12_duration += link->panel_config.pps.extra_t12_ms; // Add extra T12 if (time_since_edp_poweroff_ms < t12_duration) msleep(t12_duration - time_since_edp_poweroff_ms); @@ -965,6 +964,8 @@ void dce110_edp_backlight_control( struct dc_context *ctx = link->ctx; struct bp_transmitter_control cntl = { 0 }; uint8_t panel_instance; + unsigned int pre_T11_delay = OLED_PRE_T11_DELAY; + unsigned int post_T7_delay = OLED_POST_T7_DELAY; if (dal_graphics_object_id_get_connector_id(link->link_enc->connector) != CONNECTOR_ID_EDP) { @@ -1043,8 +1044,10 @@ void dce110_edp_backlight_control( link_transmitter_control(ctx->dc_bios, &cntl); - if (enable && link->dpcd_sink_ext_caps.bits.oled) - msleep(OLED_POST_T7_DELAY); + if (enable && link->dpcd_sink_ext_caps.bits.oled) { + post_T7_delay += link->panel_config.pps.extra_post_t7_ms; + msleep(post_T7_delay); + } if (link->dpcd_sink_ext_caps.bits.oled || link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 || @@ -1066,8 +1069,10 @@ void dce110_edp_backlight_control( DC_LOG_DC("edp_receiver_ready_T9 skipped\n"); } - if (!enable && link->dpcd_sink_ext_caps.bits.oled) - msleep(OLED_PRE_T11_DELAY); + if (!enable && link->dpcd_sink_ext_caps.bits.oled) { + pre_T11_delay += link->panel_config.pps.extra_pre_t11_ms; + msleep(pre_T11_delay); + } } void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) @@ -1441,6 +1446,14 @@ static enum dc_status dce110_enable_stream_timing( return DC_ERROR_UNEXPECTED; } + if (dc_is_hdmi_tmds_signal(stream->signal)) { + stream->link->phy_state.symclk_ref_cnts.otg = 1; + if (stream->link->phy_state.symclk_state == SYMCLK_OFF_TX_OFF) + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + else + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_ON; + } + pipe_ctx->stream_res.tg->funcs->program_timing( pipe_ctx->stream_res.tg, &stream->timing, @@ -1577,25 +1590,8 @@ static enum dc_status apply_single_controller_ctx_to_hw( if (dc_is_dp_signal(pipe_ctx->stream->signal)) dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_CONNECT_DIG_FE_OTG); - /* Have to setup DSC before DIG FE and BE are connected (which happens before the - * link training). This is to make sure the bandwidth sent to DIG BE won't be - * bigger than what the link and/or DIG BE can handle. VBID[6]/CompressedStream_flag - * will be automatically set at a later time when the video is enabled - * (DP_VID_STREAM_EN = 1). - */ - if (pipe_ctx->stream->timing.flags.DSC) { - if (dc_is_dp_signal(pipe_ctx->stream->signal) || - dc_is_virtual_signal(pipe_ctx->stream->signal)) - dp_set_dsc_enable(pipe_ctx, true); - - } - - if (!stream->dpms_off) { - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(context, pipe_ctx, TX_ON_SYMCLK_ON); - else - core_link_enable_stream(context, pipe_ctx); - } + if (!stream->dpms_off) + core_link_enable_stream(context, pipe_ctx); /* DCN3.1 FPGA Workaround * Need to enable HPO DP Stream Encoder before setting OTG master enable. @@ -2131,6 +2127,7 @@ static void dce110_reset_hw_ctx_wrap( BREAK_TO_DEBUGGER(); } pipe_ctx_old->stream_res.tg->funcs->disable_crtc(pipe_ctx_old->stream_res.tg); + pipe_ctx_old->stream->link->phy_state.symclk_ref_cnts.otg = 0; pipe_ctx_old->plane_res.mi->funcs->free_mem_input( pipe_ctx_old->plane_res.mi, dc->current_state->stream_count); @@ -3009,6 +3006,124 @@ void dce110_set_pipe(struct pipe_ctx *pipe_ctx) abm->funcs->set_pipe(abm, otg_inst, panel_cntl->inst); } +void dce110_enable_lvds_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum clock_source_id clock_source, + uint32_t pixel_clock) +{ + link->link_enc->funcs->enable_lvds_output( + link->link_enc, + clock_source, + pixel_clock); + link->phy_state.symclk_state = SYMCLK_ON_TX_ON; +} + +void dce110_enable_tmds_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + enum dc_color_depth color_depth, + uint32_t pixel_clock) +{ + link->link_enc->funcs->enable_tmds_output( + link->link_enc, + clock_source, + color_depth, + signal, + pixel_clock); + link->phy_state.symclk_state = SYMCLK_ON_TX_ON; +} + +void dce110_enable_dp_link_output( + struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + const struct dc_link_settings *link_settings) +{ + struct dc *dc = link->ctx->dc; + struct dmcu *dmcu = dc->res_pool->dmcu; + struct pipe_ctx *pipes = + link->dc->current_state->res_ctx.pipe_ctx; + struct clock_source *dp_cs = + link->dc->res_pool->dp_clock_source; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + unsigned int i; + + + if (link->connector_signal == SIGNAL_TYPE_EDP) { + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, true); + link->dc->hwss.edp_wait_for_hpd_ready(link, true); + } + + /* If the current pixel clock source is not DTO(happens after + * switching from HDMI passive dongle to DP on the same connector), + * switch the pixel clock source to DTO. + */ + + for (i = 0; i < MAX_PIPES; i++) { + if (pipes[i].stream != NULL && + pipes[i].stream->link == link) { + if (pipes[i].clock_source != NULL && + pipes[i].clock_source->id != CLOCK_SOURCE_ID_DP_DTO) { + pipes[i].clock_source = dp_cs; + pipes[i].stream_res.pix_clk_params.requested_pix_clk_100hz = + pipes[i].stream->timing.pix_clk_100hz; + pipes[i].clock_source->funcs->program_pix_clk( + pipes[i].clock_source, + &pipes[i].stream_res.pix_clk_params, + dp_get_link_encoding_format(link_settings), + &pipes[i].pll_settings); + } + } + } + + if (dp_get_link_encoding_format(link_settings) == DP_8b_10b_ENCODING) { + if (dc->clk_mgr->funcs->notify_link_rate_change) + dc->clk_mgr->funcs->notify_link_rate_change(dc->clk_mgr, link); + } + + if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + if (link_hwss->ext.enable_dp_link_output) + link_hwss->ext.enable_dp_link_output(link, link_res, signal, + clock_source, link_settings); + + link->phy_state.symclk_state = SYMCLK_ON_TX_ON; + + if (dmcu != NULL && dmcu->funcs->unlock_phy) + dmcu->funcs->unlock_phy(dmcu); + + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_LINK_PHY); +} + +void dce110_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct dc *dc = link->ctx->dc; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + struct dmcu *dmcu = dc->res_pool->dmcu; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + link_hwss->disable_link_output(link, link_res, signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_power_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->unlock_phy(dmcu); + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); +} + static const struct hw_sequencer_funcs dce110_funcs = { .program_gamut_remap = program_gamut_remap, .program_output_csc = program_output_csc, @@ -3048,6 +3163,10 @@ static const struct hw_sequencer_funcs dce110_funcs = { .set_backlight_level = dce110_set_backlight_level, .set_abm_immediate_disable = dce110_set_abm_immediate_disable, .set_pipe = dce110_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, }; static const struct hwseq_private_funcs dce110_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h index b6f3843d3d05..758f4b3b0087 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h @@ -90,6 +90,24 @@ bool dce110_set_backlight_level(struct pipe_ctx *pipe_ctx, uint32_t frame_ramp); void dce110_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx); void dce110_set_pipe(struct pipe_ctx *pipe_ctx); - +void dce110_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal); +void dce110_enable_lvds_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum clock_source_id clock_source, + uint32_t pixel_clock); +void dce110_enable_tmds_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + enum dc_color_depth color_depth, + uint32_t pixel_clock); +void dce110_enable_dp_link_output( + struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + const struct dc_link_settings *link_settings); #endif /* __DC_HWSS_DCE110_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c index 897f412f539e..b9765b3899e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c @@ -469,6 +469,7 @@ void dpp1_set_cursor_position( REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en); + dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; } void dpp1_cnv_set_optional_cursor_attributes( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index f26e08032da0..11e4c4e46947 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -899,6 +899,14 @@ enum dc_status dcn10_enable_stream_timing( return DC_ERROR_UNEXPECTED; } + if (dc_is_hdmi_tmds_signal(stream->signal)) { + stream->link->phy_state.symclk_ref_cnts.otg = 1; + if (stream->link->phy_state.symclk_state == SYMCLK_OFF_TX_OFF) + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + else + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_ON; + } + pipe_ctx->stream_res.tg->funcs->program_timing( pipe_ctx->stream_res.tg, &stream->timing, @@ -1017,6 +1025,7 @@ static void dcn10_reset_back_end_for_pipe( if (pipe_ctx->stream_res.tg->funcs->set_drr) pipe_ctx->stream_res.tg->funcs->set_drr( pipe_ctx->stream_res.tg, NULL); + pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; } for (i = 0; i < dc->res_pool->pipe_count; i++) @@ -2235,6 +2244,9 @@ void dcn10_enable_timing_synchronization( DC_SYNC_INFO("Setting up OTG reset trigger\n"); for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); @@ -2245,13 +2257,21 @@ void dcn10_enable_timing_synchronization( for (i = 0; i < group_size; i++) { if (grouped_pipes[i]->stream == NULL) continue; + + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream->vblank_synchronized = false; } - for (i = 1; i < group_size; i++) + for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream_res.tg->funcs->enable_reset_trigger( grouped_pipes[i]->stream_res.tg, grouped_pipes[0]->stream_res.tg->inst); + } DC_SYNC_INFO("Waiting for trigger\n"); @@ -2259,12 +2279,21 @@ void dcn10_enable_timing_synchronization( * synchronized. Look at last pipe programmed to reset. */ - wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[1]->stream_res.tg); - for (i = 1; i < group_size; i++) + if (grouped_pipes[1]->stream && grouped_pipes[1]->stream->mall_stream_config.type != SUBVP_PHANTOM) + wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[1]->stream_res.tg); + + for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream_res.tg->funcs->disable_reset_trigger( grouped_pipes[i]->stream_res.tg); + } for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); @@ -2996,6 +3025,7 @@ void dcn10_prepare_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3018,8 +3048,11 @@ void dcn10_prepare_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3032,6 +3065,7 @@ void dcn10_optimize_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3055,8 +3089,11 @@ void dcn10_optimize_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3335,127 +3372,6 @@ static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) return false; } -static bool dcn10_dmub_should_update_cursor_data( - struct pipe_ctx *pipe_ctx, - struct dc_debug_options *debug) -{ - if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) - return false; - - if (dcn10_can_pipe_disable_cursor(pipe_ctx)) - return false; - - if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) - && pipe_ctx->stream->ctx->dce_version >= DCN_VERSION_3_1) - return true; - - return false; -} - -static void dcn10_dmub_update_cursor_data( - struct pipe_ctx *pipe_ctx, - struct hubp *hubp, - const struct dc_cursor_mi_param *param, - const struct dc_cursor_position *cur_pos, - const struct dc_cursor_attributes *cur_attr) -{ - union dmub_rb_cmd cmd; - struct dmub_cmd_update_cursor_info_data *update_cursor_info; - const struct dc_cursor_position *pos; - const struct dc_cursor_attributes *attr; - int src_x_offset = 0; - int src_y_offset = 0; - int x_hotspot = 0; - int cursor_height = 0; - int cursor_width = 0; - uint32_t cur_en = 0; - unsigned int panel_inst = 0; - - struct dc_debug_options *debug = &hubp->ctx->dc->debug; - - if (!dcn10_dmub_should_update_cursor_data(pipe_ctx, debug)) - return; - /** - * if cur_pos == NULL means the caller is from cursor_set_attribute - * then driver use previous cursor position data - * if cur_attr == NULL means the caller is from cursor_set_position - * then driver use previous cursor attribute - * if cur_pos or cur_attr is not NULL then update it - */ - if (cur_pos != NULL) - pos = cur_pos; - else - pos = &hubp->curs_pos; - - if (cur_attr != NULL) - attr = cur_attr; - else - attr = &hubp->curs_attr; - - if (!dc_get_edp_link_panel_inst(hubp->ctx->dc, pipe_ctx->stream->link, &panel_inst)) - return; - - src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; - x_hotspot = pos->x_hotspot; - cursor_height = (int)attr->height; - cursor_width = (int)attr->width; - cur_en = pos->enable ? 1:0; - - // Rotated cursor width/height and hotspots tweaks for offset calculation - if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { - swap(cursor_height, cursor_width); - if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; - } - } else if (param->rotation == ROTATION_ANGLE_180) { - src_x_offset = pos->x - param->viewport.x; - src_y_offset = pos->y - param->viewport.y; - } - - if (param->mirror) { - x_hotspot = param->viewport.width - x_hotspot; - src_x_offset = param->viewport.x + param->viewport.width - src_x_offset; - } - - if (src_x_offset >= (int)param->viewport.width) - cur_en = 0; /* not visible beyond right edge*/ - - if (src_x_offset + cursor_width <= 0) - cur_en = 0; /* not visible beyond left edge*/ - - if (src_y_offset >= (int)param->viewport.height) - cur_en = 0; /* not visible beyond bottom edge*/ - - if (src_y_offset + cursor_height <= 0) - cur_en = 0; /* not visible beyond top edge*/ - - // Cursor bitmaps have different hotspot values - // There's a possibility that the above logic returns a negative value, so we clamp them to 0 - if (src_x_offset < 0) - src_x_offset = 0; - if (src_y_offset < 0) - src_y_offset = 0; - - memset(&cmd, 0x0, sizeof(cmd)); - cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; - cmd.update_cursor_info.header.payload_bytes = - sizeof(cmd.update_cursor_info.update_cursor_info_data); - update_cursor_info = &cmd.update_cursor_info.update_cursor_info_data; - update_cursor_info->cursor_rect.x = src_x_offset + param->viewport.x; - update_cursor_info->cursor_rect.y = src_y_offset + param->viewport.y; - update_cursor_info->cursor_rect.width = attr->width; - update_cursor_info->cursor_rect.height = attr->height; - update_cursor_info->enable = cur_en; - update_cursor_info->pipe_idx = pipe_ctx->pipe_idx; - update_cursor_info->cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1; - update_cursor_info->panel_inst = panel_inst; - dc_dmub_srv_cmd_queue(pipe_ctx->stream->ctx->dmub_srv, &cmd); - dc_dmub_srv_cmd_execute(pipe_ctx->stream->ctx->dmub_srv); - dc_dmub_srv_wait_idle(pipe_ctx->stream->ctx->dmub_srv); -} - void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) { struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; @@ -3690,7 +3606,6 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.y; } - dcn10_dmub_update_cursor_data(pipe_ctx, hubp, ¶m, &pos_cpy, NULL); hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width, hubp->curs_attr.height); } @@ -3698,25 +3613,6 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx) { struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; - struct dc_cursor_mi_param param = { 0 }; - - /** - * If enter PSR without cursor attribute update - * the cursor attribute of dmub_restore_plane - * are initial value. call dmub to exit PSR and - * restore plane then update cursor attribute to - * avoid override with initial value - */ - if (pipe_ctx->plane_state != NULL) { - param.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; - param.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clocks.dchub_ref_clock_inKhz; - param.viewport = pipe_ctx->plane_res.scl_data.viewport; - param.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz; - param.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert; - param.rotation = pipe_ctx->plane_state->rotation; - param.mirror = pipe_ctx->plane_state->horizontal_mirror; - dcn10_dmub_update_cursor_data(pipe_ctx, pipe_ctx->plane_res.hubp, ¶m, NULL, attributes); - } pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( pipe_ctx->plane_res.hubp, attributes); @@ -3801,81 +3697,56 @@ void dcn10_calc_vupdate_position( uint32_t *start_line, uint32_t *end_line) { - const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing; - int vline_int_offset_from_vupdate = - pipe_ctx->stream->periodic_interrupt0.lines_offset; - int vupdate_offset_from_vsync = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); - int start_position; - - if (vline_int_offset_from_vupdate > 0) - vline_int_offset_from_vupdate--; - else if (vline_int_offset_from_vupdate < 0) - vline_int_offset_from_vupdate++; - - start_position = vline_int_offset_from_vupdate + vupdate_offset_from_vsync; + const struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + int vupdate_pos = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); - if (start_position >= 0) - *start_line = start_position; + if (vupdate_pos >= 0) + *start_line = vupdate_pos - ((vupdate_pos / timing->v_total) * timing->v_total); else - *start_line = dc_crtc_timing->v_total + start_position - 1; - - *end_line = *start_line + 2; - - if (*end_line >= dc_crtc_timing->v_total) - *end_line = 2; + *start_line = vupdate_pos + ((-vupdate_pos / timing->v_total) + 1) * timing->v_total - 1; + *end_line = (*start_line + 2) % timing->v_total; } static void dcn10_cal_vline_position( struct dc *dc, struct pipe_ctx *pipe_ctx, - enum vline_select vline, uint32_t *start_line, uint32_t *end_line) { - enum vertical_interrupt_ref_point ref_point = INVALID_POINT; + const struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + int vline_pos = pipe_ctx->stream->periodic_interrupt.lines_offset; - if (vline == VLINE0) - ref_point = pipe_ctx->stream->periodic_interrupt0.ref_point; - else if (vline == VLINE1) - ref_point = pipe_ctx->stream->periodic_interrupt1.ref_point; + if (pipe_ctx->stream->periodic_interrupt.ref_point == START_V_UPDATE) { + if (vline_pos > 0) + vline_pos--; + else if (vline_pos < 0) + vline_pos++; - switch (ref_point) { - case START_V_UPDATE: - dcn10_calc_vupdate_position( - dc, - pipe_ctx, - start_line, - end_line); - break; - case START_V_SYNC: - // Suppose to do nothing because vsync is 0; - break; - default: + vline_pos += dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); + if (vline_pos >= 0) + *start_line = vline_pos - ((vline_pos / timing->v_total) * timing->v_total); + else + *start_line = vline_pos + ((-vline_pos / timing->v_total) + 1) * timing->v_total - 1; + *end_line = (*start_line + 2) % timing->v_total; + } else if (pipe_ctx->stream->periodic_interrupt.ref_point == START_V_SYNC) { + // vsync is line 0 so start_line is just the requested line offset + *start_line = vline_pos; + *end_line = (*start_line + 2) % timing->v_total; + } else ASSERT(0); - break; - } } void dcn10_setup_periodic_interrupt( struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline) + struct pipe_ctx *pipe_ctx) { struct timing_generator *tg = pipe_ctx->stream_res.tg; + uint32_t start_line = 0; + uint32_t end_line = 0; - if (vline == VLINE0) { - uint32_t start_line = 0; - uint32_t end_line = 0; - - dcn10_cal_vline_position(dc, pipe_ctx, vline, &start_line, &end_line); + dcn10_cal_vline_position(dc, pipe_ctx, &start_line, &end_line); - tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line); - - } else if (vline == VLINE1) { - pipe_ctx->stream_res.tg->funcs->setup_vertical_interrupt1( - tg, - pipe_ctx->stream->periodic_interrupt1.lines_offset); - } + tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line); } void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h index 9ae07c77fdc0..0ef7bf7ddb75 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h @@ -175,8 +175,7 @@ void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx); void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx); void dcn10_setup_periodic_interrupt( struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline); + struct pipe_ctx *pipe_ctx); enum dc_status dcn10_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32_t clk_khz, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c index 10e613ec7d24..f2371c948822 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c @@ -82,6 +82,10 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .set_backlight_level = dce110_set_backlight_level, .set_abm_immediate_disable = dce110_set_abm_immediate_disable, .set_pipe = dce110_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .get_dcc_en_bits = dcn10_get_dcc_en_bits, .update_visual_confirm_color = dcn10_update_visual_confirm_color, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 294827906c69..33d780218790 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -207,10 +207,7 @@ void optc1_program_timing( /* In case of V_TOTAL_CONTROL is on, make sure OTG_V_TOTAL_MAX and * OTG_V_TOTAL_MIN are equal to V_TOTAL. */ - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, v_total); - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, v_total); + optc->funcs->set_vtotal_min_max(optc, v_total, v_total); /* v_sync_start = 0, v_sync_end = v_sync_width */ v_sync_end = patched_crtc_timing.v_sync_width; @@ -649,13 +646,6 @@ uint32_t optc1_get_vblank_counter(struct timing_generator *optc) void optc1_lock(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - uint32_t regval = 0; - - regval = REG_READ(OTG_CONTROL); - - /* otg is not running, do not need to be locked */ - if ((regval & 0x1) == 0x0) - return; REG_SET(OTG_GLOBAL_CONTROL0, 0, OTG_MASTER_UPDATE_LOCK_SEL, optc->inst); @@ -663,12 +653,10 @@ void optc1_lock(struct timing_generator *optc) OTG_MASTER_UPDATE_LOCK, 1); /* Should be fast, status does not update on maximus */ - if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS) { - + if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS) REG_WAIT(OTG_MASTER_UPDATE_LOCK, UPDATE_LOCK_STATUS, 1, 1, 10); - } } void optc1_unlock(struct timing_generator *optc) @@ -679,16 +667,6 @@ void optc1_unlock(struct timing_generator *optc) OTG_MASTER_UPDATE_LOCK, 0); } -bool optc1_is_locked(struct timing_generator *optc) -{ - struct optc *optc1 = DCN10TG_FROM_TG(optc); - uint32_t locked; - - REG_GET(OTG_MASTER_UPDATE_LOCK, UPDATE_LOCK_STATUS, &locked); - - return (locked == 1); -} - void optc1_get_position(struct timing_generator *optc, struct crtc_position *position) { @@ -941,11 +919,7 @@ void optc1_set_drr( } - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, params->vertical_total_max - 1); - - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, params->vertical_total_min - 1); + optc->funcs->set_vtotal_min_max(optc, params->vertical_total_min - 1, params->vertical_total_max - 1); REG_UPDATE_5(OTG_V_TOTAL_CONTROL, OTG_V_TOTAL_MIN_SEL, 1, @@ -964,11 +938,7 @@ void optc1_set_drr( OTG_V_TOTAL_MAX_SEL, 0, OTG_FORCE_LOCK_ON_EVENT, 0); - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, 0); - - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, 0); + optc->funcs->set_vtotal_min_max(optc, 0, 0); } } @@ -1393,6 +1363,12 @@ void optc1_read_otg_state(struct optc *optc1, REG_GET(OPTC_INPUT_GLOBAL_CONTROL, OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status); + REG_GET(OTG_VERTICAL_INTERRUPT1_CONTROL, + OTG_VERTICAL_INTERRUPT1_INT_ENABLE, &s->vertical_interrupt1_en); + + REG_GET(OTG_VERTICAL_INTERRUPT1_POSITION, + OTG_VERTICAL_INTERRUPT1_LINE_START, &s->vertical_interrupt1_line); + REG_GET(OTG_VERTICAL_INTERRUPT2_CONTROL, OTG_VERTICAL_INTERRUPT2_INT_ENABLE, &s->vertical_interrupt2_en); @@ -1577,11 +1553,11 @@ static const struct timing_generator_funcs dcn10_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc1_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = NULL, + .set_vtotal_min_max = optc1_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .set_test_pattern = optc1_set_test_pattern, .program_stereo = optc1_program_stereo, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index 3fe5882ed018..88ac5f6f4c96 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -583,6 +583,8 @@ struct dcn_otg_state { uint32_t underflow_occurred_status; uint32_t otg_enabled; uint32_t blank_enabled; + uint32_t vertical_interrupt1_en; + uint32_t vertical_interrupt1_line; uint32_t vertical_interrupt2_en; uint32_t vertical_interrupt2_line; }; @@ -652,7 +654,6 @@ void optc1_set_blank(struct timing_generator *optc, bool enable_blanking); bool optc1_is_blanked(struct timing_generator *optc); -bool optc1_is_locked(struct timing_generator *optc); void optc1_program_blank_color( struct timing_generator *optc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 831080b9eb87..56d30baf12df 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1336,6 +1336,21 @@ static noinline void dcn10_resource_construct_fp( } } +static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks) +{ + int i; + + if (clks->num_levels == 0) + return false; + + for (i = 0; i < clks->num_levels; i++) + /* Ensure that the result is sane */ + if (clks->data[i].clocks_in_khz == 0) + return false; + + return true; +} + static bool dcn10_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -1345,6 +1360,9 @@ static bool dcn10_resource_construct( int j; struct dc_context *ctx = dc->ctx; uint32_t pipe_fuses = read_pipe_fuses(ctx); + struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0}; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; + bool res; ctx->dc_bios->regs = &bios_regs; @@ -1523,15 +1541,53 @@ static bool dcn10_resource_construct( && pool->base.pp_smu->rv_funcs.set_pme_wa_enable != NULL) dc->debug.az_endpoint_mute_only = false; - DC_FP_START(); - if (!dc->debug.disable_pplib_clock_request) - dcn_bw_update_from_pplib(dc); + + if (!dc->debug.disable_pplib_clock_request) { + /* + * TODO: This is not the proper way to obtain + * fabric_and_dram_bandwidth, should be min(fclk, memclk). + */ + res = dm_pp_get_clock_levels_by_type_with_voltage( + ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks); + + DC_FP_START(); + + if (res) + res = verify_clock_values(&fclks); + + if (res) + dcn_bw_update_from_pplib_fclks(dc, &fclks); + else + BREAK_TO_DEBUGGER(); + + DC_FP_END(); + + res = dm_pp_get_clock_levels_by_type_with_voltage( + ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks); + + DC_FP_START(); + + if (res) + res = verify_clock_values(&dcfclks); + + if (res) + dcn_bw_update_from_pplib_dcfclks(dc, &dcfclks); + else + BREAK_TO_DEBUGGER(); + + DC_FP_END(); + } + dcn_bw_sync_calcs_and_dml(dc); if (!dc->debug.disable_pplib_wm_range) { dc->res_pool = &pool->base; - dcn_bw_notify_pplib_of_wm_ranges(dc); + DC_FP_START(); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); + DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } - DC_FP_END(); { struct irq_service_init_data init_data; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h index 2b9d3e63191b..915a20461c77 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h @@ -274,6 +274,7 @@ struct dccg_registers { uint32_t DSCCLK2_DTO_PARAM; uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; uint32_t DPSTREAMCLK_GATE_DISABLE; + uint32_t DCCG_GATE_DISABLE_CNTL; uint32_t DCCG_GATE_DISABLE_CNTL2; uint32_t DCCG_GATE_DISABLE_CNTL3; uint32_t HDMISTREAMCLK0_DTO_PARAM; 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_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index b1ec0e6f7f58..4996d2810edb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -617,6 +617,17 @@ void hubp2_cursor_set_attributes( CURSOR0_DST_Y_OFFSET, 0, /* used to shift the cursor chunk request deadline */ CURSOR0_CHUNK_HDL_ADJUST, 3); + + hubp->att.SURFACE_ADDR_HIGH = attr->address.high_part; + hubp->att.SURFACE_ADDR = attr->address.low_part; + hubp->att.size.bits.width = attr->width; + hubp->att.size.bits.height = attr->height; + hubp->att.cur_ctl.bits.mode = attr->color_format; + hubp->att.cur_ctl.bits.pitch = hw_pitch; + hubp->att.cur_ctl.bits.line_per_chunk = lpc; + hubp->att.cur_ctl.bits.cur_2x_magnify = attr->attribute_flags.bits.ENABLE_MAGNIFICATION; + hubp->att.settings.bits.dst_y_offset = 0; + hubp->att.settings.bits.chunk_hdl_adjust = 3; } void hubp2_dmdata_set_attributes( @@ -1033,6 +1044,25 @@ void hubp2_cursor_set_position( REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); /* TODO Handle surface pixel formats other than 4:4:4 */ + /* Cursor Position Register Config */ + hubp->pos.cur_ctl.bits.cur_enable = cur_en; + hubp->pos.position.bits.x_pos = pos->x; + hubp->pos.position.bits.y_pos = pos->y; + hubp->pos.hot_spot.bits.x_hot = x_hotspot; + hubp->pos.hot_spot.bits.y_hot = y_hotspot; + hubp->pos.dst_offset.bits.dst_x_offset = dst_x_offset; + /* Cursor Rectangle Cache + * Cursor bitmaps have different hotspot values + * There's a possibility that the above logic returns a negative value, + * so we clamp them to 0 + */ + if (src_x_offset < 0) + src_x_offset = 0; + if (src_y_offset < 0) + src_y_offset = 0; + /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; } void hubp2_clk_cntl(struct hubp *hubp, bool enable) 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 6271caca4d9a..d732b6f031a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -706,6 +706,14 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } + if (dc_is_hdmi_tmds_signal(stream->signal)) { + stream->link->phy_state.symclk_ref_cnts.otg = 1; + if (stream->link->phy_state.symclk_state == SYMCLK_OFF_TX_OFF) + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + else + stream->link->phy_state.symclk_state = SYMCLK_ON_TX_ON; + } + if (dc->hwseq->funcs.PLAT_58856_wa && (!dc_is_dp_signal(stream->signal))) dc->hwseq->funcs.PLAT_58856_wa(context, pipe_ctx); @@ -1565,6 +1573,7 @@ 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*/ @@ -1853,24 +1862,6 @@ void dcn20_post_unlock_program_front_end( for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - struct pipe_ctx *mpcc_pipe; - - if (pipe->vtp_locked) { - dc->hwseq->funcs.wait_for_blank_complete(pipe->stream_res.opp); - pipe->plane_res.hubp->funcs->set_blank(pipe->plane_res.hubp, true); - pipe->vtp_locked = false; - - for (mpcc_pipe = pipe->bottom_pipe; mpcc_pipe; mpcc_pipe = mpcc_pipe->bottom_pipe) - mpcc_pipe->plane_res.hubp->funcs->set_blank(mpcc_pipe->plane_res.hubp, true); - - for (i = 0; i < dc->res_pool->pipe_count; i++) - if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable) - dc->hwss.disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]); - } - } - - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; /* If an active, non-phantom pipe is being transitioned into a phantom @@ -1898,8 +1889,14 @@ void dcn20_post_unlock_program_front_end( * can underflow due to HUBP_VTG_SEL programming if done in the regular front end * programming sequence). */ - if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) + while (pipe) { + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (dc->hwss.update_phantom_vp_position) + dc->hwss.update_phantom_vp_position(dc, context, pipe); dcn20_program_pipe(dc, pipe, context); + } + pipe = pipe->bottom_pipe; + } } } @@ -2003,6 +2000,10 @@ void dcn20_optimize_bandwidth( context->bw_ctx.bw.dcn.clk.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->dc_mode_softmax_memclk); + /* increase compbuf size */ + if (hubbub->funcs->program_compbuf_size) + hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); + dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, @@ -2018,9 +2019,6 @@ void dcn20_optimize_bandwidth( pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); } } - /* increase compbuf size */ - if (hubbub->funcs->program_compbuf_size) - hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); } bool dcn20_update_bandwidth( @@ -2346,7 +2344,9 @@ static void dcn20_reset_back_end_for_pipe( struct dc_state *context) { int i; - struct dc_link *link; + struct dc_link *link = pipe_ctx->stream->link; + const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); + DC_LOGGER_INIT(dc->ctx->logger); if (pipe_ctx->stream_res.stream_enc == NULL) { pipe_ctx->stream = NULL; @@ -2354,19 +2354,15 @@ static void dcn20_reset_back_end_for_pipe( } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { - link = pipe_ctx->stream->link; /* DPMS may already disable or */ /* dpms_off status is incorrect due to fastboot * feature. When system resume from S4 with second * screen only, the dpms_off would be true but * VBIOS lit up eDP, so check link status too. */ - if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) { - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(dc->current_state, pipe_ctx, TX_OFF_SYMCLK_OFF); - else - core_link_disable_stream(pipe_ctx); - } else if (pipe_ctx->stream_res.audio) + if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) + core_link_disable_stream(pipe_ctx); + else if (pipe_ctx->stream_res.audio) dc->hwss.disable_audio_stream(pipe_ctx); /* free acquired resources */ @@ -2406,6 +2402,16 @@ static void dcn20_reset_back_end_for_pipe( if (pipe_ctx->stream_res.tg->funcs->set_drr) pipe_ctx->stream_res.tg->funcs->set_drr( pipe_ctx->stream_res.tg, NULL); + /* TODO - convert symclk_ref_cnts for otg to a bit map to solve + * the case where the same symclk is shared across multiple otg + * instances + */ + link->phy_state.symclk_ref_cnts.otg = 0; + if (link->phy_state.symclk_state == SYMCLK_ON_TX_OFF) { + link_hwss->disable_link_output(link, + &pipe_ctx->link_res, pipe_ctx->stream->signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + } } for (i = 0; i < dc->res_pool->pipe_count; i++) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c index 91e4885b743e..7c5817c426fa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c @@ -96,6 +96,10 @@ static const struct hw_sequencer_funcs dcn20_funcs = { #ifndef TRIM_FSFT .optimize_timing_for_fsft = dcn20_optimize_timing_for_fsft, #endif + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .set_disp_pattern_generator = dcn20_set_disp_pattern_generator, .get_dcc_en_bits = dcn10_get_dcc_en_bits, .update_visual_confirm_color = dcn20_update_visual_confirm_color diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.c index 694260c10a01..ccd91792991b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.c @@ -215,7 +215,8 @@ void mmhubbub2_config_mcif_irq(struct mcif_wb *mcif_wb, REG_UPDATE(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUFMGR_SW_OVERRUN_INT_EN, params->sw_overrun_int_en); REG_UPDATE(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_EN, params->vce_int_en); - REG_UPDATE(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_SLICE_INT_EN, params->vce_slice_int_en); + if (mcif_wb20->mcif_wb_mask->MCIF_WB_BUFMGR_VCE_SLICE_INT_EN) + REG_UPDATE(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_SLICE_INT_EN, params->vce_slice_int_en); } void mmhubbub2_enable_mcif(struct mcif_wb *mcif_wb) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 0340fdd3f5fb..a08c335b7383 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -529,6 +529,7 @@ static struct timing_generator_funcs dcn20_tg_funcs = { .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, + .set_vtotal_min_max = optc1_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_hwseq.c index 05b3fba9ccce..61bcfa03c4e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_hwseq.c @@ -82,7 +82,7 @@ static bool patch_address_for_sbs_tb_stereo( return false; } -static void gpu_addr_to_uma(struct dce_hwseq *hwseq, +static bool gpu_addr_to_uma(struct dce_hwseq *hwseq, PHYSICAL_ADDRESS_LOC *addr) { bool is_in_uma; @@ -98,6 +98,7 @@ static void gpu_addr_to_uma(struct dce_hwseq *hwseq, } else { is_in_uma = false; } + return is_in_uma; } static void plane_address_in_gpu_space_to_uma(struct dce_hwseq *hwseq, diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_init.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_init.c index 1826dd7f3da1..9c16633e473a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_init.c @@ -86,6 +86,10 @@ static const struct hw_sequencer_funcs dcn201_funcs = { .set_backlight_level = dce110_set_backlight_level, .set_abm_immediate_disable = dce110_set_abm_immediate_disable, .set_pipe = dce110_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .set_disp_pattern_generator = dcn20_set_disp_pattern_generator, .update_visual_confirm_color = dcn20_update_visual_confirm_color, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c index 5752271f22df..c5e200d09038 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c @@ -67,15 +67,9 @@ static uint32_t convert_and_clamp( void dcn21_dchvm_init(struct hubbub *hubbub) { struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub); - uint32_t riommu_active, prefetch_done; + uint32_t riommu_active; int i; - REG_GET(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, &prefetch_done); - - if (prefetch_done) { - hubbub->riommu_active = true; - return; - } //Init DCHVM block REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c index b270f0b194dc..fe1a8e2e08ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c @@ -99,6 +99,10 @@ static const struct hw_sequencer_funcs dcn21_funcs = { #ifndef TRIM_FSFT .optimize_timing_for_fsft = dcn20_optimize_timing_for_fsft, #endif + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .is_abm_supported = dcn21_is_abm_supported, .set_disp_pattern_generator = dcn20_set_disp_pattern_generator, .get_dcc_en_bits = dcn10_get_dcc_en_bits, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 7cb35bb1c0f1..887081472c0d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -657,7 +657,6 @@ static const struct dc_debug_options debug_defaults_drv = { .usbc_combo_phy_reset_wa = true, .dmub_command_table = true, .use_max_lb = true, - .optimize_edp_link_rate = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -677,6 +676,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, @@ -1367,6 +1372,11 @@ static struct panel_cntl *dcn21_panel_cntl_create(const struct panel_cntl_init_d return &panel_cntl->base; } +static void dcn21_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + #define CTX ctx #define REG(reg_name) \ @@ -1408,6 +1418,7 @@ static const struct resource_funcs dcn21_res_pool_funcs = { .set_mcif_arb_params = dcn20_set_mcif_arb_params, .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, .update_bw_bounding_box = dcn21_update_bw_bounding_box, + .get_panel_config_defaults = dcn21_get_panel_config_defaults, }; static bool dcn21_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index 4a668d6563df..e5b7ef7422b8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -372,6 +372,10 @@ void dpp3_set_cursor_attributes( REG_UPDATE(CURSOR0_COLOR1, CUR0_COLOR1, 0xFFFFFFFF); } + + dpp_base->att.cur0_ctl.bits.expansion_mode = 0; + dpp_base->att.cur0_ctl.bits.cur0_rom_en = cur_rom_en; + dpp_base->att.cur0_ctl.bits.mode = color_format; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index fb59fed8f425..8c5045711264 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -939,13 +939,32 @@ bool dcn30_does_plane_fit_in_mall(struct dc *dc, struct dc_plane_state *plane, s void dcn30_hardware_release(struct dc *dc) { + bool subvp_in_use = false; + uint32_t i; + dc_dmub_srv_p_state_delegate(dc, false, NULL); + dc_dmub_setup_subvp_dmub_command(dc, dc->current_state, false); + + /* SubVP treated the same way as FPO. If driver disable and + * we are using a SubVP config, disable and force on DCN side + * to prevent P-State hang on driver enable. + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + if (!pipe->stream) + continue; + + if (pipe->stream->mall_stream_config.type == SUBVP_MAIN) { + subvp_in_use = true; + break; + } + } /* If pstate unsupported, or still supported * by firmware, force it supported by dcn */ if (dc->current_state) - if ((!dc->clk_mgr->clks.p_state_change_support || + if ((!dc->clk_mgr->clks.p_state_change_support || subvp_in_use || dc->current_state->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) && dc->res_pool->hubbub->funcs->force_pstate_change_control) dc->res_pool->hubbub->funcs->force_pstate_change_control( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c index 4c06e6e1ba4a..3216d10c58ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c @@ -100,6 +100,10 @@ static const struct hw_sequencer_funcs dcn30_funcs = { .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, .set_pipe = dcn21_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, .get_dcc_en_bits = dcn10_get_dcc_en_bits, .update_visual_confirm_color = dcn20_update_visual_confirm_color, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h index f2580e65196c..7446e54bf5aa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h @@ -227,11 +227,7 @@ SF(MCIF_WB0_MCIF_WB_BUF_3_ADDR_C, MCIF_WB_BUF_3_ADDR_C, mask_sh),\ SF(MCIF_WB0_MCIF_WB_BUF_4_ADDR_Y, MCIF_WB_BUF_4_ADDR_Y, mask_sh),\ SF(MCIF_WB0_MCIF_WB_BUF_4_ADDR_C, MCIF_WB_BUF_4_ADDR_C, mask_sh),\ - SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK_IGNORE, mask_sh),\ - SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_EN, mask_sh),\ - SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_ACK, mask_sh),\ SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_SLICE_INT_EN, mask_sh),\ - SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK, mask_sh),\ SF(MCIF_WB0_MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_SLICE_SIZE, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_REFRESH_WATERMARK, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_WATERMARK_MASK, mask_sh),\ @@ -363,11 +359,7 @@ SF(MCIF_WB_BUF_3_ADDR_C, MCIF_WB_BUF_3_ADDR_C, mask_sh),\ SF(MCIF_WB_BUF_4_ADDR_Y, MCIF_WB_BUF_4_ADDR_Y, mask_sh),\ SF(MCIF_WB_BUF_4_ADDR_C, MCIF_WB_BUF_4_ADDR_C, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK_IGNORE, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_EN, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_ACK, mask_sh),\ SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_SLICE_INT_EN, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK, mask_sh),\ SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_SLICE_SIZE, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_REFRESH_WATERMARK, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_WATERMARK_MASK, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c index 1782b9c26cf4..892d3c4d01a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c @@ -319,13 +319,13 @@ static struct timing_generator_funcs dcn30_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc3_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .lock_doublebuffer_enable = optc3_lock_doublebuffer_enable, .lock_doublebuffer_disable = optc3_lock_doublebuffer_disable, .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, + .set_vtotal_min_max = optc3_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, @@ -366,4 +366,3 @@ void dcn30_timing_generator_init(struct optc *optc1) optc1->min_h_sync_width = 4; optc1->min_v_sync_width = 1; } - diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 64320e0ca446..020f512e9690 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -724,7 +724,8 @@ static const struct dc_debug_options debug_defaults_drv = { .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, .disable_psr = false, - .use_max_lb = true + .use_max_lb = true, + .exit_idle_opt_for_cursor_updates = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -1654,6 +1655,9 @@ noinline bool dcn30_internal_validate_bw( if (!pipes) return false; + context->bw_ctx.dml.vba.maxMpcComb = 0; + context->bw_ctx.dml.vba.VoltageLevel = 0; + context->bw_ctx.dml.vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; dc->res_pool->funcs->update_soc_for_wm_a(dc, context); pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); @@ -1872,6 +1876,7 @@ noinline bool dcn30_internal_validate_bw( if (repopulate_pipes) pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); + context->bw_ctx.dml.vba.VoltageLevel = vlevel; *vlevel_out = vlevel; *pipe_cnt_out = pipe_cnt; @@ -1916,7 +1921,7 @@ static int get_refresh_rate(struct dc_state *context) */ #define V_SCALE (10000 / MAX_STRETCHED_V_BLANK) -int get_frame_rate_at_max_stretch_100hz(struct dc_state *context) +static int get_frame_rate_at_max_stretch_100hz(struct dc_state *context) { struct dc_crtc_timing *timing = NULL; uint32_t sec_per_100_lines; @@ -1946,7 +1951,7 @@ int get_frame_rate_at_max_stretch_100hz(struct dc_state *context) return scaled_refresh_rate; } -bool is_refresh_rate_support_mclk_switch_using_fw_based_vblank_stretch(struct dc_state *context) +static bool is_refresh_rate_support_mclk_switch_using_fw_based_vblank_stretch(struct dc_state *context) { int refresh_rate_max_stretch_100hz; int min_refresh_100hz; diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c index 3d42a1a337ec..6192851c59ed 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c @@ -99,6 +99,10 @@ static const struct hw_sequencer_funcs dcn301_funcs = { .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .set_pipe = dcn21_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, .get_dcc_en_bits = dcn10_get_dcc_en_bits, .optimize_pwr_state = dcn21_optimize_pwr_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index db172677d613..f04595b750ab 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -634,7 +634,7 @@ static const struct dcn20_vmid_mask vmid_masks = { DCN20_VMID_MASK_SH_LIST(_MASK) }; -static const struct resource_caps res_cap_dcn301 = { +static struct resource_caps res_cap_dcn301 = { .num_timing_generator = 4, .num_opp = 4, .num_video_plane = 4, @@ -700,6 +700,7 @@ static const struct dc_debug_options debug_defaults_drv = { .dwb_fi_phase = -1, // -1 = disable .dmub_command_table = true, .use_max_lb = false, + .exit_idle_opt_for_cursor_updates = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -851,7 +852,7 @@ static struct hubbub *dcn301_hubbub_create(struct dc_context *ctx) vmid->masks = &vmid_masks; } - hubbub3->num_vmid = res_cap_dcn301.num_vmid; + hubbub3->num_vmid = res_cap_dcn301.num_vmid; return &hubbub3->base; } @@ -1429,6 +1430,8 @@ static bool dcn301_resource_construct( ctx->dc_bios->regs = &bios_regs; + if (dc->ctx->asic_id.chip_id == DEVICE_ID_VGH_1435) + res_cap_dcn301.num_pll = 2; pool->base.res_cap = &res_cap_dcn301; pool->base.funcs = &dcn301_res_pool_funcs; diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index 4fab537e822f..b925b6ddde5a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -93,7 +93,8 @@ static const struct dc_debug_options debug_defaults_drv = { .underflow_assert_delay_us = 0xFFFFFFFF, .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, - .use_max_lb = true + .use_max_lb = true, + .exit_idle_opt_for_cursor_updates = true }; static const struct dc_debug_options debug_defaults_diags = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index d97076648acb..527d5c902878 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -77,6 +77,7 @@ static const struct dc_debug_options debug_defaults_drv = { .underflow_assert_delay_us = 0xFFFFFFFF, .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, + .exit_idle_opt_for_cursor_updates = true, .disable_idle_power_optimizations = false, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c index 23621ff08c90..814f401db3b3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c @@ -150,9 +150,9 @@ static void dcn31_hpo_dp_stream_enc_dp_blank( * 10us*5000=50ms. This covers 41.7ms of minimum 24 Hz mode + * a little more because we may not trust delay accuracy. */ - //REG_WAIT(DP_SYM32_ENC_VID_STREAM_CONTROL, - // VID_STREAM_STATUS, 0, - // 10, 5000); + REG_WAIT(DP_SYM32_ENC_VID_STREAM_CONTROL, + VID_STREAM_STATUS, 0, + 10, 5000); /* Disable SDP tranmission */ REG_UPDATE(DP_SYM32_ENC_SDP_CONTROL, @@ -197,7 +197,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute( uint32_t h_back_porch; uint32_t h_width; uint32_t v_height; - unsigned long long v_freq; + uint64_t v_freq; uint8_t misc0 = 0; uint8_t misc1 = 0; uint8_t hsp; @@ -360,7 +360,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute( v_height = hw_crtc_timing.v_border_top + hw_crtc_timing.v_addressable + hw_crtc_timing.v_border_bottom; hsp = hw_crtc_timing.flags.HSYNC_POSITIVE_POLARITY ? 0 : 0x80; vsp = hw_crtc_timing.flags.VSYNC_POSITIVE_POLARITY ? 0 : 0x80; - v_freq = hw_crtc_timing.pix_clk_100hz * 100; + v_freq = (uint64_t)hw_crtc_timing.pix_clk_100hz * 100; /* MSA Packet Mapping to 32-bit Link Symbols - DP2 spec, section 2.7.4.1 * @@ -436,32 +436,28 @@ static void dcn31_hpo_dp_stream_enc_update_dp_info_packets( { struct dcn31_hpo_dp_stream_encoder *enc3 = DCN3_1_HPO_DP_STREAM_ENC_FROM_HPO_STREAM_ENC(enc); uint32_t dmdata_packet_enabled = 0; - bool sdp_stream_enable = false; - if (info_frame->vsc.valid) { + if (info_frame->vsc.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 0, /* packetIndex */ &info_frame->vsc, true); - sdp_stream_enable = true; - } - if (info_frame->spd.valid) { + + if (info_frame->spd.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 2, /* packetIndex */ &info_frame->spd, true); - sdp_stream_enable = true; - } - if (info_frame->hdrsmd.valid) { + + if (info_frame->hdrsmd.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 3, /* packetIndex */ &info_frame->hdrsmd, true); - sdp_stream_enable = true; - } + /* enable/disable transmission of packet(s). * If enabled, packet transmission begins on the next frame */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 51c5f3685470..6360dc9502e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -876,7 +876,7 @@ static bool hubbub31_get_dcc_compression_cap(struct hubbub *hubbub, return true; } -static int hubbub31_init_dchub_sys_ctx(struct hubbub *hubbub, +int hubbub31_init_dchub_sys_ctx(struct hubbub *hubbub, struct dcn_hubbub_phys_addr_config *pa_config) { struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h index e3a654bf04e8..70c60de448ac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.h @@ -122,6 +122,8 @@ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh) +int hubbub31_init_dchub_sys_ctx(struct hubbub *hubbub, + struct dcn_hubbub_phys_addr_config *pa_config); void hubbub31_construct(struct dcn20_hubbub *hubbub3, struct dc_context *ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 8d83b611507a..bdf101547484 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -535,11 +535,11 @@ static void dcn31_reset_back_end_for_pipe( pipe_ctx->stream_res.tg, OPTC_DSC_DISABLED, 0, 0); pipe_ctx->stream_res.tg->funcs->disable_crtc(pipe_ctx->stream_res.tg); - pipe_ctx->stream_res.tg->funcs->enable_optc_clock(pipe_ctx->stream_res.tg, false); if (pipe_ctx->stream_res.tg->funcs->set_odm_bypass) pipe_ctx->stream_res.tg->funcs->set_odm_bypass( pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); + pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; if (pipe_ctx->stream_res.tg->funcs->set_drr) pipe_ctx->stream_res.tg->funcs->set_drr( @@ -553,12 +553,9 @@ static void dcn31_reset_back_end_for_pipe( * screen only, the dpms_off would be true but * VBIOS lit up eDP, so check link status too. */ - if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) { - if (dc->hwss.update_phy_state) - dc->hwss.update_phy_state(dc->current_state, pipe_ctx, TX_OFF_SYMCLK_OFF); - else - core_link_disable_stream(pipe_ctx); - } else if (pipe_ctx->stream_res.audio) + if (!pipe_ctx->stream->dpms_off || link->link_status.link_active) + core_link_disable_stream(pipe_ctx); + else if (pipe_ctx->stream_res.audio) dc->hwss.disable_audio_stream(pipe_ctx); /* free acquired resources */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index e708f07fe75a..3a32810bbe38 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -100,6 +100,10 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .set_pipe = dcn21_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 2f7404a97479..63a677c8ee27 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -201,7 +201,6 @@ void optc31_set_drr( // Setup manual flow control for EOF via TRIG_A optc->funcs->setup_manual_trigger(optc); - } else { REG_UPDATE_4(OTG_V_TOTAL_CONTROL, OTG_SET_V_TOTAL_MIN_MASK, 0, @@ -260,7 +259,6 @@ static struct timing_generator_funcs dcn31_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc3_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .lock_doublebuffer_enable = optc3_lock_doublebuffer_enable, .lock_doublebuffer_disable = optc3_lock_doublebuffer_disable, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 8745132d6374..fddc21a5a04c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -888,7 +888,6 @@ static const struct dc_debug_options debug_defaults_drv = { } }, .disable_z10 = true, - .optimize_edp_link_rate = true, .enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/ .dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE, }; @@ -911,6 +910,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1803,6 +1808,11 @@ validate_out: return out; } +static void dcn31_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1829,6 +1839,7 @@ static struct resource_funcs dcn31_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn31_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn31_get_panel_config_defaults, }; static struct clock_source *dcn30_clock_source_create( 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..1bd7e0f327d8 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: @@ -137,7 +184,7 @@ static void dccg314_set_dtbclk_p_src( } /* Controls the generation of pixel valid for OTG in (OTG -> HPO case) */ -void dccg314_set_dtbclk_dto( +static void dccg314_set_dtbclk_dto( struct dccg *dccg, const struct dtbclk_dto_params *params) { @@ -181,7 +228,7 @@ void dccg314_set_dtbclk_dto( } } -void dccg314_set_dpstreamclk( +static void dccg314_set_dpstreamclk( struct dccg *dccg, enum streamclk_source src, int otg_inst, @@ -220,7 +267,7 @@ void dccg314_set_dpstreamclk( } } -void dccg314_set_valid_pixel_rate( +static void dccg314_set_valid_pixel_rate( struct dccg *dccg, int ref_dtbclk_khz, int otg_inst, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.h index 9a4a9efc0203..6a35986307af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.h @@ -63,34 +63,28 @@ DCCG_SRII(PHASE, DTBCLK_DTO, 3),\ SR(DCCG_AUDIO_DTBCLK_DTO_MODULO),\ SR(DCCG_AUDIO_DTBCLK_DTO_PHASE),\ + SR(DCCG_AUDIO_DTO_SOURCE),\ + SR(DENTIST_DISPCLK_CNTL),\ + SR(DSCCLK0_DTO_PARAM),\ + SR(DSCCLK1_DTO_PARAM),\ + SR(DSCCLK2_DTO_PARAM),\ + SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL2),\ + SR(DCCG_GATE_DISABLE_CNTL3),\ + SR(HDMISTREAMCLK0_DTO_PARAM),\ SR(OTG_PIXEL_RATE_DIV),\ SR(DTBCLK_P_CNTL),\ SR(DCCG_AUDIO_DTO_SOURCE) - -#define DCCG_MASK_SH_LIST_DCN314(mask_sh) \ - DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\ +#define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\ - DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 1, mask_sh),\ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 1, mask_sh),\ - DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 2, mask_sh),\ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 2, mask_sh),\ - DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 3, mask_sh),\ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 3, mask_sh),\ DCCG_SF(DPPCLK0_DTO_PARAM, DPPCLK0_DTO_PHASE, mask_sh),\ DCCG_SF(DPPCLK0_DTO_PARAM, DPPCLK0_DTO_MODULO, mask_sh),\ DCCG_SF(HDMICHARCLK0_CLOCK_CNTL, HDMICHARCLK0_EN, mask_sh),\ DCCG_SF(HDMICHARCLK0_CLOCK_CNTL, HDMICHARCLK0_SRC_SEL, mask_sh),\ - DCCG_SF(PHYASYMCLK_CLOCK_CNTL, PHYASYMCLK_FORCE_EN, mask_sh),\ - DCCG_SF(PHYASYMCLK_CLOCK_CNTL, PHYASYMCLK_FORCE_SRC_SEL, mask_sh),\ - DCCG_SF(PHYBSYMCLK_CLOCK_CNTL, PHYBSYMCLK_FORCE_EN, mask_sh),\ - DCCG_SF(PHYBSYMCLK_CLOCK_CNTL, PHYBSYMCLK_FORCE_SRC_SEL, mask_sh),\ - DCCG_SF(PHYCSYMCLK_CLOCK_CNTL, PHYCSYMCLK_FORCE_EN, mask_sh),\ - DCCG_SF(PHYCSYMCLK_CLOCK_CNTL, PHYCSYMCLK_FORCE_SRC_SEL, mask_sh),\ - DCCG_SF(PHYDSYMCLK_CLOCK_CNTL, PHYDSYMCLK_FORCE_EN, mask_sh),\ - DCCG_SF(PHYDSYMCLK_CLOCK_CNTL, PHYDSYMCLK_FORCE_SRC_SEL, mask_sh),\ - DCCG_SF(PHYESYMCLK_CLOCK_CNTL, PHYESYMCLK_FORCE_EN, mask_sh),\ - DCCG_SF(PHYESYMCLK_CLOCK_CNTL, PHYESYMCLK_FORCE_SRC_SEL, mask_sh),\ DCCG_SF(DPSTREAMCLK_CNTL, DPSTREAMCLK0_EN, mask_sh),\ DCCG_SF(DPSTREAMCLK_CNTL, DPSTREAMCLK1_EN, mask_sh),\ DCCG_SF(DPSTREAMCLK_CNTL, DPSTREAMCLK2_EN, mask_sh),\ @@ -100,7 +94,6 @@ DCCG_SF(DPSTREAMCLK_CNTL, DPSTREAMCLK2_SRC_SEL, mask_sh),\ DCCG_SF(DPSTREAMCLK_CNTL, DPSTREAMCLK3_SRC_SEL, mask_sh),\ DCCG_SF(HDMISTREAMCLK_CNTL, HDMISTREAMCLK0_EN, mask_sh),\ - DCCG_SF(HDMISTREAMCLK_CNTL, HDMISTREAMCLK0_DTO_FORCE_DIS, mask_sh),\ DCCG_SF(HDMISTREAMCLK_CNTL, HDMISTREAMCLK0_SRC_SEL, mask_sh),\ DCCG_SF(SYMCLK32_SE_CNTL, SYMCLK32_SE0_SRC_SEL, mask_sh),\ DCCG_SF(SYMCLK32_SE_CNTL, SYMCLK32_SE1_SRC_SEL, mask_sh),\ @@ -148,7 +141,48 @@ DCCG_SF(DTBCLK_P_CNTL, DTBCLK_P3_SRC_SEL, mask_sh),\ DCCG_SF(DTBCLK_P_CNTL, DTBCLK_P3_EN, mask_sh),\ DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, mask_sh),\ - DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO_SEL, mask_sh) + DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO_SEL, mask_sh),\ + DCCG_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_MODE, mask_sh),\ + DCCG_SF(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_MODULO, mask_sh),\ + DCCG_SF(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_MODULO, mask_sh),\ + DCCG_SF(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_MODULO, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE0_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE1_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE2_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE3_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_LE0_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_LE1_GATE_DISABLE, mask_sh),\ + DCCG_SF(HDMISTREAMCLK0_DTO_PARAM, HDMISTREAMCLK0_DTO_PHASE, mask_sh),\ + DCCG_SF(HDMISTREAMCLK0_DTO_PARAM, HDMISTREAMCLK0_DTO_MODULO, mask_sh) + +#define DCCG_MASK_SH_LIST_DCN314(mask_sh) \ + DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh),\ + DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\ + DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 1, mask_sh),\ + DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 2, mask_sh),\ + DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 3, mask_sh),\ + DCCG_SF(PHYASYMCLK_CLOCK_CNTL, PHYASYMCLK_FORCE_EN, mask_sh),\ + DCCG_SF(PHYASYMCLK_CLOCK_CNTL, PHYASYMCLK_FORCE_SRC_SEL, mask_sh),\ + DCCG_SF(PHYBSYMCLK_CLOCK_CNTL, PHYBSYMCLK_FORCE_EN, mask_sh),\ + DCCG_SF(PHYBSYMCLK_CLOCK_CNTL, PHYBSYMCLK_FORCE_SRC_SEL, mask_sh),\ + DCCG_SF(PHYCSYMCLK_CLOCK_CNTL, PHYCSYMCLK_FORCE_EN, mask_sh),\ + DCCG_SF(PHYCSYMCLK_CLOCK_CNTL, PHYCSYMCLK_FORCE_SRC_SEL, mask_sh),\ + DCCG_SF(PHYDSYMCLK_CLOCK_CNTL, PHYDSYMCLK_FORCE_EN, mask_sh),\ + DCCG_SF(PHYDSYMCLK_CLOCK_CNTL, PHYDSYMCLK_FORCE_SRC_SEL, mask_sh),\ + DCCG_SF(PHYESYMCLK_CLOCK_CNTL, PHYESYMCLK_FORCE_EN, mask_sh),\ + DCCG_SF(PHYESYMCLK_CLOCK_CNTL, PHYESYMCLK_FORCE_SRC_SEL, mask_sh),\ + DCCG_SF(HDMISTREAMCLK_CNTL, HDMISTREAMCLK0_DTO_FORCE_DIS, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK0_DTO_ENABLE, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK1_DTO_ENABLE, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK2_DTO_ENABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL2, PHYASYMCLK_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL2, PHYBSYMCLK_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL2, PHYCSYMCLK_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL2, PHYDSYMCLK_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL2, PHYESYMCLK_GATE_DISABLE, mask_sh) struct dccg *dccg314_create( struct dc_context *ctx, 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 e3351ddc566c..7e773bf7b895 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( @@ -81,7 +81,7 @@ static void enc314_dp_set_odm_combine( } /* setup stream encoder in dvi mode */ -void enc314_stream_encoder_dvi_set_stream_attribute( +static void enc314_stream_encoder_dvi_set_stream_attribute( struct stream_encoder *enc, struct dc_crtc_timing *crtc_timing, bool is_dual_link) @@ -262,6 +262,16 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } +static 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, @@ -317,15 +327,11 @@ static void enc314_stream_encoder_dp_unblank( /* switch DP encoder to CRTC data, but reset it the fifo first. It may happen * that it overflows during mode transition, and sometimes doesn't recover. */ - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1); udelay(10); 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) */ @@ -341,6 +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); } @@ -409,7 +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..588c1c71241f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -343,12 +343,14 @@ 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); odm_combine_factor = get_odm_config(pipe_ctx, NULL); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) + return odm_combine_factor; + if (is_dp_128b_132b_signal(pipe_ctx)) { *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { @@ -364,7 +366,7 @@ 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 +386,10 @@ 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..5b6c2d94ec71 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -102,6 +102,10 @@ static const struct hw_sequencer_funcs dcn314_funcs = { .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .set_pipe = dcn21_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dce110_disable_link_output, .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, @@ -146,7 +150,6 @@ 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 38aa28ec6b13..47eb162f1a75 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c @@ -150,7 +150,7 @@ static bool optc314_disable_crtc(struct timing_generator *optc) return true; } -void optc314_phantom_crtc_post_enable(struct timing_generator *optc) +static void optc314_phantom_crtc_post_enable(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); 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 49b7e256d4ea..d0ad72caead2 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" @@ -579,7 +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[] = { @@ -590,11 +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 = { @@ -844,7 +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 = { @@ -878,7 +881,8 @@ static const struct dc_plane_cap plane_cap = { }; static const struct dc_debug_options debug_defaults_drv = { - .disable_z10 = true, /*hw not support it*/ + .disable_z10 = false, + .enable_z9_disable_interface = true, .disable_dmcu = true, .force_abm_enable = false, .timing_trace = false, @@ -911,7 +915,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, .seamless_boot_odm_combine = true }; @@ -933,6 +936,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1672,6 +1681,11 @@ static void dcn314_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b DC_FP_END(); } +static void dcn314_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct resource_funcs dcn314_res_pool_funcs = { .destroy = dcn314_destroy_resource_pool, .link_enc_create = dcn31_link_encoder_create, @@ -1694,6 +1708,7 @@ static struct resource_funcs dcn314_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn314_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn314_get_panel_config_defaults, }; static struct clock_source *dcn30_clock_source_create( diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index eebb42c9ddd6..58746c437554 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -885,7 +885,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, .psr_power_use_phy_fsm = 0, }; @@ -907,6 +906,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1708,6 +1713,11 @@ static int dcn315_populate_dml_pipes_from_context( return pipe_cnt; } +static void dcn315_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1721,7 +1731,7 @@ static struct resource_funcs dcn315_res_pool_funcs = { .panel_cntl_create = dcn31_panel_cntl_create, .validate_bandwidth = dcn31_validate_bandwidth, .calculate_wm_and_dlg = dcn31_calculate_wm_and_dlg, - .update_soc_for_wm_a = dcn31_update_soc_for_wm_a, + .update_soc_for_wm_a = dcn315_update_soc_for_wm_a, .populate_dml_pipes = dcn315_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, @@ -1734,6 +1744,7 @@ static struct resource_funcs dcn315_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn315_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn315_get_panel_config_defaults, }; static bool dcn315_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c index f4b52a35ad84..6b40a11ac83a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c @@ -885,7 +885,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, }; static const struct dc_debug_options debug_defaults_diags = { @@ -906,6 +905,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1710,6 +1715,11 @@ static int dcn316_populate_dml_pipes_from_context( return pipe_cnt; } +static void dcn316_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1736,6 +1746,7 @@ static struct resource_funcs dcn316_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn316_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn316_get_panel_config_defaults, }; static bool dcn316_resource_construct( 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 0d5e8a441512..e4daed44ef5f 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, @@ -133,7 +186,7 @@ static void dccg32_set_dtbclk_p_src( } /* Controls the generation of pixel valid for OTG in (OTG -> HPO case) */ -void dccg32_set_dtbclk_dto( +static void dccg32_set_dtbclk_dto( struct dccg *dccg, const struct dtbclk_dto_params *params) { @@ -208,7 +261,7 @@ static void dccg32_get_dccg_ref_freq(struct dccg *dccg, return; } -void dccg32_set_dpstreamclk( +static void dccg32_set_dpstreamclk( struct dccg *dccg, enum streamclk_source src, int otg_inst, @@ -245,7 +298,7 @@ void dccg32_set_dpstreamclk( } } -void dccg32_otg_add_pixel(struct dccg *dccg, +static void dccg32_otg_add_pixel(struct dccg *dccg, uint32_t otg_inst) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); @@ -254,7 +307,7 @@ void dccg32_otg_add_pixel(struct dccg *dccg, OTG_ADD_PIXEL[otg_inst], 1); } -void dccg32_otg_drop_pixel(struct dccg *dccg, +static void dccg32_otg_drop_pixel(struct dccg *dccg, uint32_t otg_inst) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c index d6855d4f749b..076969d928af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c @@ -118,7 +118,7 @@ void dcn32_link_encoder_enable_dp_output( } } -bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc) +static bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc) { struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); uint32_t dp_alt_mode_disable = 0; @@ -133,7 +133,7 @@ bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc) return is_usb_c_alt_mode; } -void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, +static void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, struct dc_link_settings *link_settings) { struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); @@ -150,12 +150,6 @@ void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, } -void enc32_set_dig_output_mode(struct link_encoder *enc, uint8_t pix_per_container) -{ - struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_OUTPUT_PIXEL_MODE, pix_per_container); -} - static const struct link_encoder_funcs dcn32_link_enc_funcs = { .read_state = link_enc2_read_state, .validate_output_with_stream = @@ -186,7 +180,6 @@ static const struct link_encoder_funcs dcn32_link_enc_funcs = { .is_in_alt_mode = dcn32_link_encoder_is_in_alt_mode, .get_max_link_cap = dcn32_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, - .set_dig_output_mode = enc32_set_dig_output_mode, }; void dcn32_link_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h index 749a1e8cb811..bbcfce06bec0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h @@ -53,8 +53,4 @@ void dcn32_link_encoder_enable_dp_output( const struct dc_link_settings *link_settings, enum clock_source_id clock_source); -void enc32_set_dig_output_mode( - struct link_encoder *enc, - uint8_t pix_per_container); - #endif /* __DC_LINK_ENCODER__DCN32_H__ */ 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 38a48983f663..d19fc93dbc75 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 @@ -60,7 +60,7 @@ static void enc32_dp_set_odm_combine( } /* setup stream encoder in dvi mode */ -void enc32_stream_encoder_dvi_set_stream_attribute( +static void enc32_stream_encoder_dvi_set_stream_attribute( struct stream_encoder *enc, struct dc_crtc_timing *crtc_timing, bool is_dual_link) @@ -243,6 +243,39 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } +static bool is_h_timing_divisible_by_2(const struct dc_crtc_timing *timing) +{ + /* math borrowed from function of same name in inc/resource + * checks if h_timing is divisible by 2 + */ + + bool divisible = false; + uint16_t h_blank_start = 0; + uint16_t h_blank_end = 0; + + if (timing) { + h_blank_start = timing->h_total - timing->h_front_porch; + h_blank_end = h_blank_start - timing->h_addressable; + + /* HTOTAL, Hblank start/end, and Hsync start/end all must be + * divisible by 2 in order for the horizontal timing params + * to be considered divisible by 2. Hsync start is always 0. + */ + divisible = (timing->h_total % 2 == 0) && + (h_blank_start % 2 == 0) && + (h_blank_end % 2 == 0) && + (timing->h_sync_width % 2 == 0); + } + return divisible; +} + +static bool is_dp_dig_pixel_rate_div_policy(struct dc *dc, const struct dc_crtc_timing *timing) +{ + /* should be functionally the same as dcn32_is_dp_dig_pixel_rate_div_policy for DP encoders*/ + return is_h_timing_divisible_by_2(timing) && + dc->debug.enable_dp_dig_pixel_rate_div_policy; +} + static void enc32_stream_encoder_dp_unblank( struct dc_link *link, struct stream_encoder *enc, @@ -259,7 +292,7 @@ static void enc32_stream_encoder_dp_unblank( /* YCbCr 4:2:0 : Computed VID_M will be 2X the input rate */ if (is_two_pixels_per_containter(¶m->timing) || param->opp_cnt > 1 - || dc->debug.enable_dp_dig_pixel_rate_div_policy) { + || is_dp_dig_pixel_rate_div_policy(dc, ¶m->timing)) { /*this logic should be the same in get_pixel_clock_parameters() */ n_multiply = 1; } @@ -355,7 +388,7 @@ static void enc32_dp_set_dsc_config(struct stream_encoder *enc, { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - REG_UPDATE(DP_DSC_CNTL, DP_DSC_MODE, dsc_mode); + REG_UPDATE(DP_DSC_CNTL, DP_DSC_MODE, dsc_mode == OPTC_DSC_DISABLED ? 0 : 1); } /* this function read dsc related register fields to be logged later in dcn10_log_hw_state @@ -378,24 +411,6 @@ static void enc32_read_state(struct stream_encoder *enc, struct enc_state *s) } } -static void enc32_stream_encoder_reset_fifo(struct stream_encoder *enc) -{ - struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - uint32_t fifo_enabled; - - REG_GET(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, &fifo_enabled); - - if (fifo_enabled == 0) { - /* reset DIG resync FIFO */ - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); - /* TODO: fix timeout when wait for DIG_FIFO_RESET_DONE */ - //REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 1, 100); - udelay(1); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 1, 100); - } -} - static void enc32_set_dig_input_mode(struct stream_encoder *enc, unsigned int pix_per_container) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); @@ -425,8 +440,6 @@ static const struct stream_encoder_funcs dcn32_str_enc_funcs = { enc3_stream_encoder_update_dp_info_packets, .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, - .reset_fifo = - enc32_stream_encoder_reset_fifo, .dp_blank = enc1_stream_encoder_dp_blank, .dp_unblank = diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h index 250d9a341cf6..ecd041a446d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h @@ -71,7 +71,9 @@ SRI(DP_MSE_RATE_UPDATE, DP, id), \ SRI(DP_PIXEL_FORMAT, DP, id), \ SRI(DP_SEC_CNTL, DP, id), \ + SRI(DP_SEC_CNTL1, DP, id), \ SRI(DP_SEC_CNTL2, DP, id), \ + SRI(DP_SEC_CNTL5, DP, id), \ SRI(DP_SEC_CNTL6, DP, id), \ SRI(DP_STEER_FIFO, DP, id), \ SRI(DP_VID_M, DP, id), \ @@ -93,7 +95,7 @@ SRI(DIG_FIFO_CTRL0, DIG, id) -#define SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh)\ +#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_PIXEL_ENCODING, mask_sh),\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH, mask_sh),\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_PIXEL_PER_CYCLE_PROCESSING_MODE, mask_sh),\ @@ -106,6 +108,7 @@ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_CONT, mask_sh),\ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_SEND, mask_sh),\ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_NULL_SEND, mask_sh),\ + SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_ACP_SEND, mask_sh),\ SE_SF(DIG0_HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_SEND, mask_sh),\ SE_SF(DIG0_HDMI_INFOFRAME_CONTROL1, HDMI_AUDIO_INFO_LINE, mask_sh),\ SE_SF(DIG0_HDMI_GC, HDMI_GC_AVMUTE, mask_sh),\ @@ -244,15 +247,6 @@ SE_SF(DIG0_DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, mask_sh),\ SE_SF(DIG0_DIG_FIFO_CTRL0, DIG_FIFO_OUTPUT_PIXEL_MODE, mask_sh) -#if defined(CONFIG_DRM_AMD_DC_HDCP) -#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ - SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh),\ - SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_ACP_SEND, mask_sh) -#else -#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ - SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh) -#endif - void dcn32_dio_stream_encoder_construct( struct dcn10_stream_encoder *enc1, struct dc_context *ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dpp.c index f349cbe2a0f0..dcf12a0b031c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dpp.c @@ -31,7 +31,7 @@ #include "dcn30/dcn30_cm_common.h" /* Compute the maximum number of lines that we can fit in the line buffer */ -void dscl32_calc_lb_num_partitions( +static void dscl32_calc_lb_num_partitions( const struct scaler_data *scl_data, enum lb_memory_config lb_config, int *num_part_y, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h index 9db1323e1933..176b1537d2a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h @@ -47,6 +47,7 @@ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL1, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL2, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL3, mask_sh),\ + SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_SQ_PULSE, TP_SQ_PULSE_WIDTH, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_SAT_VC0, SAT_STREAM_SOURCE, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_SAT_VC0, SAT_SLOT_COUNT, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_VC_RATE_CNTL0, STREAM_VC_RATE_X, mask_sh),\ 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..9fbb72369c10 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c @@ -68,7 +68,7 @@ static void dcn32_init_crb(struct hubbub *hubbub) REG_UPDATE(DCHUBBUB_DEBUG_CTRL_0, DET_DEPTH, 0x47F); } -static void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigned int det_buffer_size_in_kbyte) +void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigned int det_buffer_size_in_kbyte) { struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); @@ -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) @@ -140,7 +144,7 @@ static uint32_t convert_and_clamp( return ret_val; } -static bool hubbub32_program_urgent_watermarks( +bool hubbub32_program_urgent_watermarks( struct hubbub *hubbub, struct dcn_watermark_set *watermarks, unsigned int refclk_mhz, @@ -330,7 +334,7 @@ static bool hubbub32_program_urgent_watermarks( return wm_pending; } -static bool hubbub32_program_stutter_watermarks( +bool hubbub32_program_stutter_watermarks( struct hubbub *hubbub, struct dcn_watermark_set *watermarks, unsigned int refclk_mhz, @@ -476,7 +480,7 @@ static bool hubbub32_program_stutter_watermarks( } -static bool hubbub32_program_pstate_watermarks( +bool hubbub32_program_pstate_watermarks( struct hubbub *hubbub, struct dcn_watermark_set *watermarks, unsigned int refclk_mhz, @@ -629,7 +633,7 @@ static bool hubbub32_program_pstate_watermarks( } -static bool hubbub32_program_usr_watermarks( +bool hubbub32_program_usr_watermarks( struct hubbub *hubbub, struct dcn_watermark_set *watermarks, unsigned int refclk_mhz, @@ -769,7 +773,7 @@ static bool hubbub32_program_watermarks( } /* Copy values from WM set A to all other sets */ -void hubbub32_init_watermarks(struct hubbub *hubbub) +static void hubbub32_init_watermarks(struct hubbub *hubbub) { struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); uint32_t reg; @@ -820,7 +824,7 @@ void hubbub32_init_watermarks(struct hubbub *hubbub) REG_WRITE(DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_D, reg); } -void hubbub32_wm_read_state(struct hubbub *hubbub, +static void hubbub32_wm_read_state(struct hubbub *hubbub, struct dcn_hubbub_wm *wm) { struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); @@ -932,6 +936,7 @@ static const struct hubbub_funcs hubbub32_funcs = { .program_watermarks = hubbub32_program_watermarks, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .verify_allow_pstate_change_high = hubbub1_verify_allow_pstate_change_high, .force_wm_propagate_to_pipes = hubbub32_force_wm_propagate_to_pipes, .force_pstate_change_control = hubbub3_force_pstate_change_control, .init_watermarks = hubbub32_init_watermarks, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h index 3bae6e558971..cda94e0e31bf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h @@ -161,6 +161,35 @@ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh) +bool hubbub32_program_urgent_watermarks( + struct hubbub *hubbub, + struct dcn_watermark_set *watermarks, + unsigned int refclk_mhz, + bool safe_to_lower); + +bool hubbub32_program_stutter_watermarks( + struct hubbub *hubbub, + struct dcn_watermark_set *watermarks, + unsigned int refclk_mhz, + bool safe_to_lower); + +bool hubbub32_program_pstate_watermarks( + struct hubbub *hubbub, + struct dcn_watermark_set *watermarks, + unsigned int refclk_mhz, + bool safe_to_lower); + +bool hubbub32_program_usr_watermarks( + struct hubbub *hubbub, + struct dcn_watermark_set *watermarks, + unsigned int refclk_mhz, + bool safe_to_lower); + +void hubbub32_force_usr_retraining_allow(struct hubbub *hubbub, bool allow); + +void hubbub32_force_wm_propagate_to_pipes(struct hubbub *hubbub); + +void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigned int det_buffer_size_in_kbyte); void hubbub32_construct(struct dcn20_hubbub *hubbub2, struct dc_context *ctx, 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..ac1c6458dd55 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -79,6 +79,8 @@ void hubp32_phantom_hubp_post_enable(struct hubp *hubp) uint32_t reg_val; struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + /* For phantom pipe enable, disable GSL */ + REG_UPDATE(DCSURF_FLIP_CONTROL2, SURFACE_GSL_ENABLE, 0); REG_UPDATE(DCHUBP_CNTL, HUBP_BLANK_EN, 1); reg_val = REG_READ(DCHUBP_CNTL); if (reg_val) { @@ -103,6 +105,11 @@ 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 +133,24 @@ 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); @@ -157,12 +181,12 @@ static struct hubp_funcs dcn32_hubp_funcs = { .hubp_init = hubp3_init, .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, .hubp_in_blank = hubp1_in_blank, .hubp_update_force_pstate_disallow = hubp32_update_force_pstate_disallow, .phantom_hubp_post_enable = hubp32_phantom_hubp_post_enable, .hubp_update_mall_sel = hubp32_update_mall_sel, - .hubp_prepare_subvp_buffering = hubp32_prepare_subvp_buffering, - .hubp_set_flip_int = hubp1_set_flip_int + .hubp_prepare_subvp_buffering = hubp32_prepare_subvp_buffering }; bool hubp32_construct( 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 769171ab8ef6..cf5bd9713f54 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -49,6 +49,7 @@ #include "dcn20/dcn20_optc.h" #include "dmub_subvp_state.h" #include "dce/dmub_hw_lock_mgr.h" +#include "dcn32_resource.h" #include "dc_link_dp.h" #include "dmub/inc/dmub_subvp_state.h" @@ -198,42 +199,6 @@ static bool dcn32_check_no_memory_request_for_cab(struct dc *dc) return false; } -/* This function takes in the start address and surface size to be cached in CAB - * and calculates the total number of cache lines required to store the surface. - * The number of cache lines used for each surface is calculated independently of - * one another. For example, if there is a primary surface(1), meta surface(2), and - * cursor(3), this function should be called 3 times to calculate the number of cache - * lines used for each of those surfaces. - */ -static uint32_t dcn32_cache_lines_for_surface(struct dc *dc, uint32_t surface_size, uint64_t start_address) -{ - uint32_t lines_used = 1; - uint32_t num_cached_bytes = 0; - uint32_t remaining_size = 0; - uint32_t cache_line_size = dc->caps.cache_line_size; - uint32_t remainder = 0; - - /* 1. Calculate surface size minus the number of bytes stored - * in the first cache line (all bytes in first cache line might - * not be fully used). - */ - div_u64_rem(start_address, cache_line_size, &remainder); - num_cached_bytes = cache_line_size - remainder; - remaining_size = surface_size - num_cached_bytes; - - /* 2. Calculate number of cache lines that will be fully used with - * the remaining number of bytes to be stored. - */ - lines_used += (remaining_size / cache_line_size); - - /* 3. Check if we need an extra line due to the remaining size not being - * a multiple of CACHE_LINE_SIZE. - */ - if (remaining_size % cache_line_size > 0) - lines_used++; - - return lines_used; -} /* This function loops through every surface that needs to be cached in CAB for SS, * and calculates the total number of ways required to store all surfaces (primary, @@ -241,94 +206,115 @@ static uint32_t dcn32_cache_lines_for_surface(struct dc *dc, uint32_t surface_si */ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *ctx) { - uint8_t i, j; + int i, j; struct dc_stream_state *stream = NULL; struct dc_plane_state *plane = NULL; - uint32_t surface_size = 0; uint32_t cursor_size = 0; - uint32_t cache_lines_used = 0; uint32_t total_lines = 0; uint32_t lines_per_way = 0; - uint32_t num_ways = 0; - uint32_t prev_addr_low = 0; + uint8_t num_ways = 0; + uint8_t bytes_per_pixel = 0; + uint8_t cursor_bpp = 0; + uint16_t mblk_width = 0; + uint16_t mblk_height = 0; + uint16_t mall_alloc_width_blk_aligned = 0; + uint16_t mall_alloc_height_blk_aligned = 0; + uint16_t num_mblks = 0; + uint32_t bytes_in_mall = 0; + uint32_t cache_lines_used = 0; + uint32_t cache_lines_per_plane = 0; - for (i = 0; i < ctx->stream_count; i++) { - stream = ctx->streams[i]; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; - // Don't include PSR surface in the total surface size for CAB allocation - if (stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED) + if (!pipe->stream || !pipe->plane_state || + pipe->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED || + pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) continue; - if (ctx->stream_status[i].plane_count == 0) - continue; + 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; - // For each stream, loop through each plane to calculate the number of cache - // lines required to store the surface in CAB - for (j = 0; j < ctx->stream_status[i].plane_count; j++) { - plane = ctx->stream_status[i].plane_states[j]; + /* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) - + * FLOOR(vp_x_start, blk_width) + * + * mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c + */ + mall_alloc_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) + * + * mall_alloc_height_blk_aligned_l/c = full_vp_height_blk_aligned_l/c + */ + mall_alloc_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + + pipe->plane_res.scl_data.viewport.height + mblk_height - 1) / mblk_height * mblk_height) - + (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); - // Calculate total surface size - if (prev_addr_low != plane->address.grph.addr.u.low_part) { - /* if plane address are different from prev FB, then userspace allocated separate FBs*/ - surface_size += plane->plane_size.surface_pitch * - plane->plane_size.surface_size.height * - (plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4); + num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * + ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); - prev_addr_low = plane->address.grph.addr.u.low_part; - } else { - /* We have the same fb for all the planes. - * Xorg always creates one giant fb that holds all surfaces, - * so allocating it once is sufficient. - * */ - continue; - } - // Convert surface size + starting address to number of cache lines required - // (alignment accounted for) - cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size, - plane->address.grph.addr.quad_part); - - if (plane->address.grph.meta_addr.quad_part) { - // Meta surface - cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size, - plane->address.grph.meta_addr.quad_part); - } - } + /* For DCC: + * meta_num_mblk = CEILING(full_mblk_width_ub_l*full_mblk_height_ub_l*Bpe/256/mblk_bytes, 1) + */ + if (pipe->plane_state->dcc.enable) + num_mblks += (mall_alloc_width_blk_aligned * mall_alloc_width_blk_aligned * bytes_per_pixel + + (256 * DCN3_2_MALL_MBLK_SIZE_BYTES) - 1) / (256 * DCN3_2_MALL_MBLK_SIZE_BYTES); - // Include cursor size for CAB allocation - 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; + bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; - 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; - } - } + /* (cache lines used is total bytes / cache_line size. Add +2 for worst case alignment + * (MALL is 64-byte aligned) + */ + cache_lines_per_plane = bytes_in_mall / dc->caps.cache_line_size + 2; + cache_lines_used += cache_lines_per_plane; + } - 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; + // Include cursor size for CAB allocation + 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; - } + if (pipe->stream && pipe->plane_state && hubp) + /* Find the cursor plane and use the exact size instead of + using the max for calculation */ - 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); - } + if (hubp->curs_attr.width > 0) { + // Round cursor width to next multiple of 64 + cursor_size = (((hubp->curs_attr.width + 63) / 64) * 64) * hubp->curs_attr.height; + + switch (pipe->stream->cursor_attributes.color_format) { + case CURSOR_MODE_MONO: + cursor_size /= 2; + cursor_bpp = 4; + 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; + cursor_bpp = 4; + break; + + case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED: + case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED: + cursor_size *= 8; + cursor_bpp = 8; + break; + } + + if (pipe->stream->cursor_position.enable && !dc->debug.alloc_extra_way_for_cursor && + cursor_size > 16384) { + /* cursor_num_mblk = CEILING(num_cursors*cursor_width*cursor_width*cursor_Bpe/mblk_bytes, 1) + */ + cache_lines_used += (((hubp->curs_attr.width * hubp->curs_attr.height * cursor_bpp + + DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES) * + DCN3_2_MALL_MBLK_SIZE_BYTES) / dc->caps.cache_line_size + 2; + } + break; + } } // Convert number of cache lines required to number of ways @@ -345,8 +331,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c 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) { + dc->debug.alloc_extra_way_for_cursor && + 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 @@ -358,7 +344,9 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c } } } - + if (dc->debug.force_mall_ss_num_ways > 0) { + num_ways = dc->debug.force_mall_ss_num_ways; + } return num_ways; } @@ -367,7 +355,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) union dmub_rb_cmd cmd; uint8_t ways, i; int j; - bool stereo_in_use = false; + bool mall_ss_unsupported = false; struct dc_plane_state *plane = NULL; if (!dc->ctx->dmub_srv) @@ -398,22 +386,23 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) */ ways = dcn32_calculate_cab_allocation(dc, dc->current_state); - /* MALL not supported with Stereo3D. If any plane is using stereo, - * don't try to enter MALL. + /* MALL not supported with Stereo3D or TMZ surface. If any plane is using stereo, + * or TMZ surface, don't try to enter MALL. */ for (i = 0; i < dc->current_state->stream_count; i++) { for (j = 0; j < dc->current_state->stream_status[i].plane_count; j++) { plane = dc->current_state->stream_status[i].plane_states[j]; - if (plane->address.type == PLN_ADDR_TYPE_GRPH_STEREO) { - stereo_in_use = true; + if (plane->address.type == PLN_ADDR_TYPE_GRPH_STEREO || + plane->address.tmz_surface) { + mall_ss_unsupported = true; break; } } - if (stereo_in_use) + if (mall_ss_unsupported) break; } - if (ways <= dc->caps.cache_num_ways && !stereo_in_use) { + if (ways <= dc->caps.cache_num_ways && !mall_ss_unsupported) { memset(&cmd, 0, sizeof(cmd)); cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB; @@ -451,7 +440,6 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) */ void dcn32_commit_subvp_config(struct dc *dc, struct dc_state *context) { -/* int i; bool enable_subvp = false; @@ -469,7 +457,6 @@ void dcn32_commit_subvp_config(struct dc *dc, struct dc_state *context) } } dc_dmub_setup_subvp_dmub_command(dc, context, enable_subvp); -*/ } /* Sub-Viewport DMUB lock needs to be acquired by driver whenever SubVP is active and: @@ -642,10 +629,9 @@ bool dcn32_set_input_transfer_func(struct dc *dc, params = &dpp_base->degamma_params; } - result = dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); + dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); - if (result && - pipe_ctx->stream_res.opp && + if (pipe_ctx->stream_res.opp && pipe_ctx->stream_res.opp->ctx && hws->funcs.set_mcm_luts) result = hws->funcs.set_mcm_luts(pipe_ctx, plane_state); @@ -741,7 +727,29 @@ 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) { @@ -751,7 +759,8 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) hubp->funcs->hubp_update_mall_sel(hubp, num_ways <= dc->caps.cache_num_ways && pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED && - pipe->plane_state->address.type != PLN_ADDR_TYPE_GRPH_STEREO ? 2 : 0, + pipe->plane_state->address.type != PLN_ADDR_TYPE_GRPH_STEREO && + !pipe->plane_state->address.tmz_surface ? 2 : 0, cache_cursor); } } @@ -861,6 +870,7 @@ void dcn32_init_hw(struct dc *dc) if (link->link_enc->funcs->is_dig_enabled && link->link_enc->funcs->is_dig_enabled(link->link_enc)) { link->link_status.link_active = true; + link->phy_state.symclk_state = SYMCLK_ON_TX_ON; if (link->link_enc->funcs->fec_is_active && link->link_enc->funcs->fec_is_active(link->link_enc)) link->fec_state = dc_link_fec_enabled; @@ -979,6 +989,10 @@ void dcn32_init_hw(struct dc *dc) dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; } + + /* Enable support for ODM and windowed MPO if policy flag is set */ + if (dc->debug.enable_single_display_2to1_odm_policy) + dc->config.enable_windowed_mpo_odm = true; } static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, @@ -1133,23 +1147,25 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * true); } - // Don't program pixel clock after link is already enabled -/* if (false == pipe_ctx->clock_source->funcs->program_pix_clk( - pipe_ctx->clock_source, - &pipe_ctx->stream_res.pix_clk_params, - &pipe_ctx->pll_settings)) { - BREAK_TO_DEBUGGER(); - }*/ + if (pipe_ctx->stream_res.dsc) { + struct pipe_ctx *current_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx]; - if (pipe_ctx->stream_res.dsc) update_dsc_on_stream(pipe_ctx, pipe_ctx->stream->timing.flags.DSC); + + /* Check if no longer using pipe for ODM, then need to disconnect DSC for that pipe */ + if (!pipe_ctx->next_odm_pipe && current_pipe_ctx->next_odm_pipe && + current_pipe_ctx->next_odm_pipe->stream_res.dsc) { + struct display_stream_compressor *dsc = current_pipe_ctx->next_odm_pipe->stream_res.dsc; + /* disconnect DSC block from stream */ + dsc->funcs->dsc_disconnect(dsc); + } + } } unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div) { 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; // For phantom pipes, use the same programming as the main pipes @@ -1159,6 +1175,9 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); odm_combine_factor = get_odm_config(pipe_ctx, NULL); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) + return odm_combine_factor; + if (is_dp_128b_132b_signal(pipe_ctx)) { *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { @@ -1174,7 +1193,7 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign } 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) || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) *k2_div = PIXEL_RATE_DIV_BY_2; } } @@ -1211,7 +1230,6 @@ void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, struct dc_link *link = stream->link; struct dce_hwseq *hws = link->dc->hwseq; struct pipe_ctx *odm_pipe; - struct dc *dc = pipe_ctx->stream->ctx->dc; uint32_t pix_per_cycle = 1; params.opp_cnt = 1; @@ -1230,7 +1248,7 @@ void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, pipe_ctx->stream_res.tg->inst); } else if (dc_is_dp_signal(pipe_ctx->stream->signal)) { if (optc2_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1 - || dc->debug.enable_dp_dig_pixel_rate_div_policy) { + || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) { params.timing.pix_clk_100hz /= 2; pix_per_cycle = 2; } @@ -1247,35 +1265,163 @@ bool dcn32_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) { struct dc *dc = pipe_ctx->stream->ctx->dc; + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + 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; } -void dcn32_update_phy_state(struct dc_state *state, struct pipe_ctx *pipe_ctx, - enum phy_state target_state) +static void apply_symclk_on_tx_off_wa(struct dc_link *link) { - enum phy_state current_state = pipe_ctx->stream->link->phy_state; - - if (target_state == TX_OFF_SYMCLK_OFF) { - core_link_disable_stream(pipe_ctx); - pipe_ctx->stream->link->phy_state = TX_OFF_SYMCLK_OFF; - } else if (target_state == TX_ON_SYMCLK_ON) { - core_link_enable_stream(state, pipe_ctx); - pipe_ctx->stream->link->phy_state = TX_ON_SYMCLK_ON; - } else if (target_state == TX_OFF_SYMCLK_ON) { - if (current_state == TX_ON_SYMCLK_ON) { - core_link_disable_stream(pipe_ctx); - pipe_ctx->stream->link->phy_state = TX_OFF_SYMCLK_OFF; + /* There are use cases where SYMCLK is referenced by OTG. For instance + * for TMDS signal, OTG relies SYMCLK even if TX video output is off. + * However current link interface will power off PHY when disabling link + * output. This will turn off SYMCLK generated by PHY. The workaround is + * to identify such case where SYMCLK is still in use by OTG when we + * power off PHY. When this is detected, we will temporarily power PHY + * back on and move PHY's SYMCLK state to SYMCLK_ON_TX_OFF by calling + * program_pix_clk interface. When OTG is disabled, we will then power + * off PHY by calling disable link output again. + * + * In future dcn generations, we plan to rework transmitter control + * interface so that we could have an option to set SYMCLK ON TX OFF + * state in one step without this workaround + */ + + struct dc *dc = link->ctx->dc; + struct pipe_ctx *pipe_ctx = NULL; + uint8_t i; + + if (link->phy_state.symclk_ref_cnts.otg > 0) { + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx->stream && pipe_ctx->stream->link == link && pipe_ctx->top_pipe == NULL) { + pipe_ctx->clock_source->funcs->program_pix_clk( + pipe_ctx->clock_source, + &pipe_ctx->stream_res.pix_clk_params, + dp_get_link_encoding_format(&pipe_ctx->link_config.dp_link_settings), + &pipe_ctx->pll_settings); + link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + break; + } } + } +} - pipe_ctx->clock_source->funcs->program_pix_clk( - pipe_ctx->clock_source, - &pipe_ctx->stream_res.pix_clk_params, - dp_get_link_encoding_format(&pipe_ctx->link_config.dp_link_settings), - &pipe_ctx->pll_settings); - pipe_ctx->stream->link->phy_state = TX_OFF_SYMCLK_ON; - } else +void dcn32_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct dc *dc = link->ctx->dc; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + struct dmcu *dmcu = dc->res_pool->dmcu; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + link_hwss->disable_link_output(link, link_res, signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_power_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->unlock_phy(dmcu); + + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); + + apply_symclk_on_tx_off_wa(link); +} + +/* For SubVP the main pipe can have a viewport position change + * without a full update. In this case we must also update the + * viewport positions for the phantom pipe accordingly. + */ +void dcn32_update_phantom_vp_position(struct dc *dc, + struct dc_state *context, + struct pipe_ctx *phantom_pipe) +{ + uint32_t i; + struct dc_plane_state *phantom_plane = phantom_pipe->plane_state; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN && + pipe->stream->mall_stream_config.paired_stream == phantom_pipe->stream) { + if (pipe->plane_state && pipe->plane_state->update_flags.bits.position_change) { + + phantom_plane->src_rect.x = pipe->plane_state->src_rect.x; + phantom_plane->src_rect.y = pipe->plane_state->src_rect.y; + phantom_plane->clip_rect.x = pipe->plane_state->clip_rect.x; + phantom_plane->dst_rect.x = pipe->plane_state->dst_rect.x; + phantom_plane->dst_rect.y = pipe->plane_state->dst_rect.y; + + phantom_pipe->plane_state->update_flags.bits.position_change = 1; + resource_build_scaling_params(phantom_pipe); + return; + } + } + } +} + +bool dcn32_dsc_pg_status( + struct dce_hwseq *hws, + unsigned int dsc_inst) +{ + uint32_t pwr_status = 0; + + switch (dsc_inst) { + case 0: /* DSC0 */ + REG_GET(DOMAIN16_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 1: /* DSC1 */ + + REG_GET(DOMAIN17_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 2: /* DSC2 */ + REG_GET(DOMAIN18_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + case 3: /* DSC3 */ + REG_GET(DOMAIN19_PG_STATUS, + DOMAIN_PGFSM_PWR_STATUS, &pwr_status); + break; + default: BREAK_TO_DEBUGGER(); + break; + } + + return pwr_status == 0; +} + +void dcn32_update_dsc_pg(struct dc *dc, + struct dc_state *context, + bool safe_to_disable) +{ + struct dce_hwseq *hws = dc->hwseq; + int i; + + for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) { + struct display_stream_compressor *dsc = dc->res_pool->dscs[i]; + bool is_dsc_ungated = hws->funcs.dsc_pg_status(hws, dsc->inst); + + if (context->res_ctx.is_dsc_acquired[i]) { + if (!is_dsc_ungated) { + hws->funcs.dsc_pg_control(hws, dsc->inst, true); + } + } else if (safe_to_disable) { + if (is_dsc_ungated) { + hws->funcs.dsc_pg_control(hws, dsc->inst, false); + } + } + } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h index 221e31144d50..ac3657a5b9ea 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h @@ -84,7 +84,20 @@ void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, bool dcn32_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); -void dcn32_update_phy_state(struct dc_state *state, struct pipe_ctx *pipe_ctx, - enum phy_state target_state); +void dcn32_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal); + +void dcn32_update_phantom_vp_position(struct dc *dc, + struct dc_state *context, + struct pipe_ctx *phantom_pipe); + +bool dcn32_dsc_pg_status( + struct dce_hwseq *hws, + unsigned int dsc_inst); + +void dcn32_update_dsc_pg(struct dc *dc, + struct dc_state *context, + bool safe_to_disable); #endif /* __DC_HWSS_DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index 28d220218133..45a949ba6f3f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -99,12 +99,17 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, .set_pipe = dcn21_set_pipe, + .enable_lvds_link_output = dce110_enable_lvds_link_output, + .enable_tmds_link_output = dce110_enable_tmds_link_output, + .enable_dp_link_output = dce110_enable_dp_link_output, + .disable_link_output = dcn32_disable_link_output, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, .get_dcc_en_bits = dcn10_get_dcc_en_bits, .commit_subvp_config = dcn32_commit_subvp_config, .subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock, .update_visual_confirm_color = dcn20_update_visual_confirm_color, - .update_phy_state = dcn32_update_phy_state, + .update_phantom_vp_position = dcn32_update_phantom_vp_position, + .update_dsc_pg = dcn32_update_dsc_pg, }; static const struct hwseq_private_funcs dcn32_private_funcs = { @@ -134,6 +139,7 @@ static const struct hwseq_private_funcs dcn32_private_funcs = { .program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree, .update_odm = dcn32_update_odm, .dsc_pg_control = dcn32_dsc_pg_control, + .dsc_pg_status = dcn32_dsc_pg_status, .set_hdr_multiplier = dcn10_set_hdr_multiplier, .verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high, .wait_for_blank_complete = dcn20_wait_for_blank_complete, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.c index adf93cc8359c..41b0baf8e183 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.c @@ -100,7 +100,7 @@ static void mmhubbub32_warmup_mcif(struct mcif_wb *mcif_wb, REG_UPDATE(MMHUBBUB_WARMUP_CONTROL_STATUS, MMHUBBUB_WARMUP_EN, false); } -void mmhubbub32_config_mcif_buf(struct mcif_wb *mcif_wb, +static void mmhubbub32_config_mcif_buf(struct mcif_wb *mcif_wb, struct mcif_buf_params *params, unsigned int dest_height) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.h index 22355051f5f7..e460cf8d9041 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mmhubbub.h @@ -90,7 +90,6 @@ SF(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUFMGR_SW_OVERRUN_INT_EN, mask_sh),\ SF(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUFMGR_SW_LOCK, mask_sh),\ SF(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUF_ADDR_FENCE_EN, mask_sh),\ - SF(MCIF_WB_BUFMGR_STATUS, MCIF_WB_BUFMGR_VCE_INT_STATUS, mask_sh),\ SF(MCIF_WB_BUFMGR_STATUS, MCIF_WB_BUFMGR_SW_INT_STATUS, mask_sh),\ SF(MCIF_WB_BUFMGR_STATUS, MCIF_WB_BUFMGR_SW_OVERRUN_INT_STATUS, mask_sh),\ SF(MCIF_WB_BUFMGR_STATUS, MCIF_WB_BUFMGR_CUR_BUF, mask_sh),\ @@ -101,7 +100,6 @@ SF(MCIF_WB_BUF_PITCH, MCIF_WB_BUF_CHROMA_PITCH, mask_sh),\ SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_ACTIVE, mask_sh),\ SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_SW_LOCKED, mask_sh),\ - SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_VCE_LOCKED, mask_sh),\ SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_OVERFLOW, mask_sh),\ SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_DISABLE, mask_sh),\ SF(MCIF_WB_BUF_1_STATUS, MCIF_WB_BUF_1_MODE, mask_sh),\ @@ -116,7 +114,6 @@ SF(MCIF_WB_BUF_1_STATUS2, MCIF_WB_BUF_1_C_OVERRUN, mask_sh),\ SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_ACTIVE, mask_sh),\ SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_SW_LOCKED, mask_sh),\ - SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_VCE_LOCKED, mask_sh),\ SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_OVERFLOW, mask_sh),\ SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_DISABLE, mask_sh),\ SF(MCIF_WB_BUF_2_STATUS, MCIF_WB_BUF_2_MODE, mask_sh),\ @@ -131,7 +128,6 @@ SF(MCIF_WB_BUF_2_STATUS2, MCIF_WB_BUF_2_C_OVERRUN, mask_sh),\ SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_ACTIVE, mask_sh),\ SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_SW_LOCKED, mask_sh),\ - SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_VCE_LOCKED, mask_sh),\ SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_OVERFLOW, mask_sh),\ SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_DISABLE, mask_sh),\ SF(MCIF_WB_BUF_3_STATUS, MCIF_WB_BUF_3_MODE, mask_sh),\ @@ -146,7 +142,6 @@ SF(MCIF_WB_BUF_3_STATUS2, MCIF_WB_BUF_3_C_OVERRUN, mask_sh),\ SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_ACTIVE, mask_sh),\ SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_SW_LOCKED, mask_sh),\ - SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_VCE_LOCKED, mask_sh),\ SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_OVERFLOW, mask_sh),\ SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_DISABLE, mask_sh),\ SF(MCIF_WB_BUF_4_STATUS, MCIF_WB_BUF_4_MODE, mask_sh),\ @@ -172,11 +167,6 @@ SF(MCIF_WB_BUF_3_ADDR_C, MCIF_WB_BUF_3_ADDR_C, mask_sh),\ SF(MCIF_WB_BUF_4_ADDR_Y, MCIF_WB_BUF_4_ADDR_Y, mask_sh),\ SF(MCIF_WB_BUF_4_ADDR_C, MCIF_WB_BUF_4_ADDR_C, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK_IGNORE, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_EN, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_INT_ACK, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_SLICE_INT_EN, mask_sh),\ - SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_VCE_LOCK, mask_sh),\ SF(MCIF_WB_BUFMGR_VCE_CONTROL, MCIF_WB_BUFMGR_SLICE_SIZE, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_REFRESH_WATERMARK, mask_sh),\ SF(MCIF_WB_NB_PSTATE_LATENCY_WATERMARK, NB_PSTATE_CHANGE_WATERMARK_MASK, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c index 357bd2461bc9..4edd0655965b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c @@ -701,7 +701,7 @@ static void mpc32_power_on_shaper_3dlut( } -bool mpc32_program_shaper( +static bool mpc32_program_shaper( struct mpc *mpc, const struct pwl_params *params, uint32_t mpcc_id) @@ -726,7 +726,7 @@ bool mpc32_program_shaper( else next_mode = LUT_RAM_A; - mpc32_configure_shaper_lut(mpc, next_mode == LUT_RAM_A ? true:false, mpcc_id); + mpc32_configure_shaper_lut(mpc, next_mode == LUT_RAM_A, mpcc_id); if (next_mode == LUT_RAM_A) mpc32_program_shaper_luta_settings(mpc, params, mpcc_id); @@ -897,7 +897,7 @@ static void mpc32_set_3dlut_mode( } -bool mpc32_program_3dlut( +static bool mpc32_program_3dlut( struct mpc *mpc, const struct tetrahedral_params *params, int mpcc_id) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index 1fad7b48bd5b..2b33eeb213e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -151,12 +151,12 @@ static bool optc32_disable_crtc(struct timing_generator *optc) /* CRTC disabled, so disable clock. */ REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, - 1, 100000); + 1, 150000); return true; } -void optc32_phantom_crtc_post_enable(struct timing_generator *optc) +static void optc32_phantom_crtc_post_enable(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); @@ -190,7 +190,7 @@ static void optc32_set_odm_bypass(struct timing_generator *optc, optc1->opp_count = 1; } -void optc32_setup_manual_trigger(struct timing_generator *optc) +static void optc32_setup_manual_trigger(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); struct dc *dc = optc->ctx->dc; @@ -215,7 +215,7 @@ void optc32_setup_manual_trigger(struct timing_generator *optc) } } -void optc32_set_drr( +static void optc32_set_drr( struct timing_generator *optc, const struct drr_params *params) { 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 ef0a6d468a10..a88dd7b3d1c1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -90,29 +90,6 @@ #include "dcn20/dcn20_vmid.h" #include "dml/dcn32/dcn32_fpu.h" -#define DCN_BASE__INST0_SEG1 0x000000C0 -#define DCN_BASE__INST0_SEG2 0x000034C0 -#define DCN_BASE__INST0_SEG3 0x00009000 -#define NBIO_BASE__INST0_SEG1 0x00000014 - -#define MAX_INSTANCE 6 -#define MAX_SEGMENT 6 - -struct IP_BASE_INSTANCE { - unsigned int segment[MAX_SEGMENT]; -}; - -struct IP_BASE { - struct IP_BASE_INSTANCE instance[MAX_INSTANCE]; -}; - -static const struct IP_BASE DCN_BASE = { { { { 0x00000012, 0x000000C0, 0x000034C0, 0x00009000, 0x02403C00, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } } } }; - #define DC_LOGGER_INIT(logger) enum dcn32_clk_src_array_id { @@ -152,6 +129,13 @@ enum dcn32_clk_src_array_id { REG_STRUCT[id].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name +#define SR_ARR_I2C(reg_name, id) \ + REG_STRUCT[id-1].reg_name = BASE(reg##reg_name##_BASE_IDX) + reg##reg_name + +#define SRI_ARR_I2C(reg_name, block, id)\ + REG_STRUCT[id-1].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ + reg ## block ## id ## _ ## reg_name + #define SRI_ARR_ALPHABET(reg_name, block, index, id)\ REG_STRUCT[index].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -461,22 +445,17 @@ static const struct dcn20_dsc_mask dsc_mask = { }; static struct dcn30_mpc_registers mpc_regs; -#define dcn_mpc_regs_init()\ - ( \ - MPC_REG_LIST_DCN3_0_RI(0),\ - MPC_REG_LIST_DCN3_0_RI(1),\ - MPC_REG_LIST_DCN3_0_RI(2),\ - MPC_REG_LIST_DCN3_0_RI(3),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\ - MPC_MCM_REG_LIST_DCN32_RI(0),\ - MPC_MCM_REG_LIST_DCN32_RI(1),\ - MPC_MCM_REG_LIST_DCN32_RI(2),\ - MPC_MCM_REG_LIST_DCN32_RI(3),\ - MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)\ - ) + +#define dcn_mpc_regs_init() \ + MPC_REG_LIST_DCN3_2_RI(0),\ + MPC_REG_LIST_DCN3_2_RI(1),\ + MPC_REG_LIST_DCN3_2_RI(2),\ + MPC_REG_LIST_DCN3_2_RI(3),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\ + MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0) static const struct dcn30_mpc_shift mpc_shift = { MPC_COMMON_MASK_SH_LIST_DCN32(__SHIFT) @@ -739,7 +718,12 @@ static const struct dc_debug_options debug_defaults_drv = { .force_disable_subvp = false, .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, + + /* Must match enable_single_display_2to1_odm_policy to support dynamic ODM transitions*/ + .enable_double_buffered_dsc_pg_support = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, + .alloc_extra_way_for_cursor = true, }; static const struct dc_debug_options debug_defaults_diags = { @@ -792,7 +776,7 @@ static struct dce_aux *dcn32_aux_engine_create( #define i2c_inst_regs_init(id)\ I2C_HW_ENGINE_COMMON_REG_LIST_DCN30_RI(id) -static struct dce_i2c_registers i2c_hw_regs[6]; +static struct dce_i2c_registers i2c_hw_regs[5]; static const struct dce_i2c_shift i2c_shifts = { I2C_COMMON_MASK_SH_LIST_DCN30(__SHIFT) @@ -916,10 +900,10 @@ static struct hubp *dcn32_hubp_create( #undef REG_STRUCT #define REG_STRUCT hubp_regs - hubp_regs_init(0), - hubp_regs_init(1), - hubp_regs_init(2), - hubp_regs_init(3); + hubp_regs_init(0), + hubp_regs_init(1), + hubp_regs_init(2), + hubp_regs_init(3); if (hubp32_construct(hubp2, ctx, inst, &hubp_regs[inst], &hubp_shift, &hubp_mask)) @@ -1696,6 +1680,8 @@ static void dcn32_enable_phantom_plane(struct dc *dc, phantom_plane->clip_rect.y = 0; phantom_plane->clip_rect.height = phantom_stream->timing.v_addressable; + phantom_plane->is_phantom = true; + dc_add_plane_to_context(dc, phantom_stream, phantom_plane, context); curr_pipe = curr_pipe->bottom_pipe; @@ -1765,6 +1751,10 @@ bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context) pipe->stream->mall_stream_config.type = SUBVP_NONE; pipe->stream->mall_stream_config.paired_stream = NULL; } + + if (pipe->plane_state) { + pipe->plane_state->is_phantom = false; + } } return removed_pipe; } @@ -1814,14 +1804,39 @@ bool dcn32_validate_bandwidth(struct dc *dc, int vlevel = 0; int pipe_cnt = 0; display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + struct mall_temp_config mall_temp_config; + + /* To handle Freesync properly, setting FreeSync DML parameters + * to its default state for the first stage of validation + */ + context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching = false; + context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true; + DC_LOGGER_INIT(dc->ctx->logger); + /* For fast validation, there are situations where a shallow copy of + * of the dc->current_state is created for the validation. In this case + * we want to save and restore the mall config because we always + * teardown subvp at the beginning of validation (and don't attempt + * to add it back if it's fast validation). If we don't restore the + * subvp config in cases of fast validation + shallow copy of the + * dc->current_state, the dc->current_state will have a partially + * removed subvp state when we did not intend to remove it. + */ + if (fast_validate) { + memset(&mall_temp_config, 0, sizeof(mall_temp_config)); + dcn32_save_mall_state(dc, context, &mall_temp_config); + } + BW_VAL_TRACE_COUNT(); DC_FP_START(); out = dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); DC_FP_END(); + if (fast_validate) + dcn32_restore_mall_state(dc, context, &mall_temp_config); + if (pipe_cnt == 0) goto validate_out; @@ -1856,12 +1871,6 @@ validate_out: return out; } - -static bool is_dual_plane(enum surface_pixel_format format) -{ - return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA; -} - int dcn32_populate_dml_pipes_from_context( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, @@ -1870,12 +1879,37 @@ int dcn32_populate_dml_pipes_from_context( int i, pipe_cnt; struct resource_context *res_ctx = &context->res_ctx; struct pipe_ctx *pipe; - bool subvp_in_use = false, is_pipe_split_expected[MAX_PIPES]; - int plane_count = 0; + bool subvp_in_use = false; + uint8_t is_pipe_split_expected[MAX_PIPES] = {0}; struct dc_crtc_timing *timing; dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + /* Determine whether we will apply ODM 2to1 policy: + * Applies to single display and where the number of planes is less than 3. + * For 3 plane case ( 2 MPO planes ), we will not set the policy for the MPO pipes. + * + * Apply pipe split policy first so we can predict the pipe split correctly + * (dcn32_predict_pipe_split). + */ + for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + if (!res_ctx->pipe_ctx[i].stream) + continue; + pipe = &res_ctx->pipe_ctx[i]; + timing = &pipe->stream->timing; + + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + if (context->stream_count == 1 && + context->stream_status[0].plane_count <= 1 && + !dc_is_hdmi_signal(res_ctx->pipe_ctx[i].stream->signal) && + is_h_timing_divisible_by_2(res_ctx->pipe_ctx[i].stream) && + pipe->stream->timing.pix_clk_100hz * 100 > DCN3_2_VMIN_DISPCLK_HZ && + dc->debug.enable_single_display_2to1_odm_policy) { + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; + } + pipe_cnt++; + } + for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { if (!res_ctx->pipe_ctx[i].stream) @@ -1928,57 +1962,18 @@ int dcn32_populate_dml_pipes_from_context( } } - /* Calculate the number of planes we have so we can determine - * whether to apply ODM 2to1 policy or not - */ - if (pipe->stream && !pipe->prev_odm_pipe && - (!pipe->top_pipe || pipe->top_pipe->plane_state != pipe->plane_state)) - ++plane_count; - DC_FP_START(); - is_pipe_split_expected[i] = dcn32_predict_pipe_split(context, pipes[i].pipe, i); + is_pipe_split_expected[i] = dcn32_predict_pipe_split(context, &pipes[pipe_cnt]); DC_FP_END(); pipe_cnt++; } - /* Determine whether we will apply ODM 2to1 policy - * Applies to single display and where the number of planes is less than 3 - * For 3 plane case ( 2 MPO planes ), we will not set the policy for the MPO pipes - */ - for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { - if (!res_ctx->pipe_ctx[i].stream) - continue; - pipe = &res_ctx->pipe_ctx[i]; - timing = &pipe->stream->timing; - - pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; - if (context->stream_count == 1 && !dc_is_hdmi_signal(res_ctx->pipe_ctx[i].stream->signal)) { - if (dc->debug.enable_single_display_2to1_odm_policy) { - if (!((plane_count > 2) && pipe->top_pipe)) - pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; - } - } - pipe_cnt++; - } - /* For DET allocation, we don't want to use DML policy (not optimal for utilizing all * the DET available for each pipe). Use the DET override input to maintain our driver * policy. */ - if (pipe_cnt == 1 && !is_pipe_split_expected[0]) { - pipes[0].pipe.src.det_size_override = DCN3_2_MAX_DET_SIZE; - if (pipe->plane_state && !dc->debug.disable_z9_mpc) { - if (!is_dual_plane(pipe->plane_state->format)) { - pipes[0].pipe.src.det_size_override = DCN3_2_DEFAULT_DET_SIZE; - pipes[0].pipe.src.unbounded_req_mode = true; - if (pipe->plane_state->src_rect.width >= 5120 && - pipe->plane_state->src_rect.height >= 2880) - pipes[0].pipe.src.det_size_override = 320; // 5K or higher - } - } - } else - dcn32_determine_det_override(context, pipes, is_pipe_split_expected, dc->res_pool->pipe_count); + dcn32_set_det_allocations(dc, context, pipes); // In general cases we want to keep the dram clock change requirement // (prefer configs that support MCLK switch). Only override to false @@ -2108,7 +2103,8 @@ 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 60d8fad16eee..f76120e67c16 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -28,8 +28,16 @@ #include "core_types.h" +#define DCN3_2_DEFAULT_DET_SIZE 256 +#define DCN3_2_MAX_DET_SIZE 1152 +#define DCN3_2_MIN_DET_SIZE 128 +#define DCN3_2_MIN_COMPBUF_SIZE_KB 128 #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 DCN3_2_VMIN_DISPCLK_HZ 717000000 #define TO_DCN32_RES_POOL(pool)\ container_of(pool, struct dcn32_resource_pool, base) @@ -37,6 +45,17 @@ extern struct _vcs_dpi_ip_params_st dcn3_2_ip; extern struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc; +/* Temp struct used to save and restore MALL config + * during validation. + * + * TODO: Move MALL config into dc_state instead of stream struct + * to avoid needing to save/restore. + */ +struct mall_temp_config { + struct mall_stream_config mall_stream_config[MAX_PIPES]; + bool is_phantom_plane[MAX_PIPES]; +}; + struct dcn32_resource_pool { struct resource_pool base; }; @@ -100,14 +119,28 @@ bool dcn32_subvp_in_use(struct dc *dc, bool dcn32_mpo_in_use(struct dc_state *context); +bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context); + struct pipe_ctx *dcn32_acquire_idle_pipe_for_head_pipe_in_layer( struct dc_state *state, const struct resource_pool *pool, struct dc_stream_state *stream, struct pipe_ctx *head_pipe); -void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_params_st *pipes, - bool *is_pipe_split_expected, int pipe_cnt); +void dcn32_determine_det_override(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes); + +void dcn32_set_det_allocations(struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes); + +void dcn32_save_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config); + +void dcn32_restore_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config); /* definitions for run time init of reg offsets */ @@ -222,7 +255,8 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par SRI_ARR(DP_MSA_TIMING_PARAM4, DP, id), \ SRI_ARR(DP_MSE_RATE_CNTL, DP, id), SRI_ARR(DP_MSE_RATE_UPDATE, DP, id), \ SRI_ARR(DP_PIXEL_FORMAT, DP, id), SRI_ARR(DP_SEC_CNTL, DP, id), \ - SRI_ARR(DP_SEC_CNTL2, DP, id), SRI_ARR(DP_SEC_CNTL6, DP, id), \ + SRI_ARR(DP_SEC_CNTL1, DP, id), SRI_ARR(DP_SEC_CNTL2, DP, id), \ + SRI_ARR(DP_SEC_CNTL5, DP, id), SRI_ARR(DP_SEC_CNTL6, DP, id), \ SRI_ARR(DP_STEER_FIFO, DP, id), SRI_ARR(DP_VID_M, DP, id), \ SRI_ARR(DP_VID_N, DP, id), SRI_ARR(DP_VID_STREAM_CNTL, DP, id), \ SRI_ARR(DP_VID_TIMING, DP, id), SRI_ARR(DP_SEC_AUD_N, DP, id), \ @@ -735,75 +769,6 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par #define MPC_DWB_MUX_REG_LIST_DCN3_0_RI(inst) \ SRII_DWB(DWB_MUX, MUX, MPC_DWB, inst) -#define MPC_MCM_REG_LIST_DCN32_RI(inst) \ - ( \ - SRII(MPCC_MCM_SHAPER_CONTROL, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_OFFSET_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_OFFSET_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_OFFSET_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_SCALE_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_SCALE_G_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_LUT_INDEX, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_LUT_DATA, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_LUT_WRITE_EN_MASK, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_0_1, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_2_3, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_4_5, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_6_7, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_8_9, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_10_11, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_12_13, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_14_15, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_16_17, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_18_19, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_20_21, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_22_23, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_24_25, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_26_27, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_28_29, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_30_31, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMA_REGION_32_33, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_0_1, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_2_3, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_4_5, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_6_7, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_8_9, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_10_11, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_12_13, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_14_15, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_16_17, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_18_19, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_20_21, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_22_23, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_24_25, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_26_27, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_28_29, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_30_31, MPCC_MCM, inst), \ - SRII(MPCC_MCM_SHAPER_RAMB_REGION_32_33, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_MODE, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_INDEX, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_DATA, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_DATA_30BIT, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_READ_WRITE_CONTROL, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_OUT_NORM_FACTOR, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_OUT_OFFSET_R, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_OUT_OFFSET_G, MPCC_MCM, inst), \ - SRII(MPCC_MCM_3DLUT_OUT_OFFSET_B, MPCC_MCM, inst), \ - SRII(MPCC_MCM_MEM_PWR_CTRL, MPCC_MCM, inst) \ - ) - #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0_RI(inst) \ ( \ SRII(MUX, MPC_OUT, inst), VUPDATE_SRII(CUR, VUPDATE_LOCK_SET, inst) \ @@ -887,6 +852,149 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par SRII(MPCC_OGAM_LUT_CONTROL, MPCC_OGAM, inst) \ ) +#define MPC_REG_LIST_DCN3_2_RI(inst) \ + MPC_REG_LIST_DCN3_0_RI(inst),\ + SRII(MPCC_MOVABLE_CM_LOCATION_CONTROL, MPCC, inst),\ + SRII(MPCC_MCM_SHAPER_CONTROL, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_OFFSET_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_OFFSET_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_OFFSET_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_SCALE_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_SCALE_G_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_LUT_INDEX, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_LUT_DATA, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_LUT_WRITE_EN_MASK, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_0_1, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_2_3, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_4_5, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_6_7, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_8_9, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_10_11, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_12_13, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_14_15, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_16_17, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_18_19, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_20_21, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_22_23, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_24_25, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_26_27, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_28_29, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_30_31, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMA_REGION_32_33, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_0_1, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_2_3, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_4_5, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_6_7, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_8_9, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_10_11, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_12_13, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_14_15, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_16_17, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_18_19, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_20_21, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_22_23, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_24_25, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_26_27, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_28_29, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_30_31, MPCC_MCM, inst),\ + SRII(MPCC_MCM_SHAPER_RAMB_REGION_32_33, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_MODE, MPCC_MCM, inst), /*TODO: may need to add other 3DLUT regs*/\ + SRII(MPCC_MCM_3DLUT_INDEX, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_DATA, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_DATA_30BIT, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_READ_WRITE_CONTROL, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_OUT_NORM_FACTOR, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_OUT_OFFSET_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_OUT_OFFSET_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_3DLUT_OUT_OFFSET_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_CONTROL, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_LUT_INDEX, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_LUT_DATA, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_LUT_CONTROL, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_0_1, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_2_3, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_4_5, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_6_7, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_8_9, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_10_11, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_12_13, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_14_15, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_16_17, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_18_19, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_20_21, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_22_23, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_24_25, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_26_27, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_28_29, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_30_31, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMA_REGION_32_33, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_B, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_G, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_R, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_0_1, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_2_3, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_4_5, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_6_7, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_8_9, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_10_11, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_12_13, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_14_15, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_16_17, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_18_19, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_20_21, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_22_23, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_24_25, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_26_27, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_28_29, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_30_31, MPCC_MCM, inst),\ + SRII(MPCC_MCM_1DLUT_RAMB_REGION_32_33, MPCC_MCM, inst),\ + SRII(MPCC_MCM_MEM_PWR_CTRL, MPCC_MCM, inst) + /* OPTC */ #define OPTC_COMMON_REG_LIST_DCN3_2_RI(inst) \ @@ -1121,6 +1229,7 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D), SR(DCHUBBUB_DET0_CTRL), \ SR(DCHUBBUB_DET1_CTRL), SR(DCHUBBUB_DET2_CTRL), SR(DCHUBBUB_DET3_CTRL), \ SR(DCHUBBUB_COMPBUF_CTRL), SR(COMPBUF_RESERVED_SPACE), \ + SR(DCHUBBUB_DEBUG_CTRL_0), \ SR(DCHUBBUB_ARB_USR_RETRAINING_CNTL), \ SR(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_A), \ SR(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_B), \ @@ -1175,18 +1284,19 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par #define I2C_HW_ENGINE_COMMON_REG_LIST_RI(id) \ ( \ - SRI_ARR(SETUP, DC_I2C_DDC, id), SRI_ARR(SPEED, DC_I2C_DDC, id), \ - SRI_ARR(HW_STATUS, DC_I2C_DDC, id), SR_ARR(DC_I2C_ARBITRATION, id), \ - SR_ARR(DC_I2C_CONTROL, id), SR_ARR(DC_I2C_SW_STATUS, id), \ - SR_ARR(DC_I2C_TRANSACTION0, id), SR_ARR(DC_I2C_TRANSACTION1, id), \ - SR_ARR(DC_I2C_TRANSACTION2, id), SR_ARR(DC_I2C_TRANSACTION3, id), \ - SR_ARR(DC_I2C_DATA, id), SR_ARR(MICROSECOND_TIME_BASE_DIV, id) \ + SRI_ARR_I2C(SETUP, DC_I2C_DDC, id), SRI_ARR_I2C(SPEED, DC_I2C_DDC, id), \ + SRI_ARR_I2C(HW_STATUS, DC_I2C_DDC, id), \ + SR_ARR_I2C(DC_I2C_ARBITRATION, id), \ + SR_ARR_I2C(DC_I2C_CONTROL, id), SR_ARR_I2C(DC_I2C_SW_STATUS, id), \ + SR_ARR_I2C(DC_I2C_TRANSACTION0, id), SR_ARR_I2C(DC_I2C_TRANSACTION1, id),\ + SR_ARR_I2C(DC_I2C_TRANSACTION2, id), SR_ARR_I2C(DC_I2C_TRANSACTION3, id),\ + SR_ARR_I2C(DC_I2C_DATA, id), SR_ARR_I2C(MICROSECOND_TIME_BASE_DIV, id) \ ) #define I2C_HW_ENGINE_COMMON_REG_LIST_DCN30_RI(id) \ ( \ - I2C_HW_ENGINE_COMMON_REG_LIST_RI(id), SR_ARR(DIO_MEM_PWR_CTRL, id), \ - SR_ARR(DIO_MEM_PWR_STATUS, id) \ + I2C_HW_ENGINE_COMMON_REG_LIST_RI(id), SR_ARR_I2C(DIO_MEM_PWR_CTRL, id), \ + SR_ARR_I2C(DIO_MEM_PWR_STATUS, id) \ ) #endif /* _DCN32_RESOURCE_H_ */ 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 ab918fe38f6a..d51d0c40ae5b 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 @@ -28,6 +28,11 @@ #include "dcn20/dcn20_resource.h" #include "dml/dcn32/display_mode_vba_util_32.h" +static bool is_dual_plane(enum surface_pixel_format format) +{ + return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA; +} + /** * ******************************************************************************************** * dcn32_helper_calculate_num_ways_for_subvp: Calculate number of ways needed for SubVP @@ -46,7 +51,6 @@ 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; @@ -54,28 +58,77 @@ 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; + uint16_t mblk_width = 0; + uint16_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; + uint16_t full_vp_height = 0; + bool subvp_in_use = false; 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 && + /* Find the phantom pipes. + * - For pipe split case we need to loop through the bottom and next ODM + * pipes or only half the viewport size is counted + */ + if (pipe->stream && pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + struct pipe_ctx *main_pipe = NULL; + + subvp_in_use = true; + /* 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; - mall_region_pixels = pipe->plane_state->plane_size.surface_pitch * pipe->stream->timing.v_addressable; + 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; - // 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; + /* 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) cache_lines_per_plane = bytes_in_mall / dc->caps.cache_line_size + 2; - // For DCC we must cache the meat surface, so double cache lines required + /* For DCC divide by 256 */ if (pipe->plane_state->dcc.enable) - cache_lines_per_plane *= 2; + cache_lines_per_plane = cache_lines_per_plane + (cache_lines_per_plane / 256) + 1; cache_lines_used += cache_lines_per_plane; } } @@ -86,6 +139,9 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat if (cache_lines_used % lines_per_way > 0) num_ways++; + if (subvp_in_use && dc->debug.force_subvp_num_ways > 0) + num_ways = dc->debug.force_subvp_num_ways; + return num_ways; } @@ -177,36 +233,221 @@ bool dcn32_mpo_in_use(struct dc_state *context) return false; } -void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_params_st *pipes, - bool *is_pipe_split_expected, int pipe_cnt) + +bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->stream) + continue; + + if (pipe->plane_state && pipe->plane_state->rotation != ROTATION_ANGLE_0) + return true; + } + return false; +} + +/** + * ******************************************************************************************* + * dcn32_determine_det_override: Determine DET allocation for each pipe + * + * This function determines how much DET to allocate for each pipe. The total number of + * DET segments will be split equally among each of the streams, and after that the DET + * segments per stream will be split equally among the planes for the given stream. + * + * If there is a plane that's driven by more than 1 pipe (i.e. pipe split), then the + * number of DET for that given plane will be split among the pipes driving that plane. + * + * + * High level algorithm: + * 1. Split total DET among number of streams + * 2. For each stream, split DET among the planes + * 3. For each plane, check if there is a pipe split. If yes, split the DET allocation + * among those pipes. + * 4. Assign the DET override to the DML pipes. + * + * @param [in]: dc: Current DC state + * @param [in]: context: New DC state to be programmed + * @param [in]: pipes: Array of DML pipes + * + * @return: void + * + * ******************************************************************************************* + */ +void dcn32_determine_det_override(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes) { - int i, j, count, stream_segments, pipe_segments[MAX_PIPES]; + uint32_t i, j, k; + uint8_t pipe_plane_count, stream_segments, plane_segments, pipe_segments[MAX_PIPES] = {0}; + uint8_t pipe_counted[MAX_PIPES] = {0}; + uint8_t pipe_cnt = 0; + struct dc_plane_state *current_plane = NULL; + uint8_t stream_count = 0; - if (context->stream_count > 0) { - stream_segments = 18 / context->stream_count; + for (i = 0; i < context->stream_count; i++) { + /* Don't count SubVP streams for DET allocation */ + if (context->streams[i]->mall_stream_config.type != SUBVP_PHANTOM) { + stream_count++; + } + } + + if (stream_count > 0) { + stream_segments = 18 / stream_count; for (i = 0; i < context->stream_count; i++) { - count = 0; - for (j = 0; j < pipe_cnt; j++) { - if (context->res_ctx.pipe_ctx[j].stream == context->streams[i]) { - count++; - if (is_pipe_split_expected[j]) - count++; + if (context->streams[i]->mall_stream_config.type == SUBVP_PHANTOM) + continue; + if (context->stream_status[i].plane_count > 0) + plane_segments = stream_segments / context->stream_status[i].plane_count; + else + plane_segments = stream_segments; + for (j = 0; j < dc->res_pool->pipe_count; j++) { + pipe_plane_count = 0; + if (context->res_ctx.pipe_ctx[j].stream == context->streams[i] && + pipe_counted[j] != 1) { + /* Note: pipe_plane_count indicates the number of pipes to be used for a + * given plane. e.g. pipe_plane_count = 1 means single pipe (i.e. not split), + * pipe_plane_count = 2 means 2:1 split, etc. + */ + pipe_plane_count++; + pipe_counted[j] = 1; + current_plane = context->res_ctx.pipe_ctx[j].plane_state; + for (k = 0; k < dc->res_pool->pipe_count; k++) { + if (k != j && context->res_ctx.pipe_ctx[k].stream == context->streams[i] && + context->res_ctx.pipe_ctx[k].plane_state == current_plane) { + pipe_plane_count++; + pipe_counted[k] = 1; + } + } + + pipe_segments[j] = plane_segments / pipe_plane_count; + for (k = 0; k < dc->res_pool->pipe_count; k++) { + if (k != j && context->res_ctx.pipe_ctx[k].stream == context->streams[i] && + context->res_ctx.pipe_ctx[k].plane_state == current_plane) { + pipe_segments[k] = plane_segments / pipe_plane_count; + } + } } } - pipe_segments[i] = stream_segments / count; } - for (i = 0; i < pipe_cnt; i++) { - pipes[i].pipe.src.det_size_override = 0; - for (j = 0; j < context->stream_count; j++) { - if (context->res_ctx.pipe_ctx[i].stream == context->streams[j]) { - pipes[i].pipe.src.det_size_override = pipe_segments[j] * DCN3_2_DET_SEG_SIZE; - break; - } - } + for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + pipes[pipe_cnt].pipe.src.det_size_override = pipe_segments[i] * DCN3_2_DET_SEG_SIZE; + pipe_cnt++; } } else { - for (i = 0; i < pipe_cnt; i++) + for (i = 0; i < dc->res_pool->pipe_count; i++) pipes[i].pipe.src.det_size_override = 4 * DCN3_2_DET_SEG_SIZE; //DCN3_2_DEFAULT_DET_SIZE } } + +void dcn32_set_det_allocations(struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes) +{ + int i, pipe_cnt; + struct resource_context *res_ctx = &context->res_ctx; + struct pipe_ctx *pipe; + + for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { + + if (!res_ctx->pipe_ctx[i].stream) + continue; + + pipe = &res_ctx->pipe_ctx[i]; + pipe_cnt++; + } + + /* For DET allocation, we don't want to use DML policy (not optimal for utilizing all + * the DET available for each pipe). Use the DET override input to maintain our driver + * policy. + */ + if (pipe_cnt == 1) { + pipes[0].pipe.src.det_size_override = DCN3_2_MAX_DET_SIZE; + if (pipe->plane_state && !dc->debug.disable_z9_mpc && pipe->plane_state->tiling_info.gfx9.swizzle != DC_SW_LINEAR) { + if (!is_dual_plane(pipe->plane_state->format)) { + pipes[0].pipe.src.det_size_override = DCN3_2_DEFAULT_DET_SIZE; + pipes[0].pipe.src.unbounded_req_mode = true; + if (pipe->plane_state->src_rect.width >= 5120 && + pipe->plane_state->src_rect.height >= 2880) + pipes[0].pipe.src.det_size_override = 320; // 5K or higher + } + } + } else + dcn32_determine_det_override(dc, context, pipes); +} + +/** + * ******************************************************************************************* + * dcn32_save_mall_state: Save MALL (SubVP) state for fast validation cases + * + * This function saves the MALL (SubVP) case for fast validation cases. For fast validation, + * there are situations where a shallow copy of the dc->current_state is created for the + * validation. In this case we want to save and restore the mall config because we always + * teardown subvp at the beginning of validation (and don't attempt to add it back if it's + * fast validation). If we don't restore the subvp config in cases of fast validation + + * shallow copy of the dc->current_state, the dc->current_state will have a partially + * removed subvp state when we did not intend to remove it. + * + * NOTE: This function ONLY works if the streams are not moved to a different pipe in the + * validation. We don't expect this to happen in fast_validation=1 cases. + * + * @param [in]: dc: Current DC state + * @param [in]: context: New DC state to be programmed + * @param [out]: temp_config: struct used to cache the existing MALL state + * + * @return: void + * + * ******************************************************************************************* + */ +void dcn32_save_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream) + temp_config->mall_stream_config[i] = pipe->stream->mall_stream_config; + + if (pipe->plane_state) + temp_config->is_phantom_plane[i] = pipe->plane_state->is_phantom; + } +} + +/** + * ******************************************************************************************* + * dcn32_restore_mall_state: Restore MALL (SubVP) state for fast validation cases + * + * Restore the MALL state based on the previously saved state from dcn32_save_mall_state + * + * @param [in]: dc: Current DC state + * @param [in/out]: context: New DC state to be programmed, restore MALL state into here + * @param [in]: temp_config: struct that has the cached MALL state + * + * @return: void + * + * ******************************************************************************************* + */ +void dcn32_restore_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream) + pipe->stream->mall_stream_config = temp_config->mall_stream_config[i]; + + if (pipe->plane_state) + pipe->plane_state->is_phantom = temp_config->is_phantom_plane[i]; + } +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c index 49682a31ecbd..fa9b6603cfd3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c @@ -91,7 +91,6 @@ static const struct link_encoder_funcs dcn321_link_enc_funcs = { .is_in_alt_mode = dcn20_link_encoder_is_in_alt_mode, .get_max_link_cap = dcn20_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, - .set_dig_output_mode = enc32_set_dig_output_mode, }; void dcn321_link_encoder_construct( 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 a93dc00ebfb5..61087f2385a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -93,34 +93,7 @@ #include "vm_helper.h" #include "dcn20/dcn20_vmid.h" -#define DCN_BASE__INST0_SEG1 0x000000C0 -#define DCN_BASE__INST0_SEG2 0x000034C0 -#define DCN_BASE__INST0_SEG3 0x00009000 -#define NBIO_BASE__INST0_SEG1 0x00000014 - -#define MAX_INSTANCE 8 -#define MAX_SEGMENT 6 - -struct IP_BASE_INSTANCE { - unsigned int segment[MAX_SEGMENT]; -}; - -struct IP_BASE { - struct IP_BASE_INSTANCE instance[MAX_INSTANCE]; -}; - -static const struct IP_BASE DCN_BASE = { { { { 0x00000012, 0x000000C0, 0x000034C0, 0x00009000, 0x02403C00, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } }, - { { 0, 0, 0, 0, 0, 0 } } } }; - #define DC_LOGGER_INIT(logger) -#define fixed16_to_double(x) (((double)x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) enum dcn321_clk_src_array_id { DCN321_CLK_SRC_PLL0, @@ -159,6 +132,13 @@ enum dcn321_clk_src_array_id { REG_STRUCT[id].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name +#define SR_ARR_I2C(reg_name, id) \ + REG_STRUCT[id-1].reg_name = BASE(reg##reg_name##_BASE_IDX) + reg##reg_name + +#define SRI_ARR_I2C(reg_name, block, id)\ + REG_STRUCT[id-1].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ + reg ## block ## id ## _ ## reg_name + #define SRI_ARR_ALPHABET(reg_name, block, index, id)\ REG_STRUCT[index].reg_name = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -466,21 +446,15 @@ static const struct dcn20_dsc_mask dsc_mask = { static struct dcn30_mpc_registers mpc_regs; #define dcn_mpc_regs_init()\ - ( \ - MPC_REG_LIST_DCN3_0_RI(0),\ - MPC_REG_LIST_DCN3_0_RI(1),\ - MPC_REG_LIST_DCN3_0_RI(2),\ - MPC_REG_LIST_DCN3_0_RI(3),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\ - MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\ - MPC_MCM_REG_LIST_DCN32_RI(0),\ - MPC_MCM_REG_LIST_DCN32_RI(1),\ - MPC_MCM_REG_LIST_DCN32_RI(2),\ - MPC_MCM_REG_LIST_DCN32_RI(3),\ - MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)\ - ) + MPC_REG_LIST_DCN3_2_RI(0),\ + MPC_REG_LIST_DCN3_2_RI(1),\ + MPC_REG_LIST_DCN3_2_RI(2),\ + MPC_REG_LIST_DCN3_2_RI(3),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\ + MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\ + MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0) static const struct dcn30_mpc_shift mpc_shift = { MPC_COMMON_MASK_SH_LIST_DCN32(__SHIFT) @@ -742,7 +716,12 @@ static const struct dc_debug_options debug_defaults_drv = { .force_disable_subvp = false, .exit_idle_opt_for_cursor_updates = true, .enable_single_display_2to1_odm_policy = true, + + /*must match enable_single_display_2to1_odm_policy to support dynamic ODM transitions*/ + .enable_double_buffered_dsc_pg_support = true, .enable_dp_dig_pixel_rate_div_policy = 1, + .allow_sw_cursor_fallback = false, + .alloc_extra_way_for_cursor = true, }; static const struct dc_debug_options debug_defaults_diags = { @@ -796,7 +775,7 @@ static struct dce_aux *dcn321_aux_engine_create( #define i2c_inst_regs_init(id)\ I2C_HW_ENGINE_COMMON_REG_LIST_DCN30_RI(id) -static struct dce_i2c_registers i2c_hw_regs[6]; +static struct dce_i2c_registers i2c_hw_regs[5]; static const struct dce_i2c_shift i2c_shifts = { I2C_COMMON_MASK_SH_LIST_DCN30(__SHIFT) @@ -818,11 +797,11 @@ static struct dce_i2c_hw *dcn321_i2c_hw_create( #undef REG_STRUCT #define REG_STRUCT i2c_hw_regs - i2c_inst_regs_init(1), - i2c_inst_regs_init(2), - i2c_inst_regs_init(3), - i2c_inst_regs_init(4), - i2c_inst_regs_init(5); + i2c_inst_regs_init(1), + i2c_inst_regs_init(2), + i2c_inst_regs_init(3), + i2c_inst_regs_init(4), + i2c_inst_regs_init(5); dcn2_i2c_hw_construct(dce_i2c_hw, ctx, inst, &i2c_hw_regs[inst], &i2c_shifts, &i2c_masks); @@ -920,10 +899,10 @@ static struct hubp *dcn321_hubp_create( #undef REG_STRUCT #define REG_STRUCT hubp_regs - hubp_regs_init(0), - hubp_regs_init(1), - hubp_regs_init(2), - hubp_regs_init(3); + hubp_regs_init(0), + hubp_regs_init(1), + hubp_regs_init(2), + hubp_regs_init(3); if (hubp32_construct(hubp2, ctx, inst, &hubp_regs[inst], &hubp_shift, &hubp_mask)) @@ -1625,7 +1604,7 @@ static struct resource_funcs dcn321_res_pool_funcs = { .validate_bandwidth = dcn32_validate_bandwidth, .calculate_wm_and_dlg = dcn32_calculate_wm_and_dlg, .populate_dml_pipes = dcn32_populate_dml_pipes_from_context, - .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, + .acquire_idle_pipe_for_head_pipe_in_layer = dcn32_acquire_idle_pipe_for_head_pipe_in_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, .add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource, .remove_stream_from_ctx = dcn20_remove_stream_from_ctx, @@ -1668,14 +1647,14 @@ static bool dcn321_resource_construct( #undef REG_STRUCT #define REG_STRUCT abm_regs - abm_regs_init(0), - abm_regs_init(1), - abm_regs_init(2), - abm_regs_init(3); + abm_regs_init(0), + abm_regs_init(1), + abm_regs_init(2), + abm_regs_init(3); #undef REG_STRUCT #define REG_STRUCT dccg_regs - dccg_regs_init(); + dccg_regs_init(); ctx->dc_bios->regs = &bios_regs; @@ -1713,7 +1692,8 @@ 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/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h index e93187c06648..e3e5c39895a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h @@ -173,7 +173,8 @@ void dm_helpers_smu_timeout(struct dc_context *ctx, unsigned int msg_id, unsigne (result == 0x0) void dm_helpers_init_panel_settings( struct dc_context *ctx, - struct dc_panel_config *config); + struct dc_panel_config *config, + struct dc_sink *sink); void dm_helpers_override_panel_settings( struct dc_context *ctx, struct dc_panel_config *config); diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 86a3b5bfd699..d70838edba80 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -34,7 +34,7 @@ dml_ccflags := -mhard-float -maltivec endif ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) +ifneq ($(call gcc-min-version, 70100),y) IS_OLD_GCC = 1 endif endif @@ -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/calcs/dcn_calc_auto.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_auto.c index 41284e263325..288d22a16cf2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_auto.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_auto.c @@ -526,10 +526,10 @@ void mode_support_and_system_configuration(struct dcn_bw_internal_vars *v) } if (v->max_swath_height_c[k] > 0.0) { v->swath_width_granularity_c = 256.0 /dcn_bw_ceil2(v->byte_per_pixel_in_detc[k], 2.0) / v->max_swath_height_c[k]; - } - v->rounded_up_max_swath_size_bytes_c = (dcn_bw_ceil2(v->swath_width_yper_state[i][j][k] / 2.0 - 1.0, v->swath_width_granularity_c) + v->swath_width_granularity_c) * v->byte_per_pixel_in_detc[k] * v->max_swath_height_c[k]; - if (v->source_pixel_format[k] == dcn_bw_yuv420_sub_10) { - v->rounded_up_max_swath_size_bytes_c =dcn_bw_ceil2(v->rounded_up_max_swath_size_bytes_c, 256.0) + 256; + v->rounded_up_max_swath_size_bytes_c = (dcn_bw_ceil2(v->swath_width_yper_state[i][j][k] / 2.0 - 1.0, v->swath_width_granularity_c) + v->swath_width_granularity_c) * v->byte_per_pixel_in_detc[k] * v->max_swath_height_c[k]; + if (v->source_pixel_format[k] == dcn_bw_yuv420_sub_10) { + v->rounded_up_max_swath_size_bytes_c = dcn_bw_ceil2(v->rounded_up_max_swath_size_bytes_c, 256.0) + 256; + } } if (v->rounded_up_max_swath_size_bytes_y + v->rounded_up_max_swath_size_bytes_c <= v->det_buffer_size_in_kbyte * 1024.0 / 2.0) { v->swath_height_yper_state[i][j][k] = v->max_swath_height_y[k]; @@ -552,14 +552,14 @@ void mode_support_and_system_configuration(struct dcn_bw_internal_vars *v) v->lines_in_det_chroma = v->det_buffer_size_in_kbyte * 1024.0 / 3.0 / v->byte_per_pixel_in_dety[k] / (v->swath_width_yper_state[i][j][k] / 2.0); } v->effective_lb_latency_hiding_source_lines_luma =dcn_bw_min2(v->max_line_buffer_lines,dcn_bw_floor2(v->line_buffer_size / v->lb_bit_per_pixel[k] / (v->swath_width_yper_state[i][j][k] /dcn_bw_max2(v->h_ratio[k], 1.0)), 1.0)) - (v->vtaps[k] - 1.0); - v->effective_lb_latency_hiding_source_lines_chroma =dcn_bw_min2(v->max_line_buffer_lines,dcn_bw_floor2(v->line_buffer_size / v->lb_bit_per_pixel[k] / (v->swath_width_yper_state[i][j][k] / 2.0 /dcn_bw_max2(v->h_ratio[k] / 2.0, 1.0)), 1.0)) - (v->vta_pschroma[k] - 1.0); v->effective_detlb_lines_luma =dcn_bw_floor2(v->lines_in_det_luma +dcn_bw_min2(v->lines_in_det_luma * v->required_dispclk[i][j] * v->byte_per_pixel_in_dety[k] * v->pscl_factor[k] / v->return_bw_per_state[i], v->effective_lb_latency_hiding_source_lines_luma), v->swath_height_yper_state[i][j][k]); - v->effective_detlb_lines_chroma =dcn_bw_floor2(v->lines_in_det_chroma +dcn_bw_min2(v->lines_in_det_chroma * v->required_dispclk[i][j] * v->byte_per_pixel_in_detc[k] * v->pscl_factor_chroma[k] / v->return_bw_per_state[i], v->effective_lb_latency_hiding_source_lines_chroma), v->swath_height_cper_state[i][j][k]); if (v->byte_per_pixel_in_detc[k] == 0.0) { v->urgent_latency_support_us_per_state[i][j][k] = v->effective_detlb_lines_luma * (v->htotal[k] / v->pixel_clock[k]) / v->v_ratio[k] - v->effective_detlb_lines_luma * v->swath_width_yper_state[i][j][k] *dcn_bw_ceil2(v->byte_per_pixel_in_dety[k], 1.0) / (v->return_bw_per_state[i] / v->no_of_dpp[i][j][k]); } else { - v->urgent_latency_support_us_per_state[i][j][k] =dcn_bw_min2(v->effective_detlb_lines_luma * (v->htotal[k] / v->pixel_clock[k]) / v->v_ratio[k] - v->effective_detlb_lines_luma * v->swath_width_yper_state[i][j][k] *dcn_bw_ceil2(v->byte_per_pixel_in_dety[k], 1.0) / (v->return_bw_per_state[i] / v->no_of_dpp[i][j][k]), v->effective_detlb_lines_chroma * (v->htotal[k] / v->pixel_clock[k]) / (v->v_ratio[k] / 2.0) - v->effective_detlb_lines_chroma * v->swath_width_yper_state[i][j][k] / 2.0 *dcn_bw_ceil2(v->byte_per_pixel_in_detc[k], 2.0) / (v->return_bw_per_state[i] / v->no_of_dpp[i][j][k])); + v->effective_lb_latency_hiding_source_lines_chroma = dcn_bw_min2(v->max_line_buffer_lines, dcn_bw_floor2(v->line_buffer_size / v->lb_bit_per_pixel[k] / (v->swath_width_yper_state[i][j][k] / 2.0 / dcn_bw_max2(v->h_ratio[k] / 2.0, 1.0)), 1.0)) - (v->vta_pschroma[k] - 1.0); + v->effective_detlb_lines_chroma = dcn_bw_floor2(v->lines_in_det_chroma + dcn_bw_min2(v->lines_in_det_chroma * v->required_dispclk[i][j] * v->byte_per_pixel_in_detc[k] * v->pscl_factor_chroma[k] / v->return_bw_per_state[i], v->effective_lb_latency_hiding_source_lines_chroma), v->swath_height_cper_state[i][j][k]); + v->urgent_latency_support_us_per_state[i][j][k] = dcn_bw_min2(v->effective_detlb_lines_luma * (v->htotal[k] / v->pixel_clock[k]) / v->v_ratio[k] - v->effective_detlb_lines_luma * v->swath_width_yper_state[i][j][k] * dcn_bw_ceil2(v->byte_per_pixel_in_dety[k], 1.0) / (v->return_bw_per_state[i] / v->no_of_dpp[i][j][k]), v->effective_detlb_lines_chroma * (v->htotal[k] / v->pixel_clock[k]) / (v->v_ratio[k] / 2.0) - v->effective_detlb_lines_chroma * v->swath_width_yper_state[i][j][k] / 2.0 * dcn_bw_ceil2(v->byte_per_pixel_in_detc[k], 2.0) / (v->return_bw_per_state[i] / v->no_of_dpp[i][j][k])); } } } @@ -1146,10 +1146,10 @@ void display_pipe_configuration(struct dcn_bw_internal_vars *v) } if (v->maximum_swath_height_c > 0.0) { v->swath_width_granularity_c = 256.0 /dcn_bw_ceil2(v->byte_per_pix_detc, 2.0) / v->maximum_swath_height_c; - } - v->rounded_up_max_swath_size_bytes_c = (dcn_bw_ceil2(v->swath_width / 2.0 - 1.0, v->swath_width_granularity_c) + v->swath_width_granularity_c) * v->byte_per_pix_detc * v->maximum_swath_height_c; - if (v->source_pixel_format[k] == dcn_bw_yuv420_sub_10) { - v->rounded_up_max_swath_size_bytes_c =dcn_bw_ceil2(v->rounded_up_max_swath_size_bytes_c, 256.0) + 256; + v->rounded_up_max_swath_size_bytes_c = (dcn_bw_ceil2(v->swath_width / 2.0 - 1.0, v->swath_width_granularity_c) + v->swath_width_granularity_c) * v->byte_per_pix_detc * v->maximum_swath_height_c; + if (v->source_pixel_format[k] == dcn_bw_yuv420_sub_10) { + v->rounded_up_max_swath_size_bytes_c = dcn_bw_ceil2(v->rounded_up_max_swath_size_bytes_c, 256.0) + 256; + } } if (v->rounded_up_max_swath_size_bytes_y + v->rounded_up_max_swath_size_bytes_c <= v->det_buffer_size_in_kbyte * 1024.0 / 2.0) { v->swath_height_y[k] = v->maximum_swath_height_y; diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_math.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_math.c index 07d18e78de49..cac72413a097 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_math.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calc_math.c @@ -23,6 +23,7 @@ * */ +#include "os_types.h" #include "dcn_calc_math.h" #define isNaN(number) ((number) != (number)) @@ -69,8 +70,8 @@ float dcn_bw_max2(const float arg1, const float arg2) float dcn_bw_floor2(const float arg, const float significance) { - if (significance == 0) - return 0; + ASSERT(significance != 0); + return ((int) (arg / significance)) * significance; } float dcn_bw_floor(const float arg) @@ -80,17 +81,14 @@ float dcn_bw_floor(const float arg) float dcn_bw_ceil(const float arg) { - float flr = dcn_bw_floor2(arg, 1); - - return flr + 0.00001 >= arg ? arg : flr + 1; + return (int) (arg + 0.99999); } float dcn_bw_ceil2(const float arg, const float significance) { - float flr = dcn_bw_floor2(arg, significance); - if (significance == 0) - return 0; - return flr + 0.00001 >= arg ? arg : flr + significance; + ASSERT(significance != 0); + + return ((int) (arg / significance + 0.99999)) * significance; } float dcn_bw_max3(float v1, float v2, float v3) diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c index d46adc849d2a..e73f089c84bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c @@ -1444,81 +1444,67 @@ unsigned int dcn_find_dcfclk_suits_all( return dcf_clk; } -static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks) +void dcn_bw_update_from_pplib_fclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *fclks) { - int i; - - if (clks->num_levels == 0) - return false; - - for (i = 0; i < clks->num_levels; i++) - /* Ensure that the result is sane */ - if (clks->data[i].clocks_in_khz == 0) - return false; + unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx; - return true; + ASSERT(fclks->num_levels); + + vmin0p65_idx = 0; + vmid0p72_idx = fclks->num_levels - + (fclks->num_levels > 2 ? 3 : (fclks->num_levels > 1 ? 2 : 1)); + vnom0p8_idx = fclks->num_levels - (fclks->num_levels > 1 ? 2 : 1); + vmax0p9_idx = fclks->num_levels - 1; + + dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = + 32 * (fclks->data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = + dc->dcn_soc->number_of_channels * + (fclks->data[vmid0p72_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = + dc->dcn_soc->number_of_channels * + (fclks->data[vnom0p8_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = + dc->dcn_soc->number_of_channels * + (fclks->data[vmax0p9_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; } -void dcn_bw_update_from_pplib(struct dc *dc) +void dcn_bw_update_from_pplib_dcfclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *dcfclks) { - struct dc_context *ctx = dc->ctx; - struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0}; - bool res; - unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx; - - /* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */ - res = dm_pp_get_clock_levels_by_type_with_voltage( - ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks); - - if (res) - res = verify_clock_values(&fclks); - - if (res) { - ASSERT(fclks.num_levels); - - vmin0p65_idx = 0; - vmid0p72_idx = fclks.num_levels - - (fclks.num_levels > 2 ? 3 : (fclks.num_levels > 1 ? 2 : 1)); - vnom0p8_idx = fclks.num_levels - (fclks.num_levels > 1 ? 2 : 1); - vmax0p9_idx = fclks.num_levels - 1; - - dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = - 32 * (fclks.data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = - dc->dcn_soc->number_of_channels * - (fclks.data[vmid0p72_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = - dc->dcn_soc->number_of_channels * - (fclks.data[vnom0p8_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = - dc->dcn_soc->number_of_channels * - (fclks.data[vmax0p9_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - } else - BREAK_TO_DEBUGGER(); - - res = dm_pp_get_clock_levels_by_type_with_voltage( - ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks); - - if (res) - res = verify_clock_values(&dcfclks); + if (dcfclks->num_levels >= 3) { + dc->dcn_soc->dcfclkv_min0p65 = dcfclks->data[0].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_mid0p72 = dcfclks->data[dcfclks->num_levels - 3].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_nom0p8 = dcfclks->data[dcfclks->num_levels - 2].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_max0p9 = dcfclks->data[dcfclks->num_levels - 1].clocks_in_khz / 1000.0; + } +} - if (res && dcfclks.num_levels >= 3) { - dc->dcn_soc->dcfclkv_min0p65 = dcfclks.data[0].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_mid0p72 = dcfclks.data[dcfclks.num_levels - 3].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_nom0p8 = dcfclks.data[dcfclks.num_levels - 2].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_max0p9 = dcfclks.data[dcfclks.num_levels - 1].clocks_in_khz / 1000.0; - } else - BREAK_TO_DEBUGGER(); +void dcn_get_soc_clks( + struct dc *dc, + int *min_fclk_khz, + int *min_dcfclk_khz, + int *socclk_khz) +{ + *min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32; + *min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000; + *socclk_khz = dc->dcn_soc->socclk * 1000; } -void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) +void dcn_bw_notify_pplib_of_wm_ranges( + struct dc *dc, + int min_fclk_khz, + int min_dcfclk_khz, + int socclk_khz) { struct pp_smu_funcs_rv *pp = NULL; struct pp_smu_wm_range_sets ranges = {0}; - int min_fclk_khz, min_dcfclk_khz, socclk_khz; const int overdrive = 5000000; /* 5 GHz to cover Overdrive */ if (dc->res_pool->pp_smu) @@ -1526,10 +1512,6 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) if (!pp || !pp->set_wm_ranges) return; - min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32; - min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000; - socclk_khz = dc->dcn_soc->socclk * 1000; - /* Now notify PPLib/SMU about which Watermarks sets they should select * depending on DPM state they are in. And update BW MGR GFX Engine and * Memory clock member variables for Watermarks calculations for each diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c index 63bbdf8b8678..edd098c7eb92 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c @@ -4478,17 +4478,17 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->EffectiveLBLatencyHidingSourceLinesLuma), locals->SwathHeightYPerState[i][j][k]); - locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min( - locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] * - locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0], - locals->EffectiveLBLatencyHidingSourceLinesChroma), - locals->SwathHeightCPerState[i][j][k]); if (locals->BytePerPixelInDETC[k] == 0) { locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]); } else { + locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min( + locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] * + locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0], + locals->EffectiveLBLatencyHidingSourceLinesChroma), + locals->SwathHeightCPerState[i][j][k]); locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min( locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k]) / locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] * diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index 8a7485e21d53..1d84ae50311d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -806,10 +806,12 @@ static bool CalculatePrefetchSchedule( if (myPipe->SourceScan == dm_horz) { *swath_width_luma_ub = dml_ceil(SwathWidthY - 1, myPipe->BlockWidth256BytesY) + myPipe->BlockWidth256BytesY; - *swath_width_chroma_ub = dml_ceil(SwathWidthY / 2 - 1, myPipe->BlockWidth256BytesC) + myPipe->BlockWidth256BytesC; + if (myPipe->BlockWidth256BytesC > 0) + *swath_width_chroma_ub = dml_ceil(SwathWidthY / 2 - 1, myPipe->BlockWidth256BytesC) + myPipe->BlockWidth256BytesC; } else { *swath_width_luma_ub = dml_ceil(SwathWidthY - 1, myPipe->BlockHeight256BytesY) + myPipe->BlockHeight256BytesY; - *swath_width_chroma_ub = dml_ceil(SwathWidthY / 2 - 1, myPipe->BlockHeight256BytesC) + myPipe->BlockHeight256BytesC; + if (myPipe->BlockWidth256BytesC > 0) + *swath_width_chroma_ub = dml_ceil(SwathWidthY / 2 - 1, myPipe->BlockHeight256BytesC) + myPipe->BlockHeight256BytesC; } prefetch_bw_oto = (PrefetchSourceLinesY * *swath_width_luma_ub * dml_ceil(BytePerPixelDETY, 1) + PrefetchSourceLinesC * *swath_width_chroma_ub * dml_ceil(BytePerPixelDETC, 2)) / Tsw_oto; @@ -2634,7 +2636,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman &mode_lib->vba.SrcActiveDrainRate, &mode_lib->vba.TInitXFill, &mode_lib->vba.TslvChk); - locals->XFCRemoteSurfaceFlipLatency[k] = + locals->XFCRemoteSurfaceFlipLatency[k] = dml_floor( mode_lib->vba.XFCRemoteSurfaceFlipDelay / (mode_lib->vba.HTotal[k] 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 b7fa003ffe06..479e2c1a1301 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 @@ -6322,10 +6322,6 @@ static void CalculateSwathWidth( for (k = 0; k < NumberOfActivePlanes; ++k) { enum odm_combine_mode MainPlaneODMCombine = 0; - surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]); - surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]); - surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); - surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); if (SourceScan[k] != dm_vert) { SwathWidthSingleDPPY[k] = ViewportWidth[k]; @@ -6365,8 +6361,6 @@ static void CalculateSwathWidth( surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]); surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]); - surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); - surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); if (SourceScan[k] != dm_vert) { MaximumSwathHeightY[k] = Read256BytesBlockHeightY[k]; @@ -6374,6 +6368,7 @@ static void CalculateSwathWidth( swath_width_luma_ub[k] = dml_min(surface_width_ub_l, (long) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockWidthY[k]) + Read256BytesBlockWidthY[k]); if (BytePerPixC[k] > 0) { + surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); swath_width_chroma_ub[k] = dml_min(surface_width_ub_c, (long) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockWidthC[k]) + Read256BytesBlockWidthC[k]); } else { @@ -6385,6 +6380,7 @@ static void CalculateSwathWidth( swath_width_luma_ub[k] = dml_min(surface_height_ub_l, (long) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockHeightY[k]) + Read256BytesBlockHeightY[k]); if (BytePerPixC[k] > 0) { + surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); swath_width_chroma_ub[k] = dml_min(surface_height_ub_c, (long) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockHeightC[k]) + Read256BytesBlockHeightC[k]); } else { @@ -6497,7 +6493,7 @@ static double CalculateUrgentLatency( return ret; } -static void UseMinimumDCFCLK( +static noinline_for_stack void UseMinimumDCFCLK( struct display_mode_lib *mode_lib, struct vba_vars_st *v, int MaxPrefetchMode, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c index 241d28d0b7fb..422f17aefd4a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c @@ -379,6 +379,11 @@ void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_01_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + if ((int)(dcn3_01_soc.dram_clock_change_latency_us * 1000) + != dc->debug.dram_clock_change_latency_ns + && dc->debug.dram_clock_change_latency_ns) { + dcn3_01_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000.0; + } dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); } 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 0e62eb823e34..7dd0845d1bd9 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 +291,8 @@ 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, + .dummy_pstate_latency_us = 10.0 }; struct _vcs_dpi_ip_params_st dcn3_16_ip = { @@ -458,13 +460,30 @@ void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) } } +void dcn315_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) +{ + dc_assert_fp_enabled(); + + if (dc->clk_mgr->bw_params->wm_table.entries[WM_A].valid) { + /* For 315 pstate change is only supported if possible in vactive */ + if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[context->bw_ctx.dml.vba.VoltageLevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_vactive) + context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; + else + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.entries[WM_A].pstate_latency_us; + context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = + dc->clk_mgr->bw_params->wm_table.entries[WM_A].sr_enter_plus_exit_time_us; + context->bw_ctx.dml.soc.sr_exit_time_us = + dc->clk_mgr->bw_params->wm_table.entries[WM_A].sr_exit_time_us; + } +} + void dcn31_calculate_wm_and_dlg_fp( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, int vlevel) { - int i, pipe_idx; + int i, pipe_idx, active_dpp_count = 0; double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; dc_assert_fp_enabled(); @@ -485,72 +504,6 @@ void dcn31_calculate_wm_and_dlg_fp( pipes[0].clks_cfg.dcfclk_mhz = dcfclk; pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; -#if 0 // TODO - /* Set B: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].valid) { - if (vlevel == 0) { - pipes[0].clks_cfg.voltage = 1; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dcfclk_mhz; - } - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.b.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = dcfclk; - - /* Set C: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - /* Set D: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.d.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; -#endif - /* Set A: * All clocks min required * @@ -567,16 +520,17 @@ void dcn31_calculate_wm_and_dlg_fp( context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - /* TODO: remove: */ context->bw_ctx.bw.dcn.watermarks.b = context->bw_ctx.bw.dcn.watermarks.a; context->bw_ctx.bw.dcn.watermarks.c = context->bw_ctx.bw.dcn.watermarks.a; context->bw_ctx.bw.dcn.watermarks.d = context->bw_ctx.bw.dcn.watermarks.a; - /* end remove*/ for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { if (!context->res_ctx.pipe_ctx[i].stream) continue; + if (context->res_ctx.pipe_ctx[i].plane_state) + active_dpp_count++; + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); @@ -593,6 +547,9 @@ void dcn31_calculate_wm_and_dlg_fp( } dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + /* For 31x apu pstate change is only supported if possible in vactive or if there are no active dpps */ + context->bw_ctx.bw.dcn.clk.p_state_change_support = + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive || !active_dpp_count; } void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) @@ -667,6 +624,12 @@ void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params dcn3_1_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + if ((int)(dcn3_1_soc.dram_clock_change_latency_us * 1000) + != dc->debug.dram_clock_change_latency_ns + && dc->debug.dram_clock_change_latency_ns) { + dcn3_1_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000; + } + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) dml_init_instance(&dc->dml, &dcn3_1_soc, &dcn3_1_ip, DML_PROJECT_DCN31); else @@ -682,7 +645,11 @@ 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); @@ -721,8 +688,14 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param */ dcn3_15_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2; + if ((int)(dcn3_15_soc.dram_clock_change_latency_us * 1000) + != dc->debug.dram_clock_change_latency_ns + && dc->debug.dram_clock_change_latency_ns) { + dcn3_15_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000; + } + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) - dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN31); + dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN315); else dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN31_FPGA); } @@ -813,6 +786,11 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_16_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2; } + if ((int)(dcn3_16_soc.dram_clock_change_latency_us * 1000) + != dc->debug.dram_clock_change_latency_ns + && dc->debug.dram_clock_change_latency_ns) { + dcn3_16_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000; + } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) dml_init_instance(&dc->dml, &dcn3_16_soc, &dcn3_16_ip, DML_PROJECT_DCN31); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h index 4372f17b55d4..fd58b2561ec9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h @@ -35,6 +35,7 @@ void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes, int pipe_cnt); void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); +void dcn315_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); void dcn31_calculate_wm_and_dlg_fp( struct dc *dc, struct dc_state *context, 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..b612edb14417 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 @@ -43,6 +43,8 @@ #define BPP_BLENDED_PIPE 0xffffffff #define DCN31_MAX_DSC_IMAGE_WIDTH 5184 #define DCN31_MAX_FMT_420_BUFFER_WIDTH 4096 +#define DCN3_15_MIN_COMPBUF_SIZE_KB 128 +#define DCN3_15_MAX_DET_SIZE 384 // For DML-C changes that hasn't been propagated to VBA yet //#define __DML_VBA_ALLOW_DELTA__ @@ -251,33 +253,13 @@ 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 +293,28 @@ 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, @@ -1107,10 +1053,10 @@ static bool CalculatePrefetchSchedule( bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC; /*rev 99*/ prefetch_bw_pr = dml_min(1, bytes_pp * myPipe->PixelClock / (double) myPipe->DPPPerPlane); - max_Tsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime; + max_Tsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime; prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC; prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerPlane, prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime)); - prefetch_bw_oto = dml_max(prefetch_bw_pr, prefetch_sw_bytes / max_Tsw); + prefetch_bw_oto = dml_max(prefetch_bw_pr, prefetch_sw_bytes / max_Tsw); min_Lsw = dml_max(1, dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre); Lsw_oto = dml_ceil(4 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1) / 4; @@ -2904,33 +2850,13 @@ 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 +2943,28 @@ 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 +3488,43 @@ 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 +3533,54 @@ 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 } @@ -3905,6 +3777,17 @@ static noinline void CalculatePrefetchSchedulePerPlane( &v->VReadyOffsetPix[k]); } +static void PatchDETBufferSizeInKByte(unsigned int NumberOfActivePlanes, int NoOfDPPThisState[], unsigned int config_return_buffer_size_in_kbytes, unsigned int *DETBufferSizeInKByte) +{ + int i, total_pipes = 0; + for (i = 0; i < NumberOfActivePlanes; i++) + total_pipes += NoOfDPPThisState[i]; + *DETBufferSizeInKByte = ((config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB) / 64 / total_pipes) * 64; + if (*DETBufferSizeInKByte > DCN3_15_MAX_DET_SIZE) + *DETBufferSizeInKByte = DCN3_15_MAX_DET_SIZE; +} + + void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) { struct vba_vars_st *v = &mode_lib->vba; @@ -4663,6 +4546,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->ODMCombineEnableThisState[k] = v->ODMCombineEnablePerState[i][k]; } + if (v->NumberOfActivePlanes > 1 && mode_lib->project == DML_PROJECT_DCN315) + PatchDETBufferSizeInKByte(v->NumberOfActivePlanes, v->NoOfDPPThisState, v->ip.config_return_buffer_size_in_kbytes, &v->DETBufferSizeInKByte[0]); CalculateSwathAndDETConfiguration( false, v->NumberOfActivePlanes, @@ -5300,33 +5185,13 @@ 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 +5249,28 @@ 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 +5395,28 @@ 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 +5436,103 @@ 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 +5542,14 @@ 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 +5557,11 @@ 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 +5569,25 @@ 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); @@ -6933,8 +6726,6 @@ static void CalculateSwathWidth( { int surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]); int surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]); - int surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); - int surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d surface_width_ub_l=%0d\n", __func__, k, surface_width_ub_l); @@ -6945,6 +6736,8 @@ static void CalculateSwathWidth( MaximumSwathHeightC[k] = Read256BytesBlockHeightC[k]; swath_width_luma_ub[k] = dml_min(surface_width_ub_l, (int) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockWidthY[k]) + Read256BytesBlockWidthY[k]); if (BytePerPixC[k] > 0) { + int surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); + swath_width_chroma_ub[k] = dml_min( surface_width_ub_c, (int) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockWidthC[k]) + Read256BytesBlockWidthC[k]); @@ -6956,6 +6749,8 @@ static void CalculateSwathWidth( MaximumSwathHeightC[k] = Read256BytesBlockWidthC[k]; swath_width_luma_ub[k] = dml_min(surface_height_ub_l, (int) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockHeightY[k]) + Read256BytesBlockHeightY[k]); if (BytePerPixC[k] > 0) { + int surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); + swath_width_chroma_ub[k] = dml_min( surface_height_ub_c, (int) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockHeightC[k]) + Read256BytesBlockHeightC[k]); 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..cf420ad2b8dc 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; @@ -261,8 +264,13 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2; } + if ((int)(dcn3_14_soc.dram_clock_change_latency_us * 1000) + != dc->debug.dram_clock_change_latency_ns + && dc->debug.dram_clock_change_latency_ns) { + dcn3_14_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000; + } 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); } @@ -315,6 +323,8 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0; pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; + pipes[pipe_cnt].pipe.dest.vblank_nom = + dcn3_14_ip.VBlankNomDefaultUS / (timing->h_total / (timing->pix_clk_100hz / 10000.0)); pipes[pipe_cnt].pipe.src.dcc_rate = 3; pipes[pipe_cnt].dout.dsc_input_bpc = 0; 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..0d12fd079cd6 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, @@ -1362,7 +1306,7 @@ static bool CalculatePrefetchSchedule( // - ((NumberOfCursors > 0 || GPUVMEnable || DCCEnable) ? - ((GPUVMEnable || myPipe->DCCEnable) ? (*DestinationLinesToRequestVMInVBlank + 2 * *DestinationLinesToRequestRowInVBlank) : 0.0); // TODO: Did someone else add this?? #else - LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch - *DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank; + LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch - *DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank; #endif #ifdef __DML_VBA_DEBUG__ @@ -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); @@ -7049,8 +6825,6 @@ static void CalculateSwathWidth( { int surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]); int surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]); - int surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); - int surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d surface_width_ub_l=%0d\n", __func__, k, surface_width_ub_l); @@ -7061,6 +6835,8 @@ static void CalculateSwathWidth( MaximumSwathHeightC[k] = Read256BytesBlockHeightC[k]; swath_width_luma_ub[k] = dml_min(surface_width_ub_l, (int) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockWidthY[k]) + Read256BytesBlockWidthY[k]); if (BytePerPixC[k] > 0) { + int surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); + swath_width_chroma_ub[k] = dml_min( surface_width_ub_c, (int) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockWidthC[k]) + Read256BytesBlockWidthC[k]); @@ -7072,6 +6848,8 @@ static void CalculateSwathWidth( MaximumSwathHeightC[k] = Read256BytesBlockWidthC[k]; swath_width_luma_ub[k] = dml_min(surface_height_ub_l, (int) dml_ceil(SwathWidthY[k] - 1, Read256BytesBlockHeightY[k]) + Read256BytesBlockHeightY[k]); if (BytePerPixC[k] > 0) { + int surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); + swath_width_chroma_ub[k] = dml_min( surface_height_ub_c, (int) dml_ceil(SwathWidthC[k] - 1, Read256BytesBlockHeightC[k]) + Read256BytesBlockHeightC[k]); @@ -7157,12 +6935,13 @@ 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; } @@ -7406,7 +7185,7 @@ static unsigned int CalculateMaxVStartup( double line_time_us = HTotal / PixelClock; unsigned int vblank_actual = VTotal - VActive; unsigned int vblank_nom_default_in_line = dml_floor(VBlankNomDefaultUS / line_time_us, 1.0); - unsigned int vblank_nom_input = dml_min(VBlankNom, vblank_nom_default_in_line); + unsigned int vblank_nom_input = VBlankNom; //dml_min(VBlankNom, vblank_nom_default_in_line); unsigned int vblank_avail = vblank_nom_input == 0 ? vblank_nom_default_in_line : vblank_nom_input; vblank_size = (unsigned int) dml_min(vblank_actual, vblank_avail); 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 7f6c977c4981..819de0f11012 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, @@ -243,18 +243,61 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) clk_mgr->base.bw_params->wm_table.nv_entries[WM_D].pmfw_breakdown.max_uclk = 0xFFFF; } +/* + * 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. - * - * This function must be called AFTER the phantom pipes are added to context - * and run through DML (so that the DLG params for the phantom pipes can be - * populated), and BEFORE we program the timing for the phantom pipes. - * * @dc: [in] current dc state * @context: [in] new dc state * @pipes: [in] DML pipe params array * @pipe_cnt: [in] DML pipe count + * + * This function must be called AFTER the phantom pipes are added to context + * and run through DML (so that the DLG params for the phantom pipes can be + * populated), and BEFORE we program the timing for the phantom pipes. */ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, struct dc_state *context, @@ -286,41 +329,88 @@ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, } } -bool dcn32_predict_pipe_split(struct dc_state *context, display_pipe_params_st pipe, int index) +/** + * dcn32_predict_pipe_split - Predict if pipe split will occur for a given DML pipe + * @context: [in] New DC state to be programmed + * @pipe_e2e: [in] DML pipe end to end context + * + * This function takes in a DML pipe (pipe_e2e) and predicts if pipe split is required (both + * ODM and MPC). For pipe split, ODM combine is determined by the ODM mode, and MPC combine is + * determined by DPPClk requirements + * + * This function follows the same policy as DML: + * - Check for ODM combine requirements / policy first + * - MPC combine is only chosen if there is no ODM combine requirements / policy in place, and + * MPC is required + * + * Return: Number of splits expected (1 for 2:1 split, 3 for 4:1 split, 0 for no splits). + */ +uint8_t dcn32_predict_pipe_split(struct dc_state *context, + display_e2e_pipe_params_st *pipe_e2e) { double pscl_throughput; double pscl_throughput_chroma; double dpp_clk_single_dpp, clock; double clk_frequency = 0.0; double vco_speed = context->bw_ctx.dml.soc.dispclk_dppclk_vco_speed_mhz; + bool total_available_pipes_support = false; + uint32_t number_of_dpp = 0; + enum odm_combine_mode odm_mode = dm_odm_combine_mode_disabled; + double req_dispclk_per_surface = 0; + uint8_t num_splits = 0; dc_assert_fp_enabled(); - dml32_CalculateSinglePipeDPPCLKAndSCLThroughput(pipe.scale_ratio_depth.hscl_ratio, - pipe.scale_ratio_depth.hscl_ratio_c, - pipe.scale_ratio_depth.vscl_ratio, - pipe.scale_ratio_depth.vscl_ratio_c, - context->bw_ctx.dml.ip.max_dchub_pscl_bw_pix_per_clk, - context->bw_ctx.dml.ip.max_pscl_lb_bw_pix_per_clk, - pipe.dest.pixel_rate_mhz, - pipe.src.source_format, - pipe.scale_taps.htaps, - pipe.scale_taps.htaps_c, - pipe.scale_taps.vtaps, - pipe.scale_taps.vtaps_c, - /* Output */ - &pscl_throughput, &pscl_throughput_chroma, - &dpp_clk_single_dpp); + dml32_CalculateODMMode(context->bw_ctx.dml.ip.maximum_pixels_per_line_per_dsc_unit, + pipe_e2e->pipe.dest.hactive, + pipe_e2e->dout.output_format, + pipe_e2e->dout.output_type, + pipe_e2e->pipe.dest.odm_combine_policy, + context->bw_ctx.dml.soc.clock_limits[context->bw_ctx.dml.soc.num_states - 1].dispclk_mhz, + context->bw_ctx.dml.soc.clock_limits[context->bw_ctx.dml.soc.num_states - 1].dispclk_mhz, + pipe_e2e->dout.dsc_enable != 0, + 0, /* TotalNumberOfActiveDPP can be 0 since we're predicting pipe split requirement */ + context->bw_ctx.dml.ip.max_num_dpp, + pipe_e2e->pipe.dest.pixel_rate_mhz, + context->bw_ctx.dml.soc.dcn_downspread_percent, + context->bw_ctx.dml.ip.dispclk_ramp_margin_percent, + context->bw_ctx.dml.soc.dispclk_dppclk_vco_speed_mhz, + pipe_e2e->dout.dsc_slices, + /* Output */ + &total_available_pipes_support, + &number_of_dpp, + &odm_mode, + &req_dispclk_per_surface); + + dml32_CalculateSinglePipeDPPCLKAndSCLThroughput(pipe_e2e->pipe.scale_ratio_depth.hscl_ratio, + pipe_e2e->pipe.scale_ratio_depth.hscl_ratio_c, + pipe_e2e->pipe.scale_ratio_depth.vscl_ratio, + pipe_e2e->pipe.scale_ratio_depth.vscl_ratio_c, + context->bw_ctx.dml.ip.max_dchub_pscl_bw_pix_per_clk, + context->bw_ctx.dml.ip.max_pscl_lb_bw_pix_per_clk, + pipe_e2e->pipe.dest.pixel_rate_mhz, + pipe_e2e->pipe.src.source_format, + pipe_e2e->pipe.scale_taps.htaps, + pipe_e2e->pipe.scale_taps.htaps_c, + pipe_e2e->pipe.scale_taps.vtaps, + pipe_e2e->pipe.scale_taps.vtaps_c, + /* Output */ + &pscl_throughput, &pscl_throughput_chroma, + &dpp_clk_single_dpp); clock = dpp_clk_single_dpp * (1 + context->bw_ctx.dml.soc.dcn_downspread_percent / 100); if (clock > 0) - clk_frequency = vco_speed * 4.0 / ((int)(vco_speed * 4.0)); + clk_frequency = vco_speed * 4.0 / ((int)(vco_speed * 4.0) / clock); - if (clk_frequency > context->bw_ctx.dml.soc.clock_limits[index].dppclk_mhz) - return true; - else - return false; + if (odm_mode == dm_odm_combine_mode_2to1) + num_splits = 1; + else if (odm_mode == dm_odm_combine_mode_4to1) + num_splits = 3; + else if (clk_frequency > context->bw_ctx.dml.soc.clock_limits[context->bw_ctx.dml.soc.num_states - 1].dppclk_mhz) + num_splits = 1; + + return num_splits; } static float calculate_net_bw_in_kbytes_sec(struct _vcs_dpi_voltage_scaling_st *entry) @@ -409,7 +499,14 @@ void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, } /** - * dcn32_set_phantom_stream_timing: Set timing params for the phantom stream + * dcn32_set_phantom_stream_timing - Set timing params for the phantom stream + * @dc: current dc state + * @context: new dc state + * @ref_pipe: Main pipe for the phantom stream + * @phantom_stream: target phantom stream state + * @pipes: DML pipe params + * @pipe_cnt: number of DML pipes + * @dc_pipe_idx: DC pipe index for the main pipe (i.e. ref_pipe) * * Set timing params of the phantom stream based on calculated output from DML. * This function first gets the DML pipe index using the DC pipe index, then @@ -422,13 +519,6 @@ void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, * that separately. * * - Set phantom backporch = vstartup of main pipe - * - * @dc: current dc state - * @context: new dc state - * @ref_pipe: Main pipe for the phantom stream - * @pipes: DML pipe params - * @pipe_cnt: number of DML pipes - * @dc_pipe_idx: DC pipe index for the main pipe (i.e. ref_pipe) */ void dcn32_set_phantom_stream_timing(struct dc *dc, struct dc_state *context, @@ -497,16 +587,14 @@ void dcn32_set_phantom_stream_timing(struct dc *dc, } /** - * dcn32_get_num_free_pipes: Calculate number of free pipes + * dcn32_get_num_free_pipes - Calculate number of free pipes + * @dc: current dc state + * @context: new dc state * * This function assumes that a "used" pipe is a pipe that has * both a stream and a plane assigned to it. * - * @dc: current dc state - * @context: new dc state - * - * Return: - * Number of free pipes available in the context + * Return: Number of free pipes available in the context */ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *context) { @@ -530,7 +618,10 @@ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *con } /** - * dcn32_assign_subvp_pipe: Function to decide which pipe will use Sub-VP. + * dcn32_assign_subvp_pipe - Function to decide which pipe will use Sub-VP. + * @dc: current dc state + * @context: new dc state + * @index: [out] dc pipe index for the pipe chosen to have phantom pipes assigned * * We enter this function if we are Sub-VP capable (i.e. enough pipes available) * and regular P-State switching (i.e. VACTIVE/VBLANK) is not supported, or if @@ -544,12 +635,7 @@ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *con * for determining which should be the SubVP pipe (need a way to determine if a pipe / plane doesn't * support MCLK switching naturally [i.e. ACTIVE or VBLANK]). * - * @param dc: current dc state - * @param context: new dc state - * @param index: [out] dc pipe index for the pipe chosen to have phantom pipes assigned - * - * Return: - * True if a valid pipe assignment was found for Sub-VP. Otherwise false. + * Return: True if a valid pipe assignment was found for Sub-VP. Otherwise false. */ static bool dcn32_assign_subvp_pipe(struct dc *dc, struct dc_state *context, @@ -579,9 +665,10 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, * - Not able to switch in vactive naturally (switching in active means the * DET provides enough buffer to hide the P-State switch latency -- trying * to combine this with SubVP can cause issues with the scheduling). + * - Not TMZ surface */ if (pipe->plane_state && !pipe->top_pipe && - pipe->stream->mall_stream_config.type == SUBVP_NONE && refresh_rate < 120 && + pipe->stream->mall_stream_config.type == SUBVP_NONE && refresh_rate < 120 && !pipe->plane_state->address.tmz_surface && vba->ActiveDRAMClockChangeLatencyMarginPerState[vba->VoltageLevel][vba->maxMpcComb][vba->pipe_plane[pipe_idx]] <= 0) { while (pipe) { num_pipes++; @@ -615,7 +702,9 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, } /** - * dcn32_enough_pipes_for_subvp: Function to check if there are "enough" pipes for SubVP. + * dcn32_enough_pipes_for_subvp - Function to check if there are "enough" pipes for SubVP. + * @dc: current dc state + * @context: new dc state * * This function returns true if there are enough free pipes * to create the required phantom pipes for any given stream @@ -627,9 +716,6 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, * pipe which can be used as the phantom pipe for the non pipe * split pipe. * - * @dc: current dc state - * @context: new dc state - * * Return: * True if there are enough free pipes to assign phantom pipes to at least one * stream that does not already have phantom pipes assigned. Otherwise false. @@ -668,7 +754,9 @@ static bool dcn32_enough_pipes_for_subvp(struct dc *dc, struct dc_state *context } /** - * subvp_subvp_schedulable: Determine if SubVP + SubVP config is schedulable + * subvp_subvp_schedulable - Determine if SubVP + SubVP config is schedulable + * @dc: current dc state + * @context: new dc state * * High level algorithm: * 1. Find longest microschedule length (in us) between the two SubVP pipes @@ -676,11 +764,7 @@ static bool dcn32_enough_pipes_for_subvp(struct dc *dc, struct dc_state *context * pipes still allows for the maximum microschedule to fit in the active * region for both pipes. * - * @dc: current dc state - * @context: new dc state - * - * Return: - * bool - True if the SubVP + SubVP config is schedulable, false otherwise + * Return: True if the SubVP + SubVP config is schedulable, false otherwise */ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) { @@ -740,7 +824,10 @@ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) } /** - * subvp_drr_schedulable: Determine if SubVP + DRR config is schedulable + * subvp_drr_schedulable - Determine if SubVP + DRR config is schedulable + * @dc: current dc state + * @context: new dc state + * @drr_pipe: DRR pipe_ctx for the SubVP + DRR config * * High level algorithm: * 1. Get timing for SubVP pipe, phantom pipe, and DRR pipe @@ -749,12 +836,7 @@ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) * 3.If (SubVP Active - Prefetch > Stretched DRR frame + max(MALL region, Stretched DRR frame)) * then report the configuration as supported * - * @dc: current dc state - * @context: new dc state - * @drr_pipe: DRR pipe_ctx for the SubVP + DRR config - * - * Return: - * bool - True if the SubVP + DRR config is schedulable, false otherwise + * Return: True if the SubVP + DRR config is schedulable, false otherwise */ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struct pipe_ctx *drr_pipe) { @@ -818,7 +900,9 @@ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struc /** - * subvp_vblank_schedulable: Determine if SubVP + VBLANK config is schedulable + * subvp_vblank_schedulable - Determine if SubVP + VBLANK config is schedulable + * @dc: current dc state + * @context: new dc state * * High level algorithm: * 1. Get timing for SubVP pipe, phantom pipe, and VBLANK pipe @@ -826,11 +910,7 @@ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struc * then report the configuration as supported * 3. If the VBLANK display is DRR, then take the DRR static schedulability path * - * @dc: current dc state - * @context: new dc state - * - * Return: - * bool - True if the SubVP + VBLANK/DRR config is schedulable, false otherwise + * Return: True if the SubVP + VBLANK/DRR config is schedulable, false otherwise */ static bool subvp_vblank_schedulable(struct dc *dc, struct dc_state *context) { @@ -907,20 +987,18 @@ static bool subvp_vblank_schedulable(struct dc *dc, struct dc_state *context) } /** - * subvp_validate_static_schedulability: Check which SubVP case is calculated and handle - * static analysis based on the case. + * subvp_validate_static_schedulability - Check which SubVP case is calculated + * and handle static analysis based on the case. + * @dc: current dc state + * @context: new dc state + * @vlevel: Voltage level calculated by DML * * Three cases: * 1. SubVP + SubVP * 2. SubVP + VBLANK (DRR checked internally) * 3. SubVP + VACTIVE (currently unsupported) * - * @dc: current dc state - * @context: new dc state - * @vlevel: Voltage level calculated by DML - * - * Return: - * bool - True if statically schedulable, false otherwise + * Return: True if statically schedulable, false otherwise */ static bool subvp_validate_static_schedulability(struct dc *dc, struct dc_state *context, @@ -1019,12 +1097,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, * 5. (Config doesn't support MCLK in VACTIVE/VBLANK || dc->debug.force_subvp_mclk_switch) */ if (!dc->debug.force_disable_subvp && dcn32_all_pipes_have_stream_and_plane(dc, context) && - !dcn32_mpo_in_use(context) && (*vlevel == context->bw_ctx.dml.soc.num_states || + !dcn32_mpo_in_use(context) && !dcn32_any_surfaces_rotated(dc, context) && + (*vlevel == context->bw_ctx.dml.soc.num_states || vba->DRAMClockChangeSupport[*vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported || dc->debug.force_subvp_mclk_switch)) { dcn32_merge_pipes_for_subvp(dc, context); - // to re-initialize viewport after the pipe merge + memset(merge, 0, MAX_PIPES * sizeof(bool)); + + /* to re-initialize viewport after the pipe merge */ for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; @@ -1109,17 +1190,23 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, vba->VoltageLevel = *vlevel; } } else { - // only call dcn20_validate_apply_pipe_split_flags if we found a supported config - memset(split, 0, MAX_PIPES * sizeof(int)); - memset(merge, 0, MAX_PIPES * sizeof(bool)); - *vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, *vlevel, split, merge); - vba->VoltageLevel = *vlevel; - // Most populate phantom DLG params before programming hardware / timing for phantom pipe DC_FP_START(); dcn32_helper_populate_phantom_dlg_params(dc, context, pipes, *pipe_cnt); DC_FP_END(); + /* Call validate_apply_pipe_split flags after calling DML getters for + * phantom dlg params, or some of the VBA params indicating pipe split + * can be overwritten by the getters. + * + * When setting up SubVP config, all pipes are merged before attempting to + * add phantom pipes. If pipe split (ODM / MPC) is required, both the main + * and phantom pipes will be split in the regular pipe splitting sequence. + */ + memset(split, 0, MAX_PIPES * sizeof(int)); + memset(merge, 0, MAX_PIPES * sizeof(bool)); + *vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, *vlevel, split, merge); + vba->VoltageLevel = *vlevel; // Note: We can't apply the phantom pipes to hardware at this time. We have to wait // until driver has acquired the DMCUB lock to do it safely. } @@ -1487,6 +1574,33 @@ bool dcn32_internal_validate_bw(struct dc *dc, if (pipe->next_odm_pipe) pipe->next_odm_pipe->prev_odm_pipe = pipe->prev_odm_pipe; + /*2:1ODM+MPC Split MPO to Single Pipe + MPC Split MPO*/ + if (pipe->bottom_pipe) { + if (pipe->bottom_pipe->prev_odm_pipe || pipe->bottom_pipe->next_odm_pipe) { + /*MPC split rules will handle this case*/ + pipe->bottom_pipe->top_pipe = NULL; + } else { + /* when merging an ODM pipes, the bottom MPC pipe must now point to + * the previous ODM pipe and its associated stream assets + */ + if (pipe->prev_odm_pipe->bottom_pipe) { + /* 3 plane MPO*/ + pipe->bottom_pipe->top_pipe = pipe->prev_odm_pipe->bottom_pipe; + pipe->prev_odm_pipe->bottom_pipe->bottom_pipe = pipe->bottom_pipe; + } else { + /* 2 plane MPO*/ + pipe->bottom_pipe->top_pipe = pipe->prev_odm_pipe; + pipe->prev_odm_pipe->bottom_pipe = pipe->bottom_pipe; + } + + memcpy(&pipe->bottom_pipe->stream_res, &pipe->bottom_pipe->top_pipe->stream_res, sizeof(struct stream_resource)); + } + } + + if (pipe->top_pipe) { + pipe->top_pipe->bottom_pipe = NULL; + } + pipe->bottom_pipe = NULL; pipe->next_odm_pipe = NULL; pipe->plane_state = NULL; @@ -1619,8 +1733,20 @@ bool dcn32_internal_validate_bw(struct dc *dc, goto validate_fail; } - if (repopulate_pipes) + if (repopulate_pipes) { pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); + + /* repopulate_pipes = 1 means the pipes were either split or merged. In this case + * we have to re-calculate the DET allocation and run through DML once more to + * ensure all the params are calculated correctly. We do not need to run the + * pipe split check again after this call (pipes are already split / merged). + * */ + if (!fast_validate) { + context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final = + dm_prefetch_support_uclk_fclk_and_stutter_if_possible; + vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt); + } + } *vlevel_out = vlevel; *pipe_cnt_out = pipe_cnt; @@ -1643,6 +1769,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, int i, pipe_idx, vlevel_temp = 0; double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz; double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation; bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; unsigned int dummy_latency_index = 0; @@ -1666,7 +1793,7 @@ 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 @@ -1678,7 +1805,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; - dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + dcfclk_from_fw_based_mclk_switching = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] != dm_dram_clock_change_unsupported; } @@ -1764,6 +1891,10 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, pipes[0].clks_cfg.dcfclk_mhz = dcfclk_from_validation; pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + pipes[0].clks_cfg.dcfclk_mhz = dcfclk_from_fw_based_mclk_switching; + } + if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; min_dram_speed_mts_margin = 160; @@ -1906,6 +2037,45 @@ 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) { @@ -2098,7 +2268,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, return 0; } -/** +/* * dcn32_update_bw_bounding_box * * This would override some dcn3_2 ip_or_soc initial parameters hardcoded from @@ -2140,6 +2310,7 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa if ((int)(dcn3_2_soc.urgent_latency_us * 1000) != dc->bb_overrides.urgent_latency_ns && dc->bb_overrides.urgent_latency_ns) { dcn3_2_soc.urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; + dcn3_2_soc.urgent_latency_pixel_data_only_us = dc->bb_overrides.urgent_latency_ns / 1000.0; } if ((int)(dcn3_2_soc.dram_clock_change_latency_us * 1000) 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..3a3dc2ce4c73 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 @@ -29,11 +29,6 @@ #include "clk_mgr_internal.h" -#define DCN3_2_DEFAULT_DET_SIZE 256 -#define DCN3_2_MAX_DET_SIZE 1152 -#define DCN3_2_MIN_DET_SIZE 128 -#define DCN3_2_MIN_COMPBUF_SIZE_KB 128 - void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr); void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, @@ -41,9 +36,8 @@ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, display_e2e_pipe_params_st *pipes, int pipe_cnt); -bool dcn32_predict_pipe_split(struct dc_state *context, - display_pipe_params_st pipe, - int index); +uint8_t dcn32_predict_pipe_split(struct dc_state *context, + display_e2e_pipe_params_st *pipe_e2e); void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries, @@ -71,4 +65,12 @@ 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 d8014bfbc3fe..5b91660a6496 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 @@ -733,6 +733,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman mode_lib->vba.FCLKChangeLatency, v->UrgentLatency, mode_lib->vba.SREnterPlusExitTime); + memset(&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, 0, sizeof(DmlPipe)); + v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.Dppclk = mode_lib->vba.DPPCLK[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.Dispclk = mode_lib->vba.DISPCLK; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.PixelClock = mode_lib->vba.PixelClock[k]; @@ -755,30 +757,18 @@ 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 +782,8 @@ 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 +1153,28 @@ 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 +1766,10 @@ 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 +1994,7 @@ 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], @@ -2056,6 +2017,7 @@ 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], @@ -2292,9 +2254,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) { if (!(mode_lib->vba.DSCInputBitPerComponent[k] == 12.0 || mode_lib->vba.DSCInputBitPerComponent[k] == 10.0 - || mode_lib->vba.DSCInputBitPerComponent[k] == 8.0 - || mode_lib->vba.DSCInputBitPerComponent[k] > - mode_lib->vba.MaximumDSCBitsPerComponent)) { + || mode_lib->vba.DSCInputBitPerComponent[k] == 8.0) + || mode_lib->vba.DSCInputBitPerComponent[k] > mode_lib->vba.MaximumDSCBitsPerComponent) { mode_lib->vba.NonsupportedDSCInputBPC = true; } } @@ -2370,16 +2331,15 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l if (mode_lib->vba.OutputMultistreamId[k] == k && mode_lib->vba.ForcedOutputLinkBPP[k] == 0) mode_lib->vba.BPPForMultistreamNotIndicated = true; for (j = 0; j < mode_lib->vba.NumberOfActiveSurfaces; ++j) { - if (mode_lib->vba.OutputMultistreamId[k] == j && mode_lib->vba.OutputMultistreamEn[k] + if (mode_lib->vba.OutputMultistreamId[k] == j && mode_lib->vba.ForcedOutputLinkBPP[k] == 0) mode_lib->vba.BPPForMultistreamNotIndicated = true; } } if ((mode_lib->vba.Output[k] == dm_edp || mode_lib->vba.Output[k] == dm_hdmi)) { - if (mode_lib->vba.OutputMultistreamId[k] == k && mode_lib->vba.OutputMultistreamEn[k]) + if (mode_lib->vba.OutputMultistreamEn[k] == true && mode_lib->vba.OutputMultistreamId[k] == k) mode_lib->vba.MultistreamWithHDMIOreDP = true; - for (j = 0; j < mode_lib->vba.NumberOfActiveSurfaces; ++j) { if (mode_lib->vba.OutputMultistreamEn[k] == true && mode_lib->vba.OutputMultistreamId[k] == j) mode_lib->vba.MultistreamWithHDMIOreDP = true; @@ -2518,8 +2478,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k]); } - m = 0; - for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) { for (m = 0; m <= mode_lib->vba.NumberOfActiveSurfaces - 1; m++) { for (j = 0; j <= mode_lib->vba.NumberOfActiveSurfaces - 1; j++) { @@ -2661,10 +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, @@ -2711,10 +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]; @@ -2896,8 +2854,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } - m = 0; - //Calculate Return BW for (i = 0; i < (int) v->soc.num_states; ++i) { for (j = 0; j <= 1; ++j) { @@ -3260,63 +3216,47 @@ 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 @@ -3559,62 +3499,32 @@ 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.ActiveDRAMClockChangeLatencyMarginPerState[i][j]); @@ -3704,11 +3614,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.ModeIsSupported = mode_lib->vba.ModeSupport[i][0] == true || mode_lib->vba.ModeSupport[i][1] == true; - if (mode_lib->vba.ModeSupport[i][0] == true) { + if (mode_lib->vba.ModeSupport[i][0] == true) MaximumMPCCombine = 0; - } else { + else MaximumMPCCombine = 1; - } } } 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 dc501ee7d01a..ad66e241f9ae 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, @@ -719,8 +721,8 @@ void dml32_CalculateSwathWidth( unsigned int surface_width_ub_l; unsigned int surface_height_ub_l; - unsigned int surface_width_ub_c; - unsigned int surface_height_ub_c; + unsigned int surface_width_ub_c = 0; + unsigned int surface_height_ub_c = 0; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: ForceSingleDPP = %d\n", __func__, ForceSingleDPP); @@ -784,21 +786,6 @@ void dml32_CalculateSwathWidth( surface_width_ub_l = dml_ceil(SurfaceWidthY[k], Read256BytesBlockWidthY[k]); surface_height_ub_l = dml_ceil(SurfaceHeightY[k], Read256BytesBlockHeightY[k]); - surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); - surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); - -#ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: k=%d surface_width_ub_l=%0d\n", __func__, k, surface_width_ub_l); - dml_print("DML::%s: k=%d surface_height_ub_l=%0d\n", __func__, k, surface_height_ub_l); - dml_print("DML::%s: k=%d surface_width_ub_c=%0d\n", __func__, k, surface_width_ub_c); - dml_print("DML::%s: k=%d surface_height_ub_c=%0d\n", __func__, k, surface_height_ub_c); - dml_print("DML::%s: k=%d Read256BytesBlockWidthY=%0d\n", __func__, k, Read256BytesBlockWidthY[k]); - dml_print("DML::%s: k=%d Read256BytesBlockHeightY=%0d\n", __func__, k, Read256BytesBlockHeightY[k]); - dml_print("DML::%s: k=%d Read256BytesBlockWidthC=%0d\n", __func__, k, Read256BytesBlockWidthC[k]); - dml_print("DML::%s: k=%d Read256BytesBlockHeightC=%0d\n", __func__, k, Read256BytesBlockHeightC[k]); - dml_print("DML::%s: k=%d ViewportStationary=%0d\n", __func__, k, ViewportStationary[k]); - dml_print("DML::%s: k=%d DPPPerSurface=%0d\n", __func__, k, DPPPerSurface[k]); -#endif if (!IsVertical(SourceRotation[k])) { MaximumSwathHeightY[k] = Read256BytesBlockHeightY[k]; @@ -818,6 +805,7 @@ void dml32_CalculateSwathWidth( Read256BytesBlockWidthY[k]); } if (BytePerPixC[k] > 0) { + surface_width_ub_c = dml_ceil(SurfaceWidthC[k], Read256BytesBlockWidthC[k]); if (ViewportStationary[k] && DPPPerSurface[k] == 1) { swath_width_chroma_ub[k] = dml_min(surface_width_ub_c, dml_floor(ViewportXStartC[k] + SwathWidthC[k] + @@ -848,6 +836,7 @@ void dml32_CalculateSwathWidth( Read256BytesBlockHeightY[k]) + Read256BytesBlockHeightY[k]); } if (BytePerPixC[k] > 0) { + surface_height_ub_c = dml_ceil(SurfaceHeightC[k], Read256BytesBlockHeightC[k]); if (ViewportStationary[k] && DPPPerSurface[k] == 1) { swath_width_chroma_ub[k] = dml_min(surface_height_ub_c, dml_floor(ViewportYStartC[k] + SwathWidthC[k] + @@ -866,6 +855,16 @@ void dml32_CalculateSwathWidth( } #ifdef __DML_VBA_DEBUG__ + dml_print("DML::%s: k=%d surface_width_ub_l=%0d\n", __func__, k, surface_width_ub_l); + dml_print("DML::%s: k=%d surface_height_ub_l=%0d\n", __func__, k, surface_height_ub_l); + dml_print("DML::%s: k=%d surface_width_ub_c=%0d\n", __func__, k, surface_width_ub_c); + dml_print("DML::%s: k=%d surface_height_ub_c=%0d\n", __func__, k, surface_height_ub_c); + dml_print("DML::%s: k=%d Read256BytesBlockWidthY=%0d\n", __func__, k, Read256BytesBlockWidthY[k]); + dml_print("DML::%s: k=%d Read256BytesBlockHeightY=%0d\n", __func__, k, Read256BytesBlockHeightY[k]); + dml_print("DML::%s: k=%d Read256BytesBlockWidthC=%0d\n", __func__, k, Read256BytesBlockWidthC[k]); + dml_print("DML::%s: k=%d Read256BytesBlockHeightC=%0d\n", __func__, k, Read256BytesBlockHeightC[k]); + dml_print("DML::%s: k=%d ViewportStationary=%0d\n", __func__, k, ViewportStationary[k]); + dml_print("DML::%s: k=%d DPPPerSurface=%0d\n", __func__, k, DPPPerSurface[k]); dml_print("DML::%s: k=%d swath_width_luma_ub=%0d\n", __func__, k, swath_width_luma_ub[k]); dml_print("DML::%s: k=%d swath_width_chroma_ub=%0d\n", __func__, k, swath_width_chroma_ub[k]); dml_print("DML::%s: k=%d MaximumSwathHeightY=%0d\n", __func__, k, MaximumSwathHeightY[k]); @@ -1182,6 +1181,7 @@ 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, @@ -1256,6 +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( @@ -1873,7 +1896,7 @@ void dml32_CalculateSurfaceSizeInMall( if (UseMALLForStaticScreen[k] == dm_use_mall_static_screen_enable) TotalSurfaceSizeInMALL = TotalSurfaceSizeInMALL + SurfaceSizeInMALL[k]; } - *ExceededMALLSize = (TotalSurfaceSizeInMALL <= MALLAllocatedForDCN * 1024 * 1024 ? false : true); + *ExceededMALLSize = (TotalSurfaceSizeInMALL > MALLAllocatedForDCN * 1024 * 1024); } // CalculateSurfaceSizeInMall void dml32_CalculateVMRowAndSwath( @@ -3366,28 +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, @@ -3428,6 +3437,7 @@ bool dml32_CalculatePrefetchSchedule( double *VUpdateWidthPix, double *VReadyOffsetPix) { + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles, DISPCLKCycles; double DSTTotalPixelsAfterScaler; @@ -3464,27 +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, @@ -3499,19 +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__ @@ -3531,17 +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; @@ -3567,7 +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; @@ -3584,13 +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; @@ -3625,7 +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, @@ -3633,7 +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, @@ -3836,7 +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); @@ -3844,7 +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); @@ -4209,58 +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[], @@ -4302,136 +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); @@ -4439,24 +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); @@ -4464,22 +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; @@ -4487,8 +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; @@ -4500,9 +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)) { @@ -4522,17 +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; @@ -4546,10 +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; } @@ -4576,16 +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]); @@ -4596,21 +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 } @@ -4663,10 +4643,6 @@ void dml32_CalculateMinAndMaxPrefetchMode( } else if (AllowForPStateChangeOrStutterInVBlankFinal == dm_prefetch_support_uclk_fclk_and_stutter) { *MinPrefetchMode = 0; *MaxPrefetchMode = 0; - } else if (AllowForPStateChangeOrStutterInVBlankFinal == - dm_prefetch_support_uclk_fclk_and_stutter_if_possible) { - *MinPrefetchMode = 0; - *MaxPrefetchMode = 3; } else { *MinPrefetchMode = 0; *MaxPrefetchMode = 3; 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 626f6605e2d5..55cead0d4237 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, @@ -713,28 +715,14 @@ 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, @@ -808,58 +796,28 @@ 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/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index 7ebf25e87933..dd90f241e906 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -489,6 +489,7 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p if ((int)(dcn3_21_soc.urgent_latency_us * 1000) != dc->bb_overrides.urgent_latency_ns && dc->bb_overrides.urgent_latency_ns) { dcn3_21_soc.urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0; + dcn3_21_soc.urgent_latency_pixel_data_only_us = dc->bb_overrides.urgent_latency_ns / 1000.0; } if ((int)(dcn3_21_soc.dram_clock_change_latency_us * 1000) 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..4125d3d111d1 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, @@ -105,8 +114,12 @@ void dml_init_instance(struct display_mode_lib *lib, break; case DML_PROJECT_DCN31: case DML_PROJECT_DCN31_FPGA: + case DML_PROJECT_DCN315: 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..3d643d50c3eb 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 @@ -40,7 +40,9 @@ enum dml_project { DML_PROJECT_DCN21, DML_PROJECT_DCN30, DML_PROJECT_DCN31, + DML_PROJECT_DCN315, DML_PROJECT_DCN31_FPGA, + DML_PROJECT_DCN314, DML_PROJECT_DCN32, }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index c596187a1e09..f33a8879b05a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -510,6 +510,7 @@ struct _vcs_dpi_display_pipe_dest_params_st { unsigned int htotal; unsigned int vtotal; unsigned int vfront_porch; + unsigned int vblank_nom; unsigned int vactive; unsigned int hactive; unsigned int vstartup_start; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 503e7d984ff0..03924aed8d5c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -597,6 +597,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) mode_lib->vba.HTotal[mode_lib->vba.NumberOfActivePlanes] = dst->htotal; mode_lib->vba.VTotal[mode_lib->vba.NumberOfActivePlanes] = dst->vtotal; mode_lib->vba.VFrontPorch[mode_lib->vba.NumberOfActivePlanes] = dst->vfront_porch; + mode_lib->vba.VBlankNom[mode_lib->vba.NumberOfActivePlanes] = dst->vblank_nom; mode_lib->vba.DCCFractionOfZeroSizeRequestsLuma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_fraction_of_zs_req_luma; mode_lib->vba.DCCFractionOfZeroSizeRequestsChroma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_fraction_of_zs_req_chroma; mode_lib->vba.DCCEnable[mode_lib->vba.NumberOfActivePlanes] = 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 da8acf59ccac..630f3395e90a 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 @@ -652,10 +652,10 @@ 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; @@ -801,8 +801,6 @@ 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/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h index 479d7d83220c..072bd0539605 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h @@ -76,14 +76,9 @@ static inline double dml_floor(double a, double granularity) static inline double dml_round(double a) { - double round_pt = 0.5; - double ceil = dml_ceil(a, 1); - double floor = dml_floor(a, 1); + const double round_pt = 0.5; - if (a - floor >= round_pt) - return ceil; - else - return floor; + return dml_floor(a + round_pt, 1); } /* float diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 8919a2092ac5..9498105c98ab 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -39,6 +39,8 @@ #include "panel_cntl.h" #define MAX_CLOCK_SOURCES 7 +#define MAX_SVP_PHANTOM_STREAMS 2 +#define MAX_SVP_PHANTOM_PLANES 2 void enable_surface_flip_reporting(struct dc_plane_state *plane_state, uint32_t controller_id); @@ -232,6 +234,7 @@ struct resource_funcs { unsigned int index); bool (*remove_phantom_pipes)(struct dc *dc, struct dc_state *context); + void (*get_panel_config_defaults)(struct dc_panel_config *panel_config); }; struct audio_support{ @@ -438,7 +441,6 @@ struct pipe_ctx { union pipe_update_flags update_flags; struct dwbc *dwbc; struct mcif_wb *mcif_wb; - bool vtp_locked; }; /* Data used for dynamic link encoder assignment. @@ -492,6 +494,8 @@ struct dcn_bw_output { struct dcn_watermark_set watermarks; struct dcn_bw_writeback bw_writeback; int compbuf_size_kb; + unsigned int legacy_svp_drr_stream_index; + bool legacy_svp_drr_stream_index_valid; }; union bw_output { diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index 6682d9e181c6..b304d450b038 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -194,6 +194,11 @@ enum dc_status dpcd_configure_lttpr_mode( enum dp_link_encoding dp_get_link_encoding_format(const struct dc_link_settings *link_settings); bool dp_retrieve_lttpr_cap(struct dc_link *link); +bool dp_is_lttpr_present(struct dc_link *link); +enum lttpr_mode dp_decide_lttpr_mode(struct dc_link *link, struct dc_link_settings *link_setting); +void dp_get_lttpr_mode_override(struct dc_link *link, enum lttpr_mode *override); +enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link); +enum lttpr_mode dp_decide_128b_132b_lttpr_mode(struct dc_link *link); bool dpcd_write_128b_132b_sst_payload_allocation_table( const struct dc_stream_state *stream, struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h index 806f3041db14..9e4ddc985240 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h @@ -628,8 +628,23 @@ unsigned int dcn_find_dcfclk_suits_all( const struct dc *dc, struct dc_clocks *clocks); -void dcn_bw_update_from_pplib(struct dc *dc); -void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc); +void dcn_get_soc_clks( + struct dc *dc, + int *min_fclk_khz, + int *min_dcfclk_khz, + int *socclk_khz); + +void dcn_bw_update_from_pplib_fclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *fclks); +void dcn_bw_update_from_pplib_dcfclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *dcfclks); +void dcn_bw_notify_pplib_of_wm_ranges( + struct dc *dc, + int min_fclk_khz, + int min_dcfclk_khz, + int socclk_khz); void dcn_bw_sync_calcs_and_dml(struct dc *dc); enum source_macro_tile_size swizzle_mode_to_macro_tile_size(enum swizzle_mode_values sw_mode); 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..591ab1389e3b 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 @@ -95,10 +95,23 @@ struct clk_limit_table_entry { unsigned int wck_ratio; }; +struct clk_limit_num_entries { + unsigned int num_dcfclk_levels; + unsigned int num_fclk_levels; + unsigned int num_memclk_levels; + unsigned int num_socclk_levels; + unsigned int num_dtbclk_levels; + unsigned int num_dispclk_levels; + unsigned int num_dppclk_levels; + unsigned int num_phyclk_levels; + unsigned int num_phyclk_d18_levels; +}; + /* This table is contiguous */ struct clk_limit_table { struct clk_limit_table_entry entries[MAX_NUM_DPM_LVL]; - unsigned int num_entries; + struct clk_limit_num_entries num_entries_per_clk; + unsigned int num_entries; /* highest populated dpm level for back compatibility */ }; struct wm_range_table_entry { @@ -214,6 +227,7 @@ 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/hw/cursor_reg_cache.h b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h new file mode 100644 index 000000000000..45645f9fd86c --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2022 Advanced Micro Devices, Inc. All rights reserved. */ + +#ifndef __DAL_CURSOR_CACHE_H__ +#define __DAL_CURSOR_CACHE_H__ + +union reg_cursor_control_cfg { + struct { + uint32_t cur_enable: 1; + uint32_t reser0: 3; + uint32_t cur_2x_magnify: 1; + uint32_t reser1: 3; + uint32_t mode: 3; + uint32_t reser2: 5; + uint32_t pitch: 2; + uint32_t reser3: 6; + uint32_t line_per_chunk: 5; + uint32_t reser4: 3; + } bits; + uint32_t raw; +}; +struct cursor_position_cache_hubp { + union reg_cursor_control_cfg cur_ctl; + union reg_position_cfg { + struct { + uint32_t x_pos: 16; + uint32_t y_pos: 16; + } bits; + uint32_t raw; + } position; + union reg_hot_spot_cfg { + struct { + uint32_t x_hot: 16; + uint32_t y_hot: 16; + } bits; + uint32_t raw; + } hot_spot; + union reg_dst_offset_cfg { + struct { + uint32_t dst_x_offset: 13; + uint32_t reserved: 19; + } bits; + uint32_t raw; + } dst_offset; +}; + +struct cursor_attribute_cache_hubp { + uint32_t SURFACE_ADDR_HIGH; + uint32_t SURFACE_ADDR; + union reg_cursor_control_cfg cur_ctl; + union reg_cursor_size_cfg { + struct { + uint32_t width: 16; + uint32_t height: 16; + } bits; + uint32_t raw; + } size; + union reg_cursor_settings_cfg { + struct { + uint32_t dst_y_offset: 8; + uint32_t chunk_hdl_adjust: 2; + uint32_t reserved: 22; + } bits; + uint32_t raw; + } settings; +}; + +struct cursor_rect { + uint32_t x; + uint32_t y; + uint32_t w; + uint32_t h; +}; + +union reg_cur0_control_cfg { + struct { + uint32_t cur0_enable: 1; + uint32_t expansion_mode: 1; + uint32_t reser0: 1; + uint32_t cur0_rom_en: 1; + uint32_t mode: 3; + uint32_t reserved: 25; + } bits; + uint32_t raw; +}; +struct cursor_position_cache_dpp { + union reg_cur0_control_cfg cur0_ctl; +}; + +struct cursor_attribute_cache_dpp { + union reg_cur0_control_cfg cur0_ctl; +}; + +struct cursor_attributes_cfg { + struct cursor_attribute_cache_hubp aHubp; + struct cursor_attribute_cache_dpp aDpp; +}; + +#endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 3ef7faa92052..dcb80c4747b0 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -28,6 +28,7 @@ #define __DAL_DPP_H__ #include "transform.h" +#include "cursor_reg_cache.h" union defer_reg_writes { struct { @@ -58,6 +59,9 @@ struct dpp { struct pwl_params shaper_params; bool cm_bypass_mode; + + struct cursor_position_cache_dpp pos; + struct cursor_attribute_cache_dpp att; }; struct dpp_input_csc_matrix { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 44c4578193a3..d5ea7545583e 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -27,6 +27,7 @@ #define __DAL_HUBP_H__ #include "mem_input.h" +#include "cursor_reg_cache.h" #define OPP_ID_INVALID 0xf #define MAX_TTU 0xffffff @@ -65,6 +66,10 @@ struct hubp { struct dc_cursor_attributes curs_attr; struct dc_cursor_position curs_pos; bool power_gated; + + struct cursor_position_cache_hubp pos; + struct cursor_attribute_cache_hubp att; + struct cursor_rect cur_rect; }; struct surface_flip_registers { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h index 437b64e87377..cd2be729846b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h @@ -268,10 +268,18 @@ enum dc_lut_mode { LUT_RAM_B }; -enum phy_state { - TX_OFF_SYMCLK_OFF, - TX_ON_SYMCLK_ON, - TX_OFF_SYMCLK_ON +enum symclk_state { + SYMCLK_OFF_TX_OFF, + SYMCLK_ON_TX_ON, + SYMCLK_ON_TX_OFF, +}; + +struct phy_state { + struct { + uint8_t otg : 1; + uint8_t reserved : 7; + } symclk_ref_cnts; + enum symclk_state symclk_state; }; /** diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 72eef7a5ed83..25a1df45b264 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -209,7 +209,6 @@ struct timing_generator_funcs { void (*set_blank)(struct timing_generator *tg, bool enable_blanking); bool (*is_blanked)(struct timing_generator *tg); - bool (*is_locked)(struct timing_generator *tg); void (*set_overscan_blank_color) (struct timing_generator *tg, const struct tg_color *color); void (*set_blank_color)(struct timing_generator *tg, const struct tg_color *color); void (*set_colors)(struct timing_generator *tg, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 52b4350c9cd8..d04b68dad413 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -32,11 +32,6 @@ #include "inc/hw/link_encoder.h" #include "core_status.h" -enum vline_select { - VLINE0, - VLINE1 -}; - struct pipe_ctx; struct dc_state; struct dc_stream_status; @@ -48,6 +43,7 @@ struct dc_phy_addr_space_config; struct dc_virtual_addr_space_config; struct dpp; struct dce_hwseq; +struct link_resource; struct hw_sequencer_funcs { void (*hardware_release)(struct dc *dc); @@ -88,6 +84,7 @@ struct hw_sequencer_funcs { struct pipe_ctx *pipe_ctx, bool enableTripleBuffer); void (*update_pending_status)(struct pipe_ctx *pipe_ctx); void (*power_down)(struct dc *dc); + void (*update_dsc_pg)(struct dc *dc, struct dc_state *context, bool safe_to_disable); /* Pipe Lock Related */ void (*pipe_control_lock)(struct dc *dc, @@ -116,8 +113,7 @@ struct hw_sequencer_funcs { int group_index, int group_size, struct pipe_ctx *grouped_pipes[]); void (*setup_periodic_interrupt)(struct dc *dc, - struct pipe_ctx *pipe_ctx, - enum vline_select vline); + struct pipe_ctx *pipe_ctx); void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes, struct dc_crtc_timing_adjust adjust); void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx, @@ -218,6 +214,25 @@ struct hw_sequencer_funcs { void (*set_pipe)(struct pipe_ctx *pipe_ctx); + void (*enable_dp_link_output)(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + const struct dc_link_settings *link_settings); + void (*enable_tmds_link_output)(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal, + enum clock_source_id clock_source, + enum dc_color_depth color_depth, + uint32_t pixel_clock); + void (*enable_lvds_link_output)(struct dc_link *link, + const struct link_resource *link_res, + enum clock_source_id clock_source, + uint32_t pixel_clock); + void (*disable_link_output)(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal); + void (*get_dcc_en_bits)(struct dc *dc, int *dcc_en_bits); /* Idle Optimization Related */ @@ -245,7 +260,9 @@ struct hw_sequencer_funcs { struct tg_color *color, int mpcc_id); - void (*update_phy_state)(struct dc_state *state, struct pipe_ctx *pipe_ctx, enum phy_state target_state); + void (*update_phantom_vp_position)(struct dc *dc, + struct dc_state *context, + struct pipe_ctx *phantom_pipe); void (*commit_subvp_config)(struct dc *dc, struct dc_state *context); void (*subvp_pipe_control_lock)(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index 1cdea0efe5c1..a4d61bb724b6 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -124,6 +124,8 @@ struct hwseq_private_funcs { void (*dsc_pg_control)(struct dce_hwseq *hws, unsigned int dsc_inst, bool power_on); + bool (*dsc_pg_status)(struct dce_hwseq *hws, + unsigned int dsc_inst); void (*update_odm)(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx); void (*program_all_writeback_pipes_in_tree)(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h index 3482a877b6af..89964c980b87 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h @@ -55,9 +55,6 @@ struct link_hwss_ext { enum signal_type signal, enum clock_source_id clock_source, const struct dc_link_settings *link_settings); - void (*disable_dp_link_output)(struct dc_link *link, - const struct link_resource *link_res, - enum signal_type signal); void (*set_dp_link_test_pattern)(struct dc_link *link, const struct link_resource *link_res, struct encoder_set_dp_phy_pattern_param *tp_params); @@ -79,6 +76,9 @@ struct link_hwss { void (*setup_stream_encoder)(struct pipe_ctx *pipe_ctx); void (*reset_stream_encoder)(struct pipe_ctx *pipe_ctx); void (*setup_stream_attribute)(struct pipe_ctx *pipe_ctx); + void (*disable_link_output)(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal); }; #endif /* __DC_LINK_HWSS_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 58158764adc0..5040836f404d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -219,9 +219,21 @@ 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, const struct link_resource *link_res); +bool is_h_timing_divisible_by_2(struct dc_stream_state *stream); + +bool dc_resource_acquire_secondary_pipe_for_mpc_odm( + const struct dc *dc, + struct dc_state *state, + struct pipe_ctx *pri_pipe, + struct pipe_ctx *sec_pipe, + bool odm); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.c index 5e92019539c8..4227adbc646a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.c @@ -130,7 +130,7 @@ void enable_dio_dp_link_output(struct dc_link *link, dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_LINK_PHY); } -void disable_dio_dp_link_output(struct dc_link *link, +void disable_dio_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { @@ -174,10 +174,10 @@ static const struct link_hwss dio_link_hwss = { .setup_stream_encoder = setup_dio_stream_encoder, .reset_stream_encoder = reset_dio_stream_encoder, .setup_stream_attribute = setup_dio_stream_attribute, + .disable_link_output = disable_dio_link_output, .ext = { .set_throttled_vcp_size = set_dio_throttled_vcp_size, .enable_dp_link_output = enable_dio_dp_link_output, - .disable_dp_link_output = disable_dio_dp_link_output, .set_dp_link_test_pattern = set_dio_dp_link_test_pattern, .set_dp_lane_settings = set_dio_dp_lane_settings, .update_stream_allocation_table = update_dio_stream_allocation_table, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.h b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.h index 08f22b32df48..126d37f847a1 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dio.h @@ -40,7 +40,7 @@ void enable_dio_dp_link_output(struct dc_link *link, enum signal_type signal, enum clock_source_id clock_source, const struct dc_link_settings *link_settings); -void disable_dio_dp_link_output(struct dc_link *link, +void disable_dio_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal); void set_dio_dp_link_test_pattern(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dpia.c index 89d4e8159138..64f7ea6a9aa3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_dpia.c @@ -56,10 +56,10 @@ static const struct link_hwss dpia_link_hwss = { .setup_stream_encoder = setup_dio_stream_encoder, .reset_stream_encoder = reset_dio_stream_encoder, .setup_stream_attribute = setup_dio_stream_attribute, + .disable_link_output = disable_dio_link_output, .ext = { .set_throttled_vcp_size = set_dio_throttled_vcp_size, .enable_dp_link_output = enable_dio_dp_link_output, - .disable_dp_link_output = disable_dio_dp_link_output, .set_dp_link_test_pattern = set_dio_dp_link_test_pattern, .set_dp_lane_settings = set_dio_dp_lane_settings, .update_stream_allocation_table = update_dpia_stream_allocation_table, 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 226af06278ce..153a88381f2c 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 @@ -111,7 +111,7 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx) enum phyd32clk_clock_source phyd32clk = get_phyd32clk_src(pipe_ctx->stream->link); dto_params.otg_inst = tg->inst; - dto_params.pixclk_khz = pipe_ctx->stream->phy_pix_clk; + dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; dto_params.num_odm_segments = get_odm_segment_count(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); @@ -266,11 +266,11 @@ static const struct link_hwss hpo_dp_link_hwss = { .setup_stream_encoder = setup_hpo_dp_stream_encoder, .reset_stream_encoder = reset_hpo_dp_stream_encoder, .setup_stream_attribute = setup_hpo_dp_stream_attribute, + .disable_link_output = disable_hpo_dp_link_output, .ext = { .set_throttled_vcp_size = set_hpo_dp_throttled_vcp_size, .set_hblank_min_symbol_width = set_hpo_dp_hblank_min_symbol_width, .enable_dp_link_output = enable_hpo_dp_link_output, - .disable_dp_link_output = disable_hpo_dp_link_output, .set_dp_link_test_pattern = set_hpo_dp_link_test_pattern, .set_dp_lane_settings = set_hpo_dp_lane_settings, .update_stream_allocation_table = update_hpo_dp_stream_allocation_table, diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c index 501173ce270e..4f7f99156897 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c @@ -36,10 +36,18 @@ void virtual_setup_stream_attribute(struct pipe_ctx *pipe_ctx) void virtual_reset_stream_encoder(struct pipe_ctx *pipe_ctx) { } + +static void virtual_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ +} + static const struct link_hwss virtual_link_hwss = { .setup_stream_encoder = virtual_setup_stream_encoder, .reset_stream_encoder = virtual_reset_stream_encoder, .setup_stream_attribute = virtual_setup_stream_attribute, + .disable_link_output = virtual_disable_link_output, }; const struct link_hwss *get_virtual_link_hwss(void) diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index f34c45b19fcb..eb5b7eb292ef 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -248,6 +248,7 @@ struct dmub_srv_hw_params { bool disable_dpia; bool usb4_cm_version; bool fw_in_system_memory; + bool dpia_hpd_int_enable_supported; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 7cddbc431b57..7a8f61517424 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -400,8 +400,9 @@ union dmub_fw_boot_options { uint32_t diag_env: 1; /* 1 if diagnostic environment */ uint32_t gpint_scratch8: 1; /* 1 if GPINT is in scratch8*/ uint32_t usb4_cm_version: 1; /**< 1 CM support */ + uint32_t dpia_hpd_int_enable_supported: 1; /* 1 if dpia hpd int enable supported */ - uint32_t reserved : 17; /**< reserved */ + uint32_t reserved : 16; /**< reserved */ } bits; /**< boot bits */ uint32_t all; /**< 32-bit access to bits */ }; @@ -728,6 +729,12 @@ enum dmub_cmd_type { /** * Command type used for all VBIOS interface commands. */ + + /** + * Command type used to set DPIA HPD interrupt state + */ + DMUB_CMD__DPIA_HPD_INT_ENABLE = 86, + DMUB_CMD__VBIOS = 128, }; @@ -998,7 +1005,8 @@ struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 { uint8_t scale_factor_numerator; uint8_t scale_factor_denominator; uint8_t is_drr; - uint8_t pad[2]; + uint8_t main_split_pipe_index; + uint8_t phantom_split_pipe_index; } subvp_data; struct { @@ -1255,6 +1263,14 @@ struct dmub_rb_cmd_set_mst_alloc_slots { }; /** + * DMUB command structure for DPIA HPD int enable control. + */ +struct dmub_rb_cmd_dpia_hpd_int_enable { + struct dmub_cmd_header header; /* header */ + uint32_t enable; /* dpia hpd interrupt enable */ +}; + +/** * struct dmub_rb_cmd_dpphy_init - DPPHY init. */ struct dmub_rb_cmd_dpphy_init { @@ -2083,7 +2099,99 @@ struct dmub_rb_cmd_update_dirty_rect { /** * Data passed from driver to FW in a DMUB_CMD__UPDATE_CURSOR_INFO command. */ -struct dmub_cmd_update_cursor_info_data { +union dmub_reg_cursor_control_cfg { + struct { + uint32_t cur_enable: 1; + uint32_t reser0: 3; + uint32_t cur_2x_magnify: 1; + uint32_t reser1: 3; + uint32_t mode: 3; + uint32_t reser2: 5; + uint32_t pitch: 2; + uint32_t reser3: 6; + uint32_t line_per_chunk: 5; + uint32_t reser4: 3; + } bits; + uint32_t raw; +}; +struct dmub_cursor_position_cache_hubp { + union dmub_reg_cursor_control_cfg cur_ctl; + union dmub_reg_position_cfg { + struct { + uint32_t cur_x_pos: 16; + uint32_t cur_y_pos: 16; + } bits; + uint32_t raw; + } position; + union dmub_reg_hot_spot_cfg { + struct { + uint32_t hot_x: 16; + uint32_t hot_y: 16; + } bits; + uint32_t raw; + } hot_spot; + union dmub_reg_dst_offset_cfg { + struct { + uint32_t dst_x_offset: 13; + uint32_t reserved: 19; + } bits; + uint32_t raw; + } dst_offset; +}; + +union dmub_reg_cur0_control_cfg { + struct { + uint32_t cur0_enable: 1; + uint32_t expansion_mode: 1; + uint32_t reser0: 1; + uint32_t cur0_rom_en: 1; + uint32_t mode: 3; + uint32_t reserved: 25; + } bits; + uint32_t raw; +}; +struct dmub_cursor_position_cache_dpp { + union dmub_reg_cur0_control_cfg cur0_ctl; +}; +struct dmub_cursor_position_cfg { + struct dmub_cursor_position_cache_hubp pHubp; + struct dmub_cursor_position_cache_dpp pDpp; + uint8_t pipe_idx; + /* + * Padding is required. To be 4 Bytes Aligned. + */ + uint8_t padding[3]; +}; + +struct dmub_cursor_attribute_cache_hubp { + uint32_t SURFACE_ADDR_HIGH; + uint32_t SURFACE_ADDR; + union dmub_reg_cursor_control_cfg cur_ctl; + union dmub_reg_cursor_size_cfg { + struct { + uint32_t width: 16; + uint32_t height: 16; + } bits; + uint32_t raw; + } size; + union dmub_reg_cursor_settings_cfg { + struct { + uint32_t dst_y_offset: 8; + uint32_t chunk_hdl_adjust: 2; + uint32_t reserved: 22; + } bits; + uint32_t raw; + } settings; +}; +struct dmub_cursor_attribute_cache_dpp { + union dmub_reg_cur0_control_cfg cur0_ctl; +}; +struct dmub_cursor_attributes_cfg { + struct dmub_cursor_attribute_cache_hubp aHubp; + struct dmub_cursor_attribute_cache_dpp aDpp; +}; + +struct dmub_cmd_update_cursor_payload0 { /** * Cursor dirty rects. */ @@ -2110,6 +2218,20 @@ struct dmub_cmd_update_cursor_info_data { * Currently the support is only for 0 or 1 */ uint8_t panel_inst; + /** + * Cursor Position Register. + * Registers contains Hubp & Dpp modules + */ + struct dmub_cursor_position_cfg position_cfg; +}; + +struct dmub_cmd_update_cursor_payload1 { + struct dmub_cursor_attributes_cfg attribute_cfg; +}; + +union dmub_cmd_update_cursor_info_data { + struct dmub_cmd_update_cursor_payload0 payload0; + struct dmub_cmd_update_cursor_payload1 payload1; }; /** * Definition of a DMUB_CMD__UPDATE_CURSOR_INFO command. @@ -2122,7 +2244,7 @@ struct dmub_rb_cmd_update_cursor_info { /** * Data passed from driver to FW in a DMUB_CMD__UPDATE_CURSOR_INFO command. */ - struct dmub_cmd_update_cursor_info_data update_cursor_info_data; + union dmub_cmd_update_cursor_info_data update_cursor_info_data; }; /** @@ -2819,11 +2941,7 @@ struct dmub_rb_cmd_get_visual_confirm_color { struct dmub_optc_state { uint32_t v_total_max; uint32_t v_total_min; - uint32_t v_total_mid; - uint32_t v_total_mid_frame_num; uint32_t tg_inst; - uint32_t enable_manual_trigger; - uint32_t clear_force_vsync; }; struct dmub_rb_cmd_drr_update { @@ -3229,6 +3347,10 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__QUERY_HPD_STATE command. */ struct dmub_rb_cmd_query_hpd_state query_hpd; + /** + * Definition of a DMUB_CMD__DPIA_HPD_INT_ENABLE command. + */ + struct dmub_rb_cmd_dpia_hpd_int_enable dpia_hpd_int_enable; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index c7bd7e216710..c90b9ee42e12 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -350,6 +350,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu boot_options.bits.dpia_supported = params->dpia_supported; boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1; boot_options.bits.usb4_cm_version = params->usb4_cm_version; + boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported; boot_options.bits.power_optimization = params->power_optimization; boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0; diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 9f3558c0ef11..c3089c673975 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -215,6 +215,7 @@ enum { #define DEVICE_ID_NV_143F 0x143F #define FAMILY_VGH 144 #define DEVICE_ID_VGH_163F 0x163F +#define DEVICE_ID_VGH_1435 0x1435 #define VANGOGH_A0 0x01 #define VANGOGH_UNKNOWN 0xFF diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h index 05096c644a60..a7ba5bd8dc16 100644 --- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h +++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h @@ -128,8 +128,8 @@ struct av_sync_data { uint8_t aud_del_ins3;/* DPCD 0002Dh */ }; -static const uint8_t DP_SINK_DEVICE_STR_ID_1[] = {7, 1, 8, 7, 3, 0}; -static const uint8_t DP_SINK_DEVICE_STR_ID_2[] = {7, 1, 8, 7, 5, 0}; +static const uint8_t DP_SINK_DEVICE_STR_ID_1[] = {7, 1, 8, 7, 3}; +static const uint8_t DP_SINK_DEVICE_STR_ID_2[] = {7, 1, 8, 7, 5}; static const u8 DP_SINK_BRANCH_DEV_NAME_7580[] = "7580\x80u"; diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h index d76ab72baf0c..d1e91d31d151 100644 --- a/drivers/gpu/drm/amd/display/include/link_service_types.h +++ b/drivers/gpu/drm/amd/display/include/link_service_types.h @@ -83,6 +83,7 @@ enum link_training_result { }; enum lttpr_mode { + LTTPR_MODE_UNKNOWN, LTTPR_MODE_NON_LTTPR, LTTPR_MODE_TRANSPARENT, LTTPR_MODE_NON_TRANSPARENT, 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..447a0ec9cbe2 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) @@ -1688,7 +1692,7 @@ static void apply_degamma_for_user_regamma(struct pwl_float_data_ex *rgb_regamma struct pwl_float_data_ex *rgb = rgb_regamma; const struct hw_x_point *coord_x = coordinates_x; - build_coefficients(&coeff, true); + build_coefficients(&coeff, TRANSFER_FUNCTION_SRGB); i = 0; while (i != hw_points_num + 1) { diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h index 1115dfc6ae1f..3973110f149c 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h @@ -9800,18 +9800,118 @@ // addressBlock: gc_pwrdec // base address: 0x3c000 +#define mmCGTS_RD_CTRL_REG 0x5004 +#define mmCGTS_RD_CTRL_REG_BASE_IDX 1 +#define mmCGTS_RD_REG 0x5005 +#define mmCGTS_RD_REG_BASE_IDX 1 #define mmCGTS_TCC_DISABLE 0x5006 #define mmCGTS_TCC_DISABLE_BASE_IDX 1 #define mmCGTS_USER_TCC_DISABLE 0x5007 #define mmCGTS_USER_TCC_DISABLE_BASE_IDX 1 +#define mmCGTS_STATUS_REG 0x5008 +#define mmCGTS_STATUS_REG_BASE_IDX 1 +#define mmCGTT_SPI_CGTSSM_CLK_CTRL 0x5009 +#define mmCGTT_SPI_CGTSSM_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SPI_PS_CLK_CTRL 0x507d +#define mmCGTT_SPI_PS_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SPIS_CLK_CTRL 0x507e +#define mmCGTT_SPIS_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SPI_CLK_CTRL 0x5080 +#define mmCGTT_SPI_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_PC_CLK_CTRL 0x5081 +#define mmCGTT_PC_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_BCI_CLK_CTRL 0x5082 +#define mmCGTT_BCI_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_VGT_CLK_CTRL 0x5084 +#define mmCGTT_VGT_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_IA_CLK_CTRL 0x5085 +#define mmCGTT_IA_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_WD_CLK_CTRL 0x5086 +#define mmCGTT_WD_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_GS_NGG_CLK_CTRL 0x5087 +#define mmCGTT_GS_NGG_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_PA_CLK_CTRL 0x5088 +#define mmCGTT_PA_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SC_CLK_CTRL0 0x5089 +#define mmCGTT_SC_CLK_CTRL0_BASE_IDX 1 +#define mmCGTT_SC_CLK_CTRL1 0x508a +#define mmCGTT_SC_CLK_CTRL1_BASE_IDX 1 +#define mmCGTT_SC_CLK_CTRL2 0x508b +#define mmCGTT_SC_CLK_CTRL2_BASE_IDX 1 +#define mmCGTT_SQ_CLK_CTRL 0x508c +#define mmCGTT_SQ_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SQG_CLK_CTRL 0x508d +#define mmCGTT_SQG_CLK_CTRL_BASE_IDX 1 #define mmSQ_ALU_CLK_CTRL 0x508e #define mmSQ_ALU_CLK_CTRL_BASE_IDX 1 #define mmSQ_TEX_CLK_CTRL 0x508f #define mmSQ_TEX_CLK_CTRL_BASE_IDX 1 #define mmSQ_LDS_CLK_CTRL 0x5090 #define mmSQ_LDS_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_SX_CLK_CTRL0 0x5094 +#define mmCGTT_SX_CLK_CTRL0_BASE_IDX 1 +#define mmCGTT_SX_CLK_CTRL1 0x5095 +#define mmCGTT_SX_CLK_CTRL1_BASE_IDX 1 +#define mmCGTT_SX_CLK_CTRL2 0x5096 +#define mmCGTT_SX_CLK_CTRL2_BASE_IDX 1 +#define mmCGTT_SX_CLK_CTRL3 0x5097 +#define mmCGTT_SX_CLK_CTRL3_BASE_IDX 1 +#define mmCGTT_SX_CLK_CTRL4 0x5098 +#define mmCGTT_SX_CLK_CTRL4_BASE_IDX 1 +#define mmTD_CGTT_CTRL 0x509c +#define mmTD_CGTT_CTRL_BASE_IDX 1 +#define mmTA_CGTT_CTRL 0x509d +#define mmTA_CGTT_CTRL_BASE_IDX 1 +#define mmCGTT_TCPI_CLK_CTRL 0x5109 +#define mmCGTT_TCPI_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_GDS_CLK_CTRL 0x50a0 +#define mmCGTT_GDS_CLK_CTRL_BASE_IDX 1 +#define mmDB_CGTT_CLK_CTRL_0 0x50a4 +#define mmDB_CGTT_CLK_CTRL_0_BASE_IDX 1 +#define mmCB_CGTT_SCLK_CTRL 0x50a8 +#define mmCB_CGTT_SCLK_CTRL_BASE_IDX 1 +#define mmGL2C_CGTT_SCLK_CTRL 0x50fc +#define mmGL2C_CGTT_SCLK_CTRL_BASE_IDX 1 +#define mmGL2A_CGTT_SCLK_CTRL 0x50ac +#define mmGL2A_CGTT_SCLK_CTRL_BASE_IDX 1 +#define mmGL2A_CGTT_SCLK_CTRL_1 0x50ad +#define mmGL2A_CGTT_SCLK_CTRL_1_BASE_IDX 1 +#define mmCGTT_CP_CLK_CTRL 0x50b0 +#define mmCGTT_CP_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_CPF_CLK_CTRL 0x50b1 +#define mmCGTT_CPF_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_CPC_CLK_CTRL 0x50b2 +#define mmCGTT_CPC_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_RLC_CLK_CTRL 0x50b5 +#define mmCGTT_RLC_CLK_CTRL_BASE_IDX 1 #define mmRLC_GFX_RM_CNTL 0x50b6 #define mmRLC_GFX_RM_CNTL_BASE_IDX 1 +#define mmRMI_CGTT_SCLK_CTRL 0x50c0 +#define mmRMI_CGTT_SCLK_CTRL_BASE_IDX 1 +#define mmCGTT_TCPF_CLK_CTRL 0x5111 +#define mmCGTT_TCPF_CLK_CTRL_BASE_IDX 1 +#define mmGCR_CGTT_SCLK_CTRL 0x50c2 +#define mmGCR_CGTT_SCLK_CTRL_BASE_IDX 1 +#define mmUTCL1_CGTT_CLK_CTRL 0x50c3 +#define mmUTCL1_CGTT_CLK_CTRL_BASE_IDX 1 +#define mmGCEA_CGTT_CLK_CTRL 0x50c4 +#define mmGCEA_CGTT_CLK_CTRL_BASE_IDX 1 +#define mmSE_CAC_CGTT_CLK_CTRL 0x50d0 +#define mmSE_CAC_CGTT_CLK_CTRL_BASE_IDX 1 +#define mmGC_CAC_CGTT_CLK_CTRL 0x50d8 +#define mmGC_CAC_CGTT_CLK_CTRL_BASE_IDX 1 +#define mmGRBM_CGTT_CLK_CNTL 0x50e0 +#define mmGRBM_CGTT_CLK_CNTL_BASE_IDX 1 +#define mmGUS_CGTT_CLK_CTRL 0x50f4 +#define mmGUS_CGTT_CLK_CTRL_BASE_IDX 1 +#define mmCGTT_PH_CLK_CTRL0 0x50f8 +#define mmCGTT_PH_CLK_CTRL0_BASE_IDX 1 +#define mmCGTT_PH_CLK_CTRL1 0x50f9 +#define mmCGTT_PH_CLK_CTRL1_BASE_IDX 1 +#define mmCGTT_PH_CLK_CTRL2 0x50fa +#define mmCGTT_PH_CLK_CTRL2_BASE_IDX 1 +#define mmCGTT_PH_CLK_CTRL3 0x50fb +#define mmCGTT_PH_CLK_CTRL3_BASE_IDX 1 // addressBlock: gc_hypdec diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h index 83faa276523f..d4e8ff22ecb8 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h @@ -34547,6 +34547,14 @@ // addressBlock: gc_pwrdec +//CGTS_RD_CTRL_REG +#define CGTS_RD_CTRL_REG__ROW_MUX_SEL__SHIFT 0x0 +#define CGTS_RD_CTRL_REG__REG_MUX_SEL__SHIFT 0x4 +#define CGTS_RD_CTRL_REG__ROW_MUX_SEL_MASK 0x0000000FL +#define CGTS_RD_CTRL_REG__REG_MUX_SEL_MASK 0x000000F0L +//CGTS_RD_REG +#define CGTS_RD_REG__READ_DATA__SHIFT 0x0 +#define CGTS_RD_REG__READ_DATA_MASK 0xFFFFFFFFL //CGTS_TCC_DISABLE #define CGTS_TCC_DISABLE__HI_TCC_DISABLE__SHIFT 0x8 #define CGTS_TCC_DISABLE__TCC_DISABLE__SHIFT 0x10 @@ -34557,6 +34565,485 @@ #define CGTS_USER_TCC_DISABLE__TCC_DISABLE__SHIFT 0x10 #define CGTS_USER_TCC_DISABLE__HI_TCC_DISABLE_MASK 0x0000FF00L #define CGTS_USER_TCC_DISABLE__TCC_DISABLE_MASK 0xFFFF0000L +//CGTS_STATUS_REG +#define CGTS_STATUS_REG__SA0_QUAD0_MGCG_ENABLED__SHIFT 0x0 +#define CGTS_STATUS_REG__SA0_QUAD0_CG_STATUS__SHIFT 0x1 +#define CGTS_STATUS_REG__SA1_QUAD0_MGCG_ENABLED__SHIFT 0x8 +#define CGTS_STATUS_REG__SA1_QUAD0_CG_STATUS__SHIFT 0x9 +#define CGTS_STATUS_REG__SA0_QUAD0_MGCG_ENABLED_MASK 0x00000001L +#define CGTS_STATUS_REG__SA0_QUAD0_CG_STATUS_MASK 0x00000006L +#define CGTS_STATUS_REG__SA1_QUAD0_MGCG_ENABLED_MASK 0x00000100L +#define CGTS_STATUS_REG__SA1_QUAD0_CG_STATUS_MASK 0x00000600L +//CGTT_SPI_CGTSSM_CLK_CTRL +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP3_OVERRIDE__SHIFT 0x1b +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP2_OVERRIDE__SHIFT 0x1c +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP1_OVERRIDE__SHIFT 0x1d +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP0_OVERRIDE__SHIFT 0x1e +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP3_OVERRIDE_MASK 0x08000000L +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP2_OVERRIDE_MASK 0x10000000L +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP1_OVERRIDE_MASK 0x20000000L +#define CGTT_SPI_CGTSSM_CLK_CTRL__GRP0_OVERRIDE_MASK 0x40000000L +//CGTT_SPI_PS_CLK_CTRL +#define CGTT_SPI_PS_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_SPI_PS_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x10 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_SPI_PS_CLK_CTRL__GRP6_OVERRIDE__SHIFT 0x18 +#define CGTT_SPI_PS_CLK_CTRL__GRP5_OVERRIDE__SHIFT 0x19 +#define CGTT_SPI_PS_CLK_CTRL__GRP4_OVERRIDE__SHIFT 0x1a +#define CGTT_SPI_PS_CLK_CTRL__GRP3_OVERRIDE__SHIFT 0x1b +#define CGTT_SPI_PS_CLK_CTRL__GRP2_OVERRIDE__SHIFT 0x1c +#define CGTT_SPI_PS_CLK_CTRL__GRP1_OVERRIDE__SHIFT 0x1d +#define CGTT_SPI_PS_CLK_CTRL__GRP0_OVERRIDE__SHIFT 0x1e +#define CGTT_SPI_PS_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_SPI_PS_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_SPI_PS_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00010000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_SPI_PS_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_SPI_PS_CLK_CTRL__GRP6_OVERRIDE_MASK 0x01000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP5_OVERRIDE_MASK 0x02000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP4_OVERRIDE_MASK 0x04000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP3_OVERRIDE_MASK 0x08000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP2_OVERRIDE_MASK 0x10000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP1_OVERRIDE_MASK 0x20000000L +#define CGTT_SPI_PS_CLK_CTRL__GRP0_OVERRIDE_MASK 0x40000000L +#define CGTT_SPI_PS_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_SPIS_CLK_CTRL +#define CGTT_SPIS_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_SPIS_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x10 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_SPIS_CLK_CTRL__GRP6_OVERRIDE__SHIFT 0x18 +#define CGTT_SPIS_CLK_CTRL__GRP5_OVERRIDE__SHIFT 0x19 +#define CGTT_SPIS_CLK_CTRL__GRP4_OVERRIDE__SHIFT 0x1a +#define CGTT_SPIS_CLK_CTRL__GRP3_OVERRIDE__SHIFT 0x1b +#define CGTT_SPIS_CLK_CTRL__GRP2_OVERRIDE__SHIFT 0x1c +#define CGTT_SPIS_CLK_CTRL__GRP1_OVERRIDE__SHIFT 0x1d +#define CGTT_SPIS_CLK_CTRL__GRP0_OVERRIDE__SHIFT 0x1e +#define CGTT_SPIS_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_SPIS_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_SPIS_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00010000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_SPIS_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_SPIS_CLK_CTRL__GRP6_OVERRIDE_MASK 0x01000000L +#define CGTT_SPIS_CLK_CTRL__GRP5_OVERRIDE_MASK 0x02000000L +#define CGTT_SPIS_CLK_CTRL__GRP4_OVERRIDE_MASK 0x04000000L +#define CGTT_SPIS_CLK_CTRL__GRP3_OVERRIDE_MASK 0x08000000L +#define CGTT_SPIS_CLK_CTRL__GRP2_OVERRIDE_MASK 0x10000000L +#define CGTT_SPIS_CLK_CTRL__GRP1_OVERRIDE_MASK 0x20000000L +#define CGTT_SPIS_CLK_CTRL__GRP0_OVERRIDE_MASK 0x40000000L +#define CGTT_SPIS_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_SPI_CLK_CTRL +#define CGTT_SPI_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_SPI_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x10 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_SPI_CLK_CTRL__GRP6_OVERRIDE__SHIFT 0x18 +#define CGTT_SPI_CLK_CTRL__GRP5_OVERRIDE__SHIFT 0x19 +#define CGTT_SPI_CLK_CTRL__GRP4_OVERRIDE__SHIFT 0x1a +#define CGTT_SPI_CLK_CTRL__GRP3_OVERRIDE__SHIFT 0x1b +#define CGTT_SPI_CLK_CTRL__GRP2_OVERRIDE__SHIFT 0x1c +#define CGTT_SPI_CLK_CTRL__GRP1_OVERRIDE__SHIFT 0x1d +#define CGTT_SPI_CLK_CTRL__GRP0_OVERRIDE__SHIFT 0x1e +#define CGTT_SPI_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_SPI_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_SPI_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00010000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_SPI_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_SPI_CLK_CTRL__GRP6_OVERRIDE_MASK 0x01000000L +#define CGTT_SPI_CLK_CTRL__GRP5_OVERRIDE_MASK 0x02000000L +#define CGTT_SPI_CLK_CTRL__GRP4_OVERRIDE_MASK 0x04000000L +#define CGTT_SPI_CLK_CTRL__GRP3_OVERRIDE_MASK 0x08000000L +#define CGTT_SPI_CLK_CTRL__GRP2_OVERRIDE_MASK 0x10000000L +#define CGTT_SPI_CLK_CTRL__GRP1_OVERRIDE_MASK 0x20000000L +#define CGTT_SPI_CLK_CTRL__GRP0_OVERRIDE_MASK 0x40000000L +#define CGTT_SPI_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_PC_CLK_CTRL +#define CGTT_PC_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_PC_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PC_CLK_CTRL__PC_RAM_FGCG_OVERRIDE__SHIFT 0x11 +#define CGTT_PC_CLK_CTRL__PC_WRITE_CLK_EN_OVERRIDE__SHIFT 0xd +#define CGTT_PC_CLK_CTRL__PC_READ_CLK_EN_OVERRIDE__SHIFT 0xe +#define CGTT_PC_CLK_CTRL__CORE3_OVERRIDE__SHIFT 0x1b +#define CGTT_PC_CLK_CTRL__CORE2_OVERRIDE__SHIFT 0x1c +#define CGTT_PC_CLK_CTRL__CORE1_OVERRIDE__SHIFT 0x1d +#define CGTT_PC_CLK_CTRL__CORE0_OVERRIDE__SHIFT 0x1e +#define CGTT_PC_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_PC_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PC_CLK_CTRL__PC_RAM_FGCG_OVERRIDE_MASK 0x00020000L +#define CGTT_PC_CLK_CTRL__PC_WRITE_CLK_EN_OVERRIDE_MASK 0x00002000L +#define CGTT_PC_CLK_CTRL__PC_READ_CLK_EN_OVERRIDE_MASK 0x00004000L +#define CGTT_PC_CLK_CTRL__CORE3_OVERRIDE_MASK 0x08000000L +#define CGTT_PC_CLK_CTRL__CORE2_OVERRIDE_MASK 0x10000000L +#define CGTT_PC_CLK_CTRL__CORE1_OVERRIDE_MASK 0x20000000L +#define CGTT_PC_CLK_CTRL__CORE0_OVERRIDE_MASK 0x40000000L +//CGTT_BCI_CLK_CTRL +#define CGTT_BCI_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_BCI_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_BCI_CLK_CTRL__RESERVED__SHIFT 0xc +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_BCI_CLK_CTRL__CORE6_OVERRIDE__SHIFT 0x18 +#define CGTT_BCI_CLK_CTRL__CORE5_OVERRIDE__SHIFT 0x19 +#define CGTT_BCI_CLK_CTRL__CORE4_OVERRIDE__SHIFT 0x1a +#define CGTT_BCI_CLK_CTRL__CORE3_OVERRIDE__SHIFT 0x1b +#define CGTT_BCI_CLK_CTRL__CORE2_OVERRIDE__SHIFT 0x1c +#define CGTT_BCI_CLK_CTRL__CORE1_OVERRIDE__SHIFT 0x1d +#define CGTT_BCI_CLK_CTRL__CORE0_OVERRIDE__SHIFT 0x1e +#define CGTT_BCI_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_BCI_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_BCI_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_BCI_CLK_CTRL__RESERVED_MASK 0x0000F000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_BCI_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_BCI_CLK_CTRL__CORE6_OVERRIDE_MASK 0x01000000L +#define CGTT_BCI_CLK_CTRL__CORE5_OVERRIDE_MASK 0x02000000L +#define CGTT_BCI_CLK_CTRL__CORE4_OVERRIDE_MASK 0x04000000L +#define CGTT_BCI_CLK_CTRL__CORE3_OVERRIDE_MASK 0x08000000L +#define CGTT_BCI_CLK_CTRL__CORE2_OVERRIDE_MASK 0x10000000L +#define CGTT_BCI_CLK_CTRL__CORE1_OVERRIDE_MASK 0x20000000L +#define CGTT_BCI_CLK_CTRL__CORE0_OVERRIDE_MASK 0x40000000L +#define CGTT_BCI_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_VGT_CLK_CTRL +#define CGTT_VGT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_VGT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_VGT_CLK_CTRL__PERF_ENABLE__SHIFT 0xf +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_VGT_CLK_CTRL__TESS_OVERRIDE__SHIFT 0x1c +#define CGTT_VGT_CLK_CTRL__CORE_OVERRIDE__SHIFT 0x1d +#define CGTT_VGT_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_VGT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_VGT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_VGT_CLK_CTRL__PERF_ENABLE_MASK 0x00008000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_VGT_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_VGT_CLK_CTRL__TESS_OVERRIDE_MASK 0x10000000L +#define CGTT_VGT_CLK_CTRL__CORE_OVERRIDE_MASK 0x20000000L +#define CGTT_VGT_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_IA_CLK_CTRL +#define CGTT_IA_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_IA_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_IA_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_IA_CLK_CTRL__PERF_ENABLE__SHIFT 0x19 +#define CGTT_IA_CLK_CTRL__CORE_OVERRIDE__SHIFT 0x1e +#define CGTT_IA_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_IA_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_IA_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_IA_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_IA_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_IA_CLK_CTRL__PERF_ENABLE_MASK 0x02000000L +#define CGTT_IA_CLK_CTRL__CORE_OVERRIDE_MASK 0x40000000L +#define CGTT_IA_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_WD_CLK_CTRL +#define CGTT_WD_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_WD_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_WD_CLK_CTRL__PERF_ENABLE__SHIFT 0xf +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_WD_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_WD_CLK_CTRL__CORE_OVERRIDE__SHIFT 0x1d +#define CGTT_WD_CLK_CTRL__RBIU_INPUT_OVERRIDE__SHIFT 0x1e +#define CGTT_WD_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_WD_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_WD_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_WD_CLK_CTRL__PERF_ENABLE_MASK 0x00008000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_WD_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_WD_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_WD_CLK_CTRL__CORE_OVERRIDE_MASK 0x20000000L +#define CGTT_WD_CLK_CTRL__RBIU_INPUT_OVERRIDE_MASK 0x40000000L +#define CGTT_WD_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_GS_NGG_CLK_CTRL +#define CGTT_GS_NGG_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_GS_NGG_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_GS_NGG_CLK_CTRL__PERF_ENABLE__SHIFT 0xf +#define CGTT_GS_NGG_CLK_CTRL__DBG_ENABLE__SHIFT 0x10 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_GS_NGG_CLK_CTRL__PRIMGEN_OVERRIDE__SHIFT 0x1c +#define CGTT_GS_NGG_CLK_CTRL__GS1_OVERRIDE__SHIFT 0x1d +#define CGTT_GS_NGG_CLK_CTRL__GS0_OVERRIDE__SHIFT 0x1e +#define CGTT_GS_NGG_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_GS_NGG_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_GS_NGG_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_GS_NGG_CLK_CTRL__PERF_ENABLE_MASK 0x00008000L +#define CGTT_GS_NGG_CLK_CTRL__DBG_ENABLE_MASK 0x00010000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_GS_NGG_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_GS_NGG_CLK_CTRL__PRIMGEN_OVERRIDE_MASK 0x10000000L +#define CGTT_GS_NGG_CLK_CTRL__GS1_OVERRIDE_MASK 0x20000000L +#define CGTT_GS_NGG_CLK_CTRL__GS0_OVERRIDE_MASK 0x40000000L +#define CGTT_GS_NGG_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_PA_CLK_CTRL +#define CGTT_PA_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_PA_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_PA_CLK_CTRL__SU_CLK_OVERRIDE__SHIFT 0x1d +#define CGTT_PA_CLK_CTRL__CL_CLK_OVERRIDE__SHIFT 0x1e +#define CGTT_PA_CLK_CTRL__REG_CLK_OVERRIDE__SHIFT 0x1f +#define CGTT_PA_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_PA_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_PA_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_PA_CLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_PA_CLK_CTRL__SU_CLK_OVERRIDE_MASK 0x20000000L +#define CGTT_PA_CLK_CTRL__CL_CLK_OVERRIDE_MASK 0x40000000L +#define CGTT_PA_CLK_CTRL__REG_CLK_OVERRIDE_MASK 0x80000000L +//CGTT_SC_CLK_CTRL0 +#define CGTT_SC_CLK_CTRL0__ON_DELAY__SHIFT 0x0 +#define CGTT_SC_CLK_CTRL0__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SC_CLK_CTRL0__PFF_ZFF_MEM_CLK_STALL_OVERRIDE__SHIFT 0x10 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_SC_CLK_CTRL0__REG_CLK_STALL_OVERRIDE__SHIFT 0x17 +#define CGTT_SC_CLK_CTRL0__PFF_ZFF_MEM_CLK_OVERRIDE__SHIFT 0x18 +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE5__SHIFT 0x19 +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE4__SHIFT 0x1a +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE3__SHIFT 0x1b +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE2__SHIFT 0x1c +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE1__SHIFT 0x1d +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE0__SHIFT 0x1e +#define CGTT_SC_CLK_CTRL0__REG_CLK_OVERRIDE__SHIFT 0x1f +#define CGTT_SC_CLK_CTRL0__ON_DELAY_MASK 0x0000000FL +#define CGTT_SC_CLK_CTRL0__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SC_CLK_CTRL0__PFF_ZFF_MEM_CLK_STALL_OVERRIDE_MASK 0x00010000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_SC_CLK_CTRL0__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_SC_CLK_CTRL0__REG_CLK_STALL_OVERRIDE_MASK 0x00800000L +#define CGTT_SC_CLK_CTRL0__PFF_ZFF_MEM_CLK_OVERRIDE_MASK 0x01000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE5_MASK 0x02000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE4_MASK 0x04000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE3_MASK 0x08000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE2_MASK 0x10000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE1_MASK 0x20000000L +#define CGTT_SC_CLK_CTRL0__SOFT_OVERRIDE0_MASK 0x40000000L +#define CGTT_SC_CLK_CTRL0__REG_CLK_OVERRIDE_MASK 0x80000000L +//CGTT_SC_CLK_CTRL1 +#define CGTT_SC_CLK_CTRL1__ON_DELAY__SHIFT 0x0 +#define CGTT_SC_CLK_CTRL1__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_STALL_OVERRIDE0__SHIFT 0x10 +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_STALL_OVERRIDE__SHIFT 0x11 +#define CGTT_SC_CLK_CTRL1__PBB_SCISSOR_CLK_STALL_OVERRIDE__SHIFT 0x12 +#define CGTT_SC_CLK_CTRL1__OTHER_SPECIAL_SC_REG_CLK_STALL_OVERRIDE__SHIFT 0x13 +#define CGTT_SC_CLK_CTRL1__SCREEN_EXT_REG_CLK_STALL_OVERRIDE__SHIFT 0x14 +#define CGTT_SC_CLK_CTRL1__VPORT_REG_MEM_CLK_STALL_OVERRIDE__SHIFT 0x15 +#define CGTT_SC_CLK_CTRL1__PBB_CLK_STALL_OVERRIDE__SHIFT 0x16 +#define CGTT_SC_CLK_CTRL1__PBB_WARP_CLK_STALL_OVERRIDE__SHIFT 0x17 +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_OVERRIDE0__SHIFT 0x18 +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_OVERRIDE__SHIFT 0x19 +#define CGTT_SC_CLK_CTRL1__PBB_SCISSOR_CLK_OVERRIDE__SHIFT 0x1a +#define CGTT_SC_CLK_CTRL1__OTHER_SPECIAL_SC_REG_CLK_OVERRIDE__SHIFT 0x1b +#define CGTT_SC_CLK_CTRL1__SCREEN_EXT_REG_CLK_OVERRIDE__SHIFT 0x1c +#define CGTT_SC_CLK_CTRL1__VPORT_REG_MEM_CLK_OVERRIDE__SHIFT 0x1d +#define CGTT_SC_CLK_CTRL1__PBB_CLK_OVERRIDE__SHIFT 0x1e +#define CGTT_SC_CLK_CTRL1__PBB_WARP_CLK_OVERRIDE__SHIFT 0x1f +#define CGTT_SC_CLK_CTRL1__ON_DELAY_MASK 0x0000000FL +#define CGTT_SC_CLK_CTRL1__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_STALL_OVERRIDE0_MASK 0x00010000L +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_STALL_OVERRIDE_MASK 0x00020000L +#define CGTT_SC_CLK_CTRL1__PBB_SCISSOR_CLK_STALL_OVERRIDE_MASK 0x00040000L +#define CGTT_SC_CLK_CTRL1__OTHER_SPECIAL_SC_REG_CLK_STALL_OVERRIDE_MASK 0x00080000L +#define CGTT_SC_CLK_CTRL1__SCREEN_EXT_REG_CLK_STALL_OVERRIDE_MASK 0x00100000L +#define CGTT_SC_CLK_CTRL1__VPORT_REG_MEM_CLK_STALL_OVERRIDE_MASK 0x00200000L +#define CGTT_SC_CLK_CTRL1__PBB_CLK_STALL_OVERRIDE_MASK 0x00400000L +#define CGTT_SC_CLK_CTRL1__PBB_WARP_CLK_STALL_OVERRIDE_MASK 0x00800000L +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_OVERRIDE0_MASK 0x01000000L +#define CGTT_SC_CLK_CTRL1__PBB_BINNING_CLK_OVERRIDE_MASK 0x02000000L +#define CGTT_SC_CLK_CTRL1__PBB_SCISSOR_CLK_OVERRIDE_MASK 0x04000000L +#define CGTT_SC_CLK_CTRL1__OTHER_SPECIAL_SC_REG_CLK_OVERRIDE_MASK 0x08000000L +#define CGTT_SC_CLK_CTRL1__SCREEN_EXT_REG_CLK_OVERRIDE_MASK 0x10000000L +#define CGTT_SC_CLK_CTRL1__VPORT_REG_MEM_CLK_OVERRIDE_MASK 0x20000000L +#define CGTT_SC_CLK_CTRL1__PBB_CLK_OVERRIDE_MASK 0x40000000L +#define CGTT_SC_CLK_CTRL1__PBB_WARP_CLK_OVERRIDE_MASK 0x80000000L +//CGTT_SC_CLK_CTRL2 +#define CGTT_SC_CLK_CTRL2__ON_DELAY__SHIFT 0x0 +#define CGTT_SC_CLK_CTRL2__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SC_CLK_CTRL2__DBR_CLK_OVERRIDE__SHIFT 0x1a +#define CGTT_SC_CLK_CTRL2__SCF_SCB_INTF_CLK_OVERRIDE__SHIFT 0x1b +#define CGTT_SC_CLK_CTRL2__SC_PKR_INTF_CLK_OVERRIDE__SHIFT 0x1c +#define CGTT_SC_CLK_CTRL2__SC_DB_INTF_CLK_OVERRIDE__SHIFT 0x1d +#define CGTT_SC_CLK_CTRL2__PA_SC_INTF_CLK_OVERRIDE__SHIFT 0x1e +#define CGTT_SC_CLK_CTRL2__ON_DELAY_MASK 0x0000000FL +#define CGTT_SC_CLK_CTRL2__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SC_CLK_CTRL2__DBR_CLK_OVERRIDE_MASK 0x04000000L +#define CGTT_SC_CLK_CTRL2__SCF_SCB_INTF_CLK_OVERRIDE_MASK 0x08000000L +#define CGTT_SC_CLK_CTRL2__SC_PKR_INTF_CLK_OVERRIDE_MASK 0x10000000L +#define CGTT_SC_CLK_CTRL2__SC_DB_INTF_CLK_OVERRIDE_MASK 0x20000000L +#define CGTT_SC_CLK_CTRL2__PA_SC_INTF_CLK_OVERRIDE_MASK 0x40000000L +//CGTT_SQ_CLK_CTRL +#define CGTT_SQ_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_SQ_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SQ_CLK_CTRL__CORE_OVERRIDE__SHIFT 0x1e +#define CGTT_SQ_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_SQ_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_SQ_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SQ_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SQ_CLK_CTRL__CORE_OVERRIDE_MASK 0x40000000L +#define CGTT_SQ_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L +//CGTT_SQG_CLK_CTRL +#define CGTT_SQG_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_SQG_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SQG_CLK_CTRL__TTRACE_OVERRIDE__SHIFT 0x1c +#define CGTT_SQG_CLK_CTRL__PERFMON_OVERRIDE__SHIFT 0x1d +#define CGTT_SQG_CLK_CTRL__CORE_OVERRIDE__SHIFT 0x1e +#define CGTT_SQG_CLK_CTRL__REG_OVERRIDE__SHIFT 0x1f +#define CGTT_SQG_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_SQG_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SQG_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SQG_CLK_CTRL__TTRACE_OVERRIDE_MASK 0x10000000L +#define CGTT_SQG_CLK_CTRL__PERFMON_OVERRIDE_MASK 0x20000000L +#define CGTT_SQG_CLK_CTRL__CORE_OVERRIDE_MASK 0x40000000L +#define CGTT_SQG_CLK_CTRL__REG_OVERRIDE_MASK 0x80000000L //SQ_ALU_CLK_CTRL #define SQ_ALU_CLK_CTRL__FORCE_WGP_ON_SA0__SHIFT 0x0 #define SQ_ALU_CLK_CTRL__FORCE_WGP_ON_SA1__SHIFT 0x10 @@ -34572,12 +35059,982 @@ #define SQ_LDS_CLK_CTRL__FORCE_WGP_ON_SA1__SHIFT 0x10 #define SQ_LDS_CLK_CTRL__FORCE_WGP_ON_SA0_MASK 0x0000FFFFL #define SQ_LDS_CLK_CTRL__FORCE_WGP_ON_SA1_MASK 0xFFFF0000L +//CGTT_SX_CLK_CTRL0 +#define CGTT_SX_CLK_CTRL0__ON_DELAY__SHIFT 0x0 +#define CGTT_SX_CLK_CTRL0__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SX_CLK_CTRL0__RESERVED__SHIFT 0xc +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_SX_CLK_CTRL0__ON_DELAY_MASK 0x0000000FL +#define CGTT_SX_CLK_CTRL0__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SX_CLK_CTRL0__RESERVED_MASK 0x0000F000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SX_CLK_CTRL0__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_SX_CLK_CTRL0__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_SX_CLK_CTRL1 +#define CGTT_SX_CLK_CTRL1__ON_DELAY__SHIFT 0x0 +#define CGTT_SX_CLK_CTRL1__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SX_CLK_CTRL1__RESERVED__SHIFT 0xc +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_SX_CLK_CTRL1__ON_DELAY_MASK 0x0000000FL +#define CGTT_SX_CLK_CTRL1__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SX_CLK_CTRL1__RESERVED_MASK 0x0000F000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SX_CLK_CTRL1__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_SX_CLK_CTRL1__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_SX_CLK_CTRL2 +#define CGTT_SX_CLK_CTRL2__ON_DELAY__SHIFT 0x0 +#define CGTT_SX_CLK_CTRL2__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SX_CLK_CTRL2__RESERVED__SHIFT 0xd +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_SX_CLK_CTRL2__ON_DELAY_MASK 0x0000000FL +#define CGTT_SX_CLK_CTRL2__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SX_CLK_CTRL2__RESERVED_MASK 0x0000E000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SX_CLK_CTRL2__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_SX_CLK_CTRL2__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_SX_CLK_CTRL3 +#define CGTT_SX_CLK_CTRL3__ON_DELAY__SHIFT 0x0 +#define CGTT_SX_CLK_CTRL3__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SX_CLK_CTRL3__RESERVED__SHIFT 0xd +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_SX_CLK_CTRL3__ON_DELAY_MASK 0x0000000FL +#define CGTT_SX_CLK_CTRL3__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SX_CLK_CTRL3__RESERVED_MASK 0x0000E000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SX_CLK_CTRL3__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_SX_CLK_CTRL3__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_SX_CLK_CTRL4 +#define CGTT_SX_CLK_CTRL4__ON_DELAY__SHIFT 0x0 +#define CGTT_SX_CLK_CTRL4__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_SX_CLK_CTRL4__RESERVED__SHIFT 0xc +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_SX_CLK_CTRL4__ON_DELAY_MASK 0x0000000FL +#define CGTT_SX_CLK_CTRL4__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_SX_CLK_CTRL4__RESERVED_MASK 0x0000F000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_SX_CLK_CTRL4__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_SX_CLK_CTRL4__SOFT_OVERRIDE0_MASK 0x80000000L +//TD_CGTT_CTRL +#define TD_CGTT_CTRL__ON_DELAY__SHIFT 0x0 +#define TD_CGTT_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define TD_CGTT_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define TD_CGTT_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define TD_CGTT_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define TD_CGTT_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define TD_CGTT_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define TD_CGTT_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define TD_CGTT_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define TD_CGTT_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define TD_CGTT_CTRL__ON_DELAY_MASK 0x0000000FL +#define TD_CGTT_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define TD_CGTT_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define TD_CGTT_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//TA_CGTT_CTRL +#define TA_CGTT_CTRL__ON_DELAY__SHIFT 0x0 +#define TA_CGTT_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define TA_CGTT_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define TA_CGTT_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define TA_CGTT_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define TA_CGTT_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define TA_CGTT_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define TA_CGTT_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define TA_CGTT_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define TA_CGTT_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define TA_CGTT_CTRL__ON_DELAY_MASK 0x0000000FL +#define TA_CGTT_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define TA_CGTT_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define TA_CGTT_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_TCPI_CLK_CTRL +#define CGTT_TCPI_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_TCPI_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_TCPI_CLK_CTRL__SPARE__SHIFT 0xc +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0xf +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x10 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x17 +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x18 +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x19 +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1a +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1b +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1c +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1d +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1e +#define CGTT_TCPI_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_TCPI_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_TCPI_CLK_CTRL__SPARE_MASK 0x00007000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00008000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00010000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_TCPI_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x00800000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x01000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x02000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE4_MASK 0x04000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE3_MASK 0x08000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE2_MASK 0x10000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE1_MASK 0x20000000L +#define CGTT_TCPI_CLK_CTRL__SOFT_OVERRIDE0_MASK 0x40000000L +//CGTT_GDS_CLK_CTRL +#define CGTT_GDS_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_GDS_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_GDS_CLK_CTRL__UNUSED__SHIFT 0xc +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define CGTT_GDS_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_GDS_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_GDS_CLK_CTRL__UNUSED_MASK 0x0000F000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_GDS_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define CGTT_GDS_CLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//DB_CGTT_CLK_CTRL_0 +#define DB_CGTT_CLK_CTRL_0__ON_DELAY__SHIFT 0x0 +#define DB_CGTT_CLK_CTRL_0__OFF_HYSTERESIS__SHIFT 0x4 +#define DB_CGTT_CLK_CTRL_0__RESERVED__SHIFT 0xc +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE7__SHIFT 0x18 +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE6__SHIFT 0x19 +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE5__SHIFT 0x1a +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE4__SHIFT 0x1b +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE3__SHIFT 0x1c +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE2__SHIFT 0x1d +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE1__SHIFT 0x1e +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE0__SHIFT 0x1f +#define DB_CGTT_CLK_CTRL_0__ON_DELAY_MASK 0x0000000FL +#define DB_CGTT_CLK_CTRL_0__OFF_HYSTERESIS_MASK 0x00000FF0L +#define DB_CGTT_CLK_CTRL_0__RESERVED_MASK 0x0000F000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define DB_CGTT_CLK_CTRL_0__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE7_MASK 0x01000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE6_MASK 0x02000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE5_MASK 0x04000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE4_MASK 0x08000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE3_MASK 0x10000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE2_MASK 0x20000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE1_MASK 0x40000000L +#define DB_CGTT_CLK_CTRL_0__SOFT_OVERRIDE0_MASK 0x80000000L +//CB_CGTT_SCLK_CTRL +#define CB_CGTT_SCLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CB_CGTT_SCLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define CB_CGTT_SCLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CB_CGTT_SCLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CB_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define CB_CGTT_SCLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//GL2C_CGTT_SCLK_CTRL +#define GL2C_CGTT_SCLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GL2C_CGTT_SCLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define GL2C_CGTT_SCLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GL2C_CGTT_SCLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define GL2C_CGTT_SCLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//GL2A_CGTT_SCLK_CTRL +#define GL2A_CGTT_SCLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GL2A_CGTT_SCLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x18 +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define GL2A_CGTT_SCLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GL2A_CGTT_SCLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE7_MASK 0x01000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define GL2A_CGTT_SCLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//GL2A_CGTT_SCLK_CTRL_1 +#define GL2A_CGTT_SCLK_CTRL_1__ON_DELAY__SHIFT 0x0 +#define GL2A_CGTT_SCLK_CTRL_1__OFF_HYSTERESIS__SHIFT 0x4 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE7__SHIFT 0x18 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE6__SHIFT 0x19 +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE5__SHIFT 0x1a +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE4__SHIFT 0x1b +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE3__SHIFT 0x1c +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE2__SHIFT 0x1d +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE1__SHIFT 0x1e +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE0__SHIFT 0x1f +#define GL2A_CGTT_SCLK_CTRL_1__ON_DELAY_MASK 0x0000000FL +#define GL2A_CGTT_SCLK_CTRL_1__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE7_MASK 0x01000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE6_MASK 0x02000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE5_MASK 0x04000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE4_MASK 0x08000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE3_MASK 0x10000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE2_MASK 0x20000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE1_MASK 0x40000000L +#define GL2A_CGTT_SCLK_CTRL_1__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_CP_CLK_CTRL +#define CGTT_CP_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_CP_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_CP_CLK_CTRL__MGLS_OVERRIDE__SHIFT 0xf +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_PERFMON__SHIFT 0x1d +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define CGTT_CP_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_CP_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_CP_CLK_CTRL__MGLS_OVERRIDE_MASK 0x00008000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_CP_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_PERFMON_MASK 0x20000000L +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define CGTT_CP_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L +//CGTT_CPF_CLK_CTRL +#define CGTT_CPF_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_CPF_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_CPF_CLK_CTRL__MGLS_OVERRIDE__SHIFT 0xf +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_PERFMON__SHIFT 0x1a +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_PRT__SHIFT 0x1b +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_CMP__SHIFT 0x1c +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_GFX__SHIFT 0x1d +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define CGTT_CPF_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_CPF_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_CPF_CLK_CTRL__MGLS_OVERRIDE_MASK 0x00008000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_CPF_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_PERFMON_MASK 0x04000000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_PRT_MASK 0x08000000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_CMP_MASK 0x10000000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_GFX_MASK 0x20000000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define CGTT_CPF_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L +//CGTT_CPC_CLK_CTRL +#define CGTT_CPC_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_CPC_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_CPC_CLK_CTRL__MGLS_OVERRIDE__SHIFT 0xf +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_PERFMON__SHIFT 0x1d +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define CGTT_CPC_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_CPC_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_CPC_CLK_CTRL__MGLS_OVERRIDE_MASK 0x00008000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_CPC_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_PERFMON_MASK 0x20000000L +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define CGTT_CPC_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L +//CGTT_RLC_CLK_CTRL +#define CGTT_RLC_CLK_CTRL__RESERVED__SHIFT 0x0 +#define CGTT_RLC_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define CGTT_RLC_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define CGTT_RLC_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define CGTT_RLC_CLK_CTRL__RESERVED_MASK 0x0000000FL +#define CGTT_RLC_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_RLC_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define CGTT_RLC_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define CGTT_RLC_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L //RLC_GFX_RM_CNTL #define RLC_GFX_RM_CNTL__RLC_GFX_RM_VALID__SHIFT 0x0 #define RLC_GFX_RM_CNTL__RESERVED__SHIFT 0x1 #define RLC_GFX_RM_CNTL__RLC_GFX_RM_VALID_MASK 0x00000001L #define RLC_GFX_RM_CNTL__RESERVED_MASK 0xFFFFFFFEL - +//RMI_CGTT_SCLK_CTRL +#define RMI_CGTT_SCLK_CTRL__ON_DELAY__SHIFT 0x0 +#define RMI_CGTT_SCLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define RMI_CGTT_SCLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define RMI_CGTT_SCLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define RMI_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define RMI_CGTT_SCLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//CGTT_TCPF_CLK_CTRL +#define CGTT_TCPF_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define CGTT_TCPF_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_TCPF_CLK_CTRL__SPARE__SHIFT 0xc +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0xf +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x10 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x11 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x12 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x13 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x14 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x15 +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x16 +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE7__SHIFT 0x17 +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x18 +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x19 +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1a +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1b +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1c +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1d +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1e +#define CGTT_TCPF_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define CGTT_TCPF_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_TCPF_CLK_CTRL__SPARE_MASK 0x00007000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00008000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00010000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00020000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00040000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00080000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00100000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00200000L +#define CGTT_TCPF_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00400000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE7_MASK 0x00800000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x01000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x02000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE4_MASK 0x04000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE3_MASK 0x08000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE2_MASK 0x10000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE1_MASK 0x20000000L +#define CGTT_TCPF_CLK_CTRL__SOFT_OVERRIDE0_MASK 0x40000000L +//GCR_CGTT_SCLK_CTRL +#define GCR_CGTT_SCLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GCR_CGTT_SCLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define GCR_CGTT_SCLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GCR_CGTT_SCLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define GCR_CGTT_SCLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define GCR_CGTT_SCLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//UTCL1_CGTT_CLK_CTRL +#define UTCL1_CGTT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define UTCL1_CGTT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE6__SHIFT 0x19 +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE5__SHIFT 0x1a +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE4__SHIFT 0x1b +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE3__SHIFT 0x1c +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE2__SHIFT 0x1d +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE1__SHIFT 0x1e +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE0__SHIFT 0x1f +#define UTCL1_CGTT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define UTCL1_CGTT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE6_MASK 0x02000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE5_MASK 0x04000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE4_MASK 0x08000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE3_MASK 0x10000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE2_MASK 0x20000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE1_MASK 0x40000000L +#define UTCL1_CGTT_CLK_CTRL__SOFT_OVERRIDE0_MASK 0x80000000L +//GCEA_CGTT_CLK_CTRL +#define GCEA_CGTT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GCEA_CGTT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GCEA_CGTT_CLK_CTRL__SPARE0__SHIFT 0xc +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_WRITE__SHIFT 0x14 +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_READ__SHIFT 0x15 +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_RETURN__SHIFT 0x16 +#define GCEA_CGTT_CLK_CTRL__SPARE1__SHIFT 0x17 +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_WRITE__SHIFT 0x1c +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_READ__SHIFT 0x1d +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_RETURN__SHIFT 0x1e +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_REGISTER__SHIFT 0x1f +#define GCEA_CGTT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GCEA_CGTT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GCEA_CGTT_CLK_CTRL__SPARE0_MASK 0x000FF000L +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_WRITE_MASK 0x00100000L +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_READ_MASK 0x00200000L +#define GCEA_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_RETURN_MASK 0x00400000L +#define GCEA_CGTT_CLK_CTRL__SPARE1_MASK 0x0F800000L +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_WRITE_MASK 0x10000000L +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_READ_MASK 0x20000000L +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_RETURN_MASK 0x40000000L +#define GCEA_CGTT_CLK_CTRL__SOFT_OVERRIDE_REGISTER_MASK 0x80000000L +//SE_CAC_CGTT_CLK_CTRL +#define SE_CAC_CGTT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define SE_CAC_CGTT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define SE_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define SE_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define SE_CAC_CGTT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define SE_CAC_CGTT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define SE_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define SE_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L +//GC_CAC_CGTT_CLK_CTRL +#define GC_CAC_CGTT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GC_CAC_CGTT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GC_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define GC_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_REG__SHIFT 0x1f +#define GC_CAC_CGTT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GC_CAC_CGTT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GC_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +#define GC_CAC_CGTT_CLK_CTRL__SOFT_OVERRIDE_REG_MASK 0x80000000L +//GRBM_CGTT_CLK_CNTL +#define GRBM_CGTT_CLK_CNTL__ON_DELAY__SHIFT 0x0 +#define GRBM_CGTT_CLK_CNTL__OFF_HYSTERESIS__SHIFT 0x4 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE0__SHIFT 0x17 +#define GRBM_CGTT_CLK_CNTL__SOFT_OVERRIDE_DYN__SHIFT 0x1e +#define GRBM_CGTT_CLK_CNTL__ON_DELAY_MASK 0x0000000FL +#define GRBM_CGTT_CLK_CNTL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define GRBM_CGTT_CLK_CNTL__SOFT_STALL_OVERRIDE0_MASK 0x00800000L +#define GRBM_CGTT_CLK_CNTL__SOFT_OVERRIDE_DYN_MASK 0x40000000L +//GUS_CGTT_CLK_CTRL +#define GUS_CGTT_CLK_CTRL__ON_DELAY__SHIFT 0x0 +#define GUS_CGTT_CLK_CTRL__OFF_HYSTERESIS__SHIFT 0x4 +#define GUS_CGTT_CLK_CTRL__SPARE0__SHIFT 0xc +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_DRAM__SHIFT 0x13 +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_WRITE__SHIFT 0x14 +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_READ__SHIFT 0x15 +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_RETURN__SHIFT 0x16 +#define GUS_CGTT_CLK_CTRL__SPARE1__SHIFT 0x17 +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_DRAM__SHIFT 0x1b +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_WRITE__SHIFT 0x1c +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_READ__SHIFT 0x1d +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_RETURN__SHIFT 0x1e +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_REGISTER__SHIFT 0x1f +#define GUS_CGTT_CLK_CTRL__ON_DELAY_MASK 0x0000000FL +#define GUS_CGTT_CLK_CTRL__OFF_HYSTERESIS_MASK 0x00000FF0L +#define GUS_CGTT_CLK_CTRL__SPARE0_MASK 0x0007F000L +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_DRAM_MASK 0x00080000L +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_WRITE_MASK 0x00100000L +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_READ_MASK 0x00200000L +#define GUS_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_RETURN_MASK 0x00400000L +#define GUS_CGTT_CLK_CTRL__SPARE1_MASK 0x07800000L +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_DRAM_MASK 0x08000000L +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_WRITE_MASK 0x10000000L +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_READ_MASK 0x20000000L +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_RETURN_MASK 0x40000000L +#define GUS_CGTT_CLK_CTRL__SOFT_OVERRIDE_REGISTER_MASK 0x80000000L +//CGTT_PH_CLK_CTRL0 +#define CGTT_PH_CLK_CTRL0__ON_DELAY__SHIFT 0x0 +#define CGTT_PH_CLK_CTRL0__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE7__SHIFT 0x10 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE6__SHIFT 0x11 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE5__SHIFT 0x12 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE4__SHIFT 0x13 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE3__SHIFT 0x14 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE2__SHIFT 0x15 +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE1__SHIFT 0x16 +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_PH_CLK_CTRL0__PERFMON_CLK_OVERRIDE__SHIFT 0x1e +#define CGTT_PH_CLK_CTRL0__REG_CLK_OVERRIDE__SHIFT 0x1f +#define CGTT_PH_CLK_CTRL0__ON_DELAY_MASK 0x0000000FL +#define CGTT_PH_CLK_CTRL0__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE7_MASK 0x00010000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE6_MASK 0x00020000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE5_MASK 0x00040000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE4_MASK 0x00080000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE3_MASK 0x00100000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE2_MASK 0x00200000L +#define CGTT_PH_CLK_CTRL0__SOFT_STALL_OVERRIDE1_MASK 0x00400000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_PH_CLK_CTRL0__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_PH_CLK_CTRL0__PERFMON_CLK_OVERRIDE_MASK 0x40000000L +#define CGTT_PH_CLK_CTRL0__REG_CLK_OVERRIDE_MASK 0x80000000L +//CGTT_PH_CLK_CTRL1 +#define CGTT_PH_CLK_CTRL1__ON_DELAY__SHIFT 0x0 +#define CGTT_PH_CLK_CTRL1__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_PH_CLK_CTRL1__ON_DELAY_MASK 0x0000000FL +#define CGTT_PH_CLK_CTRL1__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_PH_CLK_CTRL1__SOFT_OVERRIDE1_MASK 0x40000000L +//CGTT_PH_CLK_CTRL2 +#define CGTT_PH_CLK_CTRL2__ON_DELAY__SHIFT 0x0 +#define CGTT_PH_CLK_CTRL2__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_PH_CLK_CTRL2__ON_DELAY_MASK 0x0000000FL +#define CGTT_PH_CLK_CTRL2__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_PH_CLK_CTRL2__SOFT_OVERRIDE1_MASK 0x40000000L +//CGTT_PH_CLK_CTRL3 +#define CGTT_PH_CLK_CTRL3__ON_DELAY__SHIFT 0x0 +#define CGTT_PH_CLK_CTRL3__OFF_HYSTERESIS__SHIFT 0x4 +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE7__SHIFT 0x18 +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE6__SHIFT 0x19 +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE5__SHIFT 0x1a +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE4__SHIFT 0x1b +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE3__SHIFT 0x1c +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE2__SHIFT 0x1d +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE1__SHIFT 0x1e +#define CGTT_PH_CLK_CTRL3__ON_DELAY_MASK 0x0000000FL +#define CGTT_PH_CLK_CTRL3__OFF_HYSTERESIS_MASK 0x00000FF0L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE7_MASK 0x01000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE6_MASK 0x02000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE5_MASK 0x04000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE4_MASK 0x08000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE3_MASK 0x10000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE2_MASK 0x20000000L +#define CGTT_PH_CLK_CTRL3__SOFT_OVERRIDE1_MASK 0x40000000L // addressBlock: gc_hypdec //CP_HYP_PFP_UCODE_ADDR diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h index d8632ccf3494..c488d4a50cf4 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h @@ -4409,6 +4409,10 @@ #define mmVMSHAREDPF0_MC_VM_XGMI_LFB_SIZE_BASE_IDX 1 #define mmVMSHAREDPF0_MC_VM_CACHEABLE_DRAM_CNTL 0x0af9 #define mmVMSHAREDPF0_MC_VM_CACHEABLE_DRAM_CNTL_BASE_IDX 1 +#define mmMC_VM_XGMI_LFB_CNTL 0x0823 +#define mmMC_VM_XGMI_LFB_CNTL_BASE_IDX 0 +#define mmMC_VM_XGMI_LFB_SIZE 0x0824 +#define mmMC_VM_XGMI_LFB_SIZE_BASE_IDX 0 // addressBlock: mmhub_utcl2_vmsharedvcdec diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h index 111a71b434e2..2969fbf282b7 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h @@ -26728,6 +26728,14 @@ //VMSHAREDPF0_MC_VM_CACHEABLE_DRAM_CNTL #define VMSHAREDPF0_MC_VM_CACHEABLE_DRAM_CNTL__ENABLE_CACHEABLE_DRAM_ADDRESS_APERTURE__SHIFT 0x0 #define VMSHAREDPF0_MC_VM_CACHEABLE_DRAM_CNTL__ENABLE_CACHEABLE_DRAM_ADDRESS_APERTURE_MASK 0x00000001L +//MC_VM_XGMI_LFB_CNTL +#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION__SHIFT 0x0 +#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION__SHIFT 0x3 +#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION_MASK 0x00000007L +#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION_MASK 0x00000038L +//MC_VM_XGMI_LFB_SIZE +#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE__SHIFT 0x0 +#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE_MASK 0x0000FFFFL // addressBlock: mmhub_utcl2_vmsharedvcdec diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h index b798cf5a2c39..38adde3cae5a 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h @@ -29,5 +29,7 @@ #define regMCA_UMC_UMC0_MCUMC_STATUST0_BASE_IDX 2 #define regMCA_UMC_UMC0_MCUMC_ADDRT0 0x03c4 #define regMCA_UMC_UMC0_MCUMC_ADDRT0_BASE_IDX 2 +#define regUMCCH0_0_GeccCtrl 0x0053 +#define regUMCCH0_0_GeccCtrl_BASE_IDX 2 #endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h index bd99b431247f..4dbec524f943 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h @@ -90,5 +90,8 @@ #define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr__SHIFT 0x0 #define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved__SHIFT 0x38 #define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr_MASK 0x00FFFFFFFFFFFFFFL +//UMCCH0_0_GeccCtrl +#define UMCCH0_0_GeccCtrl__UCFatalEn__SHIFT 0xd +#define UMCCH0_0_GeccCtrl__UCFatalEn_MASK 0x00002000L #endif diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 7e3231c2191c..a40ead44778a 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -824,4 +824,62 @@ struct gpu_metrics_v2_2 { uint64_t indep_throttle_status; }; +struct gpu_metrics_v2_3 { + struct metrics_table_header common_header; + + /* Temperature */ + uint16_t temperature_gfx; // gfx temperature on APUs + uint16_t temperature_soc; // soc temperature on APUs + uint16_t temperature_core[8]; // CPU core temperature on APUs + uint16_t temperature_l3[2]; + + /* Utilization */ + uint16_t average_gfx_activity; + uint16_t average_mm_activity; // UVD or VCN + + /* Driver attached timestamp (in ns) */ + uint64_t system_clock_counter; + + /* Power/Energy */ + uint16_t average_socket_power; // dGPU + APU power on A + A platform + uint16_t average_cpu_power; + uint16_t average_soc_power; + uint16_t average_gfx_power; + uint16_t average_core_power[8]; // CPU core power on APUs + + /* Average clocks */ + uint16_t average_gfxclk_frequency; + uint16_t average_socclk_frequency; + uint16_t average_uclk_frequency; + uint16_t average_fclk_frequency; + uint16_t average_vclk_frequency; + uint16_t average_dclk_frequency; + + /* Current clocks */ + uint16_t current_gfxclk; + uint16_t current_socclk; + uint16_t current_uclk; + uint16_t current_fclk; + uint16_t current_vclk; + uint16_t current_dclk; + uint16_t current_coreclk[8]; // CPU core clocks + uint16_t current_l3clk[2]; + + /* Throttle status (ASIC dependent) */ + uint32_t throttle_status; + + /* Fans */ + uint16_t fan_pwm; + + uint16_t padding[3]; + + /* Throttle status (ASIC independent) */ + uint64_t indep_throttle_status; + + /* Average Temperature */ + uint16_t average_temperature_gfx; // average gfx temperature on APUs + uint16_t average_temperature_soc; // average soc temperature on APUs + uint16_t average_temperature_core[8]; // average CPU core temperature on APUs + uint16_t average_temperature_l3[2]; +}; #endif 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 50bfa513cb35..7e85cdc5bd34 100644 --- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h @@ -269,7 +269,8 @@ union MESAPI__ADD_QUEUE { uint32_t map_kiq_utility_queue : 1; uint32_t is_kfd_process : 1; uint32_t trap_en : 1; - uint32_t reserved : 21; + 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/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 5e318b3f6c0f..948cc75376f8 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -3405,9 +3405,6 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev) { - if (adev->pm.dpm_enabled == 0) - return; - if (adev->pm.int_hwmon_dev) hwmon_device_unregister(adev->pm.int_hwmon_dev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 8fd0782a2b20..f5e08b60f66e 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -1384,13 +1384,16 @@ static int kv_dpm_enable(struct amdgpu_device *adev) static void kv_dpm_disable(struct amdgpu_device *adev) { struct kv_power_info *pi = kv_get_pi(adev); + int err; amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, AMDGPU_THERMAL_IRQ_LOW_TO_HIGH); amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, AMDGPU_THERMAL_IRQ_HIGH_TO_LOW); - amdgpu_kv_smc_bapm_enable(adev, false); + err = amdgpu_kv_smc_bapm_enable(adev, false); + if (err) + DRM_ERROR("amdgpu_kv_smc_bapm_enable failed\n"); if (adev->asic_type == CHIP_MULLINS) kv_enable_nb_dpm(adev, false); diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 1eb4e613b27a..ec055858eb95 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1485,6 +1485,7 @@ static int pp_get_prv_buffer_details(void *handle, void **addr, size_t *size) { struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; + int err; if (!addr || !size) return -EINVAL; @@ -1492,7 +1493,9 @@ static int pp_get_prv_buffer_details(void *handle, void **addr, size_t *size) *addr = NULL; *size = 0; if (adev->pm.smu_prv_buffer) { - amdgpu_bo_kmap(adev->pm.smu_prv_buffer, addr); + err = amdgpu_bo_kmap(adev->pm.smu_prv_buffer, addr); + if (err) + return err; *size = adev->pm.smu_prv_buffer_size; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index e4fcbf8a7eb5..7ef7e81525a3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -3603,7 +3603,7 @@ static int smu7_get_pp_table_entry_callback_func_v1(struct pp_hwmgr *hwmgr, return -EINVAL); PP_ASSERT_WITH_CODE( - (smu7_power_state->performance_level_count <= + (smu7_power_state->performance_level_count < hwmgr->platform_descriptor.hardwareActivityPerformanceLevels), "Performance levels exceeds Driver limit!", return -EINVAL); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 99bfe5efe171..c8c9fb827bda 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3155,7 +3155,7 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, return -1); PP_ASSERT_WITH_CODE( - (vega10_ps->performance_level_count <= + (vega10_ps->performance_level_count < hwmgr->platform_descriptor. hardwareActivityPerformanceLevels), "Performance levels exceeds Driver limit!", diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c index dad3e3741a4e..190af79f3236 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c @@ -67,22 +67,21 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr, int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t *speed) { - uint32_t current_rpm; - uint32_t percent = 0; - - if (hwmgr->thermal_controller.fanInfo.bNoFan) - return 0; + struct amdgpu_device *adev = hwmgr->adev; + uint32_t duty100, duty; + uint64_t tmp64; - if (vega10_get_current_rpm(hwmgr, ¤t_rpm)) - return -1; + duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1), + CG_FDO_CTRL1, FMAX_DUTY100); + duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS), + CG_THERMAL_STATUS, FDO_PWM_DUTY); - if (hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM != 0) - percent = current_rpm * 255 / - hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM; + if (!duty100) + return -EINVAL; - *speed = MIN(percent, 255); + tmp64 = (uint64_t)duty * 255; + do_div(tmp64, duty100); + *speed = MIN((uint32_t)tmp64, 255); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c index 1e79baab753e..bd54fbd393b9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_processpptables.c @@ -195,7 +195,6 @@ static int init_powerplay_table_information( struct phm_ppt_v3_information *pptable_information = (struct phm_ppt_v3_information *)hwmgr->pptable; uint32_t disable_power_control = 0; - int result; hwmgr->thermal_controller.ucType = powerplay_table->ucThermalControllerType; pptable_information->uc_thermal_controller_type = powerplay_table->ucThermalControllerType; @@ -257,9 +256,7 @@ static int init_powerplay_table_information( if (pptable_information->smc_pptable == NULL) return -ENOMEM; - result = append_vbios_pptable(hwmgr, (pptable_information->smc_pptable)); - - return result; + return append_vbios_pptable(hwmgr, (pptable_information->smc_pptable)); } static int vega12_pp_tables_initialize(struct pp_hwmgr *hwmgr) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c index 45214a364baa..e7ed2a7adf8f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c @@ -2567,15 +2567,13 @@ static uint8_t polaris10_get_memory_modile_index(struct pp_hwmgr *hwmgr) static int polaris10_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) { - int result; struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend); pp_atomctrl_mc_reg_table *mc_reg_table = &smu_data->mc_reg_table; uint8_t module_index = polaris10_get_memory_modile_index(hwmgr); memset(mc_reg_table, 0, sizeof(pp_atomctrl_mc_reg_table)); - result = atomctrl_initialize_mc_reg_table_v2_2(hwmgr, module_index, mc_reg_table); - return result; + return atomctrl_initialize_mc_reg_table_v2_2(hwmgr, module_index, mc_reg_table); } static bool polaris10_is_dpm_running(struct pp_hwmgr *hwmgr) 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 7ed4d4265797..74996a8fb671 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 @@ -369,6 +369,17 @@ 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/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 847990145dcd..cb10c7e31264 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -223,14 +223,13 @@ static int vangogh_tables_init(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; struct smu_table *tables = smu_table->tables; - struct amdgpu_device *adev = smu->adev; uint32_t if_version; + uint32_t smu_version; uint32_t ret = 0; - ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); if (ret) { - dev_err(adev->dev, "Failed to get smu if version!\n"); - goto err0_out; + return ret; } SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t), @@ -255,7 +254,10 @@ static int vangogh_tables_init(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + if (smu_version >= 0x043F3E00) + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_3); + else + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) goto err1_out; @@ -1648,6 +1650,63 @@ static int vangogh_set_watermarks_table(struct smu_context *smu, return 0; } +static ssize_t vangogh_get_legacy_gpu_metrics_v2_3(struct smu_context *smu, + void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v2_3 *gpu_metrics = + (struct gpu_metrics_v2_3 *)smu_table->gpu_metrics_table; + SmuMetrics_legacy_t metrics; + int ret = 0; + + ret = smu_cmn_get_metrics_table(smu, &metrics, true); + if (ret) + return ret; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 3); + + gpu_metrics->temperature_gfx = metrics.GfxTemperature; + gpu_metrics->temperature_soc = metrics.SocTemperature; + memcpy(&gpu_metrics->temperature_core[0], + &metrics.CoreTemperature[0], + sizeof(uint16_t) * 4); + gpu_metrics->temperature_l3[0] = metrics.L3Temperature[0]; + + gpu_metrics->average_gfx_activity = metrics.GfxActivity; + gpu_metrics->average_mm_activity = metrics.UvdActivity; + + gpu_metrics->average_socket_power = metrics.CurrentSocketPower; + gpu_metrics->average_cpu_power = metrics.Power[0]; + gpu_metrics->average_soc_power = metrics.Power[1]; + gpu_metrics->average_gfx_power = metrics.Power[2]; + memcpy(&gpu_metrics->average_core_power[0], + &metrics.CorePower[0], + sizeof(uint16_t) * 4); + + gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency; + gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency; + gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency; + gpu_metrics->average_fclk_frequency = metrics.MemclkFrequency; + gpu_metrics->average_vclk_frequency = metrics.VclkFrequency; + gpu_metrics->average_dclk_frequency = metrics.DclkFrequency; + + memcpy(&gpu_metrics->current_coreclk[0], + &metrics.CoreFrequency[0], + sizeof(uint16_t) * 4); + gpu_metrics->current_l3clk[0] = metrics.L3Frequency[0]; + + gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + vangogh_throttler_map); + + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + *table = (void *)gpu_metrics; + + return sizeof(struct gpu_metrics_v2_3); +} + static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, void **table) { @@ -1705,6 +1764,77 @@ static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_2); } +static ssize_t vangogh_get_gpu_metrics_v2_3(struct smu_context *smu, + void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v2_3 *gpu_metrics = + (struct gpu_metrics_v2_3 *)smu_table->gpu_metrics_table; + SmuMetrics_t metrics; + int ret = 0; + + ret = smu_cmn_get_metrics_table(smu, &metrics, true); + if (ret) + return ret; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 3); + + gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature; + gpu_metrics->temperature_soc = metrics.Current.SocTemperature; + memcpy(&gpu_metrics->temperature_core[0], + &metrics.Current.CoreTemperature[0], + sizeof(uint16_t) * 4); + gpu_metrics->temperature_l3[0] = metrics.Current.L3Temperature[0]; + + gpu_metrics->average_temperature_gfx = metrics.Average.GfxTemperature; + gpu_metrics->average_temperature_soc = metrics.Average.SocTemperature; + memcpy(&gpu_metrics->average_temperature_core[0], + &metrics.Average.CoreTemperature[0], + sizeof(uint16_t) * 4); + gpu_metrics->average_temperature_l3[0] = metrics.Average.L3Temperature[0]; + + gpu_metrics->average_gfx_activity = metrics.Current.GfxActivity; + gpu_metrics->average_mm_activity = metrics.Current.UvdActivity; + + gpu_metrics->average_socket_power = metrics.Current.CurrentSocketPower; + gpu_metrics->average_cpu_power = metrics.Current.Power[0]; + gpu_metrics->average_soc_power = metrics.Current.Power[1]; + gpu_metrics->average_gfx_power = metrics.Current.Power[2]; + memcpy(&gpu_metrics->average_core_power[0], + &metrics.Average.CorePower[0], + sizeof(uint16_t) * 4); + + gpu_metrics->average_gfxclk_frequency = metrics.Average.GfxclkFrequency; + gpu_metrics->average_socclk_frequency = metrics.Average.SocclkFrequency; + gpu_metrics->average_uclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_fclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_vclk_frequency = metrics.Average.VclkFrequency; + gpu_metrics->average_dclk_frequency = metrics.Average.DclkFrequency; + + gpu_metrics->current_gfxclk = metrics.Current.GfxclkFrequency; + gpu_metrics->current_socclk = metrics.Current.SocclkFrequency; + gpu_metrics->current_uclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_fclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_vclk = metrics.Current.VclkFrequency; + gpu_metrics->current_dclk = metrics.Current.DclkFrequency; + + memcpy(&gpu_metrics->current_coreclk[0], + &metrics.Current.CoreFrequency[0], + sizeof(uint16_t) * 4); + gpu_metrics->current_l3clk[0] = metrics.Current.L3Frequency[0]; + + gpu_metrics->throttle_status = metrics.Current.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.Current.ThrottlerStatus, + vangogh_throttler_map); + + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + *table = (void *)gpu_metrics; + + return sizeof(struct gpu_metrics_v2_3); +} + static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, void **table) { @@ -1772,20 +1902,26 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, static ssize_t vangogh_common_get_gpu_metrics(struct smu_context *smu, void **table) { - struct amdgpu_device *adev = smu->adev; uint32_t if_version; + uint32_t smu_version; int ret = 0; - ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); if (ret) { - dev_err(adev->dev, "Failed to get smu if version!\n"); return ret; } - if (if_version < 0x3) - ret = vangogh_get_legacy_gpu_metrics(smu, table); - else - ret = vangogh_get_gpu_metrics(smu, table); + if (smu_version >= 0x043F3E00) { + if (if_version < 0x3) + ret = vangogh_get_legacy_gpu_metrics_v2_3(smu, table); + else + ret = vangogh_get_gpu_metrics_v2_3(smu, table); + } else { + if (if_version < 0x3) + ret = vangogh_get_legacy_gpu_metrics(smu, table); + else + ret = vangogh_get_gpu_metrics(smu, table); + } return ret; } 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 6e4a052dc53d..93fffdbab4f0 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 @@ -210,7 +210,8 @@ 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 */ @@ -219,27 +220,6 @@ 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 vbios carried pptable when pptable_id is 3664, 3715 or 3795 - * - use 36831 soft pptable when pptable_id is 3683 - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 3664: - case 3715: - case 3795: - pptable_id = 0; - break; - case 3683: - pptable_id = 36831; - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } } /* "pptable_id == 0" means vbios carries the pptable. */ @@ -475,28 +455,8 @@ 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; - } - } else if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10)) { + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10)) pptable_id = 6666; - } } /* 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 7db2fd9ea74a..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 (!(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 0 - if (adev->pm.pp_feature & PP_GFXOFF_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFXOFF_BIT); -#endif - - *(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); - 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); - - *(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; } @@ -410,58 +375,11 @@ 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; - uint32_t pptable_id; 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_v13_0_0_get_pptable_from_pmfw(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size); - } else { - /* override pptable_id from driver parameter */ - if (amdgpu_smu_pptable_id >= 0) { - pptable_id = amdgpu_smu_pptable_id; - dev_info(adev->dev, "override pptable id %d\n", pptable_id); - } else { - pptable_id = smu_table->boot_values.pp_table_id; - } - - /* - * Temporary solution for SMU V13.0.0 with SCPM disabled: - * - use vbios carried pptable when pptable_id is 3664, 3715 or 3795 - * - use soft pptable when pptable_id is 3683 - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 3664: - case 3715: - case 3795: - pptable_id = 0; - break; - case 3683: - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } - - /* force using vbios pptable in sriov mode */ - if ((amdgpu_sriov_vf(adev) || !pptable_id) && (amdgpu_emu_mode != 1)) - ret = smu_v13_0_0_get_pptable_from_pmfw(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size); - else - ret = smu_v13_0_get_pptable_from_firmware(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size, - pptable_id); - } + 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; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 15e4298c7cc8..e4f8f90ac5aa 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -969,6 +969,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) case METRICS_VERSION(2, 2): structure_size = sizeof(struct gpu_metrics_v2_2); break; + case METRICS_VERSION(2, 3): + structure_size = sizeof(struct gpu_metrics_v2_3); + break; default: return; } |